diff options
Diffstat (limited to 'unsupported/test')
24 files changed, 14259 insertions, 0 deletions
diff --git a/unsupported/test/BVH.cpp b/unsupported/test/BVH.cpp new file mode 100644 index 000000000..ff5b3299d --- /dev/null +++ b/unsupported/test/BVH.cpp @@ -0,0 +1,222 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Ilya Baran <ibaran@mit.edu> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <Eigen/StdVector> +#include <Eigen/Geometry> +#include <unsupported/Eigen/BVH> + +namespace Eigen { + +template<typename Scalar, int Dim> AlignedBox<Scalar, Dim> bounding_box(const Matrix<Scalar, Dim, 1> &v) { return AlignedBox<Scalar, Dim>(v); } + +} + + +template<int Dim> +struct Ball +{ +EIGEN_MAKE_ALIGNED_OPERATOR_NEW_IF_VECTORIZABLE_FIXED_SIZE(double, Dim) + + typedef Matrix<double, Dim, 1> VectorType; + + Ball() {} + Ball(const VectorType &c, double r) : center(c), radius(r) {} + + VectorType center; + double radius; +}; +template<int Dim> AlignedBox<double, Dim> bounding_box(const Ball<Dim> &b) +{ return AlignedBox<double, Dim>(b.center.array() - b.radius, b.center.array() + b.radius); } + +inline double SQR(double x) { return x * x; } + +template<int Dim> +struct BallPointStuff //this class provides functions to be both an intersector and a minimizer, both for a ball and a point and for two trees +{ + typedef double Scalar; + typedef Matrix<double, Dim, 1> VectorType; + typedef Ball<Dim> BallType; + typedef AlignedBox<double, Dim> BoxType; + + BallPointStuff() : calls(0), count(0) {} + BallPointStuff(const VectorType &inP) : p(inP), calls(0), count(0) {} + + + bool intersectVolume(const BoxType &r) { ++calls; return r.contains(p); } + bool intersectObject(const BallType &b) { + ++calls; + if((b.center - p).squaredNorm() < SQR(b.radius)) + ++count; + return false; //continue + } + + bool intersectVolumeVolume(const BoxType &r1, const BoxType &r2) { ++calls; return !(r1.intersection(r2)).isNull(); } + bool intersectVolumeObject(const BoxType &r, const BallType &b) { ++calls; return r.squaredExteriorDistance(b.center) < SQR(b.radius); } + bool intersectObjectVolume(const BallType &b, const BoxType &r) { ++calls; return r.squaredExteriorDistance(b.center) < SQR(b.radius); } + bool intersectObjectObject(const BallType &b1, const BallType &b2){ + ++calls; + if((b1.center - b2.center).norm() < b1.radius + b2.radius) + ++count; + return false; + } + bool intersectVolumeObject(const BoxType &r, const VectorType &v) { ++calls; return r.contains(v); } + bool intersectObjectObject(const BallType &b, const VectorType &v){ + ++calls; + if((b.center - v).squaredNorm() < SQR(b.radius)) + ++count; + return false; + } + + double minimumOnVolume(const BoxType &r) { ++calls; return r.squaredExteriorDistance(p); } + double minimumOnObject(const BallType &b) { ++calls; return (std::max)(0., (b.center - p).squaredNorm() - SQR(b.radius)); } + double minimumOnVolumeVolume(const BoxType &r1, const BoxType &r2) { ++calls; return r1.squaredExteriorDistance(r2); } + double minimumOnVolumeObject(const BoxType &r, const BallType &b) { ++calls; return SQR((std::max)(0., r.exteriorDistance(b.center) - b.radius)); } + double minimumOnObjectVolume(const BallType &b, const BoxType &r) { ++calls; return SQR((std::max)(0., r.exteriorDistance(b.center) - b.radius)); } + double minimumOnObjectObject(const BallType &b1, const BallType &b2){ ++calls; return SQR((std::max)(0., (b1.center - b2.center).norm() - b1.radius - b2.radius)); } + double minimumOnVolumeObject(const BoxType &r, const VectorType &v) { ++calls; return r.squaredExteriorDistance(v); } + double minimumOnObjectObject(const BallType &b, const VectorType &v){ ++calls; return SQR((std::max)(0., (b.center - v).norm() - b.radius)); } + + VectorType p; + int calls; + int count; +}; + + +template<int Dim> +struct TreeTest +{ + typedef Matrix<double, Dim, 1> VectorType; + typedef std::vector<VectorType, aligned_allocator<VectorType> > VectorTypeList; + typedef Ball<Dim> BallType; + typedef std::vector<BallType, aligned_allocator<BallType> > BallTypeList; + typedef AlignedBox<double, Dim> BoxType; + + void testIntersect1() + { + BallTypeList b; + for(int i = 0; i < 500; ++i) { + b.push_back(BallType(VectorType::Random(), 0.5 * internal::random(0., 1.))); + } + KdBVH<double, Dim, BallType> tree(b.begin(), b.end()); + + VectorType pt = VectorType::Random(); + BallPointStuff<Dim> i1(pt), i2(pt); + + for(int i = 0; i < (int)b.size(); ++i) + i1.intersectObject(b[i]); + + BVIntersect(tree, i2); + + VERIFY(i1.count == i2.count); + } + + void testMinimize1() + { + BallTypeList b; + for(int i = 0; i < 500; ++i) { + b.push_back(BallType(VectorType::Random(), 0.01 * internal::random(0., 1.))); + } + KdBVH<double, Dim, BallType> tree(b.begin(), b.end()); + + VectorType pt = VectorType::Random(); + BallPointStuff<Dim> i1(pt), i2(pt); + + double m1 = (std::numeric_limits<double>::max)(), m2 = m1; + + for(int i = 0; i < (int)b.size(); ++i) + m1 = (std::min)(m1, i1.minimumOnObject(b[i])); + + m2 = BVMinimize(tree, i2); + + VERIFY_IS_APPROX(m1, m2); + } + + void testIntersect2() + { + BallTypeList b; + VectorTypeList v; + + for(int i = 0; i < 50; ++i) { + b.push_back(BallType(VectorType::Random(), 0.5 * internal::random(0., 1.))); + for(int j = 0; j < 3; ++j) + v.push_back(VectorType::Random()); + } + + KdBVH<double, Dim, BallType> tree(b.begin(), b.end()); + KdBVH<double, Dim, VectorType> vTree(v.begin(), v.end()); + + BallPointStuff<Dim> i1, i2; + + for(int i = 0; i < (int)b.size(); ++i) + for(int j = 0; j < (int)v.size(); ++j) + i1.intersectObjectObject(b[i], v[j]); + + BVIntersect(tree, vTree, i2); + + VERIFY(i1.count == i2.count); + } + + void testMinimize2() + { + BallTypeList b; + VectorTypeList v; + + for(int i = 0; i < 50; ++i) { + b.push_back(BallType(VectorType::Random(), 1e-7 + 1e-6 * internal::random(0., 1.))); + for(int j = 0; j < 3; ++j) + v.push_back(VectorType::Random()); + } + + KdBVH<double, Dim, BallType> tree(b.begin(), b.end()); + KdBVH<double, Dim, VectorType> vTree(v.begin(), v.end()); + + BallPointStuff<Dim> i1, i2; + + double m1 = (std::numeric_limits<double>::max)(), m2 = m1; + + for(int i = 0; i < (int)b.size(); ++i) + for(int j = 0; j < (int)v.size(); ++j) + m1 = (std::min)(m1, i1.minimumOnObjectObject(b[i], v[j])); + + m2 = BVMinimize(tree, vTree, i2); + + VERIFY_IS_APPROX(m1, m2); + } +}; + + +void test_BVH() +{ + for(int i = 0; i < g_repeat; i++) { +#ifdef EIGEN_TEST_PART_1 + TreeTest<2> test2; + CALL_SUBTEST(test2.testIntersect1()); + CALL_SUBTEST(test2.testMinimize1()); + CALL_SUBTEST(test2.testIntersect2()); + CALL_SUBTEST(test2.testMinimize2()); +#endif + +#ifdef EIGEN_TEST_PART_2 + TreeTest<3> test3; + CALL_SUBTEST(test3.testIntersect1()); + CALL_SUBTEST(test3.testMinimize1()); + CALL_SUBTEST(test3.testIntersect2()); + CALL_SUBTEST(test3.testMinimize2()); +#endif + +#ifdef EIGEN_TEST_PART_3 + TreeTest<4> test4; + CALL_SUBTEST(test4.testIntersect1()); + CALL_SUBTEST(test4.testMinimize1()); + CALL_SUBTEST(test4.testIntersect2()); + CALL_SUBTEST(test4.testMinimize2()); +#endif + } +} diff --git a/unsupported/test/CMakeLists.txt b/unsupported/test/CMakeLists.txt new file mode 100644 index 000000000..b34b151b1 --- /dev/null +++ b/unsupported/test/CMakeLists.txt @@ -0,0 +1,87 @@ + +include_directories(../../test ../../unsupported ../../Eigen + ${CMAKE_CURRENT_BINARY_DIR}/../../test) + +find_package(GoogleHash) +if(GOOGLEHASH_FOUND) + add_definitions("-DEIGEN_GOOGLEHASH_SUPPORT") + include_directories(${GOOGLEHASH_INCLUDES}) + ei_add_property(EIGEN_TESTED_BACKENDS "GoogleHash, ") +else(GOOGLEHASH_FOUND) + ei_add_property(EIGEN_MISSING_BACKENDS "GoogleHash, ") +endif(GOOGLEHASH_FOUND) + +find_package(Adolc) +if(ADOLC_FOUND) + include_directories(${ADOLC_INCLUDES}) + ei_add_property(EIGEN_TESTED_BACKENDS "Adolc, ") + ei_add_test(forward_adolc "" ${ADOLC_LIBRARIES}) +else(ADOLC_FOUND) + ei_add_property(EIGEN_MISSING_BACKENDS "Adolc, ") +endif(ADOLC_FOUND) + +# this test seems to never have been successful on x87, so is considered to contain a FP-related bug. +# see thread: "non-linear optimization test summary" +#ei_add_test(NonLinearOptimization) + +ei_add_test(NumericalDiff) +ei_add_test(autodiff) + +if (NOT CMAKE_CXX_COMPILER MATCHES "clang\\+\\+$") +ei_add_test(BVH) +endif() + +ei_add_test(matrix_exponential) +ei_add_test(matrix_function) +ei_add_test(matrix_square_root) +ei_add_test(alignedvector3) +ei_add_test(FFT) + +find_package(MPFR 2.3.0) +find_package(GMP) +if(MPFR_FOUND) + include_directories(${MPFR_INCLUDES} ./mpreal) + ei_add_property(EIGEN_TESTED_BACKENDS "MPFR C++, ") + set(EIGEN_MPFR_TEST_LIBRARIES ${MPFR_LIBRARIES} ${GMP_LIBRARIES}) + ei_add_test(mpreal_support "" "${EIGEN_MPFR_TEST_LIBRARIES}" ) +else() + ei_add_property(EIGEN_MISSING_BACKENDS "MPFR C++, ") +endif() + +ei_add_test(sparse_extra "" "") + +find_package(FFTW) +if(FFTW_FOUND) + ei_add_property(EIGEN_TESTED_BACKENDS "fftw, ") + include_directories( ${FFTW_INCLUDES} ) + if(FFTWL_LIB) + ei_add_test(FFTW "-DEIGEN_FFTW_DEFAULT -DEIGEN_HAS_FFTWL" "${FFTW_LIBRARIES}" ) + else() + ei_add_test(FFTW "-DEIGEN_FFTW_DEFAULT" "${FFTW_LIBRARIES}" ) + endif() +else() + ei_add_property(EIGEN_MISSING_BACKENDS "fftw, ") +endif() + +option(EIGEN_TEST_NO_OPENGL "Disable OpenGL support in unit tests" OFF) +if(NOT EIGEN_TEST_NO_OPENGL) + find_package(OpenGL) + find_package(GLUT) + find_package(GLEW) + if(OPENGL_FOUND AND GLUT_FOUND AND GLEW_FOUND) + ei_add_property(EIGEN_TESTED_BACKENDS "OpenGL, ") + set(EIGEN_GL_LIB ${GLUT_LIBRARIES} ${GLEW_LIBRARIES}) + ei_add_test(openglsupport "" "${EIGEN_GL_LIB}" ) + else() + ei_add_property(EIGEN_MISSING_BACKENDS "OpenGL, ") + endif() +else() + ei_add_property(EIGEN_MISSING_BACKENDS "OpenGL, ") +endif() + +ei_add_test(polynomialsolver) +ei_add_test(polynomialutils) +ei_add_test(kronecker_product) +ei_add_test(splines) +ei_add_test(gmres) + diff --git a/unsupported/test/FFT.cpp b/unsupported/test/FFT.cpp new file mode 100644 index 000000000..45c87f5a7 --- /dev/null +++ b/unsupported/test/FFT.cpp @@ -0,0 +1,2 @@ +#define test_FFTW test_FFT +#include "FFTW.cpp" diff --git a/unsupported/test/FFTW.cpp b/unsupported/test/FFTW.cpp new file mode 100644 index 000000000..a07bf274b --- /dev/null +++ b/unsupported/test/FFTW.cpp @@ -0,0 +1,265 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Mark Borgerding mark a borgerding net +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/FFT> + +template <typename T> +std::complex<T> RandomCpx() { return std::complex<T>( (T)(rand()/(T)RAND_MAX - .5), (T)(rand()/(T)RAND_MAX - .5) ); } + +using namespace std; +using namespace Eigen; + +float norm(float x) {return x*x;} +double norm(double x) {return x*x;} +long double norm(long double x) {return x*x;} + +template < typename T> +complex<long double> promote(complex<T> x) { return complex<long double>(x.real(),x.imag()); } + +complex<long double> promote(float x) { return complex<long double>( x); } +complex<long double> promote(double x) { return complex<long double>( x); } +complex<long double> promote(long double x) { return complex<long double>( x); } + + + template <typename VT1,typename VT2> + long double fft_rmse( const VT1 & fftbuf,const VT2 & timebuf) + { + long double totalpower=0; + long double difpower=0; + long double pi = acos((long double)-1 ); + for (size_t k0=0;k0<(size_t)fftbuf.size();++k0) { + complex<long double> acc = 0; + long double phinc = -2.*k0* pi / timebuf.size(); + for (size_t k1=0;k1<(size_t)timebuf.size();++k1) { + acc += promote( timebuf[k1] ) * exp( complex<long double>(0,k1*phinc) ); + } + totalpower += norm(acc); + complex<long double> x = promote(fftbuf[k0]); + complex<long double> dif = acc - x; + difpower += norm(dif); + //cerr << k0 << "\t" << acc << "\t" << x << "\t" << sqrt(norm(dif)) << endl; + } + cerr << "rmse:" << sqrt(difpower/totalpower) << endl; + return sqrt(difpower/totalpower); + } + + template <typename VT1,typename VT2> + long double dif_rmse( const VT1 buf1,const VT2 buf2) + { + long double totalpower=0; + long double difpower=0; + size_t n = (min)( buf1.size(),buf2.size() ); + for (size_t k=0;k<n;++k) { + totalpower += (norm( buf1[k] ) + norm(buf2[k]) )/2.; + difpower += norm(buf1[k] - buf2[k]); + } + return sqrt(difpower/totalpower); + } + +enum { StdVectorContainer, EigenVectorContainer }; + +template<int Container, typename Scalar> struct VectorType; + +template<typename Scalar> struct VectorType<StdVectorContainer,Scalar> +{ + typedef vector<Scalar> type; +}; + +template<typename Scalar> struct VectorType<EigenVectorContainer,Scalar> +{ + typedef Matrix<Scalar,Dynamic,1> type; +}; + +template <int Container, typename T> +void test_scalar_generic(int nfft) +{ + typedef typename FFT<T>::Complex Complex; + typedef typename FFT<T>::Scalar Scalar; + typedef typename VectorType<Container,Scalar>::type ScalarVector; + typedef typename VectorType<Container,Complex>::type ComplexVector; + + FFT<T> fft; + ScalarVector tbuf(nfft); + ComplexVector freqBuf; + for (int k=0;k<nfft;++k) + tbuf[k]= (T)( rand()/(double)RAND_MAX - .5); + + // make sure it DOESN'T give the right full spectrum answer + // if we've asked for half-spectrum + fft.SetFlag(fft.HalfSpectrum ); + fft.fwd( freqBuf,tbuf); + VERIFY((size_t)freqBuf.size() == (size_t)( (nfft>>1)+1) ); + VERIFY( fft_rmse(freqBuf,tbuf) < test_precision<T>() );// gross check + + fft.ClearFlag(fft.HalfSpectrum ); + fft.fwd( freqBuf,tbuf); + VERIFY( (size_t)freqBuf.size() == (size_t)nfft); + VERIFY( fft_rmse(freqBuf,tbuf) < test_precision<T>() );// gross check + + if (nfft&1) + return; // odd FFTs get the wrong size inverse FFT + + ScalarVector tbuf2; + fft.inv( tbuf2 , freqBuf); + VERIFY( dif_rmse(tbuf,tbuf2) < test_precision<T>() );// gross check + + + // verify that the Unscaled flag takes effect + ScalarVector tbuf3; + fft.SetFlag(fft.Unscaled); + + fft.inv( tbuf3 , freqBuf); + + for (int k=0;k<nfft;++k) + tbuf3[k] *= T(1./nfft); + + + //for (size_t i=0;i<(size_t) tbuf.size();++i) + // cout << "freqBuf=" << freqBuf[i] << " in2=" << tbuf3[i] << " - in=" << tbuf[i] << " => " << (tbuf3[i] - tbuf[i] ) << endl; + + VERIFY( dif_rmse(tbuf,tbuf3) < test_precision<T>() );// gross check + + // verify that ClearFlag works + fft.ClearFlag(fft.Unscaled); + fft.inv( tbuf2 , freqBuf); + VERIFY( dif_rmse(tbuf,tbuf2) < test_precision<T>() );// gross check +} + +template <typename T> +void test_scalar(int nfft) +{ + test_scalar_generic<StdVectorContainer,T>(nfft); + //test_scalar_generic<EigenVectorContainer,T>(nfft); +} + + +template <int Container, typename T> +void test_complex_generic(int nfft) +{ + typedef typename FFT<T>::Complex Complex; + typedef typename VectorType<Container,Complex>::type ComplexVector; + + FFT<T> fft; + + ComplexVector inbuf(nfft); + ComplexVector outbuf; + ComplexVector buf3; + for (int k=0;k<nfft;++k) + inbuf[k]= Complex( (T)(rand()/(double)RAND_MAX - .5), (T)(rand()/(double)RAND_MAX - .5) ); + fft.fwd( outbuf , inbuf); + + VERIFY( fft_rmse(outbuf,inbuf) < test_precision<T>() );// gross check + fft.inv( buf3 , outbuf); + + VERIFY( dif_rmse(inbuf,buf3) < test_precision<T>() );// gross check + + // verify that the Unscaled flag takes effect + ComplexVector buf4; + fft.SetFlag(fft.Unscaled); + fft.inv( buf4 , outbuf); + for (int k=0;k<nfft;++k) + buf4[k] *= T(1./nfft); + VERIFY( dif_rmse(inbuf,buf4) < test_precision<T>() );// gross check + + // verify that ClearFlag works + fft.ClearFlag(fft.Unscaled); + fft.inv( buf3 , outbuf); + VERIFY( dif_rmse(inbuf,buf3) < test_precision<T>() );// gross check +} + +template <typename T> +void test_complex(int nfft) +{ + test_complex_generic<StdVectorContainer,T>(nfft); + test_complex_generic<EigenVectorContainer,T>(nfft); +} +/* +template <typename T,int nrows,int ncols> +void test_complex2d() +{ + typedef typename Eigen::FFT<T>::Complex Complex; + FFT<T> fft; + Eigen::Matrix<Complex,nrows,ncols> src,src2,dst,dst2; + + src = Eigen::Matrix<Complex,nrows,ncols>::Random(); + //src = Eigen::Matrix<Complex,nrows,ncols>::Identity(); + + for (int k=0;k<ncols;k++) { + Eigen::Matrix<Complex,nrows,1> tmpOut; + fft.fwd( tmpOut,src.col(k) ); + dst2.col(k) = tmpOut; + } + + for (int k=0;k<nrows;k++) { + Eigen::Matrix<Complex,1,ncols> tmpOut; + fft.fwd( tmpOut, dst2.row(k) ); + dst2.row(k) = tmpOut; + } + + fft.fwd2(dst.data(),src.data(),ncols,nrows); + fft.inv2(src2.data(),dst.data(),ncols,nrows); + VERIFY( (src-src2).norm() < test_precision<T>() ); + VERIFY( (dst-dst2).norm() < test_precision<T>() ); +} +*/ + + +void test_return_by_value(int len) +{ + VectorXf in; + VectorXf in1; + in.setRandom( len ); + VectorXcf out1,out2; + FFT<float> fft; + + fft.SetFlag(fft.HalfSpectrum ); + + fft.fwd(out1,in); + out2 = fft.fwd(in); + VERIFY( (out1-out2).norm() < test_precision<float>() ); + in1 = fft.inv(out1); + VERIFY( (in1-in).norm() < test_precision<float>() ); +} + +void test_FFTW() +{ + CALL_SUBTEST( test_return_by_value(32) ); + //CALL_SUBTEST( ( test_complex2d<float,4,8> () ) ); CALL_SUBTEST( ( test_complex2d<double,4,8> () ) ); + //CALL_SUBTEST( ( test_complex2d<long double,4,8> () ) ); + CALL_SUBTEST( test_complex<float>(32) ); CALL_SUBTEST( test_complex<double>(32) ); + CALL_SUBTEST( test_complex<float>(256) ); CALL_SUBTEST( test_complex<double>(256) ); + CALL_SUBTEST( test_complex<float>(3*8) ); CALL_SUBTEST( test_complex<double>(3*8) ); + CALL_SUBTEST( test_complex<float>(5*32) ); CALL_SUBTEST( test_complex<double>(5*32) ); + CALL_SUBTEST( test_complex<float>(2*3*4) ); CALL_SUBTEST( test_complex<double>(2*3*4) ); + CALL_SUBTEST( test_complex<float>(2*3*4*5) ); CALL_SUBTEST( test_complex<double>(2*3*4*5) ); + CALL_SUBTEST( test_complex<float>(2*3*4*5*7) ); CALL_SUBTEST( test_complex<double>(2*3*4*5*7) ); + + CALL_SUBTEST( test_scalar<float>(32) ); CALL_SUBTEST( test_scalar<double>(32) ); + CALL_SUBTEST( test_scalar<float>(45) ); CALL_SUBTEST( test_scalar<double>(45) ); + CALL_SUBTEST( test_scalar<float>(50) ); CALL_SUBTEST( test_scalar<double>(50) ); + CALL_SUBTEST( test_scalar<float>(256) ); CALL_SUBTEST( test_scalar<double>(256) ); + CALL_SUBTEST( test_scalar<float>(2*3*4*5*7) ); CALL_SUBTEST( test_scalar<double>(2*3*4*5*7) ); + + #ifdef EIGEN_HAS_FFTWL + CALL_SUBTEST( test_complex<long double>(32) ); + CALL_SUBTEST( test_complex<long double>(256) ); + CALL_SUBTEST( test_complex<long double>(3*8) ); + CALL_SUBTEST( test_complex<long double>(5*32) ); + CALL_SUBTEST( test_complex<long double>(2*3*4) ); + CALL_SUBTEST( test_complex<long double>(2*3*4*5) ); + CALL_SUBTEST( test_complex<long double>(2*3*4*5*7) ); + + CALL_SUBTEST( test_scalar<long double>(32) ); + CALL_SUBTEST( test_scalar<long double>(45) ); + CALL_SUBTEST( test_scalar<long double>(50) ); + CALL_SUBTEST( test_scalar<long double>(256) ); + CALL_SUBTEST( test_scalar<long double>(2*3*4*5*7) ); + #endif +} diff --git a/unsupported/test/NonLinearOptimization.cpp b/unsupported/test/NonLinearOptimization.cpp new file mode 100644 index 000000000..81b066897 --- /dev/null +++ b/unsupported/test/NonLinearOptimization.cpp @@ -0,0 +1,1861 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Thomas Capricelli <orzel@freehackers.org> + +#include <stdio.h> + +#include "main.h" +#include <unsupported/Eigen/NonLinearOptimization> + +// This disables some useless Warnings on MSVC. +// It is intended to be done for this test only. +#include <Eigen/src/Core/util/DisableStupidWarnings.h> + +int fcn_chkder(const VectorXd &x, VectorXd &fvec, MatrixXd &fjac, int iflag) +{ + /* subroutine fcn for chkder example. */ + + int i; + assert(15 == fvec.size()); + assert(3 == x.size()); + double tmp1, tmp2, tmp3, tmp4; + static const double y[15]={1.4e-1, 1.8e-1, 2.2e-1, 2.5e-1, 2.9e-1, 3.2e-1, 3.5e-1, + 3.9e-1, 3.7e-1, 5.8e-1, 7.3e-1, 9.6e-1, 1.34, 2.1, 4.39}; + + + if (iflag == 0) + return 0; + + if (iflag != 2) + for (i=0; i<15; i++) { + tmp1 = i+1; + tmp2 = 16-i-1; + tmp3 = tmp1; + if (i >= 8) tmp3 = tmp2; + fvec[i] = y[i] - (x[0] + tmp1/(x[1]*tmp2 + x[2]*tmp3)); + } + else { + for (i = 0; i < 15; i++) { + tmp1 = i+1; + tmp2 = 16-i-1; + + /* error introduced into next statement for illustration. */ + /* corrected statement should read tmp3 = tmp1 . */ + + tmp3 = tmp2; + if (i >= 8) tmp3 = tmp2; + tmp4 = (x[1]*tmp2 + x[2]*tmp3); tmp4=tmp4*tmp4; + fjac(i,0) = -1.; + fjac(i,1) = tmp1*tmp2/tmp4; + fjac(i,2) = tmp1*tmp3/tmp4; + } + } + return 0; +} + + +void testChkder() +{ + const int m=15, n=3; + VectorXd x(n), fvec(m), xp, fvecp(m), err; + MatrixXd fjac(m,n); + VectorXi ipvt; + + /* the following values should be suitable for */ + /* checking the jacobian matrix. */ + x << 9.2e-1, 1.3e-1, 5.4e-1; + + internal::chkder(x, fvec, fjac, xp, fvecp, 1, err); + fcn_chkder(x, fvec, fjac, 1); + fcn_chkder(x, fvec, fjac, 2); + fcn_chkder(xp, fvecp, fjac, 1); + internal::chkder(x, fvec, fjac, xp, fvecp, 2, err); + + fvecp -= fvec; + + // check those + VectorXd fvec_ref(m), fvecp_ref(m), err_ref(m); + fvec_ref << + -1.181606, -1.429655, -1.606344, + -1.745269, -1.840654, -1.921586, + -1.984141, -2.022537, -2.468977, + -2.827562, -3.473582, -4.437612, + -6.047662, -9.267761, -18.91806; + fvecp_ref << + -7.724666e-09, -3.432406e-09, -2.034843e-10, + 2.313685e-09, 4.331078e-09, 5.984096e-09, + 7.363281e-09, 8.53147e-09, 1.488591e-08, + 2.33585e-08, 3.522012e-08, 5.301255e-08, + 8.26666e-08, 1.419747e-07, 3.19899e-07; + err_ref << + 0.1141397, 0.09943516, 0.09674474, + 0.09980447, 0.1073116, 0.1220445, + 0.1526814, 1, 1, + 1, 1, 1, + 1, 1, 1; + + VERIFY_IS_APPROX(fvec, fvec_ref); + VERIFY_IS_APPROX(fvecp, fvecp_ref); + VERIFY_IS_APPROX(err, err_ref); +} + +// Generic functor +template<typename _Scalar, int NX=Dynamic, int NY=Dynamic> +struct Functor +{ + typedef _Scalar Scalar; + enum { + InputsAtCompileTime = NX, + ValuesAtCompileTime = NY + }; + typedef Matrix<Scalar,InputsAtCompileTime,1> InputType; + typedef Matrix<Scalar,ValuesAtCompileTime,1> ValueType; + typedef Matrix<Scalar,ValuesAtCompileTime,InputsAtCompileTime> JacobianType; + + const int m_inputs, m_values; + + Functor() : m_inputs(InputsAtCompileTime), m_values(ValuesAtCompileTime) {} + Functor(int inputs, int values) : m_inputs(inputs), m_values(values) {} + + int inputs() const { return m_inputs; } + int values() const { return m_values; } + + // you should define that in the subclass : +// void operator() (const InputType& x, ValueType* v, JacobianType* _j=0) const; +}; + +struct lmder_functor : Functor<double> +{ + lmder_functor(void): Functor<double>(3,15) {} + int operator()(const VectorXd &x, VectorXd &fvec) const + { + double tmp1, tmp2, tmp3; + static const double y[15] = {1.4e-1, 1.8e-1, 2.2e-1, 2.5e-1, 2.9e-1, 3.2e-1, 3.5e-1, + 3.9e-1, 3.7e-1, 5.8e-1, 7.3e-1, 9.6e-1, 1.34, 2.1, 4.39}; + + for (int i = 0; i < values(); i++) + { + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + fvec[i] = y[i] - (x[0] + tmp1/(x[1]*tmp2 + x[2]*tmp3)); + } + return 0; + } + + int df(const VectorXd &x, MatrixXd &fjac) const + { + double tmp1, tmp2, tmp3, tmp4; + for (int i = 0; i < values(); i++) + { + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + tmp4 = (x[1]*tmp2 + x[2]*tmp3); tmp4 = tmp4*tmp4; + fjac(i,0) = -1; + fjac(i,1) = tmp1*tmp2/tmp4; + fjac(i,2) = tmp1*tmp3/tmp4; + } + return 0; + } +}; + +void testLmder1() +{ + int n=3, info; + + VectorXd x; + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmder_functor functor; + LevenbergMarquardt<lmder_functor> lm(functor); + info = lm.lmder1(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 6); + VERIFY_IS_EQUAL(lm.njev, 5); + + // check norm + VERIFY_IS_APPROX(lm.fvec.blueNorm(), 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.08241058, 1.133037, 2.343695; + VERIFY_IS_APPROX(x, x_ref); +} + +void testLmder() +{ + const int m=15, n=3; + int info; + double fnorm, covfac; + VectorXd x; + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmder_functor functor; + LevenbergMarquardt<lmder_functor> lm(functor); + info = lm.minimize(x); + + // check return values + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 6); + VERIFY_IS_EQUAL(lm.njev, 5); + + // check norm + fnorm = lm.fvec.blueNorm(); + VERIFY_IS_APPROX(fnorm, 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.08241058, 1.133037, 2.343695; + VERIFY_IS_APPROX(x, x_ref); + + // check covariance + covfac = fnorm*fnorm/(m-n); + internal::covar(lm.fjac, lm.permutation.indices()); // TODO : move this as a function of lm + + MatrixXd cov_ref(n,n); + cov_ref << + 0.0001531202, 0.002869941, -0.002656662, + 0.002869941, 0.09480935, -0.09098995, + -0.002656662, -0.09098995, 0.08778727; + +// std::cout << fjac*covfac << std::endl; + + MatrixXd cov; + cov = covfac*lm.fjac.topLeftCorner<n,n>(); + VERIFY_IS_APPROX( cov, cov_ref); + // TODO: why isn't this allowed ? : + // VERIFY_IS_APPROX( covfac*fjac.topLeftCorner<n,n>() , cov_ref); +} + +struct hybrj_functor : Functor<double> +{ + hybrj_functor(void) : Functor<double>(9,9) {} + + int operator()(const VectorXd &x, VectorXd &fvec) + { + double temp, temp1, temp2; + const int n = x.size(); + assert(fvec.size()==n); + for (int k = 0; k < n; k++) + { + temp = (3. - 2.*x[k])*x[k]; + temp1 = 0.; + if (k) temp1 = x[k-1]; + temp2 = 0.; + if (k != n-1) temp2 = x[k+1]; + fvec[k] = temp - temp1 - 2.*temp2 + 1.; + } + return 0; + } + int df(const VectorXd &x, MatrixXd &fjac) + { + const int n = x.size(); + assert(fjac.rows()==n); + assert(fjac.cols()==n); + for (int k = 0; k < n; k++) + { + for (int j = 0; j < n; j++) + fjac(k,j) = 0.; + fjac(k,k) = 3.- 4.*x[k]; + if (k) fjac(k,k-1) = -1.; + if (k != n-1) fjac(k,k+1) = -2.; + } + return 0; + } +}; + + +void testHybrj1() +{ + const int n=9; + int info; + VectorXd x(n); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, -1.); + + // do the computation + hybrj_functor functor; + HybridNonLinearSolver<hybrj_functor> solver(functor); + info = solver.hybrj1(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(solver.nfev, 11); + VERIFY_IS_EQUAL(solver.njev, 1); + + // check norm + VERIFY_IS_APPROX(solver.fvec.blueNorm(), 1.192636e-08); + + +// check x + VectorXd x_ref(n); + x_ref << + -0.5706545, -0.6816283, -0.7017325, + -0.7042129, -0.701369, -0.6918656, + -0.665792, -0.5960342, -0.4164121; + VERIFY_IS_APPROX(x, x_ref); +} + +void testHybrj() +{ + const int n=9; + int info; + VectorXd x(n); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, -1.); + + + // do the computation + hybrj_functor functor; + HybridNonLinearSolver<hybrj_functor> solver(functor); + solver.diag.setConstant(n, 1.); + solver.useExternalScaling = true; + info = solver.solve(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(solver.nfev, 11); + VERIFY_IS_EQUAL(solver.njev, 1); + + // check norm + VERIFY_IS_APPROX(solver.fvec.blueNorm(), 1.192636e-08); + + +// check x + VectorXd x_ref(n); + x_ref << + -0.5706545, -0.6816283, -0.7017325, + -0.7042129, -0.701369, -0.6918656, + -0.665792, -0.5960342, -0.4164121; + VERIFY_IS_APPROX(x, x_ref); + +} + +struct hybrd_functor : Functor<double> +{ + hybrd_functor(void) : Functor<double>(9,9) {} + int operator()(const VectorXd &x, VectorXd &fvec) const + { + double temp, temp1, temp2; + const int n = x.size(); + + assert(fvec.size()==n); + for (int k=0; k < n; k++) + { + temp = (3. - 2.*x[k])*x[k]; + temp1 = 0.; + if (k) temp1 = x[k-1]; + temp2 = 0.; + if (k != n-1) temp2 = x[k+1]; + fvec[k] = temp - temp1 - 2.*temp2 + 1.; + } + return 0; + } +}; + +void testHybrd1() +{ + int n=9, info; + VectorXd x(n); + + /* the following starting values provide a rough solution. */ + x.setConstant(n, -1.); + + // do the computation + hybrd_functor functor; + HybridNonLinearSolver<hybrd_functor> solver(functor); + info = solver.hybrd1(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(solver.nfev, 20); + + // check norm + VERIFY_IS_APPROX(solver.fvec.blueNorm(), 1.192636e-08); + + // check x + VectorXd x_ref(n); + x_ref << -0.5706545, -0.6816283, -0.7017325, -0.7042129, -0.701369, -0.6918656, -0.665792, -0.5960342, -0.4164121; + VERIFY_IS_APPROX(x, x_ref); +} + +void testHybrd() +{ + const int n=9; + int info; + VectorXd x; + + /* the following starting values provide a rough fit. */ + x.setConstant(n, -1.); + + // do the computation + hybrd_functor functor; + HybridNonLinearSolver<hybrd_functor> solver(functor); + solver.parameters.nb_of_subdiagonals = 1; + solver.parameters.nb_of_superdiagonals = 1; + solver.diag.setConstant(n, 1.); + solver.useExternalScaling = true; + info = solver.solveNumericalDiff(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(solver.nfev, 14); + + // check norm + VERIFY_IS_APPROX(solver.fvec.blueNorm(), 1.192636e-08); + + // check x + VectorXd x_ref(n); + x_ref << + -0.5706545, -0.6816283, -0.7017325, + -0.7042129, -0.701369, -0.6918656, + -0.665792, -0.5960342, -0.4164121; + VERIFY_IS_APPROX(x, x_ref); +} + +struct lmstr_functor : Functor<double> +{ + lmstr_functor(void) : Functor<double>(3,15) {} + int operator()(const VectorXd &x, VectorXd &fvec) + { + /* subroutine fcn for lmstr1 example. */ + double tmp1, tmp2, tmp3; + static const double y[15]={1.4e-1, 1.8e-1, 2.2e-1, 2.5e-1, 2.9e-1, 3.2e-1, 3.5e-1, + 3.9e-1, 3.7e-1, 5.8e-1, 7.3e-1, 9.6e-1, 1.34, 2.1, 4.39}; + + assert(15==fvec.size()); + assert(3==x.size()); + + for (int i=0; i<15; i++) + { + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + fvec[i] = y[i] - (x[0] + tmp1/(x[1]*tmp2 + x[2]*tmp3)); + } + return 0; + } + int df(const VectorXd &x, VectorXd &jac_row, VectorXd::Index rownb) + { + assert(x.size()==3); + assert(jac_row.size()==x.size()); + double tmp1, tmp2, tmp3, tmp4; + + int i = rownb-2; + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + tmp4 = (x[1]*tmp2 + x[2]*tmp3); tmp4 = tmp4*tmp4; + jac_row[0] = -1; + jac_row[1] = tmp1*tmp2/tmp4; + jac_row[2] = tmp1*tmp3/tmp4; + return 0; + } +}; + +void testLmstr1() +{ + const int n=3; + int info; + + VectorXd x(n); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmstr_functor functor; + LevenbergMarquardt<lmstr_functor> lm(functor); + info = lm.lmstr1(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 6); + VERIFY_IS_EQUAL(lm.njev, 5); + + // check norm + VERIFY_IS_APPROX(lm.fvec.blueNorm(), 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.08241058, 1.133037, 2.343695 ; + VERIFY_IS_APPROX(x, x_ref); +} + +void testLmstr() +{ + const int n=3; + int info; + double fnorm; + VectorXd x(n); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmstr_functor functor; + LevenbergMarquardt<lmstr_functor> lm(functor); + info = lm.minimizeOptimumStorage(x); + + // check return values + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 6); + VERIFY_IS_EQUAL(lm.njev, 5); + + // check norm + fnorm = lm.fvec.blueNorm(); + VERIFY_IS_APPROX(fnorm, 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.08241058, 1.133037, 2.343695; + VERIFY_IS_APPROX(x, x_ref); + +} + +struct lmdif_functor : Functor<double> +{ + lmdif_functor(void) : Functor<double>(3,15) {} + int operator()(const VectorXd &x, VectorXd &fvec) const + { + int i; + double tmp1,tmp2,tmp3; + static const double y[15]={1.4e-1,1.8e-1,2.2e-1,2.5e-1,2.9e-1,3.2e-1,3.5e-1,3.9e-1, + 3.7e-1,5.8e-1,7.3e-1,9.6e-1,1.34e0,2.1e0,4.39e0}; + + assert(x.size()==3); + assert(fvec.size()==15); + for (i=0; i<15; i++) + { + tmp1 = i+1; + tmp2 = 15 - i; + tmp3 = tmp1; + + if (i >= 8) tmp3 = tmp2; + fvec[i] = y[i] - (x[0] + tmp1/(x[1]*tmp2 + x[2]*tmp3)); + } + return 0; + } +}; + +void testLmdif1() +{ + const int n=3; + int info; + + VectorXd x(n), fvec(15); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmdif_functor functor; + DenseIndex nfev; + info = LevenbergMarquardt<lmdif_functor>::lmdif1(functor, x, &nfev); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(nfev, 26); + + // check norm + functor(x, fvec); + VERIFY_IS_APPROX(fvec.blueNorm(), 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.0824106, 1.1330366, 2.3436947; + VERIFY_IS_APPROX(x, x_ref); + +} + +void testLmdif() +{ + const int m=15, n=3; + int info; + double fnorm, covfac; + VectorXd x(n); + + /* the following starting values provide a rough fit. */ + x.setConstant(n, 1.); + + // do the computation + lmdif_functor functor; + NumericalDiff<lmdif_functor> numDiff(functor); + LevenbergMarquardt<NumericalDiff<lmdif_functor> > lm(numDiff); + info = lm.minimize(x); + + // check return values + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 26); + + // check norm + fnorm = lm.fvec.blueNorm(); + VERIFY_IS_APPROX(fnorm, 0.09063596); + + // check x + VectorXd x_ref(n); + x_ref << 0.08241058, 1.133037, 2.343695; + VERIFY_IS_APPROX(x, x_ref); + + // check covariance + covfac = fnorm*fnorm/(m-n); + internal::covar(lm.fjac, lm.permutation.indices()); // TODO : move this as a function of lm + + MatrixXd cov_ref(n,n); + cov_ref << + 0.0001531202, 0.002869942, -0.002656662, + 0.002869942, 0.09480937, -0.09098997, + -0.002656662, -0.09098997, 0.08778729; + +// std::cout << fjac*covfac << std::endl; + + MatrixXd cov; + cov = covfac*lm.fjac.topLeftCorner<n,n>(); + VERIFY_IS_APPROX( cov, cov_ref); + // TODO: why isn't this allowed ? : + // VERIFY_IS_APPROX( covfac*fjac.topLeftCorner<n,n>() , cov_ref); +} + +struct chwirut2_functor : Functor<double> +{ + chwirut2_functor(void) : Functor<double>(3,54) {} + static const double m_x[54]; + static const double m_y[54]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + int i; + + assert(b.size()==3); + assert(fvec.size()==54); + for(i=0; i<54; i++) { + double x = m_x[i]; + fvec[i] = exp(-b[0]*x)/(b[1]+b[2]*x) - m_y[i]; + } + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==3); + assert(fjac.rows()==54); + assert(fjac.cols()==3); + for(int i=0; i<54; i++) { + double x = m_x[i]; + double factor = 1./(b[1]+b[2]*x); + double e = exp(-b[0]*x); + fjac(i,0) = -x*e*factor; + fjac(i,1) = -e*factor*factor; + fjac(i,2) = -x*e*factor*factor; + } + return 0; + } +}; +const double chwirut2_functor::m_x[54] = { 0.500E0, 1.000E0, 1.750E0, 3.750E0, 5.750E0, 0.875E0, 2.250E0, 3.250E0, 5.250E0, 0.750E0, 1.750E0, 2.750E0, 4.750E0, 0.625E0, 1.250E0, 2.250E0, 4.250E0, .500E0, 3.000E0, .750E0, 3.000E0, 1.500E0, 6.000E0, 3.000E0, 6.000E0, 1.500E0, 3.000E0, .500E0, 2.000E0, 4.000E0, .750E0, 2.000E0, 5.000E0, .750E0, 2.250E0, 3.750E0, 5.750E0, 3.000E0, .750E0, 2.500E0, 4.000E0, .750E0, 2.500E0, 4.000E0, .750E0, 2.500E0, 4.000E0, .500E0, 6.000E0, 3.000E0, .500E0, 2.750E0, .500E0, 1.750E0}; +const double chwirut2_functor::m_y[54] = { 92.9000E0 ,57.1000E0 ,31.0500E0 ,11.5875E0 ,8.0250E0 ,63.6000E0 ,21.4000E0 ,14.2500E0 ,8.4750E0 ,63.8000E0 ,26.8000E0 ,16.4625E0 ,7.1250E0 ,67.3000E0 ,41.0000E0 ,21.1500E0 ,8.1750E0 ,81.5000E0 ,13.1200E0 ,59.9000E0 ,14.6200E0 ,32.9000E0 ,5.4400E0 ,12.5600E0 ,5.4400E0 ,32.0000E0 ,13.9500E0 ,75.8000E0 ,20.0000E0 ,10.4200E0 ,59.5000E0 ,21.6700E0 ,8.5500E0 ,62.0000E0 ,20.2000E0 ,7.7600E0 ,3.7500E0 ,11.8100E0 ,54.7000E0 ,23.7000E0 ,11.5500E0 ,61.3000E0 ,17.7000E0 ,8.7400E0 ,59.2000E0 ,16.3000E0 ,8.6200E0 ,81.0000E0 ,4.8700E0 ,14.6200E0 ,81.7000E0 ,17.1700E0 ,81.3000E0 ,28.9000E0 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/chwirut2.shtml +void testNistChwirut2(void) +{ + const int n=3; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 0.1, 0.01, 0.02; + // do the computation + chwirut2_functor functor; + LevenbergMarquardt<chwirut2_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 10); + VERIFY_IS_EQUAL(lm.njev, 8); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.1304802941E+02); + // check x + VERIFY_IS_APPROX(x[0], 1.6657666537E-01); + VERIFY_IS_APPROX(x[1], 5.1653291286E-03); + VERIFY_IS_APPROX(x[2], 1.2150007096E-02); + + /* + * Second try + */ + x<< 0.15, 0.008, 0.010; + // do the computation + lm.resetParameters(); + lm.parameters.ftol = 1.E6*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E6*NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 7); + VERIFY_IS_EQUAL(lm.njev, 6); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.1304802941E+02); + // check x + VERIFY_IS_APPROX(x[0], 1.6657666537E-01); + VERIFY_IS_APPROX(x[1], 5.1653291286E-03); + VERIFY_IS_APPROX(x[2], 1.2150007096E-02); +} + + +struct misra1a_functor : Functor<double> +{ + misra1a_functor(void) : Functor<double>(2,14) {} + static const double m_x[14]; + static const double m_y[14]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==2); + assert(fvec.size()==14); + for(int i=0; i<14; i++) { + fvec[i] = b[0]*(1.-exp(-b[1]*m_x[i])) - m_y[i] ; + } + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==2); + assert(fjac.rows()==14); + assert(fjac.cols()==2); + for(int i=0; i<14; i++) { + fjac(i,0) = (1.-exp(-b[1]*m_x[i])); + fjac(i,1) = (b[0]*m_x[i]*exp(-b[1]*m_x[i])); + } + return 0; + } +}; +const double misra1a_functor::m_x[14] = { 77.6E0, 114.9E0, 141.1E0, 190.8E0, 239.9E0, 289.0E0, 332.8E0, 378.4E0, 434.8E0, 477.3E0, 536.8E0, 593.1E0, 689.1E0, 760.0E0}; +const double misra1a_functor::m_y[14] = { 10.07E0, 14.73E0, 17.94E0, 23.93E0, 29.61E0, 35.18E0, 40.02E0, 44.82E0, 50.76E0, 55.05E0, 61.01E0, 66.40E0, 75.47E0, 81.78E0}; + +// http://www.itl.nist.gov/div898/strd/nls/data/misra1a.shtml +void testNistMisra1a(void) +{ + const int n=2; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 500., 0.0001; + // do the computation + misra1a_functor functor; + LevenbergMarquardt<misra1a_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 19); + VERIFY_IS_EQUAL(lm.njev, 15); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.2455138894E-01); + // check x + VERIFY_IS_APPROX(x[0], 2.3894212918E+02); + VERIFY_IS_APPROX(x[1], 5.5015643181E-04); + + /* + * Second try + */ + x<< 250., 0.0005; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 5); + VERIFY_IS_EQUAL(lm.njev, 4); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.2455138894E-01); + // check x + VERIFY_IS_APPROX(x[0], 2.3894212918E+02); + VERIFY_IS_APPROX(x[1], 5.5015643181E-04); +} + +struct hahn1_functor : Functor<double> +{ + hahn1_functor(void) : Functor<double>(7,236) {} + static const double m_x[236]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + static const double m_y[236] = { .591E0 , 1.547E0 , 2.902E0 , 2.894E0 , 4.703E0 , 6.307E0 , 7.03E0 , 7.898E0 , 9.470E0 , 9.484E0 , 10.072E0 , 10.163E0 , 11.615E0 , 12.005E0 , 12.478E0 , 12.982E0 , 12.970E0 , 13.926E0 , 14.452E0 , 14.404E0 , 15.190E0 , 15.550E0 , 15.528E0 , 15.499E0 , 16.131E0 , 16.438E0 , 16.387E0 , 16.549E0 , 16.872E0 , 16.830E0 , 16.926E0 , 16.907E0 , 16.966E0 , 17.060E0 , 17.122E0 , 17.311E0 , 17.355E0 , 17.668E0 , 17.767E0 , 17.803E0 , 17.765E0 , 17.768E0 , 17.736E0 , 17.858E0 , 17.877E0 , 17.912E0 , 18.046E0 , 18.085E0 , 18.291E0 , 18.357E0 , 18.426E0 , 18.584E0 , 18.610E0 , 18.870E0 , 18.795E0 , 19.111E0 , .367E0 , .796E0 , 0.892E0 , 1.903E0 , 2.150E0 , 3.697E0 , 5.870E0 , 6.421E0 , 7.422E0 , 9.944E0 , 11.023E0 , 11.87E0 , 12.786E0 , 14.067E0 , 13.974E0 , 14.462E0 , 14.464E0 , 15.381E0 , 15.483E0 , 15.59E0 , 16.075E0 , 16.347E0 , 16.181E0 , 16.915E0 , 17.003E0 , 16.978E0 , 17.756E0 , 17.808E0 , 17.868E0 , 18.481E0 , 18.486E0 , 19.090E0 , 16.062E0 , 16.337E0 , 16.345E0 , 16.388E0 , 17.159E0 , 17.116E0 , 17.164E0 , 17.123E0 , 17.979E0 , 17.974E0 , 18.007E0 , 17.993E0 , 18.523E0 , 18.669E0 , 18.617E0 , 19.371E0 , 19.330E0 , 0.080E0 , 0.248E0 , 1.089E0 , 1.418E0 , 2.278E0 , 3.624E0 , 4.574E0 , 5.556E0 , 7.267E0 , 7.695E0 , 9.136E0 , 9.959E0 , 9.957E0 , 11.600E0 , 13.138E0 , 13.564E0 , 13.871E0 , 13.994E0 , 14.947E0 , 15.473E0 , 15.379E0 , 15.455E0 , 15.908E0 , 16.114E0 , 17.071E0 , 17.135E0 , 17.282E0 , 17.368E0 , 17.483E0 , 17.764E0 , 18.185E0 , 18.271E0 , 18.236E0 , 18.237E0 , 18.523E0 , 18.627E0 , 18.665E0 , 19.086E0 , 0.214E0 , 0.943E0 , 1.429E0 , 2.241E0 , 2.951E0 , 3.782E0 , 4.757E0 , 5.602E0 , 7.169E0 , 8.920E0 , 10.055E0 , 12.035E0 , 12.861E0 , 13.436E0 , 14.167E0 , 14.755E0 , 15.168E0 , 15.651E0 , 15.746E0 , 16.216E0 , 16.445E0 , 16.965E0 , 17.121E0 , 17.206E0 , 17.250E0 , 17.339E0 , 17.793E0 , 18.123E0 , 18.49E0 , 18.566E0 , 18.645E0 , 18.706E0 , 18.924E0 , 19.1E0 , 0.375E0 , 0.471E0 , 1.504E0 , 2.204E0 , 2.813E0 , 4.765E0 , 9.835E0 , 10.040E0 , 11.946E0 , 12.596E0 , 13.303E0 , 13.922E0 , 14.440E0 , 14.951E0 , 15.627E0 , 15.639E0 , 15.814E0 , 16.315E0 , 16.334E0 , 16.430E0 , 16.423E0 , 17.024E0 , 17.009E0 , 17.165E0 , 17.134E0 , 17.349E0 , 17.576E0 , 17.848E0 , 18.090E0 , 18.276E0 , 18.404E0 , 18.519E0 , 19.133E0 , 19.074E0 , 19.239E0 , 19.280E0 , 19.101E0 , 19.398E0 , 19.252E0 , 19.89E0 , 20.007E0 , 19.929E0 , 19.268E0 , 19.324E0 , 20.049E0 , 20.107E0 , 20.062E0 , 20.065E0 , 19.286E0 , 19.972E0 , 20.088E0 , 20.743E0 , 20.83E0 , 20.935E0 , 21.035E0 , 20.93E0 , 21.074E0 , 21.085E0 , 20.935E0 }; + + // int called=0; printf("call hahn1_functor with iflag=%d, called=%d\n", iflag, called); if (iflag==1) called++; + + assert(b.size()==7); + assert(fvec.size()==236); + for(int i=0; i<236; i++) { + double x=m_x[i], xx=x*x, xxx=xx*x; + fvec[i] = (b[0]+b[1]*x+b[2]*xx+b[3]*xxx) / (1.+b[4]*x+b[5]*xx+b[6]*xxx) - m_y[i]; + } + return 0; + } + + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==7); + assert(fjac.rows()==236); + assert(fjac.cols()==7); + for(int i=0; i<236; i++) { + double x=m_x[i], xx=x*x, xxx=xx*x; + double fact = 1./(1.+b[4]*x+b[5]*xx+b[6]*xxx); + fjac(i,0) = 1.*fact; + fjac(i,1) = x*fact; + fjac(i,2) = xx*fact; + fjac(i,3) = xxx*fact; + fact = - (b[0]+b[1]*x+b[2]*xx+b[3]*xxx) * fact * fact; + fjac(i,4) = x*fact; + fjac(i,5) = xx*fact; + fjac(i,6) = xxx*fact; + } + return 0; + } +}; +const double hahn1_functor::m_x[236] = { 24.41E0 , 34.82E0 , 44.09E0 , 45.07E0 , 54.98E0 , 65.51E0 , 70.53E0 , 75.70E0 , 89.57E0 , 91.14E0 , 96.40E0 , 97.19E0 , 114.26E0 , 120.25E0 , 127.08E0 , 133.55E0 , 133.61E0 , 158.67E0 , 172.74E0 , 171.31E0 , 202.14E0 , 220.55E0 , 221.05E0 , 221.39E0 , 250.99E0 , 268.99E0 , 271.80E0 , 271.97E0 , 321.31E0 , 321.69E0 , 330.14E0 , 333.03E0 , 333.47E0 , 340.77E0 , 345.65E0 , 373.11E0 , 373.79E0 , 411.82E0 , 419.51E0 , 421.59E0 , 422.02E0 , 422.47E0 , 422.61E0 , 441.75E0 , 447.41E0 , 448.7E0 , 472.89E0 , 476.69E0 , 522.47E0 , 522.62E0 , 524.43E0 , 546.75E0 , 549.53E0 , 575.29E0 , 576.00E0 , 625.55E0 , 20.15E0 , 28.78E0 , 29.57E0 , 37.41E0 , 39.12E0 , 50.24E0 , 61.38E0 , 66.25E0 , 73.42E0 , 95.52E0 , 107.32E0 , 122.04E0 , 134.03E0 , 163.19E0 , 163.48E0 , 175.70E0 , 179.86E0 , 211.27E0 , 217.78E0 , 219.14E0 , 262.52E0 , 268.01E0 , 268.62E0 , 336.25E0 , 337.23E0 , 339.33E0 , 427.38E0 , 428.58E0 , 432.68E0 , 528.99E0 , 531.08E0 , 628.34E0 , 253.24E0 , 273.13E0 , 273.66E0 , 282.10E0 , 346.62E0 , 347.19E0 , 348.78E0 , 351.18E0 , 450.10E0 , 450.35E0 , 451.92E0 , 455.56E0 , 552.22E0 , 553.56E0 , 555.74E0 , 652.59E0 , 656.20E0 , 14.13E0 , 20.41E0 , 31.30E0 , 33.84E0 , 39.70E0 , 48.83E0 , 54.50E0 , 60.41E0 , 72.77E0 , 75.25E0 , 86.84E0 , 94.88E0 , 96.40E0 , 117.37E0 , 139.08E0 , 147.73E0 , 158.63E0 , 161.84E0 , 192.11E0 , 206.76E0 , 209.07E0 , 213.32E0 , 226.44E0 , 237.12E0 , 330.90E0 , 358.72E0 , 370.77E0 , 372.72E0 , 396.24E0 , 416.59E0 , 484.02E0 , 495.47E0 , 514.78E0 , 515.65E0 , 519.47E0 , 544.47E0 , 560.11E0 , 620.77E0 , 18.97E0 , 28.93E0 , 33.91E0 , 40.03E0 , 44.66E0 , 49.87E0 , 55.16E0 , 60.90E0 , 72.08E0 , 85.15E0 , 97.06E0 , 119.63E0 , 133.27E0 , 143.84E0 , 161.91E0 , 180.67E0 , 198.44E0 , 226.86E0 , 229.65E0 , 258.27E0 , 273.77E0 , 339.15E0 , 350.13E0 , 362.75E0 , 371.03E0 , 393.32E0 , 448.53E0 , 473.78E0 , 511.12E0 , 524.70E0 , 548.75E0 , 551.64E0 , 574.02E0 , 623.86E0 , 21.46E0 , 24.33E0 , 33.43E0 , 39.22E0 , 44.18E0 , 55.02E0 , 94.33E0 , 96.44E0 , 118.82E0 , 128.48E0 , 141.94E0 , 156.92E0 , 171.65E0 , 190.00E0 , 223.26E0 , 223.88E0 , 231.50E0 , 265.05E0 , 269.44E0 , 271.78E0 , 273.46E0 , 334.61E0 , 339.79E0 , 349.52E0 , 358.18E0 , 377.98E0 , 394.77E0 , 429.66E0 , 468.22E0 , 487.27E0 , 519.54E0 , 523.03E0 , 612.99E0 , 638.59E0 , 641.36E0 , 622.05E0 , 631.50E0 , 663.97E0 , 646.9E0 , 748.29E0 , 749.21E0 , 750.14E0 , 647.04E0 , 646.89E0 , 746.9E0 , 748.43E0 , 747.35E0 , 749.27E0 , 647.61E0 , 747.78E0 , 750.51E0 , 851.37E0 , 845.97E0 , 847.54E0 , 849.93E0 , 851.61E0 , 849.75E0 , 850.98E0 , 848.23E0}; + +// http://www.itl.nist.gov/div898/strd/nls/data/hahn1.shtml +void testNistHahn1(void) +{ + const int n=7; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 10., -1., .05, -.00001, -.05, .001, -.000001; + // do the computation + hahn1_functor functor; + LevenbergMarquardt<hahn1_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 11); + VERIFY_IS_EQUAL(lm.njev, 10); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.5324382854E+00); + // check x + VERIFY_IS_APPROX(x[0], 1.0776351733E+00); + VERIFY_IS_APPROX(x[1],-1.2269296921E-01); + VERIFY_IS_APPROX(x[2], 4.0863750610E-03); + VERIFY_IS_APPROX(x[3],-1.426264e-06); // shoulde be : -1.4262662514E-06 + VERIFY_IS_APPROX(x[4],-5.7609940901E-03); + VERIFY_IS_APPROX(x[5], 2.4053735503E-04); + VERIFY_IS_APPROX(x[6],-1.2314450199E-07); + + /* + * Second try + */ + x<< .1, -.1, .005, -.000001, -.005, .0001, -.0000001; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 11); + VERIFY_IS_EQUAL(lm.njev, 10); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.5324382854E+00); + // check x + VERIFY_IS_APPROX(x[0], 1.077640); // should be : 1.0776351733E+00 + VERIFY_IS_APPROX(x[1], -0.1226933); // should be : -1.2269296921E-01 + VERIFY_IS_APPROX(x[2], 0.004086383); // should be : 4.0863750610E-03 + VERIFY_IS_APPROX(x[3], -1.426277e-06); // shoulde be : -1.4262662514E-06 + VERIFY_IS_APPROX(x[4],-5.7609940901E-03); + VERIFY_IS_APPROX(x[5], 0.00024053772); // should be : 2.4053735503E-04 + VERIFY_IS_APPROX(x[6], -1.231450e-07); // should be : -1.2314450199E-07 + +} + +struct misra1d_functor : Functor<double> +{ + misra1d_functor(void) : Functor<double>(2,14) {} + static const double x[14]; + static const double y[14]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==2); + assert(fvec.size()==14); + for(int i=0; i<14; i++) { + fvec[i] = b[0]*b[1]*x[i]/(1.+b[1]*x[i]) - y[i]; + } + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==2); + assert(fjac.rows()==14); + assert(fjac.cols()==2); + for(int i=0; i<14; i++) { + double den = 1.+b[1]*x[i]; + fjac(i,0) = b[1]*x[i] / den; + fjac(i,1) = b[0]*x[i]*(den-b[1]*x[i])/den/den; + } + return 0; + } +}; +const double misra1d_functor::x[14] = { 77.6E0, 114.9E0, 141.1E0, 190.8E0, 239.9E0, 289.0E0, 332.8E0, 378.4E0, 434.8E0, 477.3E0, 536.8E0, 593.1E0, 689.1E0, 760.0E0}; +const double misra1d_functor::y[14] = { 10.07E0, 14.73E0, 17.94E0, 23.93E0, 29.61E0, 35.18E0, 40.02E0, 44.82E0, 50.76E0, 55.05E0, 61.01E0, 66.40E0, 75.47E0, 81.78E0}; + +// http://www.itl.nist.gov/div898/strd/nls/data/misra1d.shtml +void testNistMisra1d(void) +{ + const int n=2; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 500., 0.0001; + // do the computation + misra1d_functor functor; + LevenbergMarquardt<misra1d_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 3); + VERIFY_IS_EQUAL(lm.nfev, 9); + VERIFY_IS_EQUAL(lm.njev, 7); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.6419295283E-02); + // check x + VERIFY_IS_APPROX(x[0], 4.3736970754E+02); + VERIFY_IS_APPROX(x[1], 3.0227324449E-04); + + /* + * Second try + */ + x<< 450., 0.0003; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 4); + VERIFY_IS_EQUAL(lm.njev, 3); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.6419295283E-02); + // check x + VERIFY_IS_APPROX(x[0], 4.3736970754E+02); + VERIFY_IS_APPROX(x[1], 3.0227324449E-04); +} + + +struct lanczos1_functor : Functor<double> +{ + lanczos1_functor(void) : Functor<double>(6,24) {} + static const double x[24]; + static const double y[24]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==6); + assert(fvec.size()==24); + for(int i=0; i<24; i++) + fvec[i] = b[0]*exp(-b[1]*x[i]) + b[2]*exp(-b[3]*x[i]) + b[4]*exp(-b[5]*x[i]) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==6); + assert(fjac.rows()==24); + assert(fjac.cols()==6); + for(int i=0; i<24; i++) { + fjac(i,0) = exp(-b[1]*x[i]); + fjac(i,1) = -b[0]*x[i]*exp(-b[1]*x[i]); + fjac(i,2) = exp(-b[3]*x[i]); + fjac(i,3) = -b[2]*x[i]*exp(-b[3]*x[i]); + fjac(i,4) = exp(-b[5]*x[i]); + fjac(i,5) = -b[4]*x[i]*exp(-b[5]*x[i]); + } + return 0; + } +}; +const double lanczos1_functor::x[24] = { 0.000000000000E+00, 5.000000000000E-02, 1.000000000000E-01, 1.500000000000E-01, 2.000000000000E-01, 2.500000000000E-01, 3.000000000000E-01, 3.500000000000E-01, 4.000000000000E-01, 4.500000000000E-01, 5.000000000000E-01, 5.500000000000E-01, 6.000000000000E-01, 6.500000000000E-01, 7.000000000000E-01, 7.500000000000E-01, 8.000000000000E-01, 8.500000000000E-01, 9.000000000000E-01, 9.500000000000E-01, 1.000000000000E+00, 1.050000000000E+00, 1.100000000000E+00, 1.150000000000E+00 }; +const double lanczos1_functor::y[24] = { 2.513400000000E+00 ,2.044333373291E+00 ,1.668404436564E+00 ,1.366418021208E+00 ,1.123232487372E+00 ,9.268897180037E-01 ,7.679338563728E-01 ,6.388775523106E-01 ,5.337835317402E-01 ,4.479363617347E-01 ,3.775847884350E-01 ,3.197393199326E-01 ,2.720130773746E-01 ,2.324965529032E-01 ,1.996589546065E-01 ,1.722704126914E-01 ,1.493405660168E-01 ,1.300700206922E-01 ,1.138119324644E-01 ,1.000415587559E-01 ,8.833209084540E-02 ,7.833544019350E-02 ,6.976693743449E-02 ,6.239312536719E-02 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/lanczos1.shtml +void testNistLanczos1(void) +{ + const int n=6; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 1.2, 0.3, 5.6, 5.5, 6.5, 7.6; + // do the computation + lanczos1_functor functor; + LevenbergMarquardt<lanczos1_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 2); + VERIFY_IS_EQUAL(lm.nfev, 79); + VERIFY_IS_EQUAL(lm.njev, 72); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.430899764097e-25); // should be 1.4307867721E-25, but nist results are on 128-bit floats + // check x + VERIFY_IS_APPROX(x[0], 9.5100000027E-02); + VERIFY_IS_APPROX(x[1], 1.0000000001E+00); + VERIFY_IS_APPROX(x[2], 8.6070000013E-01); + VERIFY_IS_APPROX(x[3], 3.0000000002E+00); + VERIFY_IS_APPROX(x[4], 1.5575999998E+00); + VERIFY_IS_APPROX(x[5], 5.0000000001E+00); + + /* + * Second try + */ + x<< 0.5, 0.7, 3.6, 4.2, 4., 6.3; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 2); + VERIFY_IS_EQUAL(lm.nfev, 9); + VERIFY_IS_EQUAL(lm.njev, 8); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.428595533845e-25); // should be 1.4307867721E-25, but nist results are on 128-bit floats + // check x + VERIFY_IS_APPROX(x[0], 9.5100000027E-02); + VERIFY_IS_APPROX(x[1], 1.0000000001E+00); + VERIFY_IS_APPROX(x[2], 8.6070000013E-01); + VERIFY_IS_APPROX(x[3], 3.0000000002E+00); + VERIFY_IS_APPROX(x[4], 1.5575999998E+00); + VERIFY_IS_APPROX(x[5], 5.0000000001E+00); + +} + +struct rat42_functor : Functor<double> +{ + rat42_functor(void) : Functor<double>(3,9) {} + static const double x[9]; + static const double y[9]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==3); + assert(fvec.size()==9); + for(int i=0; i<9; i++) { + fvec[i] = b[0] / (1.+exp(b[1]-b[2]*x[i])) - y[i]; + } + return 0; + } + + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==3); + assert(fjac.rows()==9); + assert(fjac.cols()==3); + for(int i=0; i<9; i++) { + double e = exp(b[1]-b[2]*x[i]); + fjac(i,0) = 1./(1.+e); + fjac(i,1) = -b[0]*e/(1.+e)/(1.+e); + fjac(i,2) = +b[0]*e*x[i]/(1.+e)/(1.+e); + } + return 0; + } +}; +const double rat42_functor::x[9] = { 9.000E0, 14.000E0, 21.000E0, 28.000E0, 42.000E0, 57.000E0, 63.000E0, 70.000E0, 79.000E0 }; +const double rat42_functor::y[9] = { 8.930E0 ,10.800E0 ,18.590E0 ,22.330E0 ,39.350E0 ,56.110E0 ,61.730E0 ,64.620E0 ,67.080E0 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/ratkowsky2.shtml +void testNistRat42(void) +{ + const int n=3; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 100., 1., 0.1; + // do the computation + rat42_functor functor; + LevenbergMarquardt<rat42_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 10); + VERIFY_IS_EQUAL(lm.njev, 8); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.0565229338E+00); + // check x + VERIFY_IS_APPROX(x[0], 7.2462237576E+01); + VERIFY_IS_APPROX(x[1], 2.6180768402E+00); + VERIFY_IS_APPROX(x[2], 6.7359200066E-02); + + /* + * Second try + */ + x<< 75., 2.5, 0.07; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 6); + VERIFY_IS_EQUAL(lm.njev, 5); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.0565229338E+00); + // check x + VERIFY_IS_APPROX(x[0], 7.2462237576E+01); + VERIFY_IS_APPROX(x[1], 2.6180768402E+00); + VERIFY_IS_APPROX(x[2], 6.7359200066E-02); +} + +struct MGH10_functor : Functor<double> +{ + MGH10_functor(void) : Functor<double>(3,16) {} + static const double x[16]; + static const double y[16]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==3); + assert(fvec.size()==16); + for(int i=0; i<16; i++) + fvec[i] = b[0] * exp(b[1]/(x[i]+b[2])) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==3); + assert(fjac.rows()==16); + assert(fjac.cols()==3); + for(int i=0; i<16; i++) { + double factor = 1./(x[i]+b[2]); + double e = exp(b[1]*factor); + fjac(i,0) = e; + fjac(i,1) = b[0]*factor*e; + fjac(i,2) = -b[1]*b[0]*factor*factor*e; + } + return 0; + } +}; +const double MGH10_functor::x[16] = { 5.000000E+01, 5.500000E+01, 6.000000E+01, 6.500000E+01, 7.000000E+01, 7.500000E+01, 8.000000E+01, 8.500000E+01, 9.000000E+01, 9.500000E+01, 1.000000E+02, 1.050000E+02, 1.100000E+02, 1.150000E+02, 1.200000E+02, 1.250000E+02 }; +const double MGH10_functor::y[16] = { 3.478000E+04, 2.861000E+04, 2.365000E+04, 1.963000E+04, 1.637000E+04, 1.372000E+04, 1.154000E+04, 9.744000E+03, 8.261000E+03, 7.030000E+03, 6.005000E+03, 5.147000E+03, 4.427000E+03, 3.820000E+03, 3.307000E+03, 2.872000E+03 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/mgh10.shtml +void testNistMGH10(void) +{ + const int n=3; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 2., 400000., 25000.; + // do the computation + MGH10_functor functor; + LevenbergMarquardt<MGH10_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 2); + VERIFY_IS_EQUAL(lm.nfev, 284 ); + VERIFY_IS_EQUAL(lm.njev, 249 ); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.7945855171E+01); + // check x + VERIFY_IS_APPROX(x[0], 5.6096364710E-03); + VERIFY_IS_APPROX(x[1], 6.1813463463E+03); + VERIFY_IS_APPROX(x[2], 3.4522363462E+02); + + /* + * Second try + */ + x<< 0.02, 4000., 250.; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 3); + VERIFY_IS_EQUAL(lm.nfev, 126); + VERIFY_IS_EQUAL(lm.njev, 116); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.7945855171E+01); + // check x + VERIFY_IS_APPROX(x[0], 5.6096364710E-03); + VERIFY_IS_APPROX(x[1], 6.1813463463E+03); + VERIFY_IS_APPROX(x[2], 3.4522363462E+02); +} + + +struct BoxBOD_functor : Functor<double> +{ + BoxBOD_functor(void) : Functor<double>(2,6) {} + static const double x[6]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + static const double y[6] = { 109., 149., 149., 191., 213., 224. }; + assert(b.size()==2); + assert(fvec.size()==6); + for(int i=0; i<6; i++) + fvec[i] = b[0]*(1.-exp(-b[1]*x[i])) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==2); + assert(fjac.rows()==6); + assert(fjac.cols()==2); + for(int i=0; i<6; i++) { + double e = exp(-b[1]*x[i]); + fjac(i,0) = 1.-e; + fjac(i,1) = b[0]*x[i]*e; + } + return 0; + } +}; +const double BoxBOD_functor::x[6] = { 1., 2., 3., 5., 7., 10. }; + +// http://www.itl.nist.gov/div898/strd/nls/data/boxbod.shtml +void testNistBoxBOD(void) +{ + const int n=2; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 1., 1.; + // do the computation + BoxBOD_functor functor; + LevenbergMarquardt<BoxBOD_functor> lm(functor); + lm.parameters.ftol = 1.E6*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E6*NumTraits<double>::epsilon(); + lm.parameters.factor = 10.; + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 31); + VERIFY_IS_EQUAL(lm.njev, 25); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.1680088766E+03); + // check x + VERIFY_IS_APPROX(x[0], 2.1380940889E+02); + VERIFY_IS_APPROX(x[1], 5.4723748542E-01); + + /* + * Second try + */ + x<< 100., 0.75; + // do the computation + lm.resetParameters(); + lm.parameters.ftol = NumTraits<double>::epsilon(); + lm.parameters.xtol = NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 15 ); + VERIFY_IS_EQUAL(lm.njev, 14 ); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.1680088766E+03); + // check x + VERIFY_IS_APPROX(x[0], 2.1380940889E+02); + VERIFY_IS_APPROX(x[1], 5.4723748542E-01); +} + +struct MGH17_functor : Functor<double> +{ + MGH17_functor(void) : Functor<double>(5,33) {} + static const double x[33]; + static const double y[33]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==5); + assert(fvec.size()==33); + for(int i=0; i<33; i++) + fvec[i] = b[0] + b[1]*exp(-b[3]*x[i]) + b[2]*exp(-b[4]*x[i]) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==5); + assert(fjac.rows()==33); + assert(fjac.cols()==5); + for(int i=0; i<33; i++) { + fjac(i,0) = 1.; + fjac(i,1) = exp(-b[3]*x[i]); + fjac(i,2) = exp(-b[4]*x[i]); + fjac(i,3) = -x[i]*b[1]*exp(-b[3]*x[i]); + fjac(i,4) = -x[i]*b[2]*exp(-b[4]*x[i]); + } + return 0; + } +}; +const double MGH17_functor::x[33] = { 0.000000E+00, 1.000000E+01, 2.000000E+01, 3.000000E+01, 4.000000E+01, 5.000000E+01, 6.000000E+01, 7.000000E+01, 8.000000E+01, 9.000000E+01, 1.000000E+02, 1.100000E+02, 1.200000E+02, 1.300000E+02, 1.400000E+02, 1.500000E+02, 1.600000E+02, 1.700000E+02, 1.800000E+02, 1.900000E+02, 2.000000E+02, 2.100000E+02, 2.200000E+02, 2.300000E+02, 2.400000E+02, 2.500000E+02, 2.600000E+02, 2.700000E+02, 2.800000E+02, 2.900000E+02, 3.000000E+02, 3.100000E+02, 3.200000E+02 }; +const double MGH17_functor::y[33] = { 8.440000E-01, 9.080000E-01, 9.320000E-01, 9.360000E-01, 9.250000E-01, 9.080000E-01, 8.810000E-01, 8.500000E-01, 8.180000E-01, 7.840000E-01, 7.510000E-01, 7.180000E-01, 6.850000E-01, 6.580000E-01, 6.280000E-01, 6.030000E-01, 5.800000E-01, 5.580000E-01, 5.380000E-01, 5.220000E-01, 5.060000E-01, 4.900000E-01, 4.780000E-01, 4.670000E-01, 4.570000E-01, 4.480000E-01, 4.380000E-01, 4.310000E-01, 4.240000E-01, 4.200000E-01, 4.140000E-01, 4.110000E-01, 4.060000E-01 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/mgh17.shtml +void testNistMGH17(void) +{ + const int n=5; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 50., 150., -100., 1., 2.; + // do the computation + MGH17_functor functor; + LevenbergMarquardt<MGH17_functor> lm(functor); + lm.parameters.ftol = NumTraits<double>::epsilon(); + lm.parameters.xtol = NumTraits<double>::epsilon(); + lm.parameters.maxfev = 1000; + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 2); + VERIFY_IS_EQUAL(lm.nfev, 602 ); + VERIFY_IS_EQUAL(lm.njev, 545 ); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.4648946975E-05); + // check x + VERIFY_IS_APPROX(x[0], 3.7541005211E-01); + VERIFY_IS_APPROX(x[1], 1.9358469127E+00); + VERIFY_IS_APPROX(x[2], -1.4646871366E+00); + VERIFY_IS_APPROX(x[3], 1.2867534640E-02); + VERIFY_IS_APPROX(x[4], 2.2122699662E-02); + + /* + * Second try + */ + x<< 0.5 ,1.5 ,-1 ,0.01 ,0.02; + // do the computation + lm.resetParameters(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 18); + VERIFY_IS_EQUAL(lm.njev, 15); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.4648946975E-05); + // check x + VERIFY_IS_APPROX(x[0], 3.7541005211E-01); + VERIFY_IS_APPROX(x[1], 1.9358469127E+00); + VERIFY_IS_APPROX(x[2], -1.4646871366E+00); + VERIFY_IS_APPROX(x[3], 1.2867534640E-02); + VERIFY_IS_APPROX(x[4], 2.2122699662E-02); +} + +struct MGH09_functor : Functor<double> +{ + MGH09_functor(void) : Functor<double>(4,11) {} + static const double _x[11]; + static const double y[11]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==4); + assert(fvec.size()==11); + for(int i=0; i<11; i++) { + double x = _x[i], xx=x*x; + fvec[i] = b[0]*(xx+x*b[1])/(xx+x*b[2]+b[3]) - y[i]; + } + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==4); + assert(fjac.rows()==11); + assert(fjac.cols()==4); + for(int i=0; i<11; i++) { + double x = _x[i], xx=x*x; + double factor = 1./(xx+x*b[2]+b[3]); + fjac(i,0) = (xx+x*b[1]) * factor; + fjac(i,1) = b[0]*x* factor; + fjac(i,2) = - b[0]*(xx+x*b[1]) * x * factor * factor; + fjac(i,3) = - b[0]*(xx+x*b[1]) * factor * factor; + } + return 0; + } +}; +const double MGH09_functor::_x[11] = { 4., 2., 1., 5.E-1 , 2.5E-01, 1.670000E-01, 1.250000E-01, 1.E-01, 8.330000E-02, 7.140000E-02, 6.250000E-02 }; +const double MGH09_functor::y[11] = { 1.957000E-01, 1.947000E-01, 1.735000E-01, 1.600000E-01, 8.440000E-02, 6.270000E-02, 4.560000E-02, 3.420000E-02, 3.230000E-02, 2.350000E-02, 2.460000E-02 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/mgh09.shtml +void testNistMGH09(void) +{ + const int n=4; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 25., 39, 41.5, 39.; + // do the computation + MGH09_functor functor; + LevenbergMarquardt<MGH09_functor> lm(functor); + lm.parameters.maxfev = 1000; + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 490 ); + VERIFY_IS_EQUAL(lm.njev, 376 ); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 3.0750560385E-04); + // check x + VERIFY_IS_APPROX(x[0], 0.1928077089); // should be 1.9280693458E-01 + VERIFY_IS_APPROX(x[1], 0.19126423573); // should be 1.9128232873E-01 + VERIFY_IS_APPROX(x[2], 0.12305309914); // should be 1.2305650693E-01 + VERIFY_IS_APPROX(x[3], 0.13605395375); // should be 1.3606233068E-01 + + /* + * Second try + */ + x<< 0.25, 0.39, 0.415, 0.39; + // do the computation + lm.resetParameters(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 18); + VERIFY_IS_EQUAL(lm.njev, 16); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 3.0750560385E-04); + // check x + VERIFY_IS_APPROX(x[0], 0.19280781); // should be 1.9280693458E-01 + VERIFY_IS_APPROX(x[1], 0.19126265); // should be 1.9128232873E-01 + VERIFY_IS_APPROX(x[2], 0.12305280); // should be 1.2305650693E-01 + VERIFY_IS_APPROX(x[3], 0.13605322); // should be 1.3606233068E-01 +} + + + +struct Bennett5_functor : Functor<double> +{ + Bennett5_functor(void) : Functor<double>(3,154) {} + static const double x[154]; + static const double y[154]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==3); + assert(fvec.size()==154); + for(int i=0; i<154; i++) + fvec[i] = b[0]* pow(b[1]+x[i],-1./b[2]) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==3); + assert(fjac.rows()==154); + assert(fjac.cols()==3); + for(int i=0; i<154; i++) { + double e = pow(b[1]+x[i],-1./b[2]); + fjac(i,0) = e; + fjac(i,1) = - b[0]*e/b[2]/(b[1]+x[i]); + fjac(i,2) = b[0]*e*log(b[1]+x[i])/b[2]/b[2]; + } + return 0; + } +}; +const double Bennett5_functor::x[154] = { 7.447168E0, 8.102586E0, 8.452547E0, 8.711278E0, 8.916774E0, 9.087155E0, 9.232590E0, 9.359535E0, 9.472166E0, 9.573384E0, 9.665293E0, 9.749461E0, 9.827092E0, 9.899128E0, 9.966321E0, 10.029280E0, 10.088510E0, 10.144430E0, 10.197380E0, 10.247670E0, 10.295560E0, 10.341250E0, 10.384950E0, 10.426820E0, 10.467000E0, 10.505640E0, 10.542830E0, 10.578690E0, 10.613310E0, 10.646780E0, 10.679150E0, 10.710520E0, 10.740920E0, 10.770440E0, 10.799100E0, 10.826970E0, 10.854080E0, 10.880470E0, 10.906190E0, 10.931260E0, 10.955720E0, 10.979590E0, 11.002910E0, 11.025700E0, 11.047980E0, 11.069770E0, 11.091100E0, 11.111980E0, 11.132440E0, 11.152480E0, 11.172130E0, 11.191410E0, 11.210310E0, 11.228870E0, 11.247090E0, 11.264980E0, 11.282560E0, 11.299840E0, 11.316820E0, 11.333520E0, 11.349940E0, 11.366100E0, 11.382000E0, 11.397660E0, 11.413070E0, 11.428240E0, 11.443200E0, 11.457930E0, 11.472440E0, 11.486750E0, 11.500860E0, 11.514770E0, 11.528490E0, 11.542020E0, 11.555380E0, 11.568550E0, 11.581560E0, 11.594420E0, 11.607121E0, 11.619640E0, 11.632000E0, 11.644210E0, 11.656280E0, 11.668200E0, 11.679980E0, 11.691620E0, 11.703130E0, 11.714510E0, 11.725760E0, 11.736880E0, 11.747890E0, 11.758780E0, 11.769550E0, 11.780200E0, 11.790730E0, 11.801160E0, 11.811480E0, 11.821700E0, 11.831810E0, 11.841820E0, 11.851730E0, 11.861550E0, 11.871270E0, 11.880890E0, 11.890420E0, 11.899870E0, 11.909220E0, 11.918490E0, 11.927680E0, 11.936780E0, 11.945790E0, 11.954730E0, 11.963590E0, 11.972370E0, 11.981070E0, 11.989700E0, 11.998260E0, 12.006740E0, 12.015150E0, 12.023490E0, 12.031760E0, 12.039970E0, 12.048100E0, 12.056170E0, 12.064180E0, 12.072120E0, 12.080010E0, 12.087820E0, 12.095580E0, 12.103280E0, 12.110920E0, 12.118500E0, 12.126030E0, 12.133500E0, 12.140910E0, 12.148270E0, 12.155570E0, 12.162830E0, 12.170030E0, 12.177170E0, 12.184270E0, 12.191320E0, 12.198320E0, 12.205270E0, 12.212170E0, 12.219030E0, 12.225840E0, 12.232600E0, 12.239320E0, 12.245990E0, 12.252620E0, 12.259200E0, 12.265750E0, 12.272240E0 }; +const double Bennett5_functor::y[154] = { -34.834702E0 ,-34.393200E0 ,-34.152901E0 ,-33.979099E0 ,-33.845901E0 ,-33.732899E0 ,-33.640301E0 ,-33.559200E0 ,-33.486801E0 ,-33.423100E0 ,-33.365101E0 ,-33.313000E0 ,-33.260899E0 ,-33.217400E0 ,-33.176899E0 ,-33.139198E0 ,-33.101601E0 ,-33.066799E0 ,-33.035000E0 ,-33.003101E0 ,-32.971298E0 ,-32.942299E0 ,-32.916302E0 ,-32.890202E0 ,-32.864101E0 ,-32.841000E0 ,-32.817799E0 ,-32.797501E0 ,-32.774300E0 ,-32.757000E0 ,-32.733799E0 ,-32.716400E0 ,-32.699100E0 ,-32.678799E0 ,-32.661400E0 ,-32.644001E0 ,-32.626701E0 ,-32.612202E0 ,-32.597698E0 ,-32.583199E0 ,-32.568699E0 ,-32.554298E0 ,-32.539799E0 ,-32.525299E0 ,-32.510799E0 ,-32.499199E0 ,-32.487598E0 ,-32.473202E0 ,-32.461601E0 ,-32.435501E0 ,-32.435501E0 ,-32.426800E0 ,-32.412300E0 ,-32.400799E0 ,-32.392101E0 ,-32.380501E0 ,-32.366001E0 ,-32.357300E0 ,-32.348598E0 ,-32.339901E0 ,-32.328400E0 ,-32.319698E0 ,-32.311001E0 ,-32.299400E0 ,-32.290699E0 ,-32.282001E0 ,-32.273300E0 ,-32.264599E0 ,-32.256001E0 ,-32.247299E0 ,-32.238602E0 ,-32.229900E0 ,-32.224098E0 ,-32.215401E0 ,-32.203800E0 ,-32.198002E0 ,-32.189400E0 ,-32.183601E0 ,-32.174900E0 ,-32.169102E0 ,-32.163300E0 ,-32.154598E0 ,-32.145901E0 ,-32.140099E0 ,-32.131401E0 ,-32.125599E0 ,-32.119801E0 ,-32.111198E0 ,-32.105400E0 ,-32.096699E0 ,-32.090900E0 ,-32.088001E0 ,-32.079300E0 ,-32.073502E0 ,-32.067699E0 ,-32.061901E0 ,-32.056099E0 ,-32.050301E0 ,-32.044498E0 ,-32.038799E0 ,-32.033001E0 ,-32.027199E0 ,-32.024300E0 ,-32.018501E0 ,-32.012699E0 ,-32.004002E0 ,-32.001099E0 ,-31.995300E0 ,-31.989500E0 ,-31.983700E0 ,-31.977900E0 ,-31.972099E0 ,-31.969299E0 ,-31.963501E0 ,-31.957701E0 ,-31.951900E0 ,-31.946100E0 ,-31.940300E0 ,-31.937401E0 ,-31.931601E0 ,-31.925800E0 ,-31.922899E0 ,-31.917101E0 ,-31.911301E0 ,-31.908400E0 ,-31.902599E0 ,-31.896900E0 ,-31.893999E0 ,-31.888201E0 ,-31.885300E0 ,-31.882401E0 ,-31.876600E0 ,-31.873699E0 ,-31.867901E0 ,-31.862101E0 ,-31.859200E0 ,-31.856300E0 ,-31.850500E0 ,-31.844700E0 ,-31.841801E0 ,-31.838900E0 ,-31.833099E0 ,-31.830200E0 ,-31.827299E0 ,-31.821600E0 ,-31.818701E0 ,-31.812901E0 ,-31.809999E0 ,-31.807100E0 ,-31.801300E0 ,-31.798401E0 ,-31.795500E0 ,-31.789700E0 ,-31.786800E0 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/bennett5.shtml +void testNistBennett5(void) +{ + const int n=3; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< -2000., 50., 0.8; + // do the computation + Bennett5_functor functor; + LevenbergMarquardt<Bennett5_functor> lm(functor); + lm.parameters.maxfev = 1000; + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 758); + VERIFY_IS_EQUAL(lm.njev, 744); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.2404744073E-04); + // check x + VERIFY_IS_APPROX(x[0], -2.5235058043E+03); + VERIFY_IS_APPROX(x[1], 4.6736564644E+01); + VERIFY_IS_APPROX(x[2], 9.3218483193E-01); + /* + * Second try + */ + x<< -1500., 45., 0.85; + // do the computation + lm.resetParameters(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 203); + VERIFY_IS_EQUAL(lm.njev, 192); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.2404744073E-04); + // check x + VERIFY_IS_APPROX(x[0], -2523.3007865); // should be -2.5235058043E+03 + VERIFY_IS_APPROX(x[1], 46.735705771); // should be 4.6736564644E+01); + VERIFY_IS_APPROX(x[2], 0.93219881891); // should be 9.3218483193E-01); +} + +struct thurber_functor : Functor<double> +{ + thurber_functor(void) : Functor<double>(7,37) {} + static const double _x[37]; + static const double _y[37]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + // int called=0; printf("call hahn1_functor with iflag=%d, called=%d\n", iflag, called); if (iflag==1) called++; + assert(b.size()==7); + assert(fvec.size()==37); + for(int i=0; i<37; i++) { + double x=_x[i], xx=x*x, xxx=xx*x; + fvec[i] = (b[0]+b[1]*x+b[2]*xx+b[3]*xxx) / (1.+b[4]*x+b[5]*xx+b[6]*xxx) - _y[i]; + } + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==7); + assert(fjac.rows()==37); + assert(fjac.cols()==7); + for(int i=0; i<37; i++) { + double x=_x[i], xx=x*x, xxx=xx*x; + double fact = 1./(1.+b[4]*x+b[5]*xx+b[6]*xxx); + fjac(i,0) = 1.*fact; + fjac(i,1) = x*fact; + fjac(i,2) = xx*fact; + fjac(i,3) = xxx*fact; + fact = - (b[0]+b[1]*x+b[2]*xx+b[3]*xxx) * fact * fact; + fjac(i,4) = x*fact; + fjac(i,5) = xx*fact; + fjac(i,6) = xxx*fact; + } + return 0; + } +}; +const double thurber_functor::_x[37] = { -3.067E0, -2.981E0, -2.921E0, -2.912E0, -2.840E0, -2.797E0, -2.702E0, -2.699E0, -2.633E0, -2.481E0, -2.363E0, -2.322E0, -1.501E0, -1.460E0, -1.274E0, -1.212E0, -1.100E0, -1.046E0, -0.915E0, -0.714E0, -0.566E0, -0.545E0, -0.400E0, -0.309E0, -0.109E0, -0.103E0, 0.010E0, 0.119E0, 0.377E0, 0.790E0, 0.963E0, 1.006E0, 1.115E0, 1.572E0, 1.841E0, 2.047E0, 2.200E0 }; +const double thurber_functor::_y[37] = { 80.574E0, 84.248E0, 87.264E0, 87.195E0, 89.076E0, 89.608E0, 89.868E0, 90.101E0, 92.405E0, 95.854E0, 100.696E0, 101.060E0, 401.672E0, 390.724E0, 567.534E0, 635.316E0, 733.054E0, 759.087E0, 894.206E0, 990.785E0, 1090.109E0, 1080.914E0, 1122.643E0, 1178.351E0, 1260.531E0, 1273.514E0, 1288.339E0, 1327.543E0, 1353.863E0, 1414.509E0, 1425.208E0, 1421.384E0, 1442.962E0, 1464.350E0, 1468.705E0, 1447.894E0, 1457.628E0}; + +// http://www.itl.nist.gov/div898/strd/nls/data/thurber.shtml +void testNistThurber(void) +{ + const int n=7; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 1000 ,1000 ,400 ,40 ,0.7,0.3,0.0 ; + // do the computation + thurber_functor functor; + LevenbergMarquardt<thurber_functor> lm(functor); + lm.parameters.ftol = 1.E4*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E4*NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 39); + VERIFY_IS_EQUAL(lm.njev, 36); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.6427082397E+03); + // check x + VERIFY_IS_APPROX(x[0], 1.2881396800E+03); + VERIFY_IS_APPROX(x[1], 1.4910792535E+03); + VERIFY_IS_APPROX(x[2], 5.8323836877E+02); + VERIFY_IS_APPROX(x[3], 7.5416644291E+01); + VERIFY_IS_APPROX(x[4], 9.6629502864E-01); + VERIFY_IS_APPROX(x[5], 3.9797285797E-01); + VERIFY_IS_APPROX(x[6], 4.9727297349E-02); + + /* + * Second try + */ + x<< 1300 ,1500 ,500 ,75 ,1 ,0.4 ,0.05 ; + // do the computation + lm.resetParameters(); + lm.parameters.ftol = 1.E4*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E4*NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 29); + VERIFY_IS_EQUAL(lm.njev, 28); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 5.6427082397E+03); + // check x + VERIFY_IS_APPROX(x[0], 1.2881396800E+03); + VERIFY_IS_APPROX(x[1], 1.4910792535E+03); + VERIFY_IS_APPROX(x[2], 5.8323836877E+02); + VERIFY_IS_APPROX(x[3], 7.5416644291E+01); + VERIFY_IS_APPROX(x[4], 9.6629502864E-01); + VERIFY_IS_APPROX(x[5], 3.9797285797E-01); + VERIFY_IS_APPROX(x[6], 4.9727297349E-02); +} + +struct rat43_functor : Functor<double> +{ + rat43_functor(void) : Functor<double>(4,15) {} + static const double x[15]; + static const double y[15]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==4); + assert(fvec.size()==15); + for(int i=0; i<15; i++) + fvec[i] = b[0] * pow(1.+exp(b[1]-b[2]*x[i]),-1./b[3]) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==4); + assert(fjac.rows()==15); + assert(fjac.cols()==4); + for(int i=0; i<15; i++) { + double e = exp(b[1]-b[2]*x[i]); + double power = -1./b[3]; + fjac(i,0) = pow(1.+e, power); + fjac(i,1) = power*b[0]*e*pow(1.+e, power-1.); + fjac(i,2) = -power*b[0]*e*x[i]*pow(1.+e, power-1.); + fjac(i,3) = b[0]*power*power*log(1.+e)*pow(1.+e, power); + } + return 0; + } +}; +const double rat43_functor::x[15] = { 1., 2., 3., 4., 5., 6., 7., 8., 9., 10., 11., 12., 13., 14., 15. }; +const double rat43_functor::y[15] = { 16.08, 33.83, 65.80, 97.20, 191.55, 326.20, 386.87, 520.53, 590.03, 651.92, 724.93, 699.56, 689.96, 637.56, 717.41 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/ratkowsky3.shtml +void testNistRat43(void) +{ + const int n=4; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 100., 10., 1., 1.; + // do the computation + rat43_functor functor; + LevenbergMarquardt<rat43_functor> lm(functor); + lm.parameters.ftol = 1.E6*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E6*NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 27); + VERIFY_IS_EQUAL(lm.njev, 20); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.7864049080E+03); + // check x + VERIFY_IS_APPROX(x[0], 6.9964151270E+02); + VERIFY_IS_APPROX(x[1], 5.2771253025E+00); + VERIFY_IS_APPROX(x[2], 7.5962938329E-01); + VERIFY_IS_APPROX(x[3], 1.2792483859E+00); + + /* + * Second try + */ + x<< 700., 5., 0.75, 1.3; + // do the computation + lm.resetParameters(); + lm.parameters.ftol = 1.E5*NumTraits<double>::epsilon(); + lm.parameters.xtol = 1.E5*NumTraits<double>::epsilon(); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 9); + VERIFY_IS_EQUAL(lm.njev, 8); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 8.7864049080E+03); + // check x + VERIFY_IS_APPROX(x[0], 6.9964151270E+02); + VERIFY_IS_APPROX(x[1], 5.2771253025E+00); + VERIFY_IS_APPROX(x[2], 7.5962938329E-01); + VERIFY_IS_APPROX(x[3], 1.2792483859E+00); +} + + + +struct eckerle4_functor : Functor<double> +{ + eckerle4_functor(void) : Functor<double>(3,35) {} + static const double x[35]; + static const double y[35]; + int operator()(const VectorXd &b, VectorXd &fvec) + { + assert(b.size()==3); + assert(fvec.size()==35); + for(int i=0; i<35; i++) + fvec[i] = b[0]/b[1] * exp(-0.5*(x[i]-b[2])*(x[i]-b[2])/(b[1]*b[1])) - y[i]; + return 0; + } + int df(const VectorXd &b, MatrixXd &fjac) + { + assert(b.size()==3); + assert(fjac.rows()==35); + assert(fjac.cols()==3); + for(int i=0; i<35; i++) { + double b12 = b[1]*b[1]; + double e = exp(-0.5*(x[i]-b[2])*(x[i]-b[2])/b12); + fjac(i,0) = e / b[1]; + fjac(i,1) = ((x[i]-b[2])*(x[i]-b[2])/b12-1.) * b[0]*e/b12; + fjac(i,2) = (x[i]-b[2])*e*b[0]/b[1]/b12; + } + return 0; + } +}; +const double eckerle4_functor::x[35] = { 400.0, 405.0, 410.0, 415.0, 420.0, 425.0, 430.0, 435.0, 436.5, 438.0, 439.5, 441.0, 442.5, 444.0, 445.5, 447.0, 448.5, 450.0, 451.5, 453.0, 454.5, 456.0, 457.5, 459.0, 460.5, 462.0, 463.5, 465.0, 470.0, 475.0, 480.0, 485.0, 490.0, 495.0, 500.0}; +const double eckerle4_functor::y[35] = { 0.0001575, 0.0001699, 0.0002350, 0.0003102, 0.0004917, 0.0008710, 0.0017418, 0.0046400, 0.0065895, 0.0097302, 0.0149002, 0.0237310, 0.0401683, 0.0712559, 0.1264458, 0.2073413, 0.2902366, 0.3445623, 0.3698049, 0.3668534, 0.3106727, 0.2078154, 0.1164354, 0.0616764, 0.0337200, 0.0194023, 0.0117831, 0.0074357, 0.0022732, 0.0008800, 0.0004579, 0.0002345, 0.0001586, 0.0001143, 0.0000710 }; + +// http://www.itl.nist.gov/div898/strd/nls/data/eckerle4.shtml +void testNistEckerle4(void) +{ + const int n=3; + int info; + + VectorXd x(n); + + /* + * First try + */ + x<< 1., 10., 500.; + // do the computation + eckerle4_functor functor; + LevenbergMarquardt<eckerle4_functor> lm(functor); + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 18); + VERIFY_IS_EQUAL(lm.njev, 15); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.4635887487E-03); + // check x + VERIFY_IS_APPROX(x[0], 1.5543827178); + VERIFY_IS_APPROX(x[1], 4.0888321754); + VERIFY_IS_APPROX(x[2], 4.5154121844E+02); + + /* + * Second try + */ + x<< 1.5, 5., 450.; + // do the computation + info = lm.minimize(x); + + // check return value + VERIFY_IS_EQUAL(info, 1); + VERIFY_IS_EQUAL(lm.nfev, 7); + VERIFY_IS_EQUAL(lm.njev, 6); + // check norm^2 + VERIFY_IS_APPROX(lm.fvec.squaredNorm(), 1.4635887487E-03); + // check x + VERIFY_IS_APPROX(x[0], 1.5543827178); + VERIFY_IS_APPROX(x[1], 4.0888321754); + VERIFY_IS_APPROX(x[2], 4.5154121844E+02); +} + +void test_NonLinearOptimization() +{ + // Tests using the examples provided by (c)minpack + CALL_SUBTEST/*_1*/(testChkder()); + CALL_SUBTEST/*_1*/(testLmder1()); + CALL_SUBTEST/*_1*/(testLmder()); + CALL_SUBTEST/*_2*/(testHybrj1()); + CALL_SUBTEST/*_2*/(testHybrj()); + CALL_SUBTEST/*_2*/(testHybrd1()); + CALL_SUBTEST/*_2*/(testHybrd()); + CALL_SUBTEST/*_3*/(testLmstr1()); + CALL_SUBTEST/*_3*/(testLmstr()); + CALL_SUBTEST/*_3*/(testLmdif1()); + CALL_SUBTEST/*_3*/(testLmdif()); + + // NIST tests, level of difficulty = "Lower" + CALL_SUBTEST/*_4*/(testNistMisra1a()); + CALL_SUBTEST/*_4*/(testNistChwirut2()); + + // NIST tests, level of difficulty = "Average" + CALL_SUBTEST/*_5*/(testNistHahn1()); + CALL_SUBTEST/*_6*/(testNistMisra1d()); + CALL_SUBTEST/*_7*/(testNistMGH17()); + CALL_SUBTEST/*_8*/(testNistLanczos1()); + + // NIST tests, level of difficulty = "Higher" + CALL_SUBTEST/*_9*/(testNistRat42()); + CALL_SUBTEST/*_10*/(testNistMGH10()); + CALL_SUBTEST/*_11*/(testNistBoxBOD()); + CALL_SUBTEST/*_12*/(testNistMGH09()); + CALL_SUBTEST/*_13*/(testNistBennett5()); + CALL_SUBTEST/*_14*/(testNistThurber()); + CALL_SUBTEST/*_15*/(testNistRat43()); + CALL_SUBTEST/*_16*/(testNistEckerle4()); +} + +/* + * Can be useful for debugging... + printf("info, nfev : %d, %d\n", info, lm.nfev); + printf("info, nfev, njev : %d, %d, %d\n", info, solver.nfev, solver.njev); + printf("info, nfev : %d, %d\n", info, solver.nfev); + printf("x[0] : %.32g\n", x[0]); + printf("x[1] : %.32g\n", x[1]); + printf("x[2] : %.32g\n", x[2]); + printf("x[3] : %.32g\n", x[3]); + printf("fvec.blueNorm() : %.32g\n", solver.fvec.blueNorm()); + printf("fvec.blueNorm() : %.32g\n", lm.fvec.blueNorm()); + + printf("info, nfev, njev : %d, %d, %d\n", info, lm.nfev, lm.njev); + printf("fvec.squaredNorm() : %.13g\n", lm.fvec.squaredNorm()); + std::cout << x << std::endl; + std::cout.precision(9); + std::cout << x[0] << std::endl; + std::cout << x[1] << std::endl; + std::cout << x[2] << std::endl; + std::cout << x[3] << std::endl; +*/ + diff --git a/unsupported/test/NumericalDiff.cpp b/unsupported/test/NumericalDiff.cpp new file mode 100644 index 000000000..27d888056 --- /dev/null +++ b/unsupported/test/NumericalDiff.cpp @@ -0,0 +1,114 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Thomas Capricelli <orzel@freehackers.org> + +#include <stdio.h> + +#include "main.h" +#include <unsupported/Eigen/NumericalDiff> + +// Generic functor +template<typename _Scalar, int NX=Dynamic, int NY=Dynamic> +struct Functor +{ + typedef _Scalar Scalar; + enum { + InputsAtCompileTime = NX, + ValuesAtCompileTime = NY + }; + typedef Matrix<Scalar,InputsAtCompileTime,1> InputType; + typedef Matrix<Scalar,ValuesAtCompileTime,1> ValueType; + typedef Matrix<Scalar,ValuesAtCompileTime,InputsAtCompileTime> JacobianType; + + int m_inputs, m_values; + + Functor() : m_inputs(InputsAtCompileTime), m_values(ValuesAtCompileTime) {} + Functor(int inputs, int values) : m_inputs(inputs), m_values(values) {} + + int inputs() const { return m_inputs; } + int values() const { return m_values; } + +}; + +struct my_functor : Functor<double> +{ + my_functor(void): Functor<double>(3,15) {} + int operator()(const VectorXd &x, VectorXd &fvec) const + { + double tmp1, tmp2, tmp3; + double y[15] = {1.4e-1, 1.8e-1, 2.2e-1, 2.5e-1, 2.9e-1, 3.2e-1, 3.5e-1, + 3.9e-1, 3.7e-1, 5.8e-1, 7.3e-1, 9.6e-1, 1.34, 2.1, 4.39}; + + for (int i = 0; i < values(); i++) + { + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + fvec[i] = y[i] - (x[0] + tmp1/(x[1]*tmp2 + x[2]*tmp3)); + } + return 0; + } + + int actual_df(const VectorXd &x, MatrixXd &fjac) const + { + double tmp1, tmp2, tmp3, tmp4; + for (int i = 0; i < values(); i++) + { + tmp1 = i+1; + tmp2 = 16 - i - 1; + tmp3 = (i>=8)? tmp2 : tmp1; + tmp4 = (x[1]*tmp2 + x[2]*tmp3); tmp4 = tmp4*tmp4; + fjac(i,0) = -1; + fjac(i,1) = tmp1*tmp2/tmp4; + fjac(i,2) = tmp1*tmp3/tmp4; + } + return 0; + } +}; + +void test_forward() +{ + VectorXd x(3); + MatrixXd jac(15,3); + MatrixXd actual_jac(15,3); + my_functor functor; + + x << 0.082, 1.13, 2.35; + + // real one + functor.actual_df(x, actual_jac); +// std::cout << actual_jac << std::endl << std::endl; + + // using NumericalDiff + NumericalDiff<my_functor> numDiff(functor); + numDiff.df(x, jac); +// std::cout << jac << std::endl; + + VERIFY_IS_APPROX(jac, actual_jac); +} + +void test_central() +{ + VectorXd x(3); + MatrixXd jac(15,3); + MatrixXd actual_jac(15,3); + my_functor functor; + + x << 0.082, 1.13, 2.35; + + // real one + functor.actual_df(x, actual_jac); + + // using NumericalDiff + NumericalDiff<my_functor,Central> numDiff(functor); + numDiff.df(x, jac); + + VERIFY_IS_APPROX(jac, actual_jac); +} + +void test_NumericalDiff() +{ + CALL_SUBTEST(test_forward()); + CALL_SUBTEST(test_central()); +} diff --git a/unsupported/test/alignedvector3.cpp b/unsupported/test/alignedvector3.cpp new file mode 100644 index 000000000..fc2bc2135 --- /dev/null +++ b/unsupported/test/alignedvector3.cpp @@ -0,0 +1,59 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Gael Guennebaud <g.gael@free.fr> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/AlignedVector3> + +template<typename Scalar> +void alignedvector3() +{ + Scalar s1 = internal::random<Scalar>(); + Scalar s2 = internal::random<Scalar>(); + typedef Matrix<Scalar,3,1> RefType; + typedef Matrix<Scalar,3,3> Mat33; + typedef AlignedVector3<Scalar> FastType; + RefType r1(RefType::Random()), r2(RefType::Random()), r3(RefType::Random()), + r4(RefType::Random()), r5(RefType::Random()), r6(RefType::Random()); + FastType f1(r1), f2(r2), f3(r3), f4(r4), f5(r5), f6(r6); + Mat33 m1(Mat33::Random()); + + VERIFY_IS_APPROX(f1,r1); + VERIFY_IS_APPROX(f4,r4); + + VERIFY_IS_APPROX(f4+f1,r4+r1); + VERIFY_IS_APPROX(f4-f1,r4-r1); + VERIFY_IS_APPROX(f4+f1-f2,r4+r1-r2); + VERIFY_IS_APPROX(f4+=f3,r4+=r3); + VERIFY_IS_APPROX(f4-=f5,r4-=r5); + VERIFY_IS_APPROX(f4-=f5+f1,r4-=r5+r1); + VERIFY_IS_APPROX(f5+f1-s1*f2,r5+r1-s1*r2); + VERIFY_IS_APPROX(f5+f1/s2-s1*f2,r5+r1/s2-s1*r2); + + VERIFY_IS_APPROX(m1*f4,m1*r4); + VERIFY_IS_APPROX(f4.transpose()*m1,r4.transpose()*m1); + + VERIFY_IS_APPROX(f2.dot(f3),r2.dot(r3)); + VERIFY_IS_APPROX(f2.cross(f3),r2.cross(r3)); + VERIFY_IS_APPROX(f2.norm(),r2.norm()); + + VERIFY_IS_APPROX(f2.normalized(),r2.normalized()); + + VERIFY_IS_APPROX((f2+f1).normalized(),(r2+r1).normalized()); + + f2.normalize(); + r2.normalize(); + VERIFY_IS_APPROX(f2,r2); +} + +void test_alignedvector3() +{ + for(int i = 0; i < g_repeat; i++) { + CALL_SUBTEST( alignedvector3<float>() ); + } +} diff --git a/unsupported/test/autodiff.cpp b/unsupported/test/autodiff.cpp new file mode 100644 index 000000000..6eb417e8d --- /dev/null +++ b/unsupported/test/autodiff.cpp @@ -0,0 +1,172 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Gael Guennebaud <g.gael@free.fr> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/AutoDiff> + +template<typename Scalar> +EIGEN_DONT_INLINE Scalar foo(const Scalar& x, const Scalar& y) +{ + using namespace std; +// return x+std::sin(y); + EIGEN_ASM_COMMENT("mybegin"); + return static_cast<Scalar>(x*2 - pow(x,2) + 2*sqrt(y*y) - 4 * sin(x) + 2 * cos(y) - exp(-0.5*x*x)); + //return x+2*y*x;//x*2 -std::pow(x,2);//(2*y/x);// - y*2; + EIGEN_ASM_COMMENT("myend"); +} + +template<typename Vector> +EIGEN_DONT_INLINE typename Vector::Scalar foo(const Vector& p) +{ + typedef typename Vector::Scalar Scalar; + return (p-Vector(Scalar(-1),Scalar(1.))).norm() + (p.array() * p.array()).sum() + p.dot(p); +} + +template<typename _Scalar, int NX=Dynamic, int NY=Dynamic> +struct TestFunc1 +{ + typedef _Scalar Scalar; + enum { + InputsAtCompileTime = NX, + ValuesAtCompileTime = NY + }; + typedef Matrix<Scalar,InputsAtCompileTime,1> InputType; + typedef Matrix<Scalar,ValuesAtCompileTime,1> ValueType; + typedef Matrix<Scalar,ValuesAtCompileTime,InputsAtCompileTime> JacobianType; + + int m_inputs, m_values; + + TestFunc1() : m_inputs(InputsAtCompileTime), m_values(ValuesAtCompileTime) {} + TestFunc1(int inputs, int values) : m_inputs(inputs), m_values(values) {} + + int inputs() const { return m_inputs; } + int values() const { return m_values; } + + template<typename T> + void operator() (const Matrix<T,InputsAtCompileTime,1>& x, Matrix<T,ValuesAtCompileTime,1>* _v) const + { + Matrix<T,ValuesAtCompileTime,1>& v = *_v; + + v[0] = 2 * x[0] * x[0] + x[0] * x[1]; + v[1] = 3 * x[1] * x[0] + 0.5 * x[1] * x[1]; + if(inputs()>2) + { + v[0] += 0.5 * x[2]; + v[1] += x[2]; + } + if(values()>2) + { + v[2] = 3 * x[1] * x[0] * x[0]; + } + if (inputs()>2 && values()>2) + v[2] *= x[2]; + } + + void operator() (const InputType& x, ValueType* v, JacobianType* _j) const + { + (*this)(x, v); + + if(_j) + { + JacobianType& j = *_j; + + j(0,0) = 4 * x[0] + x[1]; + j(1,0) = 3 * x[1]; + + j(0,1) = x[0]; + j(1,1) = 3 * x[0] + 2 * 0.5 * x[1]; + + if (inputs()>2) + { + j(0,2) = 0.5; + j(1,2) = 1; + } + if(values()>2) + { + j(2,0) = 3 * x[1] * 2 * x[0]; + j(2,1) = 3 * x[0] * x[0]; + } + if (inputs()>2 && values()>2) + { + j(2,0) *= x[2]; + j(2,1) *= x[2]; + + j(2,2) = 3 * x[1] * x[0] * x[0]; + j(2,2) = 3 * x[1] * x[0] * x[0]; + } + } + } +}; + +template<typename Func> void forward_jacobian(const Func& f) +{ + typename Func::InputType x = Func::InputType::Random(f.inputs()); + typename Func::ValueType y(f.values()), yref(f.values()); + typename Func::JacobianType j(f.values(),f.inputs()), jref(f.values(),f.inputs()); + + jref.setZero(); + yref.setZero(); + f(x,&yref,&jref); +// std::cerr << y.transpose() << "\n\n";; +// std::cerr << j << "\n\n";; + + j.setZero(); + y.setZero(); + AutoDiffJacobian<Func> autoj(f); + autoj(x, &y, &j); +// std::cerr << y.transpose() << "\n\n";; +// std::cerr << j << "\n\n";; + + VERIFY_IS_APPROX(y, yref); + VERIFY_IS_APPROX(j, jref); +} + +void test_autodiff_scalar() +{ + std::cerr << foo<float>(1,2) << "\n"; + typedef AutoDiffScalar<Vector2f> AD; + AD ax(1,Vector2f::UnitX()); + AD ay(2,Vector2f::UnitY()); + AD res = foo<AD>(ax,ay); + std::cerr << res.value() << " <> " + << res.derivatives().transpose() << "\n\n"; +} + +void test_autodiff_vector() +{ + std::cerr << foo<Vector2f>(Vector2f(1,2)) << "\n"; + typedef AutoDiffScalar<Vector2f> AD; + typedef Matrix<AD,2,1> VectorAD; + VectorAD p(AD(1),AD(-1)); + p.x().derivatives() = Vector2f::UnitX(); + p.y().derivatives() = Vector2f::UnitY(); + + AD res = foo<VectorAD>(p); + std::cerr << res.value() << " <> " + << res.derivatives().transpose() << "\n\n"; +} + +void test_autodiff_jacobian() +{ + for(int i = 0; i < g_repeat; i++) { + CALL_SUBTEST(( forward_jacobian(TestFunc1<double,2,2>()) )); + CALL_SUBTEST(( forward_jacobian(TestFunc1<double,2,3>()) )); + CALL_SUBTEST(( forward_jacobian(TestFunc1<double,3,2>()) )); + CALL_SUBTEST(( forward_jacobian(TestFunc1<double,3,3>()) )); + CALL_SUBTEST(( forward_jacobian(TestFunc1<double>(3,3)) )); + } +} + +void test_autodiff() +{ + test_autodiff_scalar(); + test_autodiff_vector(); +// test_autodiff_jacobian(); +} + diff --git a/unsupported/test/forward_adolc.cpp b/unsupported/test/forward_adolc.cpp new file mode 100644 index 000000000..d4baafe62 --- /dev/null +++ b/unsupported/test/forward_adolc.cpp @@ -0,0 +1,143 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2008 Gael Guennebaud <g.gael@free.fr> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <Eigen/Dense> + +#define NUMBER_DIRECTIONS 16 +#include <unsupported/Eigen/AdolcForward> + +int adtl::ADOLC_numDir; + +template<typename Vector> +EIGEN_DONT_INLINE typename Vector::Scalar foo(const Vector& p) +{ + typedef typename Vector::Scalar Scalar; + return (p-Vector(Scalar(-1),Scalar(1.))).norm() + (p.array().sqrt().abs() * p.array().sin()).sum() + p.dot(p); +} + +template<typename _Scalar, int NX=Dynamic, int NY=Dynamic> +struct TestFunc1 +{ + typedef _Scalar Scalar; + enum { + InputsAtCompileTime = NX, + ValuesAtCompileTime = NY + }; + typedef Matrix<Scalar,InputsAtCompileTime,1> InputType; + typedef Matrix<Scalar,ValuesAtCompileTime,1> ValueType; + typedef Matrix<Scalar,ValuesAtCompileTime,InputsAtCompileTime> JacobianType; + + int m_inputs, m_values; + + TestFunc1() : m_inputs(InputsAtCompileTime), m_values(ValuesAtCompileTime) {} + TestFunc1(int inputs, int values) : m_inputs(inputs), m_values(values) {} + + int inputs() const { return m_inputs; } + int values() const { return m_values; } + + template<typename T> + void operator() (const Matrix<T,InputsAtCompileTime,1>& x, Matrix<T,ValuesAtCompileTime,1>* _v) const + { + Matrix<T,ValuesAtCompileTime,1>& v = *_v; + + v[0] = 2 * x[0] * x[0] + x[0] * x[1]; + v[1] = 3 * x[1] * x[0] + 0.5 * x[1] * x[1]; + if(inputs()>2) + { + v[0] += 0.5 * x[2]; + v[1] += x[2]; + } + if(values()>2) + { + v[2] = 3 * x[1] * x[0] * x[0]; + } + if (inputs()>2 && values()>2) + v[2] *= x[2]; + } + + void operator() (const InputType& x, ValueType* v, JacobianType* _j) const + { + (*this)(x, v); + + if(_j) + { + JacobianType& j = *_j; + + j(0,0) = 4 * x[0] + x[1]; + j(1,0) = 3 * x[1]; + + j(0,1) = x[0]; + j(1,1) = 3 * x[0] + 2 * 0.5 * x[1]; + + if (inputs()>2) + { + j(0,2) = 0.5; + j(1,2) = 1; + } + if(values()>2) + { + j(2,0) = 3 * x[1] * 2 * x[0]; + j(2,1) = 3 * x[0] * x[0]; + } + if (inputs()>2 && values()>2) + { + j(2,0) *= x[2]; + j(2,1) *= x[2]; + + j(2,2) = 3 * x[1] * x[0] * x[0]; + j(2,2) = 3 * x[1] * x[0] * x[0]; + } + } + } +}; + +template<typename Func> void adolc_forward_jacobian(const Func& f) +{ + typename Func::InputType x = Func::InputType::Random(f.inputs()); + typename Func::ValueType y(f.values()), yref(f.values()); + typename Func::JacobianType j(f.values(),f.inputs()), jref(f.values(),f.inputs()); + + jref.setZero(); + yref.setZero(); + f(x,&yref,&jref); +// std::cerr << y.transpose() << "\n\n";; +// std::cerr << j << "\n\n";; + + j.setZero(); + y.setZero(); + AdolcForwardJacobian<Func> autoj(f); + autoj(x, &y, &j); +// std::cerr << y.transpose() << "\n\n";; +// std::cerr << j << "\n\n";; + + VERIFY_IS_APPROX(y, yref); + VERIFY_IS_APPROX(j, jref); +} + +void test_forward_adolc() +{ + adtl::ADOLC_numDir = NUMBER_DIRECTIONS; + + for(int i = 0; i < g_repeat; i++) { + CALL_SUBTEST(( adolc_forward_jacobian(TestFunc1<double,2,2>()) )); + CALL_SUBTEST(( adolc_forward_jacobian(TestFunc1<double,2,3>()) )); + CALL_SUBTEST(( adolc_forward_jacobian(TestFunc1<double,3,2>()) )); + CALL_SUBTEST(( adolc_forward_jacobian(TestFunc1<double,3,3>()) )); + CALL_SUBTEST(( adolc_forward_jacobian(TestFunc1<double>(3,3)) )); + } + + { + // simple instanciation tests + Matrix<adtl::adouble,2,1> x; + foo(x); + Matrix<adtl::adouble,Dynamic,Dynamic> A(4,4);; + A.selfadjointView<Lower>().eigenvalues(); + } +} diff --git a/unsupported/test/gmres.cpp b/unsupported/test/gmres.cpp new file mode 100644 index 000000000..647c16927 --- /dev/null +++ b/unsupported/test/gmres.cpp @@ -0,0 +1,33 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2011 Gael Guennebaud <g.gael@free.fr> +// Copyright (C) 2012 Kolja Brix <brix@igpm.rwth-aaachen.de> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "../../test/sparse_solver.h" +#include <Eigen/IterativeSolvers> + +template<typename T> void test_gmres_T() +{ + GMRES<SparseMatrix<T>, DiagonalPreconditioner<T> > gmres_colmajor_diag; + GMRES<SparseMatrix<T>, IdentityPreconditioner > gmres_colmajor_I; + GMRES<SparseMatrix<T>, IncompleteLUT<T> > gmres_colmajor_ilut; + //GMRES<SparseMatrix<T>, SSORPreconditioner<T> > gmres_colmajor_ssor; + + CALL_SUBTEST( check_sparse_square_solving(gmres_colmajor_diag) ); +// CALL_SUBTEST( check_sparse_square_solving(gmres_colmajor_I) ); + CALL_SUBTEST( check_sparse_square_solving(gmres_colmajor_ilut) ); + //CALL_SUBTEST( check_sparse_square_solving(gmres_colmajor_ssor) ); +} + +void test_gmres() +{ + for(int i = 0; i < g_repeat; i++) { + CALL_SUBTEST_1(test_gmres_T<double>()); + CALL_SUBTEST_2(test_gmres_T<std::complex<double> >()); + } +} diff --git a/unsupported/test/kronecker_product.cpp b/unsupported/test/kronecker_product.cpp new file mode 100644 index 000000000..a60bd3022 --- /dev/null +++ b/unsupported/test/kronecker_product.cpp @@ -0,0 +1,179 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2011 Kolja Brix <brix@igpm.rwth-aachen.de> +// Copyright (C) 2011 Andreas Platen <andiplaten@gmx.de> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + + +#include "sparse.h" +#include <Eigen/SparseExtra> +#include <Eigen/KroneckerProduct> + + +template<typename MatrixType> +void check_dimension(const MatrixType& ab, const unsigned int rows, const unsigned int cols) +{ + VERIFY_IS_EQUAL(ab.rows(), rows); + VERIFY_IS_EQUAL(ab.cols(), cols); +} + + +template<typename MatrixType> +void check_kronecker_product(const MatrixType& ab) +{ + VERIFY_IS_EQUAL(ab.rows(), 6); + VERIFY_IS_EQUAL(ab.cols(), 6); + VERIFY_IS_EQUAL(ab.nonZeros(), 36); + VERIFY_IS_APPROX(ab.coeff(0,0), -0.4017367630386106); + VERIFY_IS_APPROX(ab.coeff(0,1), 0.1056863433932735); + VERIFY_IS_APPROX(ab.coeff(0,2), -0.7255206194554212); + VERIFY_IS_APPROX(ab.coeff(0,3), 0.1908653336744706); + VERIFY_IS_APPROX(ab.coeff(0,4), 0.350864567234111); + VERIFY_IS_APPROX(ab.coeff(0,5), -0.0923032108308013); + VERIFY_IS_APPROX(ab.coeff(1,0), 0.415417514804677); + VERIFY_IS_APPROX(ab.coeff(1,1), -0.2369227701722048); + VERIFY_IS_APPROX(ab.coeff(1,2), 0.7502275131458511); + VERIFY_IS_APPROX(ab.coeff(1,3), -0.4278731019742696); + VERIFY_IS_APPROX(ab.coeff(1,4), -0.3628129162264507); + VERIFY_IS_APPROX(ab.coeff(1,5), 0.2069210808481275); + VERIFY_IS_APPROX(ab.coeff(2,0), 0.05465890160863986); + VERIFY_IS_APPROX(ab.coeff(2,1), -0.2634092511419858); + VERIFY_IS_APPROX(ab.coeff(2,2), 0.09871180285793758); + VERIFY_IS_APPROX(ab.coeff(2,3), -0.4757066334017702); + VERIFY_IS_APPROX(ab.coeff(2,4), -0.04773740823058334); + VERIFY_IS_APPROX(ab.coeff(2,5), 0.2300535609645254); + VERIFY_IS_APPROX(ab.coeff(3,0), -0.8172945853260133); + VERIFY_IS_APPROX(ab.coeff(3,1), 0.2150086428359221); + VERIFY_IS_APPROX(ab.coeff(3,2), 0.5825113847292743); + VERIFY_IS_APPROX(ab.coeff(3,3), -0.1532433770097174); + VERIFY_IS_APPROX(ab.coeff(3,4), -0.329383387282399); + VERIFY_IS_APPROX(ab.coeff(3,5), 0.08665207912033064); + VERIFY_IS_APPROX(ab.coeff(4,0), 0.8451267514863225); + VERIFY_IS_APPROX(ab.coeff(4,1), -0.481996458918977); + VERIFY_IS_APPROX(ab.coeff(4,2), -0.6023482390791535); + VERIFY_IS_APPROX(ab.coeff(4,3), 0.3435339347164565); + VERIFY_IS_APPROX(ab.coeff(4,4), 0.3406002157428891); + VERIFY_IS_APPROX(ab.coeff(4,5), -0.1942526344200915); + VERIFY_IS_APPROX(ab.coeff(5,0), 0.1111982482925399); + VERIFY_IS_APPROX(ab.coeff(5,1), -0.5358806424754169); + VERIFY_IS_APPROX(ab.coeff(5,2), -0.07925446559335647); + VERIFY_IS_APPROX(ab.coeff(5,3), 0.3819388757769038); + VERIFY_IS_APPROX(ab.coeff(5,4), 0.04481475387219876); + VERIFY_IS_APPROX(ab.coeff(5,5), -0.2159688616158057); +} + + +template<typename MatrixType> +void check_sparse_kronecker_product(const MatrixType& ab) +{ + VERIFY_IS_EQUAL(ab.rows(), 12); + VERIFY_IS_EQUAL(ab.cols(), 10); + VERIFY_IS_EQUAL(ab.nonZeros(), 3*2); + VERIFY_IS_APPROX(ab.coeff(3,0), -0.04); + VERIFY_IS_APPROX(ab.coeff(5,1), 0.05); + VERIFY_IS_APPROX(ab.coeff(0,6), -0.08); + VERIFY_IS_APPROX(ab.coeff(2,7), 0.10); + VERIFY_IS_APPROX(ab.coeff(6,8), 0.12); + VERIFY_IS_APPROX(ab.coeff(8,9), -0.15); +} + + +void test_kronecker_product() +{ + // DM = dense matrix; SM = sparse matrix + Matrix<double, 2, 3> DM_a; + MatrixXd DM_b(3,2); + SparseMatrix<double> SM_a(2,3); + SparseMatrix<double> SM_b(3,2); + SM_a.insert(0,0) = DM_a(0,0) = -0.4461540300782201; + SM_a.insert(0,1) = DM_a(0,1) = -0.8057364375283049; + SM_a.insert(0,2) = DM_a(0,2) = 0.3896572459516341; + SM_a.insert(1,0) = DM_a(1,0) = -0.9076572187376921; + SM_a.insert(1,1) = DM_a(1,1) = 0.6469156566545853; + SM_a.insert(1,2) = DM_a(1,2) = -0.3658010398782789; + SM_b.insert(0,0) = DM_b(0,0) = 0.9004440976767099; + SM_b.insert(0,1) = DM_b(0,1) = -0.2368830858139832; + SM_b.insert(1,0) = DM_b(1,0) = -0.9311078389941825; + SM_b.insert(1,1) = DM_b(1,1) = 0.5310335762980047; + SM_b.insert(2,0) = DM_b(2,0) = -0.1225112806872035; + SM_b.insert(2,1) = DM_b(2,1) = 0.5903998022741264; + SparseMatrix<double,RowMajor> SM_row_a(SM_a), SM_row_b(SM_b); + + // test kroneckerProduct(DM_block,DM,DM_fixedSize) + Matrix<double, 6, 6> DM_fix_ab; + DM_fix_ab(0,0)=37.0; + kroneckerProduct(DM_a.block(0,0,2,3),DM_b,DM_fix_ab); + CALL_SUBTEST(check_kronecker_product(DM_fix_ab)); + + // test kroneckerProduct(DM,DM,DM_block) + MatrixXd DM_block_ab(10,15); + DM_block_ab(0,0)=37.0; + kroneckerProduct(DM_a,DM_b,DM_block_ab.block(2,5,6,6)); + CALL_SUBTEST(check_kronecker_product(DM_block_ab.block(2,5,6,6))); + + // test kroneckerProduct(DM,DM,DM) + MatrixXd DM_ab(1,5); + DM_ab(0,0)=37.0; + kroneckerProduct(DM_a,DM_b,DM_ab); + CALL_SUBTEST(check_kronecker_product(DM_ab)); + + // test kroneckerProduct(SM,DM,SM) + SparseMatrix<double> SM_ab(1,20); + SM_ab.insert(0,0)=37.0; + kroneckerProduct(SM_a,DM_b,SM_ab); + CALL_SUBTEST(check_kronecker_product(SM_ab)); + SparseMatrix<double,RowMajor> SM_ab2(10,3); + SM_ab2.insert(0,0)=37.0; + kroneckerProduct(SM_a,DM_b,SM_ab2); + CALL_SUBTEST(check_kronecker_product(SM_ab2)); + + // test kroneckerProduct(DM,SM,SM) + SM_ab.insert(0,0)=37.0; + kroneckerProduct(DM_a,SM_b,SM_ab); + CALL_SUBTEST(check_kronecker_product(SM_ab)); + SM_ab2.insert(0,0)=37.0; + kroneckerProduct(DM_a,SM_b,SM_ab2); + CALL_SUBTEST(check_kronecker_product(SM_ab2)); + + // test kroneckerProduct(SM,SM,SM) + SM_ab.resize(2,33); + SM_ab.insert(0,0)=37.0; + kroneckerProduct(SM_a,SM_b,SM_ab); + CALL_SUBTEST(check_kronecker_product(SM_ab)); + SM_ab2.resize(5,11); + SM_ab2.insert(0,0)=37.0; + kroneckerProduct(SM_a,SM_b,SM_ab2); + CALL_SUBTEST(check_kronecker_product(SM_ab2)); + + // test kroneckerProduct(SM,SM,SM) with sparse pattern + SM_a.resize(4,5); + SM_b.resize(3,2); + SM_a.resizeNonZeros(0); + SM_b.resizeNonZeros(0); + SM_a.insert(1,0) = -0.1; + SM_a.insert(0,3) = -0.2; + SM_a.insert(2,4) = 0.3; + SM_a.finalize(); + SM_b.insert(0,0) = 0.4; + SM_b.insert(2,1) = -0.5; + SM_b.finalize(); + SM_ab.resize(1,1); + SM_ab.insert(0,0)=37.0; + kroneckerProduct(SM_a,SM_b,SM_ab); + CALL_SUBTEST(check_sparse_kronecker_product(SM_ab)); + + // test dimension of result of kroneckerProduct(DM,DM,DM) + MatrixXd DM_a2(2,1); + MatrixXd DM_b2(5,4); + MatrixXd DM_ab2; + kroneckerProduct(DM_a2,DM_b2,DM_ab2); + CALL_SUBTEST(check_dimension(DM_ab2,2*5,1*4)); + DM_a2.resize(10,9); + DM_b2.resize(4,8); + kroneckerProduct(DM_a2,DM_b2,DM_ab2); + CALL_SUBTEST(check_dimension(DM_ab2,10*4,9*8)); +} diff --git a/unsupported/test/matrix_exponential.cpp b/unsupported/test/matrix_exponential.cpp new file mode 100644 index 000000000..695472f91 --- /dev/null +++ b/unsupported/test/matrix_exponential.cpp @@ -0,0 +1,149 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2009 Jitse Niesen <jitse@maths.leeds.ac.uk> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/MatrixFunctions> + +double binom(int n, int k) +{ + double res = 1; + for (int i=0; i<k; i++) + res = res * (n-k+i+1) / (i+1); + return res; +} + +template <typename Derived, typename OtherDerived> +double relerr(const MatrixBase<Derived>& A, const MatrixBase<OtherDerived>& B) +{ + return std::sqrt((A - B).cwiseAbs2().sum() / (std::min)(A.cwiseAbs2().sum(), B.cwiseAbs2().sum())); +} + +template <typename T> +T expfn(T x, int) +{ + return std::exp(x); +} + +template <typename T> +void test2dRotation(double tol) +{ + Matrix<T,2,2> A, B, C; + T angle; + + A << 0, 1, -1, 0; + for (int i=0; i<=20; i++) + { + angle = static_cast<T>(pow(10, i / 5. - 2)); + B << std::cos(angle), std::sin(angle), -std::sin(angle), std::cos(angle); + + C = (angle*A).matrixFunction(expfn); + std::cout << "test2dRotation: i = " << i << " error funm = " << relerr(C, B); + VERIFY(C.isApprox(B, static_cast<T>(tol))); + + C = (angle*A).exp(); + std::cout << " error expm = " << relerr(C, B) << "\n"; + VERIFY(C.isApprox(B, static_cast<T>(tol))); + } +} + +template <typename T> +void test2dHyperbolicRotation(double tol) +{ + Matrix<std::complex<T>,2,2> A, B, C; + std::complex<T> imagUnit(0,1); + T angle, ch, sh; + + for (int i=0; i<=20; i++) + { + angle = static_cast<T>((i-10) / 2.0); + ch = std::cosh(angle); + sh = std::sinh(angle); + A << 0, angle*imagUnit, -angle*imagUnit, 0; + B << ch, sh*imagUnit, -sh*imagUnit, ch; + + C = A.matrixFunction(expfn); + std::cout << "test2dHyperbolicRotation: i = " << i << " error funm = " << relerr(C, B); + VERIFY(C.isApprox(B, static_cast<T>(tol))); + + C = A.exp(); + std::cout << " error expm = " << relerr(C, B) << "\n"; + VERIFY(C.isApprox(B, static_cast<T>(tol))); + } +} + +template <typename T> +void testPascal(double tol) +{ + for (int size=1; size<20; size++) + { + Matrix<T,Dynamic,Dynamic> A(size,size), B(size,size), C(size,size); + A.setZero(); + for (int i=0; i<size-1; i++) + A(i+1,i) = static_cast<T>(i+1); + B.setZero(); + for (int i=0; i<size; i++) + for (int j=0; j<=i; j++) + B(i,j) = static_cast<T>(binom(i,j)); + + C = A.matrixFunction(expfn); + std::cout << "testPascal: size = " << size << " error funm = " << relerr(C, B); + VERIFY(C.isApprox(B, static_cast<T>(tol))); + + C = A.exp(); + std::cout << " error expm = " << relerr(C, B) << "\n"; + VERIFY(C.isApprox(B, static_cast<T>(tol))); + } +} + +template<typename MatrixType> +void randomTest(const MatrixType& m, double tol) +{ + /* this test covers the following files: + Inverse.h + */ + typename MatrixType::Index rows = m.rows(); + typename MatrixType::Index cols = m.cols(); + MatrixType m1(rows, cols), m2(rows, cols), m3(rows, cols), + identity = MatrixType::Identity(rows, rows); + + typedef typename NumTraits<typename internal::traits<MatrixType>::Scalar>::Real RealScalar; + + for(int i = 0; i < g_repeat; i++) { + m1 = MatrixType::Random(rows, cols); + + m2 = m1.matrixFunction(expfn) * (-m1).matrixFunction(expfn); + std::cout << "randomTest: error funm = " << relerr(identity, m2); + VERIFY(identity.isApprox(m2, static_cast<RealScalar>(tol))); + + m2 = m1.exp() * (-m1).exp(); + std::cout << " error expm = " << relerr(identity, m2) << "\n"; + VERIFY(identity.isApprox(m2, static_cast<RealScalar>(tol))); + } +} + +void test_matrix_exponential() +{ + CALL_SUBTEST_2(test2dRotation<double>(1e-13)); + CALL_SUBTEST_1(test2dRotation<float>(2e-5)); // was 1e-5, relaxed for clang 2.8 / linux / x86-64 + CALL_SUBTEST_8(test2dRotation<long double>(1e-13)); + CALL_SUBTEST_2(test2dHyperbolicRotation<double>(1e-14)); + CALL_SUBTEST_1(test2dHyperbolicRotation<float>(1e-5)); + CALL_SUBTEST_8(test2dHyperbolicRotation<long double>(1e-14)); + CALL_SUBTEST_6(testPascal<float>(1e-6)); + CALL_SUBTEST_5(testPascal<double>(1e-15)); + CALL_SUBTEST_2(randomTest(Matrix2d(), 1e-13)); + CALL_SUBTEST_7(randomTest(Matrix<double,3,3,RowMajor>(), 1e-13)); + CALL_SUBTEST_3(randomTest(Matrix4cd(), 1e-13)); + CALL_SUBTEST_4(randomTest(MatrixXd(8,8), 1e-13)); + CALL_SUBTEST_1(randomTest(Matrix2f(), 1e-4)); + CALL_SUBTEST_5(randomTest(Matrix3cf(), 1e-4)); + CALL_SUBTEST_1(randomTest(Matrix4f(), 1e-4)); + CALL_SUBTEST_6(randomTest(MatrixXf(8,8), 1e-4)); + CALL_SUBTEST_9(randomTest(Matrix<long double,Dynamic,Dynamic>(7,7), 1e-13)); +} diff --git a/unsupported/test/matrix_function.cpp b/unsupported/test/matrix_function.cpp new file mode 100644 index 000000000..0439c5a7d --- /dev/null +++ b/unsupported/test/matrix_function.cpp @@ -0,0 +1,194 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2010 Jitse Niesen <jitse@maths.leeds.ac.uk> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/MatrixFunctions> + +// Variant of VERIFY_IS_APPROX which uses absolute error instead of +// relative error. +#define VERIFY_IS_APPROX_ABS(a, b) VERIFY(test_isApprox_abs(a, b)) + +template<typename Type1, typename Type2> +inline bool test_isApprox_abs(const Type1& a, const Type2& b) +{ + return ((a-b).array().abs() < test_precision<typename Type1::RealScalar>()).all(); +} + + +// Returns a matrix with eigenvalues clustered around 0, 1 and 2. +template<typename MatrixType> +MatrixType randomMatrixWithRealEivals(const typename MatrixType::Index size) +{ + typedef typename MatrixType::Index Index; + typedef typename MatrixType::Scalar Scalar; + typedef typename MatrixType::RealScalar RealScalar; + MatrixType diag = MatrixType::Zero(size, size); + for (Index i = 0; i < size; ++i) { + diag(i, i) = Scalar(RealScalar(internal::random<int>(0,2))) + + internal::random<Scalar>() * Scalar(RealScalar(0.01)); + } + MatrixType A = MatrixType::Random(size, size); + HouseholderQR<MatrixType> QRofA(A); + return QRofA.householderQ().inverse() * diag * QRofA.householderQ(); +} + +template <typename MatrixType, int IsComplex = NumTraits<typename internal::traits<MatrixType>::Scalar>::IsComplex> +struct randomMatrixWithImagEivals +{ + // Returns a matrix with eigenvalues clustered around 0 and +/- i. + static MatrixType run(const typename MatrixType::Index size); +}; + +// Partial specialization for real matrices +template<typename MatrixType> +struct randomMatrixWithImagEivals<MatrixType, 0> +{ + static MatrixType run(const typename MatrixType::Index size) + { + typedef typename MatrixType::Index Index; + typedef typename MatrixType::Scalar Scalar; + MatrixType diag = MatrixType::Zero(size, size); + Index i = 0; + while (i < size) { + Index randomInt = internal::random<Index>(-1, 1); + if (randomInt == 0 || i == size-1) { + diag(i, i) = internal::random<Scalar>() * Scalar(0.01); + ++i; + } else { + Scalar alpha = Scalar(randomInt) + internal::random<Scalar>() * Scalar(0.01); + diag(i, i+1) = alpha; + diag(i+1, i) = -alpha; + i += 2; + } + } + MatrixType A = MatrixType::Random(size, size); + HouseholderQR<MatrixType> QRofA(A); + return QRofA.householderQ().inverse() * diag * QRofA.householderQ(); + } +}; + +// Partial specialization for complex matrices +template<typename MatrixType> +struct randomMatrixWithImagEivals<MatrixType, 1> +{ + static MatrixType run(const typename MatrixType::Index size) + { + typedef typename MatrixType::Index Index; + typedef typename MatrixType::Scalar Scalar; + typedef typename MatrixType::RealScalar RealScalar; + const Scalar imagUnit(0, 1); + MatrixType diag = MatrixType::Zero(size, size); + for (Index i = 0; i < size; ++i) { + diag(i, i) = Scalar(RealScalar(internal::random<Index>(-1, 1))) * imagUnit + + internal::random<Scalar>() * Scalar(RealScalar(0.01)); + } + MatrixType A = MatrixType::Random(size, size); + HouseholderQR<MatrixType> QRofA(A); + return QRofA.householderQ().inverse() * diag * QRofA.householderQ(); + } +}; + + +template<typename MatrixType> +void testMatrixExponential(const MatrixType& A) +{ + typedef typename internal::traits<MatrixType>::Scalar Scalar; + typedef typename NumTraits<Scalar>::Real RealScalar; + typedef std::complex<RealScalar> ComplexScalar; + + VERIFY_IS_APPROX(A.exp(), A.matrixFunction(StdStemFunctions<ComplexScalar>::exp)); +} + +template<typename MatrixType> +void testMatrixLogarithm(const MatrixType& A) +{ + typedef typename internal::traits<MatrixType>::Scalar Scalar; + typedef typename NumTraits<Scalar>::Real RealScalar; + typedef std::complex<RealScalar> ComplexScalar; + + MatrixType scaledA; + RealScalar maxImagPartOfSpectrum = A.eigenvalues().imag().cwiseAbs().maxCoeff(); + if (maxImagPartOfSpectrum >= 0.9 * M_PI) + scaledA = A * 0.9 * M_PI / maxImagPartOfSpectrum; + else + scaledA = A; + + // identity X.exp().log() = X only holds if Im(lambda) < pi for all eigenvalues of X + MatrixType expA = scaledA.exp(); + MatrixType logExpA = expA.log(); + VERIFY_IS_APPROX(logExpA, scaledA); +} + +template<typename MatrixType> +void testHyperbolicFunctions(const MatrixType& A) +{ + // Need to use absolute error because of possible cancellation when + // adding/subtracting expA and expmA. + VERIFY_IS_APPROX_ABS(A.sinh(), (A.exp() - (-A).exp()) / 2); + VERIFY_IS_APPROX_ABS(A.cosh(), (A.exp() + (-A).exp()) / 2); +} + +template<typename MatrixType> +void testGonioFunctions(const MatrixType& A) +{ + typedef typename MatrixType::Scalar Scalar; + typedef typename NumTraits<Scalar>::Real RealScalar; + typedef std::complex<RealScalar> ComplexScalar; + typedef Matrix<ComplexScalar, MatrixType::RowsAtCompileTime, + MatrixType::ColsAtCompileTime, MatrixType::Options> ComplexMatrix; + + ComplexScalar imagUnit(0,1); + ComplexScalar two(2,0); + + ComplexMatrix Ac = A.template cast<ComplexScalar>(); + + ComplexMatrix exp_iA = (imagUnit * Ac).exp(); + ComplexMatrix exp_miA = (-imagUnit * Ac).exp(); + + ComplexMatrix sinAc = A.sin().template cast<ComplexScalar>(); + VERIFY_IS_APPROX_ABS(sinAc, (exp_iA - exp_miA) / (two*imagUnit)); + + ComplexMatrix cosAc = A.cos().template cast<ComplexScalar>(); + VERIFY_IS_APPROX_ABS(cosAc, (exp_iA + exp_miA) / 2); +} + +template<typename MatrixType> +void testMatrix(const MatrixType& A) +{ + testMatrixExponential(A); + testMatrixLogarithm(A); + testHyperbolicFunctions(A); + testGonioFunctions(A); +} + +template<typename MatrixType> +void testMatrixType(const MatrixType& m) +{ + // Matrices with clustered eigenvalue lead to different code paths + // in MatrixFunction.h and are thus useful for testing. + typedef typename MatrixType::Index Index; + + const Index size = m.rows(); + for (int i = 0; i < g_repeat; i++) { + testMatrix(MatrixType::Random(size, size).eval()); + testMatrix(randomMatrixWithRealEivals<MatrixType>(size)); + testMatrix(randomMatrixWithImagEivals<MatrixType>::run(size)); + } +} + +void test_matrix_function() +{ + CALL_SUBTEST_1(testMatrixType(Matrix<float,1,1>())); + CALL_SUBTEST_2(testMatrixType(Matrix3cf())); + CALL_SUBTEST_3(testMatrixType(MatrixXf(8,8))); + CALL_SUBTEST_4(testMatrixType(Matrix2d())); + CALL_SUBTEST_5(testMatrixType(Matrix<double,5,5,RowMajor>())); + CALL_SUBTEST_6(testMatrixType(Matrix4cd())); + CALL_SUBTEST_7(testMatrixType(MatrixXd(13,13))); +} diff --git a/unsupported/test/matrix_square_root.cpp b/unsupported/test/matrix_square_root.cpp new file mode 100644 index 000000000..508619a7a --- /dev/null +++ b/unsupported/test/matrix_square_root.cpp @@ -0,0 +1,62 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2011 Jitse Niesen <jitse@maths.leeds.ac.uk> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/MatrixFunctions> + +template <typename MatrixType, int IsComplex = NumTraits<typename internal::traits<MatrixType>::Scalar>::IsComplex> +struct generateTestMatrix; + +// for real matrices, make sure none of the eigenvalues are negative +template <typename MatrixType> +struct generateTestMatrix<MatrixType,0> +{ + static void run(MatrixType& result, typename MatrixType::Index size) + { + MatrixType mat = MatrixType::Random(size, size); + EigenSolver<MatrixType> es(mat); + typename EigenSolver<MatrixType>::EigenvalueType eivals = es.eigenvalues(); + for (typename MatrixType::Index i = 0; i < size; ++i) { + if (eivals(i).imag() == 0 && eivals(i).real() < 0) + eivals(i) = -eivals(i); + } + result = (es.eigenvectors() * eivals.asDiagonal() * es.eigenvectors().inverse()).real(); + } +}; + +// for complex matrices, any matrix is fine +template <typename MatrixType> +struct generateTestMatrix<MatrixType,1> +{ + static void run(MatrixType& result, typename MatrixType::Index size) + { + result = MatrixType::Random(size, size); + } +}; + +template<typename MatrixType> +void testMatrixSqrt(const MatrixType& m) +{ + MatrixType A; + generateTestMatrix<MatrixType>::run(A, m.rows()); + MatrixType sqrtA = A.sqrt(); + VERIFY_IS_APPROX(sqrtA * sqrtA, A); +} + +void test_matrix_square_root() +{ + for (int i = 0; i < g_repeat; i++) { + CALL_SUBTEST_1(testMatrixSqrt(Matrix3cf())); + CALL_SUBTEST_2(testMatrixSqrt(MatrixXcd(12,12))); + CALL_SUBTEST_3(testMatrixSqrt(Matrix4f())); + CALL_SUBTEST_4(testMatrixSqrt(Matrix<double,Dynamic,Dynamic,RowMajor>(9, 9))); + CALL_SUBTEST_5(testMatrixSqrt(Matrix<float,1,1>())); + CALL_SUBTEST_5(testMatrixSqrt(Matrix<std::complex<float>,1,1>())); + } +} diff --git a/unsupported/test/mpreal/dlmalloc.c b/unsupported/test/mpreal/dlmalloc.c new file mode 100755 index 000000000..7ce8feb07 --- /dev/null +++ b/unsupported/test/mpreal/dlmalloc.c @@ -0,0 +1,5703 @@ +/*
+ This is a version (aka dlmalloc) of malloc/free/realloc written by
+ Doug Lea and released to the public domain, as explained at
+ http://creativecommons.org/licenses/publicdomain. Send questions,
+ comments, complaints, performance data, etc to dl@cs.oswego.edu
+
+* Version 2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee)
+
+ Note: There may be an updated version of this malloc obtainable at
+ ftp://gee.cs.oswego.edu/pub/misc/malloc.c
+ Check before installing!
+
+* Quickstart
+
+ This library is all in one file to simplify the most common usage:
+ ftp it, compile it (-O3), and link it into another program. All of
+ the compile-time options default to reasonable values for use on
+ most platforms. You might later want to step through various
+ compile-time and dynamic tuning options.
+
+ For convenience, an include file for code using this malloc is at:
+ ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.4.h
+ You don't really need this .h file unless you call functions not
+ defined in your system include files. The .h file contains only the
+ excerpts from this file needed for using this malloc on ANSI C/C++
+ systems, so long as you haven't changed compile-time options about
+ naming and tuning parameters. If you do, then you can create your
+ own malloc.h that does include all settings by cutting at the point
+ indicated below. Note that you may already by default be using a C
+ library containing a malloc that is based on some version of this
+ malloc (for example in linux). You might still want to use the one
+ in this file to customize settings or to avoid overheads associated
+ with library versions.
+
+* Vital statistics:
+
+ Supported pointer/size_t representation: 4 or 8 bytes
+ size_t MUST be an unsigned type of the same width as
+ pointers. (If you are using an ancient system that declares
+ size_t as a signed type, or need it to be a different width
+ than pointers, you can use a previous release of this malloc
+ (e.g. 2.7.2) supporting these.)
+
+ Alignment: 8 bytes (default)
+ This suffices for nearly all current machines and C compilers.
+ However, you can define MALLOC_ALIGNMENT to be wider than this
+ if necessary (up to 128bytes), at the expense of using more space.
+
+ Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes)
+ 8 or 16 bytes (if 8byte sizes)
+ Each malloced chunk has a hidden word of overhead holding size
+ and status information, and additional cross-check word
+ if FOOTERS is defined.
+
+ Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead)
+ 8-byte ptrs: 32 bytes (including overhead)
+
+ Even a request for zero bytes (i.e., malloc(0)) returns a
+ pointer to something of the minimum allocatable size.
+ The maximum overhead wastage (i.e., number of extra bytes
+ allocated than were requested in malloc) is less than or equal
+ to the minimum size, except for requests >= mmap_threshold that
+ are serviced via mmap(), where the worst case wastage is about
+ 32 bytes plus the remainder from a system page (the minimal
+ mmap unit); typically 4096 or 8192 bytes.
+
+ Security: static-safe; optionally more or less
+ The "security" of malloc refers to the ability of malicious
+ code to accentuate the effects of errors (for example, freeing
+ space that is not currently malloc'ed or overwriting past the
+ ends of chunks) in code that calls malloc. This malloc
+ guarantees not to modify any memory locations below the base of
+ heap, i.e., static variables, even in the presence of usage
+ errors. The routines additionally detect most improper frees
+ and reallocs. All this holds as long as the static bookkeeping
+ for malloc itself is not corrupted by some other means. This
+ is only one aspect of security -- these checks do not, and
+ cannot, detect all possible programming errors.
+
+ If FOOTERS is defined nonzero, then each allocated chunk
+ carries an additional check word to verify that it was malloced
+ from its space. These check words are the same within each
+ execution of a program using malloc, but differ across
+ executions, so externally crafted fake chunks cannot be
+ freed. This improves security by rejecting frees/reallocs that
+ could corrupt heap memory, in addition to the checks preventing
+ writes to statics that are always on. This may further improve
+ security at the expense of time and space overhead. (Note that
+ FOOTERS may also be worth using with MSPACES.)
+
+ By default detected errors cause the program to abort (calling
+ "abort()"). You can override this to instead proceed past
+ errors by defining PROCEED_ON_ERROR. In this case, a bad free
+ has no effect, and a malloc that encounters a bad address
+ caused by user overwrites will ignore the bad address by
+ dropping pointers and indices to all known memory. This may
+ be appropriate for programs that should continue if at all
+ possible in the face of programming errors, although they may
+ run out of memory because dropped memory is never reclaimed.
+
+ If you don't like either of these options, you can define
+ CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything
+ else. And if if you are sure that your program using malloc has
+ no errors or vulnerabilities, you can define INSECURE to 1,
+ which might (or might not) provide a small performance improvement.
+
+ Thread-safety: NOT thread-safe unless USE_LOCKS defined
+ When USE_LOCKS is defined, each public call to malloc, free,
+ etc is surrounded with either a pthread mutex or a win32
+ spinlock (depending on WIN32). This is not especially fast, and
+ can be a major bottleneck. It is designed only to provide
+ minimal protection in concurrent environments, and to provide a
+ basis for extensions. If you are using malloc in a concurrent
+ program, consider instead using nedmalloc
+ (http://www.nedprod.com/programs/portable/nedmalloc/) or
+ ptmalloc (See http://www.malloc.de), which are derived
+ from versions of this malloc.
+
+ System requirements: Any combination of MORECORE and/or MMAP/MUNMAP
+ This malloc can use unix sbrk or any emulation (invoked using
+ the CALL_MORECORE macro) and/or mmap/munmap or any emulation
+ (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system
+ memory. On most unix systems, it tends to work best if both
+ MORECORE and MMAP are enabled. On Win32, it uses emulations
+ based on VirtualAlloc. It also uses common C library functions
+ like memset.
+
+ Compliance: I believe it is compliant with the Single Unix Specification
+ (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably
+ others as well.
+
+* Overview of algorithms
+
+ This is not the fastest, most space-conserving, most portable, or
+ most tunable malloc ever written. However it is among the fastest
+ while also being among the most space-conserving, portable and
+ tunable. Consistent balance across these factors results in a good
+ general-purpose allocator for malloc-intensive programs.
+
+ In most ways, this malloc is a best-fit allocator. Generally, it
+ chooses the best-fitting existing chunk for a request, with ties
+ broken in approximately least-recently-used order. (This strategy
+ normally maintains low fragmentation.) However, for requests less
+ than 256bytes, it deviates from best-fit when there is not an
+ exactly fitting available chunk by preferring to use space adjacent
+ to that used for the previous small request, as well as by breaking
+ ties in approximately most-recently-used order. (These enhance
+ locality of series of small allocations.) And for very large requests
+ (>= 256Kb by default), it relies on system memory mapping
+ facilities, if supported. (This helps avoid carrying around and
+ possibly fragmenting memory used only for large chunks.)
+
+ All operations (except malloc_stats and mallinfo) have execution
+ times that are bounded by a constant factor of the number of bits in
+ a size_t, not counting any clearing in calloc or copying in realloc,
+ or actions surrounding MORECORE and MMAP that have times
+ proportional to the number of non-contiguous regions returned by
+ system allocation routines, which is often just 1. In real-time
+ applications, you can optionally suppress segment traversals using
+ NO_SEGMENT_TRAVERSAL, which assures bounded execution even when
+ system allocators return non-contiguous spaces, at the typical
+ expense of carrying around more memory and increased fragmentation.
+
+ The implementation is not very modular and seriously overuses
+ macros. Perhaps someday all C compilers will do as good a job
+ inlining modular code as can now be done by brute-force expansion,
+ but now, enough of them seem not to.
+
+ Some compilers issue a lot of warnings about code that is
+ dead/unreachable only on some platforms, and also about intentional
+ uses of negation on unsigned types. All known cases of each can be
+ ignored.
+
+ For a longer but out of date high-level description, see
+ http://gee.cs.oswego.edu/dl/html/malloc.html
+
+* MSPACES
+ If MSPACES is defined, then in addition to malloc, free, etc.,
+ this file also defines mspace_malloc, mspace_free, etc. These
+ are versions of malloc routines that take an "mspace" argument
+ obtained using create_mspace, to control all internal bookkeeping.
+ If ONLY_MSPACES is defined, only these versions are compiled.
+ So if you would like to use this allocator for only some allocations,
+ and your system malloc for others, you can compile with
+ ONLY_MSPACES and then do something like...
+ static mspace mymspace = create_mspace(0,0); // for example
+ #define mymalloc(bytes) mspace_malloc(mymspace, bytes)
+
+ (Note: If you only need one instance of an mspace, you can instead
+ use "USE_DL_PREFIX" to relabel the global malloc.)
+
+ You can similarly create thread-local allocators by storing
+ mspaces as thread-locals. For example:
+ static __thread mspace tlms = 0;
+ void* tlmalloc(size_t bytes) {
+ if (tlms == 0) tlms = create_mspace(0, 0);
+ return mspace_malloc(tlms, bytes);
+ }
+ void tlfree(void* mem) { mspace_free(tlms, mem); }
+
+ Unless FOOTERS is defined, each mspace is completely independent.
+ You cannot allocate from one and free to another (although
+ conformance is only weakly checked, so usage errors are not always
+ caught). If FOOTERS is defined, then each chunk carries around a tag
+ indicating its originating mspace, and frees are directed to their
+ originating spaces.
+
+ ------------------------- Compile-time options ---------------------------
+
+Be careful in setting #define values for numerical constants of type
+size_t. On some systems, literal values are not automatically extended
+to size_t precision unless they are explicitly casted. You can also
+use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below.
+
+WIN32 default: defined if _WIN32 defined
+ Defining WIN32 sets up defaults for MS environment and compilers.
+ Otherwise defaults are for unix. Beware that there seem to be some
+ cases where this malloc might not be a pure drop-in replacement for
+ Win32 malloc: Random-looking failures from Win32 GDI API's (eg;
+ SetDIBits()) may be due to bugs in some video driver implementations
+ when pixel buffers are malloc()ed, and the region spans more than
+ one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb)
+ default granularity, pixel buffers may straddle virtual allocation
+ regions more often than when using the Microsoft allocator. You can
+ avoid this by using VirtualAlloc() and VirtualFree() for all pixel
+ buffers rather than using malloc(). If this is not possible,
+ recompile this malloc with a larger DEFAULT_GRANULARITY.
+
+MALLOC_ALIGNMENT default: (size_t)8
+ Controls the minimum alignment for malloc'ed chunks. It must be a
+ power of two and at least 8, even on machines for which smaller
+ alignments would suffice. It may be defined as larger than this
+ though. Note however that code and data structures are optimized for
+ the case of 8-byte alignment.
+
+MSPACES default: 0 (false)
+ If true, compile in support for independent allocation spaces.
+ This is only supported if HAVE_MMAP is true.
+
+ONLY_MSPACES default: 0 (false)
+ If true, only compile in mspace versions, not regular versions.
+
+USE_LOCKS default: 0 (false)
+ Causes each call to each public routine to be surrounded with
+ pthread or WIN32 mutex lock/unlock. (If set true, this can be
+ overridden on a per-mspace basis for mspace versions.) If set to a
+ non-zero value other than 1, locks are used, but their
+ implementation is left out, so lock functions must be supplied manually,
+ as described below.
+
+USE_SPIN_LOCKS default: 1 iff USE_LOCKS and on x86 using gcc or MSC
+ If true, uses custom spin locks for locking. This is currently
+ supported only for x86 platforms using gcc or recent MS compilers.
+ Otherwise, posix locks or win32 critical sections are used.
+
+FOOTERS default: 0
+ If true, provide extra checking and dispatching by placing
+ information in the footers of allocated chunks. This adds
+ space and time overhead.
+
+INSECURE default: 0
+ If true, omit checks for usage errors and heap space overwrites.
+
+USE_DL_PREFIX default: NOT defined
+ Causes compiler to prefix all public routines with the string 'dl'.
+ This can be useful when you only want to use this malloc in one part
+ of a program, using your regular system malloc elsewhere.
+
+ABORT default: defined as abort()
+ Defines how to abort on failed checks. On most systems, a failed
+ check cannot die with an "assert" or even print an informative
+ message, because the underlying print routines in turn call malloc,
+ which will fail again. Generally, the best policy is to simply call
+ abort(). It's not very useful to do more than this because many
+ errors due to overwriting will show up as address faults (null, odd
+ addresses etc) rather than malloc-triggered checks, so will also
+ abort. Also, most compilers know that abort() does not return, so
+ can better optimize code conditionally calling it.
+
+PROCEED_ON_ERROR default: defined as 0 (false)
+ Controls whether detected bad addresses cause them to bypassed
+ rather than aborting. If set, detected bad arguments to free and
+ realloc are ignored. And all bookkeeping information is zeroed out
+ upon a detected overwrite of freed heap space, thus losing the
+ ability to ever return it from malloc again, but enabling the
+ application to proceed. If PROCEED_ON_ERROR is defined, the
+ static variable malloc_corruption_error_count is compiled in
+ and can be examined to see if errors have occurred. This option
+ generates slower code than the default abort policy.
+
+DEBUG default: NOT defined
+ The DEBUG setting is mainly intended for people trying to modify
+ this code or diagnose problems when porting to new platforms.
+ However, it may also be able to better isolate user errors than just
+ using runtime checks. The assertions in the check routines spell
+ out in more detail the assumptions and invariants underlying the
+ algorithms. The checking is fairly extensive, and will slow down
+ execution noticeably. Calling malloc_stats or mallinfo with DEBUG
+ set will attempt to check every non-mmapped allocated and free chunk
+ in the course of computing the summaries.
+
+ABORT_ON_ASSERT_FAILURE default: defined as 1 (true)
+ Debugging assertion failures can be nearly impossible if your
+ version of the assert macro causes malloc to be called, which will
+ lead to a cascade of further failures, blowing the runtime stack.
+ ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(),
+ which will usually make debugging easier.
+
+MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32
+ The action to take before "return 0" when malloc fails to be able to
+ return memory because there is none available.
+
+HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES
+ True if this system supports sbrk or an emulation of it.
+
+MORECORE default: sbrk
+ The name of the sbrk-style system routine to call to obtain more
+ memory. See below for guidance on writing custom MORECORE
+ functions. The type of the argument to sbrk/MORECORE varies across
+ systems. It cannot be size_t, because it supports negative
+ arguments, so it is normally the signed type of the same width as
+ size_t (sometimes declared as "intptr_t"). It doesn't much matter
+ though. Internally, we only call it with arguments less than half
+ the max value of a size_t, which should work across all reasonable
+ possibilities, although sometimes generating compiler warnings.
+
+MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE
+ If true, take advantage of fact that consecutive calls to MORECORE
+ with positive arguments always return contiguous increasing
+ addresses. This is true of unix sbrk. It does not hurt too much to
+ set it true anyway, since malloc copes with non-contiguities.
+ Setting it false when definitely non-contiguous saves time
+ and possibly wasted space it would take to discover this though.
+
+MORECORE_CANNOT_TRIM default: NOT defined
+ True if MORECORE cannot release space back to the system when given
+ negative arguments. This is generally necessary only if you are
+ using a hand-crafted MORECORE function that cannot handle negative
+ arguments.
+
+NO_SEGMENT_TRAVERSAL default: 0
+ If non-zero, suppresses traversals of memory segments
+ returned by either MORECORE or CALL_MMAP. This disables
+ merging of segments that are contiguous, and selectively
+ releasing them to the OS if unused, but bounds execution times.
+
+HAVE_MMAP default: 1 (true)
+ True if this system supports mmap or an emulation of it. If so, and
+ HAVE_MORECORE is not true, MMAP is used for all system
+ allocation. If set and HAVE_MORECORE is true as well, MMAP is
+ primarily used to directly allocate very large blocks. It is also
+ used as a backup strategy in cases where MORECORE fails to provide
+ space from system. Note: A single call to MUNMAP is assumed to be
+ able to unmap memory that may have be allocated using multiple calls
+ to MMAP, so long as they are adjacent.
+
+HAVE_MREMAP default: 1 on linux, else 0
+ If true realloc() uses mremap() to re-allocate large blocks and
+ extend or shrink allocation spaces.
+
+MMAP_CLEARS default: 1 except on WINCE.
+ True if mmap clears memory so calloc doesn't need to. This is true
+ for standard unix mmap using /dev/zero and on WIN32 except for WINCE.
+
+USE_BUILTIN_FFS default: 0 (i.e., not used)
+ Causes malloc to use the builtin ffs() function to compute indices.
+ Some compilers may recognize and intrinsify ffs to be faster than the
+ supplied C version. Also, the case of x86 using gcc is special-cased
+ to an asm instruction, so is already as fast as it can be, and so
+ this setting has no effect. Similarly for Win32 under recent MS compilers.
+ (On most x86s, the asm version is only slightly faster than the C version.)
+
+malloc_getpagesize default: derive from system includes, or 4096.
+ The system page size. To the extent possible, this malloc manages
+ memory from the system in page-size units. This may be (and
+ usually is) a function rather than a constant. This is ignored
+ if WIN32, where page size is determined using getSystemInfo during
+ initialization.
+
+USE_DEV_RANDOM default: 0 (i.e., not used)
+ Causes malloc to use /dev/random to initialize secure magic seed for
+ stamping footers. Otherwise, the current time is used.
+
+NO_MALLINFO default: 0
+ If defined, don't compile "mallinfo". This can be a simple way
+ of dealing with mismatches between system declarations and
+ those in this file.
+
+MALLINFO_FIELD_TYPE default: size_t
+ The type of the fields in the mallinfo struct. This was originally
+ defined as "int" in SVID etc, but is more usefully defined as
+ size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set
+
+REALLOC_ZERO_BYTES_FREES default: not defined
+ This should be set if a call to realloc with zero bytes should
+ be the same as a call to free. Some people think it should. Otherwise,
+ since this malloc returns a unique pointer for malloc(0), so does
+ realloc(p, 0).
+
+LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H
+LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H
+LACKS_STDLIB_H default: NOT defined unless on WIN32
+ Define these if your system does not have these header files.
+ You might need to manually insert some of the declarations they provide.
+
+DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS,
+ system_info.dwAllocationGranularity in WIN32,
+ otherwise 64K.
+ Also settable using mallopt(M_GRANULARITY, x)
+ The unit for allocating and deallocating memory from the system. On
+ most systems with contiguous MORECORE, there is no reason to
+ make this more than a page. However, systems with MMAP tend to
+ either require or encourage larger granularities. You can increase
+ this value to prevent system allocation functions to be called so
+ often, especially if they are slow. The value must be at least one
+ page and must be a power of two. Setting to 0 causes initialization
+ to either page size or win32 region size. (Note: In previous
+ versions of malloc, the equivalent of this option was called
+ "TOP_PAD")
+
+DEFAULT_TRIM_THRESHOLD default: 2MB
+ Also settable using mallopt(M_TRIM_THRESHOLD, x)
+ The maximum amount of unused top-most memory to keep before
+ releasing via malloc_trim in free(). Automatic trimming is mainly
+ useful in long-lived programs using contiguous MORECORE. Because
+ trimming via sbrk can be slow on some systems, and can sometimes be
+ wasteful (in cases where programs immediately afterward allocate
+ more large chunks) the value should be high enough so that your
+ overall system performance would improve by releasing this much
+ memory. As a rough guide, you might set to a value close to the
+ average size of a process (program) running on your system.
+ Releasing this much memory would allow such a process to run in
+ memory. Generally, it is worth tuning trim thresholds when a
+ program undergoes phases where several large chunks are allocated
+ and released in ways that can reuse each other's storage, perhaps
+ mixed with phases where there are no such chunks at all. The trim
+ value must be greater than page size to have any useful effect. To
+ disable trimming completely, you can set to MAX_SIZE_T. Note that the trick
+ some people use of mallocing a huge space and then freeing it at
+ program startup, in an attempt to reserve system memory, doesn't
+ have the intended effect under automatic trimming, since that memory
+ will immediately be returned to the system.
+
+DEFAULT_MMAP_THRESHOLD default: 256K
+ Also settable using mallopt(M_MMAP_THRESHOLD, x)
+ The request size threshold for using MMAP to directly service a
+ request. Requests of at least this size that cannot be allocated
+ using already-existing space will be serviced via mmap. (If enough
+ normal freed space already exists it is used instead.) Using mmap
+ segregates relatively large chunks of memory so that they can be
+ individually obtained and released from the host system. A request
+ serviced through mmap is never reused by any other request (at least
+ not directly; the system may just so happen to remap successive
+ requests to the same locations). Segregating space in this way has
+ the benefits that: Mmapped space can always be individually released
+ back to the system, which helps keep the system level memory demands
+ of a long-lived program low. Also, mapped memory doesn't become
+ `locked' between other chunks, as can happen with normally allocated
+ chunks, which means that even trimming via malloc_trim would not
+ release them. However, it has the disadvantage that the space
+ cannot be reclaimed, consolidated, and then used to service later
+ requests, as happens with normal chunks. The advantages of mmap
+ nearly always outweigh disadvantages for "large" chunks, but the
+ value of "large" may vary across systems. The default is an
+ empirically derived value that works well in most systems. You can
+ disable mmap by setting to MAX_SIZE_T.
+
+MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP
+ The number of consolidated frees between checks to release
+ unused segments when freeing. When using non-contiguous segments,
+ especially with multiple mspaces, checking only for topmost space
+ doesn't always suffice to trigger trimming. To compensate for this,
+ free() will, with a period of MAX_RELEASE_CHECK_RATE (or the
+ current number of segments, if greater) try to release unused
+ segments to the OS when freeing chunks that result in
+ consolidation. The best value for this parameter is a compromise
+ between slowing down frees with relatively costly checks that
+ rarely trigger versus holding on to unused memory. To effectively
+ disable, set to MAX_SIZE_T. This may lead to a very slight speed
+ improvement at the expense of carrying around more memory.
+*/
+
+#define USE_DL_PREFIX
+//#define HAVE_USR_INCLUDE_MALLOC_H
+//#define MSPACES 1
+#define NO_SEGMENT_TRAVERSAL 1
+
+/* Version identifier to allow people to support multiple versions */
+#ifndef DLMALLOC_VERSION
+#define DLMALLOC_VERSION 20804
+#endif /* DLMALLOC_VERSION */
+
+#ifndef WIN32
+#ifdef _WIN32
+#define WIN32 1
+#endif /* _WIN32 */
+#ifdef _WIN32_WCE
+#define LACKS_FCNTL_H
+#define WIN32 1
+#endif /* _WIN32_WCE */
+#endif /* WIN32 */
+#ifdef WIN32
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#define HAVE_MMAP 1
+#define HAVE_MORECORE 0
+#define LACKS_UNISTD_H
+#define LACKS_SYS_PARAM_H
+#define LACKS_SYS_MMAN_H
+#define LACKS_STRING_H
+#define LACKS_STRINGS_H
+#define LACKS_SYS_TYPES_H
+#define LACKS_ERRNO_H
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION
+#endif /* MALLOC_FAILURE_ACTION */
+#ifdef _WIN32_WCE /* WINCE reportedly does not clear */
+#define MMAP_CLEARS 0
+#else
+#define MMAP_CLEARS 1
+#endif /* _WIN32_WCE */
+#endif /* WIN32 */
+
+#if defined(DARWIN) || defined(_DARWIN)
+/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */
+#ifndef HAVE_MORECORE
+#define HAVE_MORECORE 0
+#define HAVE_MMAP 1
+/* OSX allocators provide 16 byte alignment */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)16U)
+#endif
+#endif /* HAVE_MORECORE */
+#endif /* DARWIN */
+
+#ifndef LACKS_SYS_TYPES_H
+#include <sys/types.h> /* For size_t */
+#endif /* LACKS_SYS_TYPES_H */
+
+#if (defined(__GNUC__) && ((defined(__i386__) || defined(__x86_64__)))) || (defined(_MSC_VER) && _MSC_VER>=1310)
+#define SPIN_LOCKS_AVAILABLE 1
+#else
+#define SPIN_LOCKS_AVAILABLE 0
+#endif
+
+/* The maximum possible size_t value has all bits set */
+#define MAX_SIZE_T (~(size_t)0)
+
+#ifndef ONLY_MSPACES
+#define ONLY_MSPACES 0 /* define to a value */
+#else
+#define ONLY_MSPACES 1
+#endif /* ONLY_MSPACES */
+#ifndef MSPACES
+#if ONLY_MSPACES
+#define MSPACES 1
+#else /* ONLY_MSPACES */
+#define MSPACES 0
+#endif /* ONLY_MSPACES */
+#endif /* MSPACES */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)8U)
+#endif /* MALLOC_ALIGNMENT */
+#ifndef FOOTERS
+#define FOOTERS 0
+#endif /* FOOTERS */
+#ifndef ABORT
+#define ABORT abort()
+#endif /* ABORT */
+#ifndef ABORT_ON_ASSERT_FAILURE
+#define ABORT_ON_ASSERT_FAILURE 1
+#endif /* ABORT_ON_ASSERT_FAILURE */
+#ifndef PROCEED_ON_ERROR
+#define PROCEED_ON_ERROR 0
+#endif /* PROCEED_ON_ERROR */
+#ifndef USE_LOCKS
+#define USE_LOCKS 0
+#endif /* USE_LOCKS */
+#ifndef USE_SPIN_LOCKS
+#if USE_LOCKS && SPIN_LOCKS_AVAILABLE
+#define USE_SPIN_LOCKS 1
+#else
+#define USE_SPIN_LOCKS 0
+#endif /* USE_LOCKS && SPIN_LOCKS_AVAILABLE. */
+#endif /* USE_SPIN_LOCKS */
+#ifndef INSECURE
+#define INSECURE 0
+#endif /* INSECURE */
+#ifndef HAVE_MMAP
+#define HAVE_MMAP 1
+#endif /* HAVE_MMAP */
+#ifndef MMAP_CLEARS
+#define MMAP_CLEARS 1
+#endif /* MMAP_CLEARS */
+#ifndef HAVE_MREMAP
+#ifdef linux
+#define HAVE_MREMAP 1
+#else /* linux */
+#define HAVE_MREMAP 0
+#endif /* linux */
+#endif /* HAVE_MREMAP */
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION errno = ENOMEM;
+#endif /* MALLOC_FAILURE_ACTION */
+#ifndef HAVE_MORECORE
+#if ONLY_MSPACES
+#define HAVE_MORECORE 0
+#else /* ONLY_MSPACES */
+#define HAVE_MORECORE 1
+#endif /* ONLY_MSPACES */
+#endif /* HAVE_MORECORE */
+#if !HAVE_MORECORE
+#define MORECORE_CONTIGUOUS 0
+#else /* !HAVE_MORECORE */
+#define MORECORE_DEFAULT sbrk
+#ifndef MORECORE_CONTIGUOUS
+#define MORECORE_CONTIGUOUS 1
+#endif /* MORECORE_CONTIGUOUS */
+#endif /* HAVE_MORECORE */
+#ifndef DEFAULT_GRANULARITY
+#if (MORECORE_CONTIGUOUS || defined(WIN32))
+#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */
+#else /* MORECORE_CONTIGUOUS */
+#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U)
+#endif /* MORECORE_CONTIGUOUS */
+#endif /* DEFAULT_GRANULARITY */
+#ifndef DEFAULT_TRIM_THRESHOLD
+#ifndef MORECORE_CANNOT_TRIM
+#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U)
+#else /* MORECORE_CANNOT_TRIM */
+#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T
+#endif /* MORECORE_CANNOT_TRIM */
+#endif /* DEFAULT_TRIM_THRESHOLD */
+#ifndef DEFAULT_MMAP_THRESHOLD
+#if HAVE_MMAP
+#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U)
+#else /* HAVE_MMAP */
+#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T
+#endif /* HAVE_MMAP */
+#endif /* DEFAULT_MMAP_THRESHOLD */
+#ifndef MAX_RELEASE_CHECK_RATE
+#if HAVE_MMAP
+#define MAX_RELEASE_CHECK_RATE 4095
+#else
+#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T
+#endif /* HAVE_MMAP */
+#endif /* MAX_RELEASE_CHECK_RATE */
+#ifndef USE_BUILTIN_FFS
+#define USE_BUILTIN_FFS 0
+#endif /* USE_BUILTIN_FFS */
+#ifndef USE_DEV_RANDOM
+#define USE_DEV_RANDOM 0
+#endif /* USE_DEV_RANDOM */
+#ifndef NO_MALLINFO
+#define NO_MALLINFO 0
+#endif /* NO_MALLINFO */
+#ifndef MALLINFO_FIELD_TYPE
+#define MALLINFO_FIELD_TYPE size_t
+#endif /* MALLINFO_FIELD_TYPE */
+#ifndef NO_SEGMENT_TRAVERSAL
+#define NO_SEGMENT_TRAVERSAL 0
+#endif /* NO_SEGMENT_TRAVERSAL */
+
+/*
+ mallopt tuning options. SVID/XPG defines four standard parameter
+ numbers for mallopt, normally defined in malloc.h. None of these
+ are used in this malloc, so setting them has no effect. But this
+ malloc does support the following options.
+*/
+
+#define M_TRIM_THRESHOLD (-1)
+#define M_GRANULARITY (-2)
+#define M_MMAP_THRESHOLD (-3)
+
+/* ------------------------ Mallinfo declarations ------------------------ */
+
+#if !NO_MALLINFO
+/*
+ This version of malloc supports the standard SVID/XPG mallinfo
+ routine that returns a struct containing usage properties and
+ statistics. It should work on any system that has a
+ /usr/include/malloc.h defining struct mallinfo. The main
+ declaration needed is the mallinfo struct that is returned (by-copy)
+ by mallinfo(). The malloinfo struct contains a bunch of fields that
+ are not even meaningful in this version of malloc. These fields are
+ are instead filled by mallinfo() with other numbers that might be of
+ interest.
+
+ HAVE_USR_INCLUDE_MALLOC_H should be set if you have a
+ /usr/include/malloc.h file that includes a declaration of struct
+ mallinfo. If so, it is included; else a compliant version is
+ declared below. These must be precisely the same for mallinfo() to
+ work. The original SVID version of this struct, defined on most
+ systems with mallinfo, declares all fields as ints. But some others
+ define as unsigned long. If your system defines the fields using a
+ type of different width than listed here, you MUST #include your
+ system version and #define HAVE_USR_INCLUDE_MALLOC_H.
+*/
+
+/* #define HAVE_USR_INCLUDE_MALLOC_H */
+
+#ifdef HAVE_USR_INCLUDE_MALLOC_H
+#include "/usr/include/malloc.h"
+#else /* HAVE_USR_INCLUDE_MALLOC_H */
+#ifndef STRUCT_MALLINFO_DECLARED
+#define STRUCT_MALLINFO_DECLARED 1
+struct mallinfo {
+ MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */
+ MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */
+ MALLINFO_FIELD_TYPE smblks; /* always 0 */
+ MALLINFO_FIELD_TYPE hblks; /* always 0 */
+ MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */
+ MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */
+ MALLINFO_FIELD_TYPE fsmblks; /* always 0 */
+ MALLINFO_FIELD_TYPE uordblks; /* total allocated space */
+ MALLINFO_FIELD_TYPE fordblks; /* total free space */
+ MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */
+};
+#endif /* STRUCT_MALLINFO_DECLARED */
+#endif /* HAVE_USR_INCLUDE_MALLOC_H */
+#endif /* NO_MALLINFO */
+
+/*
+ Try to persuade compilers to inline. The most critical functions for
+ inlining are defined as macros, so these aren't used for them.
+*/
+
+#ifndef FORCEINLINE
+ #if defined(__GNUC__)
+#define FORCEINLINE __inline __attribute__ ((always_inline))
+ #elif defined(_MSC_VER)
+ #define FORCEINLINE __forceinline
+ #endif
+#endif
+#ifndef NOINLINE
+ #if defined(__GNUC__)
+ #define NOINLINE __attribute__ ((noinline))
+ #elif defined(_MSC_VER)
+ #define NOINLINE __declspec(noinline)
+ #else
+ #define NOINLINE
+ #endif
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#ifndef FORCEINLINE
+ #define FORCEINLINE inline
+#endif
+#endif /* __cplusplus */
+#ifndef FORCEINLINE
+ #define FORCEINLINE
+#endif
+
+#if !ONLY_MSPACES
+
+/* ------------------- Declarations of public routines ------------------- */
+
+#ifndef USE_DL_PREFIX
+#define dlcalloc calloc
+#define dlfree free
+#define dlmalloc malloc
+#define dlmemalign memalign
+#define dlrealloc realloc
+#define dlvalloc valloc
+#define dlpvalloc pvalloc
+#define dlmallinfo mallinfo
+#define dlmallopt mallopt
+#define dlmalloc_trim malloc_trim
+#define dlmalloc_stats malloc_stats
+#define dlmalloc_usable_size malloc_usable_size
+#define dlmalloc_footprint malloc_footprint
+#define dlmalloc_max_footprint malloc_max_footprint
+#define dlindependent_calloc independent_calloc
+#define dlindependent_comalloc independent_comalloc
+#endif /* USE_DL_PREFIX */
+
+
+/*
+ malloc(size_t n)
+ Returns a pointer to a newly allocated chunk of at least n bytes, or
+ null if no space is available, in which case errno is set to ENOMEM
+ on ANSI C systems.
+
+ If n is zero, malloc returns a minimum-sized chunk. (The minimum
+ size is 16 bytes on most 32bit systems, and 32 bytes on 64bit
+ systems.) Note that size_t is an unsigned type, so calls with
+ arguments that would be negative if signed are interpreted as
+ requests for huge amounts of space, which will often fail. The
+ maximum supported value of n differs across systems, but is in all
+ cases less than the maximum representable value of a size_t.
+*/
+void* dlmalloc(size_t);
+
+/*
+ free(void* p)
+ Releases the chunk of memory pointed to by p, that had been previously
+ allocated using malloc or a related routine such as realloc.
+ It has no effect if p is null. If p was not malloced or already
+ freed, free(p) will by default cause the current program to abort.
+*/
+void dlfree(void*);
+
+/*
+ calloc(size_t n_elements, size_t element_size);
+ Returns a pointer to n_elements * element_size bytes, with all locations
+ set to zero.
+*/
+void* dlcalloc(size_t, size_t);
+
+/*
+ realloc(void* p, size_t n)
+ Returns a pointer to a chunk of size n that contains the same data
+ as does chunk p up to the minimum of (n, p's size) bytes, or null
+ if no space is available.
+
+ The returned pointer may or may not be the same as p. The algorithm
+ prefers extending p in most cases when possible, otherwise it
+ employs the equivalent of a malloc-copy-free sequence.
+
+ If p is null, realloc is equivalent to malloc.
+
+ If space is not available, realloc returns null, errno is set (if on
+ ANSI) and p is NOT freed.
+
+ if n is for fewer bytes than already held by p, the newly unused
+ space is lopped off and freed if possible. realloc with a size
+ argument of zero (re)allocates a minimum-sized chunk.
+
+ The old unix realloc convention of allowing the last-free'd chunk
+ to be used as an argument to realloc is not supported.
+*/
+
+void* dlrealloc(void*, size_t);
+
+/*
+ memalign(size_t alignment, size_t n);
+ Returns a pointer to a newly allocated chunk of n bytes, aligned
+ in accord with the alignment argument.
+
+ The alignment argument should be a power of two. If the argument is
+ not a power of two, the nearest greater power is used.
+ 8-byte alignment is guaranteed by normal malloc calls, so don't
+ bother calling memalign with an argument of 8 or less.
+
+ Overreliance on memalign is a sure way to fragment space.
+*/
+void* dlmemalign(size_t, size_t);
+
+/*
+ valloc(size_t n);
+ Equivalent to memalign(pagesize, n), where pagesize is the page
+ size of the system. If the pagesize is unknown, 4096 is used.
+*/
+void* dlvalloc(size_t);
+
+/*
+ mallopt(int parameter_number, int parameter_value)
+ Sets tunable parameters The format is to provide a
+ (parameter-number, parameter-value) pair. mallopt then sets the
+ corresponding parameter to the argument value if it can (i.e., so
+ long as the value is meaningful), and returns 1 if successful else
+ 0. To workaround the fact that mallopt is specified to use int,
+ not size_t parameters, the value -1 is specially treated as the
+ maximum unsigned size_t value.
+
+ SVID/XPG/ANSI defines four standard param numbers for mallopt,
+ normally defined in malloc.h. None of these are use in this malloc,
+ so setting them has no effect. But this malloc also supports other
+ options in mallopt. See below for details. Briefly, supported
+ parameters are as follows (listed defaults are for "typical"
+ configurations).
+
+ Symbol param # default allowed param values
+ M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables)
+ M_GRANULARITY -2 page size any power of 2 >= page size
+ M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support)
+*/
+int dlmallopt(int, int);
+
+/*
+ malloc_footprint();
+ Returns the number of bytes obtained from the system. The total
+ number of bytes allocated by malloc, realloc etc., is less than this
+ value. Unlike mallinfo, this function returns only a precomputed
+ result, so can be called frequently to monitor memory consumption.
+ Even if locks are otherwise defined, this function does not use them,
+ so results might not be up to date.
+*/
+size_t dlmalloc_footprint(void);
+
+/*
+ malloc_max_footprint();
+ Returns the maximum number of bytes obtained from the system. This
+ value will be greater than current footprint if deallocated space
+ has been reclaimed by the system. The peak number of bytes allocated
+ by malloc, realloc etc., is less than this value. Unlike mallinfo,
+ this function returns only a precomputed result, so can be called
+ frequently to monitor memory consumption. Even if locks are
+ otherwise defined, this function does not use them, so results might
+ not be up to date.
+*/
+size_t dlmalloc_max_footprint(void);
+
+#if !NO_MALLINFO
+/*
+ mallinfo()
+ Returns (by copy) a struct containing various summary statistics:
+
+ arena: current total non-mmapped bytes allocated from system
+ ordblks: the number of free chunks
+ smblks: always zero.
+ hblks: current number of mmapped regions
+ hblkhd: total bytes held in mmapped regions
+ usmblks: the maximum total allocated space. This will be greater
+ than current total if trimming has occurred.
+ fsmblks: always zero
+ uordblks: current total allocated space (normal or mmapped)
+ fordblks: total free space
+ keepcost: the maximum number of bytes that could ideally be released
+ back to system via malloc_trim. ("ideally" means that
+ it ignores page restrictions etc.)
+
+ Because these fields are ints, but internal bookkeeping may
+ be kept as longs, the reported values may wrap around zero and
+ thus be inaccurate.
+*/
+struct mallinfo dlmallinfo(void);
+#endif /* NO_MALLINFO */
+
+/*
+ independent_calloc(size_t n_elements, size_t element_size, void* chunks[]);
+
+ independent_calloc is similar to calloc, but instead of returning a
+ single cleared space, it returns an array of pointers to n_elements
+ independent elements that can hold contents of size elem_size, each
+ of which starts out cleared, and can be independently freed,
+ realloc'ed etc. The elements are guaranteed to be adjacently
+ allocated (this is not guaranteed to occur with multiple callocs or
+ mallocs), which may also improve cache locality in some
+ applications.
+
+ The "chunks" argument is optional (i.e., may be null, which is
+ probably the most typical usage). If it is null, the returned array
+ is itself dynamically allocated and should also be freed when it is
+ no longer needed. Otherwise, the chunks array must be of at least
+ n_elements in length. It is filled in with the pointers to the
+ chunks.
+
+ In either case, independent_calloc returns this pointer array, or
+ null if the allocation failed. If n_elements is zero and "chunks"
+ is null, it returns a chunk representing an array with zero elements
+ (which should be freed if not wanted).
+
+ Each element must be individually freed when it is no longer
+ needed. If you'd like to instead be able to free all at once, you
+ should instead use regular calloc and assign pointers into this
+ space to represent elements. (In this case though, you cannot
+ independently free elements.)
+
+ independent_calloc simplifies and speeds up implementations of many
+ kinds of pools. It may also be useful when constructing large data
+ structures that initially have a fixed number of fixed-sized nodes,
+ but the number is not known at compile time, and some of the nodes
+ may later need to be freed. For example:
+
+ struct Node { int item; struct Node* next; };
+
+ struct Node* build_list() {
+ struct Node** pool;
+ int n = read_number_of_nodes_needed();
+ if (n <= 0) return 0;
+ pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
+ if (pool == 0) die();
+ // organize into a linked list...
+ struct Node* first = pool[0];
+ for (i = 0; i < n-1; ++i)
+ pool[i]->next = pool[i+1];
+ free(pool); // Can now free the array (or not, if it is needed later)
+ return first;
+ }
+*/
+void** dlindependent_calloc(size_t, size_t, void**);
+
+/*
+ independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]);
+
+ independent_comalloc allocates, all at once, a set of n_elements
+ chunks with sizes indicated in the "sizes" array. It returns
+ an array of pointers to these elements, each of which can be
+ independently freed, realloc'ed etc. The elements are guaranteed to
+ be adjacently allocated (this is not guaranteed to occur with
+ multiple callocs or mallocs), which may also improve cache locality
+ in some applications.
+
+ The "chunks" argument is optional (i.e., may be null). If it is null
+ the returned array is itself dynamically allocated and should also
+ be freed when it is no longer needed. Otherwise, the chunks array
+ must be of at least n_elements in length. It is filled in with the
+ pointers to the chunks.
+
+ In either case, independent_comalloc returns this pointer array, or
+ null if the allocation failed. If n_elements is zero and chunks is
+ null, it returns a chunk representing an array with zero elements
+ (which should be freed if not wanted).
+
+ Each element must be individually freed when it is no longer
+ needed. If you'd like to instead be able to free all at once, you
+ should instead use a single regular malloc, and assign pointers at
+ particular offsets in the aggregate space. (In this case though, you
+ cannot independently free elements.)
+
+ independent_comallac differs from independent_calloc in that each
+ element may have a different size, and also that it does not
+ automatically clear elements.
+
+ independent_comalloc can be used to speed up allocation in cases
+ where several structs or objects must always be allocated at the
+ same time. For example:
+
+ struct Head { ... }
+ struct Foot { ... }
+
+ void send_message(char* msg) {
+ int msglen = strlen(msg);
+ size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
+ void* chunks[3];
+ if (independent_comalloc(3, sizes, chunks) == 0)
+ die();
+ struct Head* head = (struct Head*)(chunks[0]);
+ char* body = (char*)(chunks[1]);
+ struct Foot* foot = (struct Foot*)(chunks[2]);
+ // ...
+ }
+
+ In general though, independent_comalloc is worth using only for
+ larger values of n_elements. For small values, you probably won't
+ detect enough difference from series of malloc calls to bother.
+
+ Overuse of independent_comalloc can increase overall memory usage,
+ since it cannot reuse existing noncontiguous small chunks that
+ might be available for some of the elements.
+*/
+void** dlindependent_comalloc(size_t, size_t*, void**);
+
+
+/*
+ pvalloc(size_t n);
+ Equivalent to valloc(minimum-page-that-holds(n)), that is,
+ round up n to nearest pagesize.
+ */
+void* dlpvalloc(size_t);
+
+/*
+ malloc_trim(size_t pad);
+
+ If possible, gives memory back to the system (via negative arguments
+ to sbrk) if there is unused memory at the `high' end of the malloc
+ pool or in unused MMAP segments. You can call this after freeing
+ large blocks of memory to potentially reduce the system-level memory
+ requirements of a program. However, it cannot guarantee to reduce
+ memory. Under some allocation patterns, some large free blocks of
+ memory will be locked between two used chunks, so they cannot be
+ given back to the system.
+
+ The `pad' argument to malloc_trim represents the amount of free
+ trailing space to leave untrimmed. If this argument is zero, only
+ the minimum amount of memory to maintain internal data structures
+ will be left. Non-zero arguments can be supplied to maintain enough
+ trailing space to service future expected allocations without having
+ to re-obtain memory from the system.
+
+ Malloc_trim returns 1 if it actually released any memory, else 0.
+*/
+int dlmalloc_trim(size_t);
+
+/*
+ malloc_stats();
+ Prints on stderr the amount of space obtained from the system (both
+ via sbrk and mmap), the maximum amount (which may be more than
+ current if malloc_trim and/or munmap got called), and the current
+ number of bytes allocated via malloc (or realloc, etc) but not yet
+ freed. Note that this is the number of bytes allocated, not the
+ number requested. It will be larger than the number requested
+ because of alignment and bookkeeping overhead. Because it includes
+ alignment wastage as being in use, this figure may be greater than
+ zero even when no user-level chunks are allocated.
+
+ The reported current and maximum system memory can be inaccurate if
+ a program makes other calls to system memory allocation functions
+ (normally sbrk) outside of malloc.
+
+ malloc_stats prints only the most commonly interesting statistics.
+ More information can be obtained by calling mallinfo.
+*/
+void dlmalloc_stats(void);
+
+#endif /* ONLY_MSPACES */
+
+/*
+ malloc_usable_size(void* p);
+
+ Returns the number of bytes you can actually use in
+ an allocated chunk, which may be more than you requested (although
+ often not) due to alignment and minimum size constraints.
+ You can use this many bytes without worrying about
+ overwriting other allocated objects. This is not a particularly great
+ programming practice. malloc_usable_size can be more useful in
+ debugging and assertions, for example:
+
+ p = malloc(n);
+ assert(malloc_usable_size(p) >= 256);
+*/
+size_t dlmalloc_usable_size(void*);
+
+
+#if MSPACES
+
+/*
+ mspace is an opaque type representing an independent
+ region of space that supports mspace_malloc, etc.
+*/
+typedef void* mspace;
+
+/*
+ create_mspace creates and returns a new independent space with the
+ given initial capacity, or, if 0, the default granularity size. It
+ returns null if there is no system memory available to create the
+ space. If argument locked is non-zero, the space uses a separate
+ lock to control access. The capacity of the space will grow
+ dynamically as needed to service mspace_malloc requests. You can
+ control the sizes of incremental increases of this space by
+ compiling with a different DEFAULT_GRANULARITY or dynamically
+ setting with mallopt(M_GRANULARITY, value).
+*/
+mspace create_mspace(size_t capacity, int locked);
+
+/*
+ destroy_mspace destroys the given space, and attempts to return all
+ of its memory back to the system, returning the total number of
+ bytes freed. After destruction, the results of access to all memory
+ used by the space become undefined.
+*/
+size_t destroy_mspace(mspace msp);
+
+/*
+ create_mspace_with_base uses the memory supplied as the initial base
+ of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this
+ space is used for bookkeeping, so the capacity must be at least this
+ large. (Otherwise 0 is returned.) When this initial space is
+ exhausted, additional memory will be obtained from the system.
+ Destroying this space will deallocate all additionally allocated
+ space (if possible) but not the initial base.
+*/
+mspace create_mspace_with_base(void* base, size_t capacity, int locked);
+
+/*
+ mspace_track_large_chunks controls whether requests for large chunks
+ are allocated in their own untracked mmapped regions, separate from
+ others in this mspace. By default large chunks are not tracked,
+ which reduces fragmentation. However, such chunks are not
+ necessarily released to the system upon destroy_mspace. Enabling
+ tracking by setting to true may increase fragmentation, but avoids
+ leakage when relying on destroy_mspace to release all memory
+ allocated using this space. The function returns the previous
+ setting.
+*/
+int mspace_track_large_chunks(mspace msp, int enable);
+
+
+/*
+ mspace_malloc behaves as malloc, but operates within
+ the given space.
+*/
+void* mspace_malloc(mspace msp, size_t bytes);
+
+/*
+ mspace_free behaves as free, but operates within
+ the given space.
+
+ If compiled with FOOTERS==1, mspace_free is not actually needed.
+ free may be called instead of mspace_free because freed chunks from
+ any space are handled by their originating spaces.
+*/
+void mspace_free(mspace msp, void* mem);
+
+/*
+ mspace_realloc behaves as realloc, but operates within
+ the given space.
+
+ If compiled with FOOTERS==1, mspace_realloc is not actually
+ needed. realloc may be called instead of mspace_realloc because
+ realloced chunks from any space are handled by their originating
+ spaces.
+*/
+void* mspace_realloc(mspace msp, void* mem, size_t newsize);
+
+/*
+ mspace_calloc behaves as calloc, but operates within
+ the given space.
+*/
+void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size);
+
+/*
+ mspace_memalign behaves as memalign, but operates within
+ the given space.
+*/
+void* mspace_memalign(mspace msp, size_t alignment, size_t bytes);
+
+/*
+ mspace_independent_calloc behaves as independent_calloc, but
+ operates within the given space.
+*/
+void** mspace_independent_calloc(mspace msp, size_t n_elements,
+ size_t elem_size, void* chunks[]);
+
+/*
+ mspace_independent_comalloc behaves as independent_comalloc, but
+ operates within the given space.
+*/
+void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+ size_t sizes[], void* chunks[]);
+
+/*
+ mspace_footprint() returns the number of bytes obtained from the
+ system for this space.
+*/
+size_t mspace_footprint(mspace msp);
+
+/*
+ mspace_max_footprint() returns the peak number of bytes obtained from the
+ system for this space.
+*/
+size_t mspace_max_footprint(mspace msp);
+
+
+#if !NO_MALLINFO
+/*
+ mspace_mallinfo behaves as mallinfo, but reports properties of
+ the given space.
+*/
+struct mallinfo mspace_mallinfo(mspace msp);
+#endif /* NO_MALLINFO */
+
+/*
+ malloc_usable_size(void* p) behaves the same as malloc_usable_size;
+*/
+ size_t mspace_usable_size(void* mem);
+
+/*
+ mspace_malloc_stats behaves as malloc_stats, but reports
+ properties of the given space.
+*/
+void mspace_malloc_stats(mspace msp);
+
+/*
+ mspace_trim behaves as malloc_trim, but
+ operates within the given space.
+*/
+int mspace_trim(mspace msp, size_t pad);
+
+/*
+ An alias for mallopt.
+*/
+int mspace_mallopt(int, int);
+
+#endif /* MSPACES */
+
+#ifdef __cplusplus
+} /* end of extern "C" */
+#endif /* __cplusplus */
+
+/*
+ ========================================================================
+ To make a fully customizable malloc.h header file, cut everything
+ above this line, put into file malloc.h, edit to suit, and #include it
+ on the next line, as well as in programs that use this malloc.
+ ========================================================================
+*/
+
+/* #include "malloc.h" */
+
+/*------------------------------ internal #includes ---------------------- */
+
+#ifdef WIN32
+#pragma warning( disable : 4146 ) /* no "unsigned" warnings */
+#endif /* WIN32 */
+
+#include <stdio.h> /* for printing in malloc_stats */
+
+#ifndef LACKS_ERRNO_H
+#include <errno.h> /* for MALLOC_FAILURE_ACTION */
+#endif /* LACKS_ERRNO_H */
+/*#if FOOTERS || DEBUG
+*/
+#include <time.h> /* for magic initialization */
+/*#endif*/ /* FOOTERS */
+#ifndef LACKS_STDLIB_H
+#include <stdlib.h> /* for abort() */
+#endif /* LACKS_STDLIB_H */
+#ifdef DEBUG
+#if ABORT_ON_ASSERT_FAILURE
+#undef assert
+#define assert(x) if(!(x)) ABORT
+#else /* ABORT_ON_ASSERT_FAILURE */
+#include <assert.h>
+#endif /* ABORT_ON_ASSERT_FAILURE */
+#else /* DEBUG */
+#ifndef assert
+#define assert(x)
+#endif
+#define DEBUG 0
+#endif /* DEBUG */
+#ifndef LACKS_STRING_H
+#include <string.h> /* for memset etc */
+#endif /* LACKS_STRING_H */
+#if USE_BUILTIN_FFS
+#ifndef LACKS_STRINGS_H
+#include <strings.h> /* for ffs */
+#endif /* LACKS_STRINGS_H */
+#endif /* USE_BUILTIN_FFS */
+#if HAVE_MMAP
+#ifndef LACKS_SYS_MMAN_H
+/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */
+#if (defined(linux) && !defined(__USE_GNU))
+#define __USE_GNU 1
+#include <sys/mman.h> /* for mmap */
+#undef __USE_GNU
+#else
+#include <sys/mman.h> /* for mmap */
+#endif /* linux */
+#endif /* LACKS_SYS_MMAN_H */
+#ifndef LACKS_FCNTL_H
+#include <fcntl.h>
+#endif /* LACKS_FCNTL_H */
+#endif /* HAVE_MMAP */
+#ifndef LACKS_UNISTD_H
+#include <unistd.h> /* for sbrk, sysconf */
+#else /* LACKS_UNISTD_H */
+#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
+extern void* sbrk(ptrdiff_t);
+#endif /* FreeBSD etc */
+#endif /* LACKS_UNISTD_H */
+
+/* Declarations for locking */
+#if USE_LOCKS
+#ifndef WIN32
+#include <pthread.h>
+#if defined (__SVR4) && defined (__sun) /* solaris */
+#include <thread.h>
+#endif /* solaris */
+#else
+#ifndef _M_AMD64
+/* These are already defined on AMD64 builds */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp);
+LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+#endif /* _M_AMD64 */
+#pragma intrinsic (_InterlockedCompareExchange)
+#pragma intrinsic (_InterlockedExchange)
+#define interlockedcompareexchange _InterlockedCompareExchange
+#define interlockedexchange _InterlockedExchange
+#endif /* Win32 */
+#endif /* USE_LOCKS */
+
+/* Declarations for bit scanning on win32 */
+#if defined(_MSC_VER) && _MSC_VER>=1300
+#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+unsigned char _BitScanForward(unsigned long *index, unsigned long mask);
+unsigned char _BitScanReverse(unsigned long *index, unsigned long mask);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#define BitScanForward _BitScanForward
+#define BitScanReverse _BitScanReverse
+#pragma intrinsic(_BitScanForward)
+#pragma intrinsic(_BitScanReverse)
+#endif /* BitScanForward */
+#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */
+
+#ifndef WIN32
+#ifndef malloc_getpagesize
+# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */
+# ifndef _SC_PAGE_SIZE
+# define _SC_PAGE_SIZE _SC_PAGESIZE
+# endif
+# endif
+# ifdef _SC_PAGE_SIZE
+# define malloc_getpagesize sysconf(_SC_PAGE_SIZE)
+# else
+# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE)
+ extern size_t getpagesize();
+# define malloc_getpagesize getpagesize()
+# else
+# ifdef WIN32 /* use supplied emulation of getpagesize */
+# define malloc_getpagesize getpagesize()
+# else
+# ifndef LACKS_SYS_PARAM_H
+# include <sys/param.h>
+# endif
+# ifdef EXEC_PAGESIZE
+# define malloc_getpagesize EXEC_PAGESIZE
+# else
+# ifdef NBPG
+# ifndef CLSIZE
+# define malloc_getpagesize NBPG
+# else
+# define malloc_getpagesize (NBPG * CLSIZE)
+# endif
+# else
+# ifdef NBPC
+# define malloc_getpagesize NBPC
+# else
+# ifdef PAGESIZE
+# define malloc_getpagesize PAGESIZE
+# else /* just guess */
+# define malloc_getpagesize ((size_t)4096U)
+# endif
+# endif
+# endif
+# endif
+# endif
+# endif
+# endif
+#endif
+#endif
+
+
+
+/* ------------------- size_t and alignment properties -------------------- */
+
+/* The byte and bit size of a size_t */
+#define SIZE_T_SIZE (sizeof(size_t))
+#define SIZE_T_BITSIZE (sizeof(size_t) << 3)
+
+/* Some constants coerced to size_t */
+/* Annoying but necessary to avoid errors on some platforms */
+#define SIZE_T_ZERO ((size_t)0)
+#define SIZE_T_ONE ((size_t)1)
+#define SIZE_T_TWO ((size_t)2)
+#define SIZE_T_FOUR ((size_t)4)
+#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1)
+#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2)
+#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES)
+#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U)
+
+/* The bit mask value corresponding to MALLOC_ALIGNMENT */
+#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE)
+
+/* True if address a has acceptable alignment */
+#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0)
+
+/* the number of bytes to offset an address to align it */
+#define align_offset(A)\
+ ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\
+ ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK))
+
+/* -------------------------- MMAP preliminaries ------------------------- */
+
+/*
+ If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and
+ checks to fail so compiler optimizer can delete code rather than
+ using so many "#if"s.
+*/
+
+
+/* MORECORE and MMAP must return MFAIL on failure */
+#define MFAIL ((void*)(MAX_SIZE_T))
+#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */
+
+#if HAVE_MMAP
+
+#ifndef WIN32
+#define MUNMAP_DEFAULT(a, s) munmap((a), (s))
+#define MMAP_PROT (PROT_READ|PROT_WRITE)
+#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON)
+#define MAP_ANONYMOUS MAP_ANON
+#endif /* MAP_ANON */
+#ifdef MAP_ANONYMOUS
+#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS)
+#define MMAP_DEFAULT(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0)
+#else /* MAP_ANONYMOUS */
+/*
+ Nearly all versions of mmap support MAP_ANONYMOUS, so the following
+ is unlikely to be needed, but is supplied just in case.
+*/
+#define MMAP_FLAGS (MAP_PRIVATE)
+static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */
+#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \
+ (dev_zero_fd = open("/dev/zero", O_RDWR), \
+ mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \
+ mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0))
+#endif /* MAP_ANONYMOUS */
+
+#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s)
+
+#else /* WIN32 */
+
+/* Win32 MMAP via VirtualAlloc */
+static FORCEINLINE void* win32mmap(size_t size) {
+ void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
+ return (ptr != 0)? ptr: MFAIL;
+}
+
+/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */
+static FORCEINLINE void* win32direct_mmap(size_t size) {
+ void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN,
+ PAGE_READWRITE);
+ return (ptr != 0)? ptr: MFAIL;
+}
+
+/* This function supports releasing coalesed segments */
+static FORCEINLINE int win32munmap(void* ptr, size_t size) {
+ MEMORY_BASIC_INFORMATION minfo;
+ char* cptr = (char*)ptr;
+ while (size) {
+ if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0)
+ return -1;
+ if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr ||
+ minfo.State != MEM_COMMIT || minfo.RegionSize > size)
+ return -1;
+ if (VirtualFree(cptr, 0, MEM_RELEASE) == 0)
+ return -1;
+ cptr += minfo.RegionSize;
+ size -= minfo.RegionSize;
+ }
+ return 0;
+}
+
+#define MMAP_DEFAULT(s) win32mmap(s)
+#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s))
+#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s)
+#endif /* WIN32 */
+#endif /* HAVE_MMAP */
+
+#if HAVE_MREMAP
+#ifndef WIN32
+#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv))
+#endif /* WIN32 */
+#endif /* HAVE_MREMAP */
+
+
+/**
+ * Define CALL_MORECORE
+ */
+#if HAVE_MORECORE
+ #ifdef MORECORE
+ #define CALL_MORECORE(S) MORECORE(S)
+ #else /* MORECORE */
+ #define CALL_MORECORE(S) MORECORE_DEFAULT(S)
+ #endif /* MORECORE */
+#else /* HAVE_MORECORE */
+ #define CALL_MORECORE(S) MFAIL
+#endif /* HAVE_MORECORE */
+
+/**
+ * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP
+ */
+#if HAVE_MMAP
+ #define USE_MMAP_BIT (SIZE_T_ONE)
+
+ #ifdef MMAP
+ #define CALL_MMAP(s) MMAP(s)
+ #else /* MMAP */
+ #define CALL_MMAP(s) MMAP_DEFAULT(s)
+ #endif /* MMAP */
+ #ifdef MUNMAP
+ #define CALL_MUNMAP(a, s) MUNMAP((a), (s))
+ #else /* MUNMAP */
+ #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s))
+ #endif /* MUNMAP */
+ #ifdef DIRECT_MMAP
+ #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s)
+ #else /* DIRECT_MMAP */
+ #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s)
+ #endif /* DIRECT_MMAP */
+#else /* HAVE_MMAP */
+ #define USE_MMAP_BIT (SIZE_T_ZERO)
+
+ #define MMAP(s) MFAIL
+ #define MUNMAP(a, s) (-1)
+ #define DIRECT_MMAP(s) MFAIL
+ #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s)
+ #define CALL_MMAP(s) MMAP(s)
+ #define CALL_MUNMAP(a, s) MUNMAP((a), (s))
+#endif /* HAVE_MMAP */
+
+/**
+ * Define CALL_MREMAP
+ */
+#if HAVE_MMAP && HAVE_MREMAP
+ #ifdef MREMAP
+ #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv))
+ #else /* MREMAP */
+ #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv))
+ #endif /* MREMAP */
+#else /* HAVE_MMAP && HAVE_MREMAP */
+ #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL
+#endif /* HAVE_MMAP && HAVE_MREMAP */
+
+/* mstate bit set if continguous morecore disabled or failed */
+#define USE_NONCONTIGUOUS_BIT (4U)
+
+/* segment bit set in create_mspace_with_base */
+#define EXTERN_BIT (8U)
+
+
+/* --------------------------- Lock preliminaries ------------------------ */
+
+/*
+ When locks are defined, there is one global lock, plus
+ one per-mspace lock.
+
+ The global lock_ensures that mparams.magic and other unique
+ mparams values are initialized only once. It also protects
+ sequences of calls to MORECORE. In many cases sys_alloc requires
+ two calls, that should not be interleaved with calls by other
+ threads. This does not protect against direct calls to MORECORE
+ by other threads not using this lock, so there is still code to
+ cope the best we can on interference.
+
+ Per-mspace locks surround calls to malloc, free, etc. To enable use
+ in layered extensions, per-mspace locks are reentrant.
+
+ Because lock-protected regions generally have bounded times, it is
+ OK to use the supplied simple spinlocks in the custom versions for
+ x86. Spinlocks are likely to improve performance for lightly
+ contended applications, but worsen performance under heavy
+ contention.
+
+ If USE_LOCKS is > 1, the definitions of lock routines here are
+ bypassed, in which case you will need to define the type MLOCK_T,
+ and at least INITIAL_LOCK, ACQUIRE_LOCK, RELEASE_LOCK and possibly
+ TRY_LOCK (which is not used in this malloc, but commonly needed in
+ extensions.) You must also declare a
+ static MLOCK_T malloc_global_mutex = { initialization values };.
+
+*/
+
+#if USE_LOCKS == 1
+
+#if USE_SPIN_LOCKS && SPIN_LOCKS_AVAILABLE
+#ifndef WIN32
+
+/* Custom pthread-style spin locks on x86 and x64 for gcc */
+struct pthread_mlock_t {
+ volatile unsigned int l;
+ unsigned int c;
+ pthread_t threadid;
+};
+#define MLOCK_T struct pthread_mlock_t
+#define CURRENT_THREAD pthread_self()
+#define INITIAL_LOCK(sl) ((sl)->threadid = 0, (sl)->l = (sl)->c = 0, 0)
+#define ACQUIRE_LOCK(sl) pthread_acquire_lock(sl)
+#define RELEASE_LOCK(sl) pthread_release_lock(sl)
+#define TRY_LOCK(sl) pthread_try_lock(sl)
+#define SPINS_PER_YIELD 63
+
+static MLOCK_T malloc_global_mutex = { 0, 0, 0};
+
+static FORCEINLINE int pthread_acquire_lock (MLOCK_T *sl) {
+ int spins = 0;
+ volatile unsigned int* lp = &sl->l;
+ for (;;) {
+ if (*lp != 0) {
+ if (sl->threadid == CURRENT_THREAD) {
+ ++sl->c;
+ return 0;
+ }
+ }
+ else {
+ /* place args to cmpxchgl in locals to evade oddities in some gccs */
+ int cmp = 0;
+ int val = 1;
+ int ret;
+ __asm__ __volatile__ ("lock; cmpxchgl %1, %2"
+ : "=a" (ret)
+ : "r" (val), "m" (*(lp)), "0"(cmp)
+ : "memory", "cc");
+ if (!ret) {
+ assert(!sl->threadid);
+ sl->threadid = CURRENT_THREAD;
+ sl->c = 1;
+ return 0;
+ }
+ }
+ if ((++spins & SPINS_PER_YIELD) == 0) {
+#if defined (__SVR4) && defined (__sun) /* solaris */
+ thr_yield();
+#else
+#if defined(__linux__) || defined(__FreeBSD__) || defined(__APPLE__)
+ sched_yield();
+#else /* no-op yield on unknown systems */
+ ;
+#endif /* __linux__ || __FreeBSD__ || __APPLE__ */
+#endif /* solaris */
+ }
+ }
+}
+
+static FORCEINLINE void pthread_release_lock (MLOCK_T *sl) {
+ volatile unsigned int* lp = &sl->l;
+ assert(*lp != 0);
+ assert(sl->threadid == CURRENT_THREAD);
+ if (--sl->c == 0) {
+ sl->threadid = 0;
+ int prev = 0;
+ int ret;
+ __asm__ __volatile__ ("lock; xchgl %0, %1"
+ : "=r" (ret)
+ : "m" (*(lp)), "0"(prev)
+ : "memory");
+ }
+}
+
+static FORCEINLINE int pthread_try_lock (MLOCK_T *sl) {
+ volatile unsigned int* lp = &sl->l;
+ if (*lp != 0) {
+ if (sl->threadid == CURRENT_THREAD) {
+ ++sl->c;
+ return 1;
+ }
+ }
+ else {
+ int cmp = 0;
+ int val = 1;
+ int ret;
+ __asm__ __volatile__ ("lock; cmpxchgl %1, %2"
+ : "=a" (ret)
+ : "r" (val), "m" (*(lp)), "0"(cmp)
+ : "memory", "cc");
+ if (!ret) {
+ assert(!sl->threadid);
+ sl->threadid = CURRENT_THREAD;
+ sl->c = 1;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+
+#else /* WIN32 */
+/* Custom win32-style spin locks on x86 and x64 for MSC */
+struct win32_mlock_t {
+ volatile long l;
+ unsigned int c;
+ long threadid;
+};
+
+#define MLOCK_T struct win32_mlock_t
+#define CURRENT_THREAD GetCurrentThreadId()
+#define INITIAL_LOCK(sl) ((sl)->threadid = 0, (sl)->l = (sl)->c = 0, 0)
+#define ACQUIRE_LOCK(sl) win32_acquire_lock(sl)
+#define RELEASE_LOCK(sl) win32_release_lock(sl)
+#define TRY_LOCK(sl) win32_try_lock(sl)
+#define SPINS_PER_YIELD 63
+
+static MLOCK_T malloc_global_mutex = { 0, 0, 0};
+
+static FORCEINLINE int win32_acquire_lock (MLOCK_T *sl) {
+ int spins = 0;
+ for (;;) {
+ if (sl->l != 0) {
+ if (sl->threadid == CURRENT_THREAD) {
+ ++sl->c;
+ return 0;
+ }
+ }
+ else {
+ if (!interlockedexchange(&sl->l, 1)) {
+ assert(!sl->threadid);
+ sl->threadid = CURRENT_THREAD;
+ sl->c = 1;
+ return 0;
+ }
+ }
+ if ((++spins & SPINS_PER_YIELD) == 0)
+ SleepEx(0, FALSE);
+ }
+}
+
+static FORCEINLINE void win32_release_lock (MLOCK_T *sl) {
+ assert(sl->threadid == CURRENT_THREAD);
+ assert(sl->l != 0);
+ if (--sl->c == 0) {
+ sl->threadid = 0;
+ interlockedexchange (&sl->l, 0);
+ }
+}
+
+static FORCEINLINE int win32_try_lock (MLOCK_T *sl) {
+ if (sl->l != 0) {
+ if (sl->threadid == CURRENT_THREAD) {
+ ++sl->c;
+ return 1;
+ }
+ }
+ else {
+ if (!interlockedexchange(&sl->l, 1)){
+ assert(!sl->threadid);
+ sl->threadid = CURRENT_THREAD;
+ sl->c = 1;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+#endif /* WIN32 */
+#else /* USE_SPIN_LOCKS */
+
+#ifndef WIN32
+/* pthreads-based locks */
+
+#define MLOCK_T pthread_mutex_t
+#define CURRENT_THREAD pthread_self()
+#define INITIAL_LOCK(sl) pthread_init_lock(sl)
+#define ACQUIRE_LOCK(sl) pthread_mutex_lock(sl)
+#define RELEASE_LOCK(sl) pthread_mutex_unlock(sl)
+#define TRY_LOCK(sl) (!pthread_mutex_trylock(sl))
+
+static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+/* Cope with old-style linux recursive lock initialization by adding */
+/* skipped internal declaration from pthread.h */
+#ifdef linux
+#ifndef PTHREAD_MUTEX_RECURSIVE
+extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr,
+ int __kind));
+#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP
+#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y)
+#endif
+#endif
+
+static int pthread_init_lock (MLOCK_T *sl) {
+ pthread_mutexattr_t attr;
+ if (pthread_mutexattr_init(&attr)) return 1;
+ if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1;
+ if (pthread_mutex_init(sl, &attr)) return 1;
+ if (pthread_mutexattr_destroy(&attr)) return 1;
+ return 0;
+}
+
+#else /* WIN32 */
+/* Win32 critical sections */
+#define MLOCK_T CRITICAL_SECTION
+#define CURRENT_THREAD GetCurrentThreadId()
+#define INITIAL_LOCK(s) (!InitializeCriticalSectionAndSpinCount((s), 0x80000000|4000))
+#define ACQUIRE_LOCK(s) (EnterCriticalSection(sl), 0)
+#define RELEASE_LOCK(s) LeaveCriticalSection(sl)
+#define TRY_LOCK(s) TryEnterCriticalSection(sl)
+#define NEED_GLOBAL_LOCK_INIT
+
+static MLOCK_T malloc_global_mutex;
+static volatile long malloc_global_mutex_status;
+
+/* Use spin loop to initialize global lock */
+static void init_malloc_global_mutex() {
+ for (;;) {
+ long stat = malloc_global_mutex_status;
+ if (stat > 0)
+ return;
+ /* transition to < 0 while initializing, then to > 0) */
+ if (stat == 0 &&
+ interlockedcompareexchange(&malloc_global_mutex_status, -1, 0) == 0) {
+ InitializeCriticalSection(&malloc_global_mutex);
+ interlockedexchange(&malloc_global_mutex_status,1);
+ return;
+ }
+ SleepEx(0, FALSE);
+ }
+}
+
+#endif /* WIN32 */
+#endif /* USE_SPIN_LOCKS */
+#endif /* USE_LOCKS == 1 */
+
+/* ----------------------- User-defined locks ------------------------ */
+
+#if USE_LOCKS > 1
+/* Define your own lock implementation here */
+/* #define INITIAL_LOCK(sl) ... */
+/* #define ACQUIRE_LOCK(sl) ... */
+/* #define RELEASE_LOCK(sl) ... */
+/* #define TRY_LOCK(sl) ... */
+/* static MLOCK_T malloc_global_mutex = ... */
+#endif /* USE_LOCKS > 1 */
+
+/* ----------------------- Lock-based state ------------------------ */
+
+#if USE_LOCKS
+#define USE_LOCK_BIT (2U)
+#else /* USE_LOCKS */
+#define USE_LOCK_BIT (0U)
+#define INITIAL_LOCK(l)
+#endif /* USE_LOCKS */
+
+#if USE_LOCKS
+#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK
+#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex);
+#endif
+#ifndef RELEASE_MALLOC_GLOBAL_LOCK
+#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex);
+#endif
+#else /* USE_LOCKS */
+#define ACQUIRE_MALLOC_GLOBAL_LOCK()
+#define RELEASE_MALLOC_GLOBAL_LOCK()
+#endif /* USE_LOCKS */
+
+
+/* ----------------------- Chunk representations ------------------------ */
+
+/*
+ (The following includes lightly edited explanations by Colin Plumb.)
+
+ The malloc_chunk declaration below is misleading (but accurate and
+ necessary). It declares a "view" into memory allowing access to
+ necessary fields at known offsets from a given base.
+
+ Chunks of memory are maintained using a `boundary tag' method as
+ originally described by Knuth. (See the paper by Paul Wilson
+ ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such
+ techniques.) Sizes of free chunks are stored both in the front of
+ each chunk and at the end. This makes consolidating fragmented
+ chunks into bigger chunks fast. The head fields also hold bits
+ representing whether chunks are free or in use.
+
+ Here are some pictures to make it clearer. They are "exploded" to
+ show that the state of a chunk can be thought of as extending from
+ the high 31 bits of the head field of its header through the
+ prev_foot and PINUSE_BIT bit of the following chunk header.
+
+ A chunk that's in use looks like:
+
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Size of previous chunk (if P = 0) |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+ | Size of this chunk 1| +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | |
+ +- -+
+ | |
+ +- -+
+ | :
+ +- size - sizeof(size_t) available payload bytes -+
+ : |
+ chunk-> +- -+
+ | |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1|
+ | Size of next chunk (may or may not be in use) | +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+ And if it's free, it looks like this:
+
+ chunk-> +- -+
+ | User payload (must be in use, or we would have merged!) |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+ | Size of this chunk 0| +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Next pointer |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Prev pointer |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | :
+ +- size - sizeof(struct chunk) unused bytes -+
+ : |
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Size of this chunk |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0|
+ | Size of next chunk (must be in use, or we would have merged)| +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | :
+ +- User payload -+
+ : |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ |0|
+ +-+
+ Note that since we always merge adjacent free chunks, the chunks
+ adjacent to a free chunk must be in use.
+
+ Given a pointer to a chunk (which can be derived trivially from the
+ payload pointer) we can, in O(1) time, find out whether the adjacent
+ chunks are free, and if so, unlink them from the lists that they
+ are on and merge them with the current chunk.
+
+ Chunks always begin on even word boundaries, so the mem portion
+ (which is returned to the user) is also on an even word boundary, and
+ thus at least double-word aligned.
+
+ The P (PINUSE_BIT) bit, stored in the unused low-order bit of the
+ chunk size (which is always a multiple of two words), is an in-use
+ bit for the *previous* chunk. If that bit is *clear*, then the
+ word before the current chunk size contains the previous chunk
+ size, and can be used to find the front of the previous chunk.
+ The very first chunk allocated always has this bit set, preventing
+ access to non-existent (or non-owned) memory. If pinuse is set for
+ any given chunk, then you CANNOT determine the size of the
+ previous chunk, and might even get a memory addressing fault when
+ trying to do so.
+
+ The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of
+ the chunk size redundantly records whether the current chunk is
+ inuse (unless the chunk is mmapped). This redundancy enables usage
+ checks within free and realloc, and reduces indirection when freeing
+ and consolidating chunks.
+
+ Each freshly allocated chunk must have both cinuse and pinuse set.
+ That is, each allocated chunk borders either a previously allocated
+ and still in-use chunk, or the base of its memory arena. This is
+ ensured by making all allocations from the the `lowest' part of any
+ found chunk. Further, no free chunk physically borders another one,
+ so each free chunk is known to be preceded and followed by either
+ inuse chunks or the ends of memory.
+
+ Note that the `foot' of the current chunk is actually represented
+ as the prev_foot of the NEXT chunk. This makes it easier to
+ deal with alignments etc but can be very confusing when trying
+ to extend or adapt this code.
+
+ The exceptions to all this are
+
+ 1. The special chunk `top' is the top-most available chunk (i.e.,
+ the one bordering the end of available memory). It is treated
+ specially. Top is never included in any bin, is used only if
+ no other chunk is available, and is released back to the
+ system if it is very large (see M_TRIM_THRESHOLD). In effect,
+ the top chunk is treated as larger (and thus less well
+ fitting) than any other available chunk. The top chunk
+ doesn't update its trailing size field since there is no next
+ contiguous chunk that would have to index off it. However,
+ space is still allocated for it (TOP_FOOT_SIZE) to enable
+ separation or merging when space is extended.
+
+ 3. Chunks allocated via mmap, have both cinuse and pinuse bits
+ cleared in their head fields. Because they are allocated
+ one-by-one, each must carry its own prev_foot field, which is
+ also used to hold the offset this chunk has within its mmapped
+ region, which is needed to preserve alignment. Each mmapped
+ chunk is trailed by the first two fields of a fake next-chunk
+ for sake of usage checks.
+
+*/
+
+struct malloc_chunk {
+ size_t prev_foot; /* Size of previous chunk (if free). */
+ size_t head; /* Size and inuse bits. */
+ struct malloc_chunk* fd; /* double links -- used only if free. */
+ struct malloc_chunk* bk;
+};
+
+typedef struct malloc_chunk mchunk;
+typedef struct malloc_chunk* mchunkptr;
+typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */
+typedef unsigned int bindex_t; /* Described below */
+typedef unsigned int binmap_t; /* Described below */
+typedef unsigned int flag_t; /* The type of various bit flag sets */
+
+/* ------------------- Chunks sizes and alignments ----------------------- */
+
+#define MCHUNK_SIZE (sizeof(mchunk))
+
+#if FOOTERS
+#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES)
+#else /* FOOTERS */
+#define CHUNK_OVERHEAD (SIZE_T_SIZE)
+#endif /* FOOTERS */
+
+/* MMapped chunks need a second word of overhead ... */
+#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES)
+/* ... and additional padding for fake next-chunk at foot */
+#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES)
+
+/* The smallest size we can malloc is an aligned minimal chunk */
+#define MIN_CHUNK_SIZE\
+ ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* conversion from malloc headers to user pointers, and back */
+#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES))
+#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES))
+/* chunk associated with aligned address A */
+#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A)))
+
+/* Bounds on request (not chunk) sizes. */
+#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2)
+#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE)
+
+/* pad request bytes into a usable size */
+#define pad_request(req) \
+ (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* pad request, checking for minimum (but not maximum) */
+#define request2size(req) \
+ (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req))
+
+
+/* ------------------ Operations on head and foot fields ----------------- */
+
+/*
+ The head field of a chunk is or'ed with PINUSE_BIT when previous
+ adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in
+ use, unless mmapped, in which case both bits are cleared.
+
+ FLAG4_BIT is not used by this malloc, but might be useful in extensions.
+*/
+
+#define PINUSE_BIT (SIZE_T_ONE)
+#define CINUSE_BIT (SIZE_T_TWO)
+#define FLAG4_BIT (SIZE_T_FOUR)
+#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT)
+#define FLAG_BITS (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT)
+
+/* Head value for fenceposts */
+#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE)
+
+/* extraction of fields from head words */
+#define cinuse(p) ((p)->head & CINUSE_BIT)
+#define pinuse(p) ((p)->head & PINUSE_BIT)
+#define is_inuse(p) (((p)->head & INUSE_BITS) != PINUSE_BIT)
+#define is_mmapped(p) (((p)->head & INUSE_BITS) == 0)
+
+#define chunksize(p) ((p)->head & ~(FLAG_BITS))
+
+#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT)
+
+/* Treat space at ptr +/- offset as a chunk */
+#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s)))
+#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s)))
+
+/* Ptr to next or previous physical malloc_chunk. */
+#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS)))
+#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) ))
+
+/* extract next chunk's pinuse bit */
+#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT)
+
+/* Get/set size at footer */
+#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot)
+#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s))
+
+/* Set size, pinuse bit, and foot */
+#define set_size_and_pinuse_of_free_chunk(p, s)\
+ ((p)->head = (s|PINUSE_BIT), set_foot(p, s))
+
+/* Set size, pinuse bit, foot, and clear next pinuse */
+#define set_free_with_pinuse(p, s, n)\
+ (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s))
+
+/* Get the internal overhead associated with chunk p */
+#define overhead_for(p)\
+ (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD)
+
+/* Return true if malloced space is not necessarily cleared */
+#if MMAP_CLEARS
+#define calloc_must_clear(p) (!is_mmapped(p))
+#else /* MMAP_CLEARS */
+#define calloc_must_clear(p) (1)
+#endif /* MMAP_CLEARS */
+
+/* ---------------------- Overlaid data structures ----------------------- */
+
+/*
+ When chunks are not in use, they are treated as nodes of either
+ lists or trees.
+
+ "Small" chunks are stored in circular doubly-linked lists, and look
+ like this:
+
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Size of previous chunk |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ `head:' | Size of chunk, in bytes |P|
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Forward pointer to next chunk in list |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Back pointer to previous chunk in list |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Unused space (may be 0 bytes long) .
+ . .
+ . |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ `foot:' | Size of chunk, in bytes |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+ Larger chunks are kept in a form of bitwise digital trees (aka
+ tries) keyed on chunksizes. Because malloc_tree_chunks are only for
+ free chunks greater than 256 bytes, their size doesn't impose any
+ constraints on user chunk sizes. Each node looks like:
+
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Size of previous chunk |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ `head:' | Size of chunk, in bytes |P|
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Forward pointer to next chunk of same size |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Back pointer to previous chunk of same size |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Pointer to left child (child[0]) |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Pointer to right child (child[1]) |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Pointer to parent |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | bin index of this chunk |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ | Unused space .
+ . |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ `foot:' | Size of chunk, in bytes |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+ Each tree holding treenodes is a tree of unique chunk sizes. Chunks
+ of the same size are arranged in a circularly-linked list, with only
+ the oldest chunk (the next to be used, in our FIFO ordering)
+ actually in the tree. (Tree members are distinguished by a non-null
+ parent pointer.) If a chunk with the same size an an existing node
+ is inserted, it is linked off the existing node using pointers that
+ work in the same way as fd/bk pointers of small chunks.
+
+ Each tree contains a power of 2 sized range of chunk sizes (the
+ smallest is 0x100 <= x < 0x180), which is is divided in half at each
+ tree level, with the chunks in the smaller half of the range (0x100
+ <= x < 0x140 for the top nose) in the left subtree and the larger
+ half (0x140 <= x < 0x180) in the right subtree. This is, of course,
+ done by inspecting individual bits.
+
+ Using these rules, each node's left subtree contains all smaller
+ sizes than its right subtree. However, the node at the root of each
+ subtree has no particular ordering relationship to either. (The
+ dividing line between the subtree sizes is based on trie relation.)
+ If we remove the last chunk of a given size from the interior of the
+ tree, we need to replace it with a leaf node. The tree ordering
+ rules permit a node to be replaced by any leaf below it.
+
+ The smallest chunk in a tree (a common operation in a best-fit
+ allocator) can be found by walking a path to the leftmost leaf in
+ the tree. Unlike a usual binary tree, where we follow left child
+ pointers until we reach a null, here we follow the right child
+ pointer any time the left one is null, until we reach a leaf with
+ both child pointers null. The smallest chunk in the tree will be
+ somewhere along that path.
+
+ The worst case number of steps to add, find, or remove a node is
+ bounded by the number of bits differentiating chunks within
+ bins. Under current bin calculations, this ranges from 6 up to 21
+ (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case
+ is of course much better.
+*/
+
+struct malloc_tree_chunk {
+ /* The first four fields must be compatible with malloc_chunk */
+ size_t prev_foot;
+ size_t head;
+ struct malloc_tree_chunk* fd;
+ struct malloc_tree_chunk* bk;
+
+ struct malloc_tree_chunk* child[2];
+ struct malloc_tree_chunk* parent;
+ bindex_t index;
+};
+
+typedef struct malloc_tree_chunk tchunk;
+typedef struct malloc_tree_chunk* tchunkptr;
+typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */
+
+/* A little helper macro for trees */
+#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1])
+
+/* ----------------------------- Segments -------------------------------- */
+
+/*
+ Each malloc space may include non-contiguous segments, held in a
+ list headed by an embedded malloc_segment record representing the
+ top-most space. Segments also include flags holding properties of
+ the space. Large chunks that are directly allocated by mmap are not
+ included in this list. They are instead independently created and
+ destroyed without otherwise keeping track of them.
+
+ Segment management mainly comes into play for spaces allocated by
+ MMAP. Any call to MMAP might or might not return memory that is
+ adjacent to an existing segment. MORECORE normally contiguously
+ extends the current space, so this space is almost always adjacent,
+ which is simpler and faster to deal with. (This is why MORECORE is
+ used preferentially to MMAP when both are available -- see
+ sys_alloc.) When allocating using MMAP, we don't use any of the
+ hinting mechanisms (inconsistently) supported in various
+ implementations of unix mmap, or distinguish reserving from
+ committing memory. Instead, we just ask for space, and exploit
+ contiguity when we get it. It is probably possible to do
+ better than this on some systems, but no general scheme seems
+ to be significantly better.
+
+ Management entails a simpler variant of the consolidation scheme
+ used for chunks to reduce fragmentation -- new adjacent memory is
+ normally prepended or appended to an existing segment. However,
+ there are limitations compared to chunk consolidation that mostly
+ reflect the fact that segment processing is relatively infrequent
+ (occurring only when getting memory from system) and that we
+ don't expect to have huge numbers of segments:
+
+ * Segments are not indexed, so traversal requires linear scans. (It
+ would be possible to index these, but is not worth the extra
+ overhead and complexity for most programs on most platforms.)
+ * New segments are only appended to old ones when holding top-most
+ memory; if they cannot be prepended to others, they are held in
+ different segments.
+
+ Except for the top-most segment of an mstate, each segment record
+ is kept at the tail of its segment. Segments are added by pushing
+ segment records onto the list headed by &mstate.seg for the
+ containing mstate.
+
+ Segment flags control allocation/merge/deallocation policies:
+ * If EXTERN_BIT set, then we did not allocate this segment,
+ and so should not try to deallocate or merge with others.
+ (This currently holds only for the initial segment passed
+ into create_mspace_with_base.)
+ * If USE_MMAP_BIT set, the segment may be merged with
+ other surrounding mmapped segments and trimmed/de-allocated
+ using munmap.
+ * If neither bit is set, then the segment was obtained using
+ MORECORE so can be merged with surrounding MORECORE'd segments
+ and deallocated/trimmed using MORECORE with negative arguments.
+*/
+
+struct malloc_segment {
+ char* base; /* base address */
+ size_t size; /* allocated size */
+ struct malloc_segment* next; /* ptr to next segment */
+ flag_t sflags; /* mmap and extern flag */
+};
+
+#define is_mmapped_segment(S) ((S)->sflags & USE_MMAP_BIT)
+#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT)
+
+typedef struct malloc_segment msegment;
+typedef struct malloc_segment* msegmentptr;
+
+/* ---------------------------- malloc_state ----------------------------- */
+
+/*
+ A malloc_state holds all of the bookkeeping for a space.
+ The main fields are:
+
+ Top
+ The topmost chunk of the currently active segment. Its size is
+ cached in topsize. The actual size of topmost space is
+ topsize+TOP_FOOT_SIZE, which includes space reserved for adding
+ fenceposts and segment records if necessary when getting more
+ space from the system. The size at which to autotrim top is
+ cached from mparams in trim_check, except that it is disabled if
+ an autotrim fails.
+
+ Designated victim (dv)
+ This is the preferred chunk for servicing small requests that
+ don't have exact fits. It is normally the chunk split off most
+ recently to service another small request. Its size is cached in
+ dvsize. The link fields of this chunk are not maintained since it
+ is not kept in a bin.
+
+ SmallBins
+ An array of bin headers for free chunks. These bins hold chunks
+ with sizes less than MIN_LARGE_SIZE bytes. Each bin contains
+ chunks of all the same size, spaced 8 bytes apart. To simplify
+ use in double-linked lists, each bin header acts as a malloc_chunk
+ pointing to the real first node, if it exists (else pointing to
+ itself). This avoids special-casing for headers. But to avoid
+ waste, we allocate only the fd/bk pointers of bins, and then use
+ repositioning tricks to treat these as the fields of a chunk.
+
+ TreeBins
+ Treebins are pointers to the roots of trees holding a range of
+ sizes. There are 2 equally spaced treebins for each power of two
+ from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything
+ larger.
+
+ Bin maps
+ There is one bit map for small bins ("smallmap") and one for
+ treebins ("treemap). Each bin sets its bit when non-empty, and
+ clears the bit when empty. Bit operations are then used to avoid
+ bin-by-bin searching -- nearly all "search" is done without ever
+ looking at bins that won't be selected. The bit maps
+ conservatively use 32 bits per map word, even if on 64bit system.
+ For a good description of some of the bit-based techniques used
+ here, see Henry S. Warren Jr's book "Hacker's Delight" (and
+ supplement at http://hackersdelight.org/). Many of these are
+ intended to reduce the branchiness of paths through malloc etc, as
+ well as to reduce the number of memory locations read or written.
+
+ Segments
+ A list of segments headed by an embedded malloc_segment record
+ representing the initial space.
+
+ Address check support
+ The least_addr field is the least address ever obtained from
+ MORECORE or MMAP. Attempted frees and reallocs of any address less
+ than this are trapped (unless INSECURE is defined).
+
+ Magic tag
+ A cross-check field that should always hold same value as mparams.magic.
+
+ Flags
+ Bits recording whether to use MMAP, locks, or contiguous MORECORE
+
+ Statistics
+ Each space keeps track of current and maximum system memory
+ obtained via MORECORE or MMAP.
+
+ Trim support
+ Fields holding the amount of unused topmost memory that should trigger
+ timming, and a counter to force periodic scanning to release unused
+ non-topmost segments.
+
+ Locking
+ If USE_LOCKS is defined, the "mutex" lock is acquired and released
+ around every public call using this mspace.
+
+ Extension support
+ A void* pointer and a size_t field that can be used to help implement
+ extensions to this malloc.
+*/
+
+/* Bin types, widths and sizes */
+#define NSMALLBINS (32U)
+#define NTREEBINS (32U)
+#define SMALLBIN_SHIFT (3U)
+#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT)
+#define TREEBIN_SHIFT (8U)
+#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT)
+#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE)
+#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD)
+
+struct malloc_state {
+ binmap_t smallmap;
+ binmap_t treemap;
+ size_t dvsize;
+ size_t topsize;
+ char* least_addr;
+ mchunkptr dv;
+ mchunkptr top;
+ size_t trim_check;
+ size_t release_checks;
+ size_t magic;
+ mchunkptr smallbins[(NSMALLBINS+1)*2];
+ tbinptr treebins[NTREEBINS];
+ size_t footprint;
+ size_t max_footprint;
+ flag_t mflags;
+#if USE_LOCKS
+ MLOCK_T mutex; /* locate lock among fields that rarely change */
+#endif /* USE_LOCKS */
+ msegment seg;
+ void* extp; /* Unused but available for extensions */
+ size_t exts;
+};
+
+typedef struct malloc_state* mstate;
+
+/* ------------- Global malloc_state and malloc_params ------------------- */
+
+/*
+ malloc_params holds global properties, including those that can be
+ dynamically set using mallopt. There is a single instance, mparams,
+ initialized in init_mparams. Note that the non-zeroness of "magic"
+ also serves as an initialization flag.
+*/
+
+struct malloc_params {
+ volatile size_t magic;
+ size_t page_size;
+ size_t granularity;
+ size_t mmap_threshold;
+ size_t trim_threshold;
+ flag_t default_mflags;
+};
+
+static struct malloc_params mparams;
+
+/* Ensure mparams initialized */
+#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams())
+
+#if !ONLY_MSPACES
+
+/* The global malloc_state used for all non-"mspace" calls */
+static struct malloc_state _gm_;
+#define gm (&_gm_)
+#define is_global(M) ((M) == &_gm_)
+
+#endif /* !ONLY_MSPACES */
+
+#define is_initialized(M) ((M)->top != 0)
+
+/* -------------------------- system alloc setup ------------------------- */
+
+/* Operations on mflags */
+
+#define use_lock(M) ((M)->mflags & USE_LOCK_BIT)
+#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT)
+#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT)
+
+#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT)
+#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT)
+#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT)
+
+#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT)
+#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT)
+
+#define set_lock(M,L)\
+ ((M)->mflags = (L)?\
+ ((M)->mflags | USE_LOCK_BIT) :\
+ ((M)->mflags & ~USE_LOCK_BIT))
+
+/* page-align a size */
+#define page_align(S)\
+ (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE))
+
+/* granularity-align a size */
+#define granularity_align(S)\
+ (((S) + (mparams.granularity - SIZE_T_ONE))\
+ & ~(mparams.granularity - SIZE_T_ONE))
+
+
+/* For mmap, use granularity alignment on windows, else page-align */
+#ifdef WIN32
+#define mmap_align(S) granularity_align(S)
+#else
+#define mmap_align(S) page_align(S)
+#endif
+
+/* For sys_alloc, enough padding to ensure can malloc request on success */
+#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT)
+
+#define is_page_aligned(S)\
+ (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0)
+#define is_granularity_aligned(S)\
+ (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0)
+
+/* True if segment S holds address A */
+#define segment_holds(S, A)\
+ ((char*)(A) >= S->base && (char*)(A) < S->base + S->size)
+
+/* Return segment holding given address */
+static msegmentptr segment_holding(mstate m, char* addr) {
+ msegmentptr sp = &m->seg;
+ for (;;) {
+ if (addr >= sp->base && addr < sp->base + sp->size)
+ return sp;
+ if ((sp = sp->next) == 0)
+ return 0;
+ }
+}
+
+/* Return true if segment contains a segment link */
+static int has_segment_link(mstate m, msegmentptr ss) {
+ msegmentptr sp = &m->seg;
+ for (;;) {
+ if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size)
+ return 1;
+ if ((sp = sp->next) == 0)
+ return 0;
+ }
+}
+
+#ifndef MORECORE_CANNOT_TRIM
+#define should_trim(M,s) ((s) > (M)->trim_check)
+#else /* MORECORE_CANNOT_TRIM */
+#define should_trim(M,s) (0)
+#endif /* MORECORE_CANNOT_TRIM */
+
+/*
+ TOP_FOOT_SIZE is padding at the end of a segment, including space
+ that may be needed to place segment records and fenceposts when new
+ noncontiguous segments are added.
+*/
+#define TOP_FOOT_SIZE\
+ (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE)
+
+
+/* ------------------------------- Hooks -------------------------------- */
+
+/*
+ PREACTION should be defined to return 0 on success, and nonzero on
+ failure. If you are not using locking, you can redefine these to do
+ anything you like.
+*/
+
+#if USE_LOCKS
+
+#define PREACTION(M) ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0)
+#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); }
+#else /* USE_LOCKS */
+
+#ifndef PREACTION
+#define PREACTION(M) (0)
+#endif /* PREACTION */
+
+#ifndef POSTACTION
+#define POSTACTION(M)
+#endif /* POSTACTION */
+
+#endif /* USE_LOCKS */
+
+/*
+ CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses.
+ USAGE_ERROR_ACTION is triggered on detected bad frees and
+ reallocs. The argument p is an address that might have triggered the
+ fault. It is ignored by the two predefined actions, but might be
+ useful in custom actions that try to help diagnose errors.
+*/
+
+#if PROCEED_ON_ERROR
+
+/* A count of the number of corruption errors causing resets */
+int malloc_corruption_error_count;
+
+/* default corruption action */
+static void reset_on_error(mstate m);
+
+#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m)
+#define USAGE_ERROR_ACTION(m, p)
+
+#else /* PROCEED_ON_ERROR */
+
+#ifndef CORRUPTION_ERROR_ACTION
+#define CORRUPTION_ERROR_ACTION(m) ABORT
+#endif /* CORRUPTION_ERROR_ACTION */
+
+#ifndef USAGE_ERROR_ACTION
+#define USAGE_ERROR_ACTION(m,p) ABORT
+#endif /* USAGE_ERROR_ACTION */
+
+#endif /* PROCEED_ON_ERROR */
+
+/* -------------------------- Debugging setup ---------------------------- */
+
+#if ! DEBUG
+
+#define check_free_chunk(M,P)
+#define check_inuse_chunk(M,P)
+#define check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P)
+#define check_malloc_state(M)
+#define check_top_chunk(M,P)
+
+#else /* DEBUG */
+#define check_free_chunk(M,P) do_check_free_chunk(M,P)
+#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P)
+#define check_top_chunk(M,P) do_check_top_chunk(M,P)
+#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P)
+#define check_malloc_state(M) do_check_malloc_state(M)
+
+static void do_check_any_chunk(mstate m, mchunkptr p);
+static void do_check_top_chunk(mstate m, mchunkptr p);
+static void do_check_mmapped_chunk(mstate m, mchunkptr p);
+static void do_check_inuse_chunk(mstate m, mchunkptr p);
+static void do_check_free_chunk(mstate m, mchunkptr p);
+static void do_check_malloced_chunk(mstate m, void* mem, size_t s);
+static void do_check_tree(mstate m, tchunkptr t);
+static void do_check_treebin(mstate m, bindex_t i);
+static void do_check_smallbin(mstate m, bindex_t i);
+static void do_check_malloc_state(mstate m);
+static int bin_find(mstate m, mchunkptr x);
+static size_t traverse_and_check(mstate m);
+#endif /* DEBUG */
+
+/* ---------------------------- Indexing Bins ---------------------------- */
+
+#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS)
+#define small_index(s) ((s) >> SMALLBIN_SHIFT)
+#define small_index2size(i) ((i) << SMALLBIN_SHIFT)
+#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE))
+
+/* addressing by index. See above about smallbin repositioning */
+#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1])))
+#define treebin_at(M,i) (&((M)->treebins[i]))
+
+/* assign tree index for size S to variable I. Use x86 asm if possible */
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_tree_index(S, I)\
+{\
+ unsigned int X = S >> TREEBIN_SHIFT;\
+ if (X == 0)\
+ I = 0;\
+ else if (X > 0xFFFF)\
+ I = NTREEBINS-1;\
+ else {\
+ unsigned int K;\
+ __asm__("bsrl\t%1, %0\n\t" : "=r" (K) : "g" (X));\
+ I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+ }\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_tree_index(S, I)\
+{\
+ size_t X = S >> TREEBIN_SHIFT;\
+ if (X == 0)\
+ I = 0;\
+ else if (X > 0xFFFF)\
+ I = NTREEBINS-1;\
+ else {\
+ unsigned int K = _bit_scan_reverse (X); \
+ I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+ }\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_tree_index(S, I)\
+{\
+ size_t X = S >> TREEBIN_SHIFT;\
+ if (X == 0)\
+ I = 0;\
+ else if (X > 0xFFFF)\
+ I = NTREEBINS-1;\
+ else {\
+ unsigned int K;\
+ _BitScanReverse((DWORD *) &K, X);\
+ I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+ }\
+}
+
+#else /* GNUC */
+#define compute_tree_index(S, I)\
+{\
+ size_t X = S >> TREEBIN_SHIFT;\
+ if (X == 0)\
+ I = 0;\
+ else if (X > 0xFFFF)\
+ I = NTREEBINS-1;\
+ else {\
+ unsigned int Y = (unsigned int)X;\
+ unsigned int N = ((Y - 0x100) >> 16) & 8;\
+ unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\
+ N += K;\
+ N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\
+ K = 14 - N + ((Y <<= K) >> 15);\
+ I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\
+ }\
+}
+#endif /* GNUC */
+
+/* Bit representing maximum resolved size in a treebin at i */
+#define bit_for_tree_index(i) \
+ (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2)
+
+/* Shift placing maximum resolved bit in a treebin at i as sign bit */
+#define leftshift_for_tree_index(i) \
+ ((i == NTREEBINS-1)? 0 : \
+ ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2)))
+
+/* The size of the smallest chunk held in bin with index i */
+#define minsize_for_tree_index(i) \
+ ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \
+ (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1)))
+
+
+/* ------------------------ Operations on bin maps ----------------------- */
+
+/* bit corresponding to given index */
+#define idx2bit(i) ((binmap_t)(1) << (i))
+
+/* Mark/Clear bits with given index */
+#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i))
+#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i))
+#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i))
+
+#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i))
+#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i))
+#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i))
+
+/* isolate the least set bit of a bitmap */
+#define least_bit(x) ((x) & -(x))
+
+/* mask with all bits to left of least bit of x on */
+#define left_bits(x) ((x<<1) | -(x<<1))
+
+/* mask with all bits to left of or equal to least bit of x on */
+#define same_or_left_bits(x) ((x) | -(x))
+
+/* index corresponding to given bit. Use x86 asm if possible */
+
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_bit2idx(X, I)\
+{\
+ unsigned int J;\
+ __asm__("bsfl\t%1, %0\n\t" : "=r" (J) : "g" (X));\
+ I = (bindex_t)J;\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_bit2idx(X, I)\
+{\
+ unsigned int J;\
+ J = _bit_scan_forward (X); \
+ I = (bindex_t)J;\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_bit2idx(X, I)\
+{\
+ unsigned int J;\
+ _BitScanForward((DWORD *) &J, X);\
+ I = (bindex_t)J;\
+}
+
+#elif USE_BUILTIN_FFS
+#define compute_bit2idx(X, I) I = ffs(X)-1
+
+#else
+#define compute_bit2idx(X, I)\
+{\
+ unsigned int Y = X - 1;\
+ unsigned int K = Y >> (16-4) & 16;\
+ unsigned int N = K; Y >>= K;\
+ N += K = Y >> (8-3) & 8; Y >>= K;\
+ N += K = Y >> (4-2) & 4; Y >>= K;\
+ N += K = Y >> (2-1) & 2; Y >>= K;\
+ N += K = Y >> (1-0) & 1; Y >>= K;\
+ I = (bindex_t)(N + Y);\
+}
+#endif /* GNUC */
+
+
+/* ----------------------- Runtime Check Support ------------------------- */
+
+/*
+ For security, the main invariant is that malloc/free/etc never
+ writes to a static address other than malloc_state, unless static
+ malloc_state itself has been corrupted, which cannot occur via
+ malloc (because of these checks). In essence this means that we
+ believe all pointers, sizes, maps etc held in malloc_state, but
+ check all of those linked or offsetted from other embedded data
+ structures. These checks are interspersed with main code in a way
+ that tends to minimize their run-time cost.
+
+ When FOOTERS is defined, in addition to range checking, we also
+ verify footer fields of inuse chunks, which can be used guarantee
+ that the mstate controlling malloc/free is intact. This is a
+ streamlined version of the approach described by William Robertson
+ et al in "Run-time Detection of Heap-based Overflows" LISA'03
+ http://www.usenix.org/events/lisa03/tech/robertson.html The footer
+ of an inuse chunk holds the xor of its mstate and a random seed,
+ that is checked upon calls to free() and realloc(). This is
+ (probablistically) unguessable from outside the program, but can be
+ computed by any code successfully malloc'ing any chunk, so does not
+ itself provide protection against code that has already broken
+ security through some other means. Unlike Robertson et al, we
+ always dynamically check addresses of all offset chunks (previous,
+ next, etc). This turns out to be cheaper than relying on hashes.
+*/
+
+#if !INSECURE
+/* Check if address a is at least as high as any from MORECORE or MMAP */
+#define ok_address(M, a) ((char*)(a) >= (M)->least_addr)
+/* Check if address of next chunk n is higher than base chunk p */
+#define ok_next(p, n) ((char*)(p) < (char*)(n))
+/* Check if p has inuse status */
+#define ok_inuse(p) is_inuse(p)
+/* Check if p has its pinuse bit on */
+#define ok_pinuse(p) pinuse(p)
+
+#else /* !INSECURE */
+#define ok_address(M, a) (1)
+#define ok_next(b, n) (1)
+#define ok_inuse(p) (1)
+#define ok_pinuse(p) (1)
+#endif /* !INSECURE */
+
+#if (FOOTERS && !INSECURE)
+/* Check if (alleged) mstate m has expected magic field */
+#define ok_magic(M) ((M)->magic == mparams.magic)
+#else /* (FOOTERS && !INSECURE) */
+#define ok_magic(M) (1)
+#endif /* (FOOTERS && !INSECURE) */
+
+
+/* In gcc, use __builtin_expect to minimize impact of checks */
+#if !INSECURE
+#if defined(__GNUC__) && __GNUC__ >= 3
+#define RTCHECK(e) __builtin_expect(e, 1)
+#else /* GNUC */
+#define RTCHECK(e) (e)
+#endif /* GNUC */
+#else /* !INSECURE */
+#define RTCHECK(e) (1)
+#endif /* !INSECURE */
+
+/* macros to set up inuse chunks with or without footers */
+
+#if !FOOTERS
+
+#define mark_inuse_foot(M,p,s)
+
+/* Macros for setting head/foot of non-mmapped chunks */
+
+/* Set cinuse bit and pinuse bit of next chunk */
+#define set_inuse(M,p,s)\
+ ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+ ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set cinuse and pinuse of this chunk and pinuse of next chunk */
+#define set_inuse_and_pinuse(M,p,s)\
+ ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+ ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set size, cinuse and pinuse bit of this chunk */
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+ ((p)->head = (s|PINUSE_BIT|CINUSE_BIT))
+
+#else /* FOOTERS */
+
+/* Set foot of inuse chunk to be xor of mstate and seed */
+#define mark_inuse_foot(M,p,s)\
+ (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic))
+
+#define get_mstate_for(p)\
+ ((mstate)(((mchunkptr)((char*)(p) +\
+ (chunksize(p))))->prev_foot ^ mparams.magic))
+
+#define set_inuse(M,p,s)\
+ ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+ (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \
+ mark_inuse_foot(M,p,s))
+
+#define set_inuse_and_pinuse(M,p,s)\
+ ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+ (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\
+ mark_inuse_foot(M,p,s))
+
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+ ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+ mark_inuse_foot(M, p, s))
+
+#endif /* !FOOTERS */
+
+/* ---------------------------- setting mparams -------------------------- */
+
+/* Initialize mparams */
+static int init_mparams(void) {
+#ifdef NEED_GLOBAL_LOCK_INIT
+ if (malloc_global_mutex_status <= 0)
+ init_malloc_global_mutex();
+#endif
+
+ ACQUIRE_MALLOC_GLOBAL_LOCK();
+ if (mparams.magic == 0) {
+ size_t magic;
+ size_t psize;
+ size_t gsize;
+
+#ifndef WIN32
+ psize = malloc_getpagesize;
+ gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize);
+#else /* WIN32 */
+ {
+ SYSTEM_INFO system_info;
+ GetSystemInfo(&system_info);
+ psize = system_info.dwPageSize;
+ gsize = ((DEFAULT_GRANULARITY != 0)?
+ DEFAULT_GRANULARITY : system_info.dwAllocationGranularity);
+ }
+#endif /* WIN32 */
+
+ /* Sanity-check configuration:
+ size_t must be unsigned and as wide as pointer type.
+ ints must be at least 4 bytes.
+ alignment must be at least 8.
+ Alignment, min chunk size, and page size must all be powers of 2.
+ */
+ if ((sizeof(size_t) != sizeof(char*)) ||
+ (MAX_SIZE_T < MIN_CHUNK_SIZE) ||
+ (sizeof(int) < 4) ||
+ (MALLOC_ALIGNMENT < (size_t)8U) ||
+ ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) ||
+ ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) ||
+ ((gsize & (gsize-SIZE_T_ONE)) != 0) ||
+ ((psize & (psize-SIZE_T_ONE)) != 0))
+ ABORT;
+
+ mparams.granularity = gsize;
+ mparams.page_size = psize;
+ mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD;
+ mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD;
+#if MORECORE_CONTIGUOUS
+ mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT;
+#else /* MORECORE_CONTIGUOUS */
+ mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT;
+#endif /* MORECORE_CONTIGUOUS */
+
+#if !ONLY_MSPACES
+ /* Set up lock for main malloc area */
+ gm->mflags = mparams.default_mflags;
+ INITIAL_LOCK(&gm->mutex);
+#endif
+
+ {
+#if USE_DEV_RANDOM
+ int fd;
+ unsigned char buf[sizeof(size_t)];
+ /* Try to use /dev/urandom, else fall back on using time */
+ if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 &&
+ read(fd, buf, sizeof(buf)) == sizeof(buf)) {
+ magic = *((size_t *) buf);
+ close(fd);
+ }
+ else
+#endif /* USE_DEV_RANDOM */
+#ifdef WIN32
+ magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U);
+#else
+ magic = (size_t)(time(0) ^ (size_t)0x55555555U);
+#endif
+ magic |= (size_t)8U; /* ensure nonzero */
+ magic &= ~(size_t)7U; /* improve chances of fault for bad values */
+ mparams.magic = magic;
+ }
+ }
+
+ RELEASE_MALLOC_GLOBAL_LOCK();
+ return 1;
+}
+
+/* support for mallopt */
+static int change_mparam(int param_number, int value) {
+ size_t val;
+ ensure_initialization();
+ val = (value == -1)? MAX_SIZE_T : (size_t)value;
+ switch(param_number) {
+ case M_TRIM_THRESHOLD:
+ mparams.trim_threshold = val;
+ return 1;
+ case M_GRANULARITY:
+ if (val >= mparams.page_size && ((val & (val-1)) == 0)) {
+ mparams.granularity = val;
+ return 1;
+ }
+ else
+ return 0;
+ case M_MMAP_THRESHOLD:
+ mparams.mmap_threshold = val;
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+#if DEBUG
+/* ------------------------- Debugging Support --------------------------- */
+
+/* Check properties of any chunk, whether free, inuse, mmapped etc */
+static void do_check_any_chunk(mstate m, mchunkptr p) {
+ assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+ assert(ok_address(m, p));
+}
+
+/* Check properties of top chunk */
+static void do_check_top_chunk(mstate m, mchunkptr p) {
+ msegmentptr sp = segment_holding(m, (char*)p);
+ size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */
+ assert(sp != 0);
+ assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+ assert(ok_address(m, p));
+ assert(sz == m->topsize);
+ assert(sz > 0);
+ assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE);
+ assert(pinuse(p));
+ assert(!pinuse(chunk_plus_offset(p, sz)));
+}
+
+/* Check properties of (inuse) mmapped chunks */
+static void do_check_mmapped_chunk(mstate m, mchunkptr p) {
+ size_t sz = chunksize(p);
+ size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD);
+ assert(is_mmapped(p));
+ assert(use_mmap(m));
+ assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+ assert(ok_address(m, p));
+ assert(!is_small(sz));
+ assert((len & (mparams.page_size-SIZE_T_ONE)) == 0);
+ assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD);
+ assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0);
+}
+
+/* Check properties of inuse chunks */
+static void do_check_inuse_chunk(mstate m, mchunkptr p) {
+ do_check_any_chunk(m, p);
+ assert(is_inuse(p));
+ assert(next_pinuse(p));
+ /* If not pinuse and not mmapped, previous chunk has OK offset */
+ assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p);
+ if (is_mmapped(p))
+ do_check_mmapped_chunk(m, p);
+}
+
+/* Check properties of free chunks */
+static void do_check_free_chunk(mstate m, mchunkptr p) {
+ size_t sz = chunksize(p);
+ mchunkptr next = chunk_plus_offset(p, sz);
+ do_check_any_chunk(m, p);
+ assert(!is_inuse(p));
+ assert(!next_pinuse(p));
+ assert (!is_mmapped(p));
+ if (p != m->dv && p != m->top) {
+ if (sz >= MIN_CHUNK_SIZE) {
+ assert((sz & CHUNK_ALIGN_MASK) == 0);
+ assert(is_aligned(chunk2mem(p)));
+ assert(next->prev_foot == sz);
+ assert(pinuse(p));
+ assert (next == m->top || is_inuse(next));
+ assert(p->fd->bk == p);
+ assert(p->bk->fd == p);
+ }
+ else /* markers are always of size SIZE_T_SIZE */
+ assert(sz == SIZE_T_SIZE);
+ }
+}
+
+/* Check properties of malloced chunks at the point they are malloced */
+static void do_check_malloced_chunk(mstate m, void* mem, size_t s) {
+ if (mem != 0) {
+ mchunkptr p = mem2chunk(mem);
+ size_t sz = p->head & ~INUSE_BITS;
+ do_check_inuse_chunk(m, p);
+ assert((sz & CHUNK_ALIGN_MASK) == 0);
+ assert(sz >= MIN_CHUNK_SIZE);
+ assert(sz >= s);
+ /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */
+ assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE));
+ }
+}
+
+/* Check a tree and its subtrees. */
+static void do_check_tree(mstate m, tchunkptr t) {
+ tchunkptr head = 0;
+ tchunkptr u = t;
+ bindex_t tindex = t->index;
+ size_t tsize = chunksize(t);
+ bindex_t idx;
+ compute_tree_index(tsize, idx);
+ assert(tindex == idx);
+ assert(tsize >= MIN_LARGE_SIZE);
+ assert(tsize >= minsize_for_tree_index(idx));
+ assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1))));
+
+ do { /* traverse through chain of same-sized nodes */
+ do_check_any_chunk(m, ((mchunkptr)u));
+ assert(u->index == tindex);
+ assert(chunksize(u) == tsize);
+ assert(!is_inuse(u));
+ assert(!next_pinuse(u));
+ assert(u->fd->bk == u);
+ assert(u->bk->fd == u);
+ if (u->parent == 0) {
+ assert(u->child[0] == 0);
+ assert(u->child[1] == 0);
+ }
+ else {
+ assert(head == 0); /* only one node on chain has parent */
+ head = u;
+ assert(u->parent != u);
+ assert (u->parent->child[0] == u ||
+ u->parent->child[1] == u ||
+ *((tbinptr*)(u->parent)) == u);
+ if (u->child[0] != 0) {
+ assert(u->child[0]->parent == u);
+ assert(u->child[0] != u);
+ do_check_tree(m, u->child[0]);
+ }
+ if (u->child[1] != 0) {
+ assert(u->child[1]->parent == u);
+ assert(u->child[1] != u);
+ do_check_tree(m, u->child[1]);
+ }
+ if (u->child[0] != 0 && u->child[1] != 0) {
+ assert(chunksize(u->child[0]) < chunksize(u->child[1]));
+ }
+ }
+ u = u->fd;
+ } while (u != t);
+ assert(head != 0);
+}
+
+/* Check all the chunks in a treebin. */
+static void do_check_treebin(mstate m, bindex_t i) {
+ tbinptr* tb = treebin_at(m, i);
+ tchunkptr t = *tb;
+ int empty = (m->treemap & (1U << i)) == 0;
+ if (t == 0)
+ assert(empty);
+ if (!empty)
+ do_check_tree(m, t);
+}
+
+/* Check all the chunks in a smallbin. */
+static void do_check_smallbin(mstate m, bindex_t i) {
+ sbinptr b = smallbin_at(m, i);
+ mchunkptr p = b->bk;
+ unsigned int empty = (m->smallmap & (1U << i)) == 0;
+ if (p == b)
+ assert(empty);
+ if (!empty) {
+ for (; p != b; p = p->bk) {
+ size_t size = chunksize(p);
+ mchunkptr q;
+ /* each chunk claims to be free */
+ do_check_free_chunk(m, p);
+ /* chunk belongs in bin */
+ assert(small_index(size) == i);
+ assert(p->bk == b || chunksize(p->bk) == chunksize(p));
+ /* chunk is followed by an inuse chunk */
+ q = next_chunk(p);
+ if (q->head != FENCEPOST_HEAD)
+ do_check_inuse_chunk(m, q);
+ }
+ }
+}
+
+/* Find x in a bin. Used in other check functions. */
+static int bin_find(mstate m, mchunkptr x) {
+ size_t size = chunksize(x);
+ if (is_small(size)) {
+ bindex_t sidx = small_index(size);
+ sbinptr b = smallbin_at(m, sidx);
+ if (smallmap_is_marked(m, sidx)) {
+ mchunkptr p = b;
+ do {
+ if (p == x)
+ return 1;
+ } while ((p = p->fd) != b);
+ }
+ }
+ else {
+ bindex_t tidx;
+ compute_tree_index(size, tidx);
+ if (treemap_is_marked(m, tidx)) {
+ tchunkptr t = *treebin_at(m, tidx);
+ size_t sizebits = size << leftshift_for_tree_index(tidx);
+ while (t != 0 && chunksize(t) != size) {
+ t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+ sizebits <<= 1;
+ }
+ if (t != 0) {
+ tchunkptr u = t;
+ do {
+ if (u == (tchunkptr)x)
+ return 1;
+ } while ((u = u->fd) != t);
+ }
+ }
+ }
+ return 0;
+}
+
+/* Traverse each chunk and check it; return total */
+static size_t traverse_and_check(mstate m) {
+ size_t sum = 0;
+ if (is_initialized(m)) {
+ msegmentptr s = &m->seg;
+ sum += m->topsize + TOP_FOOT_SIZE;
+ while (s != 0) {
+ mchunkptr q = align_as_chunk(s->base);
+ mchunkptr lastq = 0;
+ assert(pinuse(q));
+ while (segment_holds(s, q) &&
+ q != m->top && q->head != FENCEPOST_HEAD) {
+ sum += chunksize(q);
+ if (is_inuse(q)) {
+ assert(!bin_find(m, q));
+ do_check_inuse_chunk(m, q);
+ }
+ else {
+ assert(q == m->dv || bin_find(m, q));
+ assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */
+ do_check_free_chunk(m, q);
+ }
+ lastq = q;
+ q = next_chunk(q);
+ }
+ s = s->next;
+ }
+ }
+ return sum;
+}
+
+/* Check all properties of malloc_state. */
+static void do_check_malloc_state(mstate m) {
+ bindex_t i;
+ size_t total;
+ /* check bins */
+ for (i = 0; i < NSMALLBINS; ++i)
+ do_check_smallbin(m, i);
+ for (i = 0; i < NTREEBINS; ++i)
+ do_check_treebin(m, i);
+
+ if (m->dvsize != 0) { /* check dv chunk */
+ do_check_any_chunk(m, m->dv);
+ assert(m->dvsize == chunksize(m->dv));
+ assert(m->dvsize >= MIN_CHUNK_SIZE);
+ assert(bin_find(m, m->dv) == 0);
+ }
+
+ if (m->top != 0) { /* check top chunk */
+ do_check_top_chunk(m, m->top);
+ /*assert(m->topsize == chunksize(m->top)); redundant */
+ assert(m->topsize > 0);
+ assert(bin_find(m, m->top) == 0);
+ }
+
+ total = traverse_and_check(m);
+ assert(total <= m->footprint);
+ assert(m->footprint <= m->max_footprint);
+}
+#endif /* DEBUG */
+
+/* ----------------------------- statistics ------------------------------ */
+
+#if !NO_MALLINFO
+static struct mallinfo internal_mallinfo(mstate m) {
+ struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+ ensure_initialization();
+ if (!PREACTION(m)) {
+ check_malloc_state(m);
+ if (is_initialized(m)) {
+ size_t nfree = SIZE_T_ONE; /* top always free */
+ size_t mfree = m->topsize + TOP_FOOT_SIZE;
+ size_t sum = mfree;
+ msegmentptr s = &m->seg;
+ while (s != 0) {
+ mchunkptr q = align_as_chunk(s->base);
+ while (segment_holds(s, q) &&
+ q != m->top && q->head != FENCEPOST_HEAD) {
+ size_t sz = chunksize(q);
+ sum += sz;
+ if (!is_inuse(q)) {
+ mfree += sz;
+ ++nfree;
+ }
+ q = next_chunk(q);
+ }
+ s = s->next;
+ }
+
+ nm.arena = sum;
+ nm.ordblks = nfree;
+ nm.hblkhd = m->footprint - sum;
+ nm.usmblks = m->max_footprint;
+ nm.uordblks = m->footprint - mfree;
+ nm.fordblks = mfree;
+ nm.keepcost = m->topsize;
+ }
+
+ POSTACTION(m);
+ }
+ return nm;
+}
+#endif /* !NO_MALLINFO */
+
+static void internal_malloc_stats(mstate m) {
+ ensure_initialization();
+ if (!PREACTION(m)) {
+ size_t maxfp = 0;
+ size_t fp = 0;
+ size_t used = 0;
+ check_malloc_state(m);
+ if (is_initialized(m)) {
+ msegmentptr s = &m->seg;
+ maxfp = m->max_footprint;
+ fp = m->footprint;
+ used = fp - (m->topsize + TOP_FOOT_SIZE);
+
+ while (s != 0) {
+ mchunkptr q = align_as_chunk(s->base);
+ while (segment_holds(s, q) &&
+ q != m->top && q->head != FENCEPOST_HEAD) {
+ if (!is_inuse(q))
+ used -= chunksize(q);
+ q = next_chunk(q);
+ }
+ s = s->next;
+ }
+ }
+
+ fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp));
+ fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp));
+ fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used));
+
+ POSTACTION(m);
+ }
+}
+
+/* ----------------------- Operations on smallbins ----------------------- */
+
+/*
+ Various forms of linking and unlinking are defined as macros. Even
+ the ones for trees, which are very long but have very short typical
+ paths. This is ugly but reduces reliance on inlining support of
+ compilers.
+*/
+
+/* Link a free chunk into a smallbin */
+#define insert_small_chunk(M, P, S) {\
+ bindex_t I = small_index(S);\
+ mchunkptr B = smallbin_at(M, I);\
+ mchunkptr F = B;\
+ assert(S >= MIN_CHUNK_SIZE);\
+ if (!smallmap_is_marked(M, I))\
+ mark_smallmap(M, I);\
+ else if (RTCHECK(ok_address(M, B->fd)))\
+ F = B->fd;\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ B->fd = P;\
+ F->bk = P;\
+ P->fd = F;\
+ P->bk = B;\
+}
+
+/* Unlink a chunk from a smallbin */
+#define unlink_small_chunk(M, P, S) {\
+ mchunkptr F = P->fd;\
+ mchunkptr B = P->bk;\
+ bindex_t I = small_index(S);\
+ assert(P != B);\
+ assert(P != F);\
+ assert(chunksize(P) == small_index2size(I));\
+ if (F == B)\
+ clear_smallmap(M, I);\
+ else if (RTCHECK((F == smallbin_at(M,I) || ok_address(M, F)) &&\
+ (B == smallbin_at(M,I) || ok_address(M, B)))) {\
+ F->bk = B;\
+ B->fd = F;\
+ }\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+}
+
+/* Unlink the first chunk from a smallbin */
+#define unlink_first_small_chunk(M, B, P, I) {\
+ mchunkptr F = P->fd;\
+ assert(P != B);\
+ assert(P != F);\
+ assert(chunksize(P) == small_index2size(I));\
+ if (B == F)\
+ clear_smallmap(M, I);\
+ else if (RTCHECK(ok_address(M, F))) {\
+ B->fd = F;\
+ F->bk = B;\
+ }\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+}
+
+
+
+/* Replace dv node, binning the old one */
+/* Used only when dvsize known to be small */
+#define replace_dv(M, P, S) {\
+ size_t DVS = M->dvsize;\
+ if (DVS != 0) {\
+ mchunkptr DV = M->dv;\
+ assert(is_small(DVS));\
+ insert_small_chunk(M, DV, DVS);\
+ }\
+ M->dvsize = S;\
+ M->dv = P;\
+}
+
+/* ------------------------- Operations on trees ------------------------- */
+
+/* Insert chunk into tree */
+#define insert_large_chunk(M, X, S) {\
+ tbinptr* H;\
+ bindex_t I;\
+ compute_tree_index(S, I);\
+ H = treebin_at(M, I);\
+ X->index = I;\
+ X->child[0] = X->child[1] = 0;\
+ if (!treemap_is_marked(M, I)) {\
+ mark_treemap(M, I);\
+ *H = X;\
+ X->parent = (tchunkptr)H;\
+ X->fd = X->bk = X;\
+ }\
+ else {\
+ tchunkptr T = *H;\
+ size_t K = S << leftshift_for_tree_index(I);\
+ for (;;) {\
+ if (chunksize(T) != S) {\
+ tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\
+ K <<= 1;\
+ if (*C != 0)\
+ T = *C;\
+ else if (RTCHECK(ok_address(M, C))) {\
+ *C = X;\
+ X->parent = T;\
+ X->fd = X->bk = X;\
+ break;\
+ }\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ break;\
+ }\
+ }\
+ else {\
+ tchunkptr F = T->fd;\
+ if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\
+ T->fd = F->bk = X;\
+ X->fd = F;\
+ X->bk = T;\
+ X->parent = 0;\
+ break;\
+ }\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ break;\
+ }\
+ }\
+ }\
+ }\
+}
+
+/*
+ Unlink steps:
+
+ 1. If x is a chained node, unlink it from its same-sized fd/bk links
+ and choose its bk node as its replacement.
+ 2. If x was the last node of its size, but not a leaf node, it must
+ be replaced with a leaf node (not merely one with an open left or
+ right), to make sure that lefts and rights of descendents
+ correspond properly to bit masks. We use the rightmost descendent
+ of x. We could use any other leaf, but this is easy to locate and
+ tends to counteract removal of leftmosts elsewhere, and so keeps
+ paths shorter than minimally guaranteed. This doesn't loop much
+ because on average a node in a tree is near the bottom.
+ 3. If x is the base of a chain (i.e., has parent links) relink
+ x's parent and children to x's replacement (or null if none).
+*/
+
+#define unlink_large_chunk(M, X) {\
+ tchunkptr XP = X->parent;\
+ tchunkptr R;\
+ if (X->bk != X) {\
+ tchunkptr F = X->fd;\
+ R = X->bk;\
+ if (RTCHECK(ok_address(M, F))) {\
+ F->bk = R;\
+ R->fd = F;\
+ }\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ }\
+ else {\
+ tchunkptr* RP;\
+ if (((R = *(RP = &(X->child[1]))) != 0) ||\
+ ((R = *(RP = &(X->child[0]))) != 0)) {\
+ tchunkptr* CP;\
+ while ((*(CP = &(R->child[1])) != 0) ||\
+ (*(CP = &(R->child[0])) != 0)) {\
+ R = *(RP = CP);\
+ }\
+ if (RTCHECK(ok_address(M, RP)))\
+ *RP = 0;\
+ else {\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ }\
+ }\
+ if (XP != 0) {\
+ tbinptr* H = treebin_at(M, X->index);\
+ if (X == *H) {\
+ if ((*H = R) == 0) \
+ clear_treemap(M, X->index);\
+ }\
+ else if (RTCHECK(ok_address(M, XP))) {\
+ if (XP->child[0] == X) \
+ XP->child[0] = R;\
+ else \
+ XP->child[1] = R;\
+ }\
+ else\
+ CORRUPTION_ERROR_ACTION(M);\
+ if (R != 0) {\
+ if (RTCHECK(ok_address(M, R))) {\
+ tchunkptr C0, C1;\
+ R->parent = XP;\
+ if ((C0 = X->child[0]) != 0) {\
+ if (RTCHECK(ok_address(M, C0))) {\
+ R->child[0] = C0;\
+ C0->parent = R;\
+ }\
+ else\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ if ((C1 = X->child[1]) != 0) {\
+ if (RTCHECK(ok_address(M, C1))) {\
+ R->child[1] = C1;\
+ C1->parent = R;\
+ }\
+ else\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ }\
+ else\
+ CORRUPTION_ERROR_ACTION(M);\
+ }\
+ }\
+}
+
+/* Relays to large vs small bin operations */
+
+#define insert_chunk(M, P, S)\
+ if (is_small(S)) insert_small_chunk(M, P, S)\
+ else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); }
+
+#define unlink_chunk(M, P, S)\
+ if (is_small(S)) unlink_small_chunk(M, P, S)\
+ else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); }
+
+
+/* Relays to internal calls to malloc/free from realloc, memalign etc */
+
+#if ONLY_MSPACES
+#define internal_malloc(m, b) mspace_malloc(m, b)
+#define internal_free(m, mem) mspace_free(m,mem);
+#else /* ONLY_MSPACES */
+#if MSPACES
+#define internal_malloc(m, b)\
+ (m == gm)? dlmalloc(b) : mspace_malloc(m, b)
+#define internal_free(m, mem)\
+ if (m == gm) dlfree(mem); else mspace_free(m,mem);
+#else /* MSPACES */
+#define internal_malloc(m, b) dlmalloc(b)
+#define internal_free(m, mem) dlfree(mem)
+#endif /* MSPACES */
+#endif /* ONLY_MSPACES */
+
+/* ----------------------- Direct-mmapping chunks ----------------------- */
+
+/*
+ Directly mmapped chunks are set up with an offset to the start of
+ the mmapped region stored in the prev_foot field of the chunk. This
+ allows reconstruction of the required argument to MUNMAP when freed,
+ and also allows adjustment of the returned chunk to meet alignment
+ requirements (especially in memalign).
+*/
+
+/* Malloc using mmap */
+static void* mmap_alloc(mstate m, size_t nb) {
+ size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+ if (mmsize > nb) { /* Check for wrap around 0 */
+ char* mm = (char*)(CALL_DIRECT_MMAP(mmsize));
+ if (mm != CMFAIL) {
+ size_t offset = align_offset(chunk2mem(mm));
+ size_t psize = mmsize - offset - MMAP_FOOT_PAD;
+ mchunkptr p = (mchunkptr)(mm + offset);
+ p->prev_foot = offset;
+ p->head = psize;
+ mark_inuse_foot(m, p, psize);
+ chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD;
+ chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0;
+
+ if (m->least_addr == 0 || mm < m->least_addr)
+ m->least_addr = mm;
+ if ((m->footprint += mmsize) > m->max_footprint)
+ m->max_footprint = m->footprint;
+ assert(is_aligned(chunk2mem(p)));
+ check_mmapped_chunk(m, p);
+ return chunk2mem(p);
+ }
+ }
+ return 0;
+}
+
+/* Realloc using mmap */
+static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) {
+ size_t oldsize = chunksize(oldp);
+ if (is_small(nb)) /* Can't shrink mmap regions below small size */
+ return 0;
+ /* Keep old chunk if big enough but not too big */
+ if (oldsize >= nb + SIZE_T_SIZE &&
+ (oldsize - nb) <= (mparams.granularity << 1))
+ return oldp;
+ else {
+ size_t offset = oldp->prev_foot;
+ size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD;
+ size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+ char* cp = (char*)CALL_MREMAP((char*)oldp - offset,
+ oldmmsize, newmmsize, 1);
+ if (cp != CMFAIL) {
+ mchunkptr newp = (mchunkptr)(cp + offset);
+ size_t psize = newmmsize - offset - MMAP_FOOT_PAD;
+ newp->head = psize;
+ mark_inuse_foot(m, newp, psize);
+ chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD;
+ chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0;
+
+ if (cp < m->least_addr)
+ m->least_addr = cp;
+ if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint)
+ m->max_footprint = m->footprint;
+ check_mmapped_chunk(m, newp);
+ return newp;
+ }
+ }
+ return 0;
+}
+
+/* -------------------------- mspace management -------------------------- */
+
+/* Initialize top chunk and its size */
+static void init_top(mstate m, mchunkptr p, size_t psize) {
+ /* Ensure alignment */
+ size_t offset = align_offset(chunk2mem(p));
+ p = (mchunkptr)((char*)p + offset);
+ psize -= offset;
+
+ m->top = p;
+ m->topsize = psize;
+ p->head = psize | PINUSE_BIT;
+ /* set size of fake trailing chunk holding overhead space only once */
+ chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE;
+ m->trim_check = mparams.trim_threshold; /* reset on each update */
+}
+
+/* Initialize bins for a new mstate that is otherwise zeroed out */
+static void init_bins(mstate m) {
+ /* Establish circular links for smallbins */
+ bindex_t i;
+ for (i = 0; i < NSMALLBINS; ++i) {
+ sbinptr bin = smallbin_at(m,i);
+ bin->fd = bin->bk = bin;
+ }
+}
+
+#if PROCEED_ON_ERROR
+
+/* default corruption action */
+static void reset_on_error(mstate m) {
+ int i;
+ ++malloc_corruption_error_count;
+ /* Reinitialize fields to forget about all memory */
+ m->smallbins = m->treebins = 0;
+ m->dvsize = m->topsize = 0;
+ m->seg.base = 0;
+ m->seg.size = 0;
+ m->seg.next = 0;
+ m->top = m->dv = 0;
+ for (i = 0; i < NTREEBINS; ++i)
+ *treebin_at(m, i) = 0;
+ init_bins(m);
+}
+#endif /* PROCEED_ON_ERROR */
+
+/* Allocate chunk and prepend remainder with chunk in successor base. */
+static void* prepend_alloc(mstate m, char* newbase, char* oldbase,
+ size_t nb) {
+ mchunkptr p = align_as_chunk(newbase);
+ mchunkptr oldfirst = align_as_chunk(oldbase);
+ size_t psize = (char*)oldfirst - (char*)p;
+ mchunkptr q = chunk_plus_offset(p, nb);
+ size_t qsize = psize - nb;
+ set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+
+ assert((char*)oldfirst > (char*)q);
+ assert(pinuse(oldfirst));
+ assert(qsize >= MIN_CHUNK_SIZE);
+
+ /* consolidate remainder with first chunk of old base */
+ if (oldfirst == m->top) {
+ size_t tsize = m->topsize += qsize;
+ m->top = q;
+ q->head = tsize | PINUSE_BIT;
+ check_top_chunk(m, q);
+ }
+ else if (oldfirst == m->dv) {
+ size_t dsize = m->dvsize += qsize;
+ m->dv = q;
+ set_size_and_pinuse_of_free_chunk(q, dsize);
+ }
+ else {
+ if (!is_inuse(oldfirst)) {
+ size_t nsize = chunksize(oldfirst);
+ unlink_chunk(m, oldfirst, nsize);
+ oldfirst = chunk_plus_offset(oldfirst, nsize);
+ qsize += nsize;
+ }
+ set_free_with_pinuse(q, qsize, oldfirst);
+ insert_chunk(m, q, qsize);
+ check_free_chunk(m, q);
+ }
+
+ check_malloced_chunk(m, chunk2mem(p), nb);
+ return chunk2mem(p);
+}
+
+/* Add a segment to hold a new noncontiguous region */
+static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) {
+ /* Determine locations and sizes of segment, fenceposts, old top */
+ char* old_top = (char*)m->top;
+ msegmentptr oldsp = segment_holding(m, old_top);
+ char* old_end = oldsp->base + oldsp->size;
+ size_t ssize = pad_request(sizeof(struct malloc_segment));
+ char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+ size_t offset = align_offset(chunk2mem(rawsp));
+ char* asp = rawsp + offset;
+ char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp;
+ mchunkptr sp = (mchunkptr)csp;
+ msegmentptr ss = (msegmentptr)(chunk2mem(sp));
+ mchunkptr tnext = chunk_plus_offset(sp, ssize);
+ mchunkptr p = tnext;
+ int nfences = 0;
+
+ /* reset top to new space */
+ init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+
+ /* Set up segment record */
+ assert(is_aligned(ss));
+ set_size_and_pinuse_of_inuse_chunk(m, sp, ssize);
+ *ss = m->seg; /* Push current record */
+ m->seg.base = tbase;
+ m->seg.size = tsize;
+ m->seg.sflags = mmapped;
+ m->seg.next = ss;
+
+ /* Insert trailing fenceposts */
+ for (;;) {
+ mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE);
+ p->head = FENCEPOST_HEAD;
+ ++nfences;
+ if ((char*)(&(nextp->head)) < old_end)
+ p = nextp;
+ else
+ break;
+ }
+ assert(nfences >= 2);
+
+ /* Insert the rest of old top into a bin as an ordinary free chunk */
+ if (csp != old_top) {
+ mchunkptr q = (mchunkptr)old_top;
+ size_t psize = csp - old_top;
+ mchunkptr tn = chunk_plus_offset(q, psize);
+ set_free_with_pinuse(q, psize, tn);
+ insert_chunk(m, q, psize);
+ }
+
+ check_top_chunk(m, m->top);
+}
+
+/* -------------------------- System allocation -------------------------- */
+
+/* Get memory from system using MORECORE or MMAP */
+static void* sys_alloc(mstate m, size_t nb) {
+ char* tbase = CMFAIL;
+ size_t tsize = 0;
+ flag_t mmap_flag = 0;
+
+ ensure_initialization();
+
+ /* Directly map large chunks, but only if already initialized */
+ if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) {
+ void* mem = mmap_alloc(m, nb);
+ if (mem != 0)
+ return mem;
+ }
+
+ /*
+ Try getting memory in any of three ways (in most-preferred to
+ least-preferred order):
+ 1. A call to MORECORE that can normally contiguously extend memory.
+ (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or
+ or main space is mmapped or a previous contiguous call failed)
+ 2. A call to MMAP new space (disabled if not HAVE_MMAP).
+ Note that under the default settings, if MORECORE is unable to
+ fulfill a request, and HAVE_MMAP is true, then mmap is
+ used as a noncontiguous system allocator. This is a useful backup
+ strategy for systems with holes in address spaces -- in this case
+ sbrk cannot contiguously expand the heap, but mmap may be able to
+ find space.
+ 3. A call to MORECORE that cannot usually contiguously extend memory.
+ (disabled if not HAVE_MORECORE)
+
+ In all cases, we need to request enough bytes from system to ensure
+ we can malloc nb bytes upon success, so pad with enough space for
+ top_foot, plus alignment-pad to make sure we don't lose bytes if
+ not on boundary, and round this up to a granularity unit.
+ */
+
+ if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) {
+ char* br = CMFAIL;
+ msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top);
+ size_t asize = 0;
+ ACQUIRE_MALLOC_GLOBAL_LOCK();
+
+ if (ss == 0) { /* First time through or recovery */
+ char* base = (char*)CALL_MORECORE(0);
+ if (base != CMFAIL) {
+ asize = granularity_align(nb + SYS_ALLOC_PADDING);
+ /* Adjust to end on a page boundary */
+ if (!is_page_aligned(base))
+ asize += (page_align((size_t)base) - (size_t)base);
+ /* Can't call MORECORE if size is negative when treated as signed */
+ if (asize < HALF_MAX_SIZE_T &&
+ (br = (char*)(CALL_MORECORE(asize))) == base) {
+ tbase = base;
+ tsize = asize;
+ }
+ }
+ }
+ else {
+ /* Subtract out existing available top space from MORECORE request. */
+ asize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING);
+ /* Use mem here only if it did continuously extend old space */
+ if (asize < HALF_MAX_SIZE_T &&
+ (br = (char*)(CALL_MORECORE(asize))) == ss->base+ss->size) {
+ tbase = br;
+ tsize = asize;
+ }
+ }
+
+ if (tbase == CMFAIL) { /* Cope with partial failure */
+ if (br != CMFAIL) { /* Try to use/extend the space we did get */
+ if (asize < HALF_MAX_SIZE_T &&
+ asize < nb + SYS_ALLOC_PADDING) {
+ size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - asize);
+ if (esize < HALF_MAX_SIZE_T) {
+ char* end = (char*)CALL_MORECORE(esize);
+ if (end != CMFAIL)
+ asize += esize;
+ else { /* Can't use; try to release */
+ (void) CALL_MORECORE(-asize);
+ br = CMFAIL;
+ }
+ }
+ }
+ }
+ if (br != CMFAIL) { /* Use the space we did get */
+ tbase = br;
+ tsize = asize;
+ }
+ else
+ disable_contiguous(m); /* Don't try contiguous path in the future */
+ }
+
+ RELEASE_MALLOC_GLOBAL_LOCK();
+ }
+
+ if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */
+ size_t rsize = granularity_align(nb + SYS_ALLOC_PADDING);
+ if (rsize > nb) { /* Fail if wraps around zero */
+ char* mp = (char*)(CALL_MMAP(rsize));
+ if (mp != CMFAIL) {
+ tbase = mp;
+ tsize = rsize;
+ mmap_flag = USE_MMAP_BIT;
+ }
+ }
+ }
+
+ if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */
+ size_t asize = granularity_align(nb + SYS_ALLOC_PADDING);
+ if (asize < HALF_MAX_SIZE_T) {
+ char* br = CMFAIL;
+ char* end = CMFAIL;
+ ACQUIRE_MALLOC_GLOBAL_LOCK();
+ br = (char*)(CALL_MORECORE(asize));
+ end = (char*)(CALL_MORECORE(0));
+ RELEASE_MALLOC_GLOBAL_LOCK();
+ if (br != CMFAIL && end != CMFAIL && br < end) {
+ size_t ssize = end - br;
+ if (ssize > nb + TOP_FOOT_SIZE) {
+ tbase = br;
+ tsize = ssize;
+ }
+ }
+ }
+ }
+
+ if (tbase != CMFAIL) {
+
+ if ((m->footprint += tsize) > m->max_footprint)
+ m->max_footprint = m->footprint;
+
+ if (!is_initialized(m)) { /* first-time initialization */
+ if (m->least_addr == 0 || tbase < m->least_addr)
+ m->least_addr = tbase;
+ m->seg.base = tbase;
+ m->seg.size = tsize;
+ m->seg.sflags = mmap_flag;
+ m->magic = mparams.magic;
+ m->release_checks = MAX_RELEASE_CHECK_RATE;
+ init_bins(m);
+#if !ONLY_MSPACES
+ if (is_global(m))
+ init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+ else
+#endif
+ {
+ /* Offset top by embedded malloc_state */
+ mchunkptr mn = next_chunk(mem2chunk(m));
+ init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE);
+ }
+ }
+
+ else {
+ /* Try to merge with an existing segment */
+ msegmentptr sp = &m->seg;
+ /* Only consider most recent segment if traversal suppressed */
+ while (sp != 0 && tbase != sp->base + sp->size)
+ sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+ if (sp != 0 &&
+ !is_extern_segment(sp) &&
+ (sp->sflags & USE_MMAP_BIT) == mmap_flag &&
+ segment_holds(sp, m->top)) { /* append */
+ sp->size += tsize;
+ init_top(m, m->top, m->topsize + tsize);
+ }
+ else {
+ if (tbase < m->least_addr)
+ m->least_addr = tbase;
+ sp = &m->seg;
+ while (sp != 0 && sp->base != tbase + tsize)
+ sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+ if (sp != 0 &&
+ !is_extern_segment(sp) &&
+ (sp->sflags & USE_MMAP_BIT) == mmap_flag) {
+ char* oldbase = sp->base;
+ sp->base = tbase;
+ sp->size += tsize;
+ return prepend_alloc(m, tbase, oldbase, nb);
+ }
+ else
+ add_segment(m, tbase, tsize, mmap_flag);
+ }
+ }
+
+ if (nb < m->topsize) { /* Allocate from new or extended top space */
+ size_t rsize = m->topsize -= nb;
+ mchunkptr p = m->top;
+ mchunkptr r = m->top = chunk_plus_offset(p, nb);
+ r->head = rsize | PINUSE_BIT;
+ set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+ check_top_chunk(m, m->top);
+ check_malloced_chunk(m, chunk2mem(p), nb);
+ return chunk2mem(p);
+ }
+ }
+
+ MALLOC_FAILURE_ACTION;
+ return 0;
+}
+
+/* ----------------------- system deallocation -------------------------- */
+
+/* Unmap and unlink any mmapped segments that don't contain used chunks */
+static size_t release_unused_segments(mstate m) {
+ size_t released = 0;
+ int nsegs = 0;
+ msegmentptr pred = &m->seg;
+ msegmentptr sp = pred->next;
+ while (sp != 0) {
+ char* base = sp->base;
+ size_t size = sp->size;
+ msegmentptr next = sp->next;
+ ++nsegs;
+ if (is_mmapped_segment(sp) && !is_extern_segment(sp)) {
+ mchunkptr p = align_as_chunk(base);
+ size_t psize = chunksize(p);
+ /* Can unmap if first chunk holds entire segment and not pinned */
+ if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) {
+ tchunkptr tp = (tchunkptr)p;
+ assert(segment_holds(sp, (char*)sp));
+ if (p == m->dv) {
+ m->dv = 0;
+ m->dvsize = 0;
+ }
+ else {
+ unlink_large_chunk(m, tp);
+ }
+ if (CALL_MUNMAP(base, size) == 0) {
+ released += size;
+ m->footprint -= size;
+ /* unlink obsoleted record */
+ sp = pred;
+ sp->next = next;
+ }
+ else { /* back out if cannot unmap */
+ insert_large_chunk(m, tp, psize);
+ }
+ }
+ }
+ if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */
+ break;
+ pred = sp;
+ sp = next;
+ }
+ /* Reset check counter */
+ m->release_checks = ((nsegs > MAX_RELEASE_CHECK_RATE)?
+ nsegs : MAX_RELEASE_CHECK_RATE);
+ return released;
+}
+
+static int sys_trim(mstate m, size_t pad) {
+ size_t released = 0;
+ ensure_initialization();
+ if (pad < MAX_REQUEST && is_initialized(m)) {
+ pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */
+
+ if (m->topsize > pad) {
+ /* Shrink top space in granularity-size units, keeping at least one */
+ size_t unit = mparams.granularity;
+ size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit -
+ SIZE_T_ONE) * unit;
+ msegmentptr sp = segment_holding(m, (char*)m->top);
+
+ if (!is_extern_segment(sp)) {
+ if (is_mmapped_segment(sp)) {
+ if (HAVE_MMAP &&
+ sp->size >= extra &&
+ !has_segment_link(m, sp)) { /* can't shrink if pinned */
+ size_t newsize = sp->size - extra;
+ /* Prefer mremap, fall back to munmap */
+ if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) ||
+ (CALL_MUNMAP(sp->base + newsize, extra) == 0)) {
+ released = extra;
+ }
+ }
+ }
+ else if (HAVE_MORECORE) {
+ if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */
+ extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit;
+ ACQUIRE_MALLOC_GLOBAL_LOCK();
+ {
+ /* Make sure end of memory is where we last set it. */
+ char* old_br = (char*)(CALL_MORECORE(0));
+ if (old_br == sp->base + sp->size) {
+ char* rel_br = (char*)(CALL_MORECORE(-extra));
+ char* new_br = (char*)(CALL_MORECORE(0));
+ if (rel_br != CMFAIL && new_br < old_br)
+ released = old_br - new_br;
+ }
+ }
+ RELEASE_MALLOC_GLOBAL_LOCK();
+ }
+ }
+
+ if (released != 0) {
+ sp->size -= released;
+ m->footprint -= released;
+ init_top(m, m->top, m->topsize - released);
+ check_top_chunk(m, m->top);
+ }
+ }
+
+ /* Unmap any unused mmapped segments */
+ if (HAVE_MMAP)
+ released += release_unused_segments(m);
+
+ /* On failure, disable autotrim to avoid repeated failed future calls */
+ if (released == 0 && m->topsize > m->trim_check)
+ m->trim_check = MAX_SIZE_T;
+ }
+
+ return (released != 0)? 1 : 0;
+}
+
+
+/* ---------------------------- malloc support --------------------------- */
+
+/* allocate a large request from the best fitting chunk in a treebin */
+static void* tmalloc_large(mstate m, size_t nb) {
+ tchunkptr v = 0;
+ size_t rsize = -nb; /* Unsigned negation */
+ tchunkptr t;
+ bindex_t idx;
+ compute_tree_index(nb, idx);
+ if ((t = *treebin_at(m, idx)) != 0) {
+ /* Traverse tree for this bin looking for node with size == nb */
+ size_t sizebits = nb << leftshift_for_tree_index(idx);
+ tchunkptr rst = 0; /* The deepest untaken right subtree */
+ for (;;) {
+ tchunkptr rt;
+ size_t trem = chunksize(t) - nb;
+ if (trem < rsize) {
+ v = t;
+ if ((rsize = trem) == 0)
+ break;
+ }
+ rt = t->child[1];
+ t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+ if (rt != 0 && rt != t)
+ rst = rt;
+ if (t == 0) {
+ t = rst; /* set t to least subtree holding sizes > nb */
+ break;
+ }
+ sizebits <<= 1;
+ }
+ }
+ if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */
+ binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap;
+ if (leftbits != 0) {
+ bindex_t i;
+ binmap_t leastbit = least_bit(leftbits);
+ compute_bit2idx(leastbit, i);
+ t = *treebin_at(m, i);
+ }
+ }
+
+ while (t != 0) { /* find smallest of tree or subtree */
+ size_t trem = chunksize(t) - nb;
+ if (trem < rsize) {
+ rsize = trem;
+ v = t;
+ }
+ t = leftmost_child(t);
+ }
+
+ /* If dv is a better fit, return 0 so malloc will use it */
+ if (v != 0 && rsize < (size_t)(m->dvsize - nb)) {
+ if (RTCHECK(ok_address(m, v))) { /* split */
+ mchunkptr r = chunk_plus_offset(v, nb);
+ assert(chunksize(v) == rsize + nb);
+ if (RTCHECK(ok_next(v, r))) {
+ unlink_large_chunk(m, v);
+ if (rsize < MIN_CHUNK_SIZE)
+ set_inuse_and_pinuse(m, v, (rsize + nb));
+ else {
+ set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ insert_chunk(m, r, rsize);
+ }
+ return chunk2mem(v);
+ }
+ }
+ CORRUPTION_ERROR_ACTION(m);
+ }
+ return 0;
+}
+
+/* allocate a small request from the best fitting chunk in a treebin */
+static void* tmalloc_small(mstate m, size_t nb) {
+ tchunkptr t, v;
+ size_t rsize;
+ bindex_t i;
+ binmap_t leastbit = least_bit(m->treemap);
+ compute_bit2idx(leastbit, i);
+ v = t = *treebin_at(m, i);
+ rsize = chunksize(t) - nb;
+
+ while ((t = leftmost_child(t)) != 0) {
+ size_t trem = chunksize(t) - nb;
+ if (trem < rsize) {
+ rsize = trem;
+ v = t;
+ }
+ }
+
+ if (RTCHECK(ok_address(m, v))) {
+ mchunkptr r = chunk_plus_offset(v, nb);
+ assert(chunksize(v) == rsize + nb);
+ if (RTCHECK(ok_next(v, r))) {
+ unlink_large_chunk(m, v);
+ if (rsize < MIN_CHUNK_SIZE)
+ set_inuse_and_pinuse(m, v, (rsize + nb));
+ else {
+ set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ replace_dv(m, r, rsize);
+ }
+ return chunk2mem(v);
+ }
+ }
+
+ CORRUPTION_ERROR_ACTION(m);
+ return 0;
+}
+
+/* --------------------------- realloc support --------------------------- */
+
+static void* internal_realloc(mstate m, void* oldmem, size_t bytes) {
+ if (bytes >= MAX_REQUEST) {
+ MALLOC_FAILURE_ACTION;
+ return 0;
+ }
+ if (!PREACTION(m)) {
+ mchunkptr oldp = mem2chunk(oldmem);
+ size_t oldsize = chunksize(oldp);
+ mchunkptr next = chunk_plus_offset(oldp, oldsize);
+ mchunkptr newp = 0;
+ void* extra = 0;
+
+ /* Try to either shrink or extend into top. Else malloc-copy-free */
+
+ if (RTCHECK(ok_address(m, oldp) && ok_inuse(oldp) &&
+ ok_next(oldp, next) && ok_pinuse(next))) {
+ size_t nb = request2size(bytes);
+ if (is_mmapped(oldp))
+ newp = mmap_resize(m, oldp, nb);
+ else if (oldsize >= nb) { /* already big enough */
+ size_t rsize = oldsize - nb;
+ newp = oldp;
+ if (rsize >= MIN_CHUNK_SIZE) {
+ mchunkptr remainder = chunk_plus_offset(newp, nb);
+ set_inuse(m, newp, nb);
+ set_inuse_and_pinuse(m, remainder, rsize);
+ extra = chunk2mem(remainder);
+ }
+ }
+ else if (next == m->top && oldsize + m->topsize > nb) {
+ /* Expand into top */
+ size_t newsize = oldsize + m->topsize;
+ size_t newtopsize = newsize - nb;
+ mchunkptr newtop = chunk_plus_offset(oldp, nb);
+ set_inuse(m, oldp, nb);
+ newtop->head = newtopsize |PINUSE_BIT;
+ m->top = newtop;
+ m->topsize = newtopsize;
+ newp = oldp;
+ }
+ }
+ else {
+ USAGE_ERROR_ACTION(m, oldmem);
+ POSTACTION(m);
+ return 0;
+ }
+#if DEBUG
+ if (newp != 0) {
+ check_inuse_chunk(m, newp); /* Check requires lock */
+ }
+#endif
+
+ POSTACTION(m);
+
+ if (newp != 0) {
+ if (extra != 0) {
+ internal_free(m, extra);
+ }
+ return chunk2mem(newp);
+ }
+ else {
+ void* newmem = internal_malloc(m, bytes);
+ if (newmem != 0) {
+ size_t oc = oldsize - overhead_for(oldp);
+ memcpy(newmem, oldmem, (oc < bytes)? oc : bytes);
+ internal_free(m, oldmem);
+ }
+ return newmem;
+ }
+ }
+ return 0;
+}
+
+/* --------------------------- memalign support -------------------------- */
+
+static void* internal_memalign(mstate m, size_t alignment, size_t bytes) {
+ if (alignment <= MALLOC_ALIGNMENT) /* Can just use malloc */
+ return internal_malloc(m, bytes);
+ if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */
+ alignment = MIN_CHUNK_SIZE;
+ if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */
+ size_t a = MALLOC_ALIGNMENT << 1;
+ while (a < alignment) a <<= 1;
+ alignment = a;
+ }
+
+ if (bytes >= MAX_REQUEST - alignment) {
+ if (m != 0) { /* Test isn't needed but avoids compiler warning */
+ MALLOC_FAILURE_ACTION;
+ }
+ }
+ else {
+ size_t nb = request2size(bytes);
+ size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD;
+ char* mem = (char*)internal_malloc(m, req);
+ if (mem != 0) {
+ void* leader = 0;
+ void* trailer = 0;
+ mchunkptr p = mem2chunk(mem);
+
+ if (PREACTION(m)) return 0;
+ if ((((size_t)(mem)) % alignment) != 0) { /* misaligned */
+ /*
+ Find an aligned spot inside chunk. Since we need to give
+ back leading space in a chunk of at least MIN_CHUNK_SIZE, if
+ the first calculation places us at a spot with less than
+ MIN_CHUNK_SIZE leader, we can move to the next aligned spot.
+ We've allocated enough total room so that this is always
+ possible.
+ */
+ char* br = (char*)mem2chunk((size_t)(((size_t)(mem +
+ alignment -
+ SIZE_T_ONE)) &
+ -alignment));
+ char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)?
+ br : br+alignment;
+ mchunkptr newp = (mchunkptr)pos;
+ size_t leadsize = pos - (char*)(p);
+ size_t newsize = chunksize(p) - leadsize;
+
+ if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */
+ newp->prev_foot = p->prev_foot + leadsize;
+ newp->head = newsize;
+ }
+ else { /* Otherwise, give back leader, use the rest */
+ set_inuse(m, newp, newsize);
+ set_inuse(m, p, leadsize);
+ leader = chunk2mem(p);
+ }
+ p = newp;
+ }
+
+ /* Give back spare room at the end */
+ if (!is_mmapped(p)) {
+ size_t size = chunksize(p);
+ if (size > nb + MIN_CHUNK_SIZE) {
+ size_t remainder_size = size - nb;
+ mchunkptr remainder = chunk_plus_offset(p, nb);
+ set_inuse(m, p, nb);
+ set_inuse(m, remainder, remainder_size);
+ trailer = chunk2mem(remainder);
+ }
+ }
+
+ assert (chunksize(p) >= nb);
+ assert((((size_t)(chunk2mem(p))) % alignment) == 0);
+ check_inuse_chunk(m, p);
+ POSTACTION(m);
+ if (leader != 0) {
+ internal_free(m, leader);
+ }
+ if (trailer != 0) {
+ internal_free(m, trailer);
+ }
+ return chunk2mem(p);
+ }
+ }
+ return 0;
+}
+
+/* ------------------------ comalloc/coalloc support --------------------- */
+
+static void** ialloc(mstate m,
+ size_t n_elements,
+ size_t* sizes,
+ int opts,
+ void* chunks[]) {
+ /*
+ This provides common support for independent_X routines, handling
+ all of the combinations that can result.
+
+ The opts arg has:
+ bit 0 set if all elements are same size (using sizes[0])
+ bit 1 set if elements should be zeroed
+ */
+
+ size_t element_size; /* chunksize of each element, if all same */
+ size_t contents_size; /* total size of elements */
+ size_t array_size; /* request size of pointer array */
+ void* mem; /* malloced aggregate space */
+ mchunkptr p; /* corresponding chunk */
+ size_t remainder_size; /* remaining bytes while splitting */
+ void** marray; /* either "chunks" or malloced ptr array */
+ mchunkptr array_chunk; /* chunk for malloced ptr array */
+ flag_t was_enabled; /* to disable mmap */
+ size_t size;
+ size_t i;
+
+ ensure_initialization();
+ /* compute array length, if needed */
+ if (chunks != 0) {
+ if (n_elements == 0)
+ return chunks; /* nothing to do */
+ marray = chunks;
+ array_size = 0;
+ }
+ else {
+ /* if empty req, must still return chunk representing empty array */
+ if (n_elements == 0)
+ return (void**)internal_malloc(m, 0);
+ marray = 0;
+ array_size = request2size(n_elements * (sizeof(void*)));
+ }
+
+ /* compute total element size */
+ if (opts & 0x1) { /* all-same-size */
+ element_size = request2size(*sizes);
+ contents_size = n_elements * element_size;
+ }
+ else { /* add up all the sizes */
+ element_size = 0;
+ contents_size = 0;
+ for (i = 0; i != n_elements; ++i)
+ contents_size += request2size(sizes[i]);
+ }
+
+ size = contents_size + array_size;
+
+ /*
+ Allocate the aggregate chunk. First disable direct-mmapping so
+ malloc won't use it, since we would not be able to later
+ free/realloc space internal to a segregated mmap region.
+ */
+ was_enabled = use_mmap(m);
+ disable_mmap(m);
+ mem = internal_malloc(m, size - CHUNK_OVERHEAD);
+ if (was_enabled)
+ enable_mmap(m);
+ if (mem == 0)
+ return 0;
+
+ if (PREACTION(m)) return 0;
+ p = mem2chunk(mem);
+ remainder_size = chunksize(p);
+
+ assert(!is_mmapped(p));
+
+ if (opts & 0x2) { /* optionally clear the elements */
+ memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size);
+ }
+
+ /* If not provided, allocate the pointer array as final part of chunk */
+ if (marray == 0) {
+ size_t array_chunk_size;
+ array_chunk = chunk_plus_offset(p, contents_size);
+ array_chunk_size = remainder_size - contents_size;
+ marray = (void**) (chunk2mem(array_chunk));
+ set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size);
+ remainder_size = contents_size;
+ }
+
+ /* split out elements */
+ for (i = 0; ; ++i) {
+ marray[i] = chunk2mem(p);
+ if (i != n_elements-1) {
+ if (element_size != 0)
+ size = element_size;
+ else
+ size = request2size(sizes[i]);
+ remainder_size -= size;
+ set_size_and_pinuse_of_inuse_chunk(m, p, size);
+ p = chunk_plus_offset(p, size);
+ }
+ else { /* the final element absorbs any overallocation slop */
+ set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size);
+ break;
+ }
+ }
+
+#if DEBUG
+ if (marray != chunks) {
+ /* final element must have exactly exhausted chunk */
+ if (element_size != 0) {
+ assert(remainder_size == element_size);
+ }
+ else {
+ assert(remainder_size == request2size(sizes[i]));
+ }
+ check_inuse_chunk(m, mem2chunk(marray));
+ }
+ for (i = 0; i != n_elements; ++i)
+ check_inuse_chunk(m, mem2chunk(marray[i]));
+
+#endif /* DEBUG */
+
+ POSTACTION(m);
+ return marray;
+}
+
+
+/* -------------------------- public routines ---------------------------- */
+
+#if !ONLY_MSPACES
+
+void* dlmalloc(size_t bytes) {
+ /*
+ Basic algorithm:
+ If a small request (< 256 bytes minus per-chunk overhead):
+ 1. If one exists, use a remainderless chunk in associated smallbin.
+ (Remainderless means that there are too few excess bytes to
+ represent as a chunk.)
+ 2. If it is big enough, use the dv chunk, which is normally the
+ chunk adjacent to the one used for the most recent small request.
+ 3. If one exists, split the smallest available chunk in a bin,
+ saving remainder in dv.
+ 4. If it is big enough, use the top chunk.
+ 5. If available, get memory from system and use it
+ Otherwise, for a large request:
+ 1. Find the smallest available binned chunk that fits, and use it
+ if it is better fitting than dv chunk, splitting if necessary.
+ 2. If better fitting than any binned chunk, use the dv chunk.
+ 3. If it is big enough, use the top chunk.
+ 4. If request size >= mmap threshold, try to directly mmap this chunk.
+ 5. If available, get memory from system and use it
+
+ The ugly goto's here ensure that postaction occurs along all paths.
+ */
+
+#if USE_LOCKS
+ ensure_initialization(); /* initialize in sys_alloc if not using locks */
+#endif
+
+ if (!PREACTION(gm)) {
+ void* mem;
+ size_t nb;
+ if (bytes <= MAX_SMALL_REQUEST) {
+ bindex_t idx;
+ binmap_t smallbits;
+ nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+ idx = small_index(nb);
+ smallbits = gm->smallmap >> idx;
+
+ if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+ mchunkptr b, p;
+ idx += ~smallbits & 1; /* Uses next bin if idx empty */
+ b = smallbin_at(gm, idx);
+ p = b->fd;
+ assert(chunksize(p) == small_index2size(idx));
+ unlink_first_small_chunk(gm, b, p, idx);
+ set_inuse_and_pinuse(gm, p, small_index2size(idx));
+ mem = chunk2mem(p);
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+
+ else if (nb > gm->dvsize) {
+ if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+ mchunkptr b, p, r;
+ size_t rsize;
+ bindex_t i;
+ binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+ binmap_t leastbit = least_bit(leftbits);
+ compute_bit2idx(leastbit, i);
+ b = smallbin_at(gm, i);
+ p = b->fd;
+ assert(chunksize(p) == small_index2size(i));
+ unlink_first_small_chunk(gm, b, p, i);
+ rsize = small_index2size(i) - nb;
+ /* Fit here cannot be remainderless if 4byte sizes */
+ if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+ set_inuse_and_pinuse(gm, p, small_index2size(i));
+ else {
+ set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+ r = chunk_plus_offset(p, nb);
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ replace_dv(gm, r, rsize);
+ }
+ mem = chunk2mem(p);
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+
+ else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) {
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+ }
+ }
+ else if (bytes >= MAX_REQUEST)
+ nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+ else {
+ nb = pad_request(bytes);
+ if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) {
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+ }
+
+ if (nb <= gm->dvsize) {
+ size_t rsize = gm->dvsize - nb;
+ mchunkptr p = gm->dv;
+ if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+ mchunkptr r = gm->dv = chunk_plus_offset(p, nb);
+ gm->dvsize = rsize;
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+ }
+ else { /* exhaust dv */
+ size_t dvs = gm->dvsize;
+ gm->dvsize = 0;
+ gm->dv = 0;
+ set_inuse_and_pinuse(gm, p, dvs);
+ }
+ mem = chunk2mem(p);
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+
+ else if (nb < gm->topsize) { /* Split top */
+ size_t rsize = gm->topsize -= nb;
+ mchunkptr p = gm->top;
+ mchunkptr r = gm->top = chunk_plus_offset(p, nb);
+ r->head = rsize | PINUSE_BIT;
+ set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+ mem = chunk2mem(p);
+ check_top_chunk(gm, gm->top);
+ check_malloced_chunk(gm, mem, nb);
+ goto postaction;
+ }
+
+ mem = sys_alloc(gm, nb);
+
+ postaction:
+ POSTACTION(gm);
+ return mem;
+ }
+
+ return 0;
+}
+
+void dlfree(void* mem) {
+ /*
+ Consolidate freed chunks with preceeding or succeeding bordering
+ free chunks, if they exist, and then place in a bin. Intermixed
+ with special cases for top, dv, mmapped chunks, and usage errors.
+ */
+
+ if (mem != 0) {
+ mchunkptr p = mem2chunk(mem);
+#if FOOTERS
+ mstate fm = get_mstate_for(p);
+ if (!ok_magic(fm)) {
+ USAGE_ERROR_ACTION(fm, p);
+ return;
+ }
+#else /* FOOTERS */
+#define fm gm
+#endif /* FOOTERS */
+ if (!PREACTION(fm)) {
+ check_inuse_chunk(fm, p);
+ if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+ size_t psize = chunksize(p);
+ mchunkptr next = chunk_plus_offset(p, psize);
+ if (!pinuse(p)) {
+ size_t prevsize = p->prev_foot;
+ if (is_mmapped(p)) {
+ psize += prevsize + MMAP_FOOT_PAD;
+ if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+ fm->footprint -= psize;
+ goto postaction;
+ }
+ else {
+ mchunkptr prev = chunk_minus_offset(p, prevsize);
+ psize += prevsize;
+ p = prev;
+ if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+ if (p != fm->dv) {
+ unlink_chunk(fm, p, prevsize);
+ }
+ else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+ fm->dvsize = psize;
+ set_free_with_pinuse(p, psize, next);
+ goto postaction;
+ }
+ }
+ else
+ goto erroraction;
+ }
+ }
+
+ if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+ if (!cinuse(next)) { /* consolidate forward */
+ if (next == fm->top) {
+ size_t tsize = fm->topsize += psize;
+ fm->top = p;
+ p->head = tsize | PINUSE_BIT;
+ if (p == fm->dv) {
+ fm->dv = 0;
+ fm->dvsize = 0;
+ }
+ if (should_trim(fm, tsize))
+ sys_trim(fm, 0);
+ goto postaction;
+ }
+ else if (next == fm->dv) {
+ size_t dsize = fm->dvsize += psize;
+ fm->dv = p;
+ set_size_and_pinuse_of_free_chunk(p, dsize);
+ goto postaction;
+ }
+ else {
+ size_t nsize = chunksize(next);
+ psize += nsize;
+ unlink_chunk(fm, next, nsize);
+ set_size_and_pinuse_of_free_chunk(p, psize);
+ if (p == fm->dv) {
+ fm->dvsize = psize;
+ goto postaction;
+ }
+ }
+ }
+ else
+ set_free_with_pinuse(p, psize, next);
+
+ if (is_small(psize)) {
+ insert_small_chunk(fm, p, psize);
+ check_free_chunk(fm, p);
+ }
+ else {
+ tchunkptr tp = (tchunkptr)p;
+ insert_large_chunk(fm, tp, psize);
+ check_free_chunk(fm, p);
+ if (--fm->release_checks == 0)
+ release_unused_segments(fm);
+ }
+ goto postaction;
+ }
+ }
+ erroraction:
+ USAGE_ERROR_ACTION(fm, p);
+ postaction:
+ POSTACTION(fm);
+ }
+ }
+#if !FOOTERS
+#undef fm
+#endif /* FOOTERS */
+}
+
+void* dlcalloc(size_t n_elements, size_t elem_size) {
+ void* mem;
+ size_t req = 0;
+ if (n_elements != 0) {
+ req = n_elements * elem_size;
+ if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+ (req / n_elements != elem_size))
+ req = MAX_SIZE_T; /* force downstream failure on overflow */
+ }
+ mem = dlmalloc(req);
+ if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+ memset(mem, 0, req);
+ return mem;
+}
+
+void* dlrealloc(void* oldmem, size_t bytes) {
+ if (oldmem == 0)
+ return dlmalloc(bytes);
+#ifdef REALLOC_ZERO_BYTES_FREES
+ if (bytes == 0) {
+ dlfree(oldmem);
+ return 0;
+ }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+ else {
+#if ! FOOTERS
+ mstate m = gm;
+#else /* FOOTERS */
+ mstate m = get_mstate_for(mem2chunk(oldmem));
+ if (!ok_magic(m)) {
+ USAGE_ERROR_ACTION(m, oldmem);
+ return 0;
+ }
+#endif /* FOOTERS */
+ return internal_realloc(m, oldmem, bytes);
+ }
+}
+
+void* dlmemalign(size_t alignment, size_t bytes) {
+ return internal_memalign(gm, alignment, bytes);
+}
+
+void** dlindependent_calloc(size_t n_elements, size_t elem_size,
+ void* chunks[]) {
+ size_t sz = elem_size; /* serves as 1-element array */
+ return ialloc(gm, n_elements, &sz, 3, chunks);
+}
+
+void** dlindependent_comalloc(size_t n_elements, size_t sizes[],
+ void* chunks[]) {
+ return ialloc(gm, n_elements, sizes, 0, chunks);
+}
+
+void* dlvalloc(size_t bytes) {
+ size_t pagesz;
+ ensure_initialization();
+ pagesz = mparams.page_size;
+ return dlmemalign(pagesz, bytes);
+}
+
+void* dlpvalloc(size_t bytes) {
+ size_t pagesz;
+ ensure_initialization();
+ pagesz = mparams.page_size;
+ return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE));
+}
+
+int dlmalloc_trim(size_t pad) {
+ int result = 0;
+ ensure_initialization();
+ if (!PREACTION(gm)) {
+ result = sys_trim(gm, pad);
+ POSTACTION(gm);
+ }
+ return result;
+}
+
+size_t dlmalloc_footprint(void) {
+ return gm->footprint;
+}
+
+size_t dlmalloc_max_footprint(void) {
+ return gm->max_footprint;
+}
+
+#if !NO_MALLINFO
+struct mallinfo dlmallinfo(void) {
+ return internal_mallinfo(gm);
+}
+#endif /* NO_MALLINFO */
+
+void dlmalloc_stats() {
+ internal_malloc_stats(gm);
+}
+
+int dlmallopt(int param_number, int value) {
+ return change_mparam(param_number, value);
+}
+
+#endif /* !ONLY_MSPACES */
+
+size_t dlmalloc_usable_size(void* mem) {
+ if (mem != 0) {
+ mchunkptr p = mem2chunk(mem);
+ if (is_inuse(p))
+ return chunksize(p) - overhead_for(p);
+ }
+ return 0;
+}
+
+/* ----------------------------- user mspaces ---------------------------- */
+
+#if MSPACES
+
+static mstate init_user_mstate(char* tbase, size_t tsize) {
+ size_t msize = pad_request(sizeof(struct malloc_state));
+ mchunkptr mn;
+ mchunkptr msp = align_as_chunk(tbase);
+ mstate m = (mstate)(chunk2mem(msp));
+ memset(m, 0, msize);
+ INITIAL_LOCK(&m->mutex);
+ msp->head = (msize|INUSE_BITS);
+ m->seg.base = m->least_addr = tbase;
+ m->seg.size = m->footprint = m->max_footprint = tsize;
+ m->magic = mparams.magic;
+ m->release_checks = MAX_RELEASE_CHECK_RATE;
+ m->mflags = mparams.default_mflags;
+ m->extp = 0;
+ m->exts = 0;
+ disable_contiguous(m);
+ init_bins(m);
+ mn = next_chunk(mem2chunk(m));
+ init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE);
+ check_top_chunk(m, m->top);
+ return m;
+}
+
+mspace create_mspace(size_t capacity, int locked) {
+ mstate m = 0;
+ size_t msize;
+ ensure_initialization();
+ msize = pad_request(sizeof(struct malloc_state));
+ if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+ size_t rs = ((capacity == 0)? mparams.granularity :
+ (capacity + TOP_FOOT_SIZE + msize));
+ size_t tsize = granularity_align(rs);
+ char* tbase = (char*)(CALL_MMAP(tsize));
+ if (tbase != CMFAIL) {
+ m = init_user_mstate(tbase, tsize);
+ m->seg.sflags = USE_MMAP_BIT;
+ set_lock(m, locked);
+ }
+ }
+ return (mspace)m;
+}
+
+mspace create_mspace_with_base(void* base, size_t capacity, int locked) {
+ mstate m = 0;
+ size_t msize;
+ ensure_initialization();
+ msize = pad_request(sizeof(struct malloc_state));
+ if (capacity > msize + TOP_FOOT_SIZE &&
+ capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+ m = init_user_mstate((char*)base, capacity);
+ m->seg.sflags = EXTERN_BIT;
+ set_lock(m, locked);
+ }
+ return (mspace)m;
+}
+
+int mspace_track_large_chunks(mspace msp, int enable) {
+ int ret = 0;
+ mstate ms = (mstate)msp;
+ if (!PREACTION(ms)) {
+ if (!use_mmap(ms))
+ ret = 1;
+ if (!enable)
+ enable_mmap(ms);
+ else
+ disable_mmap(ms);
+ POSTACTION(ms);
+ }
+ return ret;
+}
+
+size_t destroy_mspace(mspace msp) {
+ size_t freed = 0;
+ mstate ms = (mstate)msp;
+ if (ok_magic(ms)) {
+ msegmentptr sp = &ms->seg;
+ while (sp != 0) {
+ char* base = sp->base;
+ size_t size = sp->size;
+ flag_t flag = sp->sflags;
+ sp = sp->next;
+ if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) &&
+ CALL_MUNMAP(base, size) == 0)
+ freed += size;
+ }
+ }
+ else {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+ return freed;
+}
+
+/*
+ mspace versions of routines are near-clones of the global
+ versions. This is not so nice but better than the alternatives.
+*/
+
+
+void* mspace_malloc(mspace msp, size_t bytes) {
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ if (!PREACTION(ms)) {
+ void* mem;
+ size_t nb;
+ if (bytes <= MAX_SMALL_REQUEST) {
+ bindex_t idx;
+ binmap_t smallbits;
+ nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+ idx = small_index(nb);
+ smallbits = ms->smallmap >> idx;
+
+ if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+ mchunkptr b, p;
+ idx += ~smallbits & 1; /* Uses next bin if idx empty */
+ b = smallbin_at(ms, idx);
+ p = b->fd;
+ assert(chunksize(p) == small_index2size(idx));
+ unlink_first_small_chunk(ms, b, p, idx);
+ set_inuse_and_pinuse(ms, p, small_index2size(idx));
+ mem = chunk2mem(p);
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+
+ else if (nb > ms->dvsize) {
+ if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+ mchunkptr b, p, r;
+ size_t rsize;
+ bindex_t i;
+ binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+ binmap_t leastbit = least_bit(leftbits);
+ compute_bit2idx(leastbit, i);
+ b = smallbin_at(ms, i);
+ p = b->fd;
+ assert(chunksize(p) == small_index2size(i));
+ unlink_first_small_chunk(ms, b, p, i);
+ rsize = small_index2size(i) - nb;
+ /* Fit here cannot be remainderless if 4byte sizes */
+ if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+ set_inuse_and_pinuse(ms, p, small_index2size(i));
+ else {
+ set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+ r = chunk_plus_offset(p, nb);
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ replace_dv(ms, r, rsize);
+ }
+ mem = chunk2mem(p);
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+
+ else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) {
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+ }
+ }
+ else if (bytes >= MAX_REQUEST)
+ nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+ else {
+ nb = pad_request(bytes);
+ if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) {
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+ }
+
+ if (nb <= ms->dvsize) {
+ size_t rsize = ms->dvsize - nb;
+ mchunkptr p = ms->dv;
+ if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+ mchunkptr r = ms->dv = chunk_plus_offset(p, nb);
+ ms->dvsize = rsize;
+ set_size_and_pinuse_of_free_chunk(r, rsize);
+ set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+ }
+ else { /* exhaust dv */
+ size_t dvs = ms->dvsize;
+ ms->dvsize = 0;
+ ms->dv = 0;
+ set_inuse_and_pinuse(ms, p, dvs);
+ }
+ mem = chunk2mem(p);
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+
+ else if (nb < ms->topsize) { /* Split top */
+ size_t rsize = ms->topsize -= nb;
+ mchunkptr p = ms->top;
+ mchunkptr r = ms->top = chunk_plus_offset(p, nb);
+ r->head = rsize | PINUSE_BIT;
+ set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+ mem = chunk2mem(p);
+ check_top_chunk(ms, ms->top);
+ check_malloced_chunk(ms, mem, nb);
+ goto postaction;
+ }
+
+ mem = sys_alloc(ms, nb);
+
+ postaction:
+ POSTACTION(ms);
+ return mem;
+ }
+
+ return 0;
+}
+
+void mspace_free(mspace msp, void* mem) {
+ if (mem != 0) {
+ mchunkptr p = mem2chunk(mem);
+#if FOOTERS
+ mstate fm = get_mstate_for(p);
+ msp = msp; /* placate people compiling -Wunused */
+#else /* FOOTERS */
+ mstate fm = (mstate)msp;
+#endif /* FOOTERS */
+ if (!ok_magic(fm)) {
+ USAGE_ERROR_ACTION(fm, p);
+ return;
+ }
+ if (!PREACTION(fm)) {
+ check_inuse_chunk(fm, p);
+ if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+ size_t psize = chunksize(p);
+ mchunkptr next = chunk_plus_offset(p, psize);
+ if (!pinuse(p)) {
+ size_t prevsize = p->prev_foot;
+ if (is_mmapped(p)) {
+ psize += prevsize + MMAP_FOOT_PAD;
+ if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+ fm->footprint -= psize;
+ goto postaction;
+ }
+ else {
+ mchunkptr prev = chunk_minus_offset(p, prevsize);
+ psize += prevsize;
+ p = prev;
+ if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+ if (p != fm->dv) {
+ unlink_chunk(fm, p, prevsize);
+ }
+ else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+ fm->dvsize = psize;
+ set_free_with_pinuse(p, psize, next);
+ goto postaction;
+ }
+ }
+ else
+ goto erroraction;
+ }
+ }
+
+ if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+ if (!cinuse(next)) { /* consolidate forward */
+ if (next == fm->top) {
+ size_t tsize = fm->topsize += psize;
+ fm->top = p;
+ p->head = tsize | PINUSE_BIT;
+ if (p == fm->dv) {
+ fm->dv = 0;
+ fm->dvsize = 0;
+ }
+ if (should_trim(fm, tsize))
+ sys_trim(fm, 0);
+ goto postaction;
+ }
+ else if (next == fm->dv) {
+ size_t dsize = fm->dvsize += psize;
+ fm->dv = p;
+ set_size_and_pinuse_of_free_chunk(p, dsize);
+ goto postaction;
+ }
+ else {
+ size_t nsize = chunksize(next);
+ psize += nsize;
+ unlink_chunk(fm, next, nsize);
+ set_size_and_pinuse_of_free_chunk(p, psize);
+ if (p == fm->dv) {
+ fm->dvsize = psize;
+ goto postaction;
+ }
+ }
+ }
+ else
+ set_free_with_pinuse(p, psize, next);
+
+ if (is_small(psize)) {
+ insert_small_chunk(fm, p, psize);
+ check_free_chunk(fm, p);
+ }
+ else {
+ tchunkptr tp = (tchunkptr)p;
+ insert_large_chunk(fm, tp, psize);
+ check_free_chunk(fm, p);
+ if (--fm->release_checks == 0)
+ release_unused_segments(fm);
+ }
+ goto postaction;
+ }
+ }
+ erroraction:
+ USAGE_ERROR_ACTION(fm, p);
+ postaction:
+ POSTACTION(fm);
+ }
+ }
+}
+
+void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) {
+ void* mem;
+ size_t req = 0;
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ if (n_elements != 0) {
+ req = n_elements * elem_size;
+ if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+ (req / n_elements != elem_size))
+ req = MAX_SIZE_T; /* force downstream failure on overflow */
+ }
+ mem = internal_malloc(ms, req);
+ if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+ memset(mem, 0, req);
+ return mem;
+}
+
+void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) {
+ if (oldmem == 0)
+ return mspace_malloc(msp, bytes);
+#ifdef REALLOC_ZERO_BYTES_FREES
+ if (bytes == 0) {
+ mspace_free(msp, oldmem);
+ return 0;
+ }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+ else {
+#if FOOTERS
+ mchunkptr p = mem2chunk(oldmem);
+ mstate ms = get_mstate_for(p);
+#else /* FOOTERS */
+ mstate ms = (mstate)msp;
+#endif /* FOOTERS */
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ return internal_realloc(ms, oldmem, bytes);
+ }
+}
+
+void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) {
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ return internal_memalign(ms, alignment, bytes);
+}
+
+void** mspace_independent_calloc(mspace msp, size_t n_elements,
+ size_t elem_size, void* chunks[]) {
+ size_t sz = elem_size; /* serves as 1-element array */
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ return ialloc(ms, n_elements, &sz, 3, chunks);
+}
+
+void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+ size_t sizes[], void* chunks[]) {
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ return 0;
+ }
+ return ialloc(ms, n_elements, sizes, 0, chunks);
+}
+
+int mspace_trim(mspace msp, size_t pad) {
+ int result = 0;
+ mstate ms = (mstate)msp;
+ if (ok_magic(ms)) {
+ if (!PREACTION(ms)) {
+ result = sys_trim(ms, pad);
+ POSTACTION(ms);
+ }
+ }
+ else {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+ return result;
+}
+
+void mspace_malloc_stats(mspace msp) {
+ mstate ms = (mstate)msp;
+ if (ok_magic(ms)) {
+ internal_malloc_stats(ms);
+ }
+ else {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+}
+
+size_t mspace_footprint(mspace msp) {
+ size_t result = 0;
+ mstate ms = (mstate)msp;
+ if (ok_magic(ms)) {
+ result = ms->footprint;
+ }
+ else {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+ return result;
+}
+
+
+size_t mspace_max_footprint(mspace msp) {
+ size_t result = 0;
+ mstate ms = (mstate)msp;
+ if (ok_magic(ms)) {
+ result = ms->max_footprint;
+ }
+ else {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+ return result;
+}
+
+
+#if !NO_MALLINFO
+struct mallinfo mspace_mallinfo(mspace msp) {
+ mstate ms = (mstate)msp;
+ if (!ok_magic(ms)) {
+ USAGE_ERROR_ACTION(ms,ms);
+ }
+ return internal_mallinfo(ms);
+}
+#endif /* NO_MALLINFO */
+
+size_t mspace_usable_size(void* mem) {
+ if (mem != 0) {
+ mchunkptr p = mem2chunk(mem);
+ if (is_inuse(p))
+ return chunksize(p) - overhead_for(p);
+ }
+ return 0;
+}
+
+int mspace_mallopt(int param_number, int value) {
+ return change_mparam(param_number, value);
+}
+
+#endif /* MSPACES */
+
+
+/* -------------------- Alternative MORECORE functions ------------------- */
+
+/*
+ Guidelines for creating a custom version of MORECORE:
+
+ * For best performance, MORECORE should allocate in multiples of pagesize.
+ * MORECORE may allocate more memory than requested. (Or even less,
+ but this will usually result in a malloc failure.)
+ * MORECORE must not allocate memory when given argument zero, but
+ instead return one past the end address of memory from previous
+ nonzero call.
+ * For best performance, consecutive calls to MORECORE with positive
+ arguments should return increasing addresses, indicating that
+ space has been contiguously extended.
+ * Even though consecutive calls to MORECORE need not return contiguous
+ addresses, it must be OK for malloc'ed chunks to span multiple
+ regions in those cases where they do happen to be contiguous.
+ * MORECORE need not handle negative arguments -- it may instead
+ just return MFAIL when given negative arguments.
+ Negative arguments are always multiples of pagesize. MORECORE
+ must not misinterpret negative args as large positive unsigned
+ args. You can suppress all such calls from even occurring by defining
+ MORECORE_CANNOT_TRIM,
+
+ As an example alternative MORECORE, here is a custom allocator
+ kindly contributed for pre-OSX macOS. It uses virtually but not
+ necessarily physically contiguous non-paged memory (locked in,
+ present and won't get swapped out). You can use it by uncommenting
+ this section, adding some #includes, and setting up the appropriate
+ defines above:
+
+ #define MORECORE osMoreCore
+
+ There is also a shutdown routine that should somehow be called for
+ cleanup upon program exit.
+
+ #define MAX_POOL_ENTRIES 100
+ #define MINIMUM_MORECORE_SIZE (64 * 1024U)
+ static int next_os_pool;
+ void *our_os_pools[MAX_POOL_ENTRIES];
+
+ void *osMoreCore(int size)
+ {
+ void *ptr = 0;
+ static void *sbrk_top = 0;
+
+ if (size > 0)
+ {
+ if (size < MINIMUM_MORECORE_SIZE)
+ size = MINIMUM_MORECORE_SIZE;
+ if (CurrentExecutionLevel() == kTaskLevel)
+ ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0);
+ if (ptr == 0)
+ {
+ return (void *) MFAIL;
+ }
+ // save ptrs so they can be freed during cleanup
+ our_os_pools[next_os_pool] = ptr;
+ next_os_pool++;
+ ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK);
+ sbrk_top = (char *) ptr + size;
+ return ptr;
+ }
+ else if (size < 0)
+ {
+ // we don't currently support shrink behavior
+ return (void *) MFAIL;
+ }
+ else
+ {
+ return sbrk_top;
+ }
+ }
+
+ // cleanup any allocated memory pools
+ // called as last thing before shutting down driver
+
+ void osCleanupMem(void)
+ {
+ void **ptr;
+
+ for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++)
+ if (*ptr)
+ {
+ PoolDeallocate(*ptr);
+ *ptr = 0;
+ }
+ }
+
+*/
+
+
+/* -----------------------------------------------------------------------
+History:
+ V2.8.4 Wed May 27 09:56:23 2009 Doug Lea (dl at gee)
+ * Use zeros instead of prev foot for is_mmapped
+ * Add mspace_track_large_chunks; thanks to Jean Brouwers
+ * Fix set_inuse in internal_realloc; thanks to Jean Brouwers
+ * Fix insufficient sys_alloc padding when using 16byte alignment
+ * Fix bad error check in mspace_footprint
+ * Adaptations for ptmalloc; thanks to Wolfram Gloger.
+ * Reentrant spin locks; thanks to Earl Chew and others
+ * Win32 improvements; thanks to Niall Douglas and Earl Chew
+ * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options
+ * Extension hook in malloc_state
+ * Various small adjustments to reduce warnings on some compilers
+ * Various configuration extensions/changes for more platforms. Thanks
+ to all who contributed these.
+
+ V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee)
+ * Add max_footprint functions
+ * Ensure all appropriate literals are size_t
+ * Fix conditional compilation problem for some #define settings
+ * Avoid concatenating segments with the one provided
+ in create_mspace_with_base
+ * Rename some variables to avoid compiler shadowing warnings
+ * Use explicit lock initialization.
+ * Better handling of sbrk interference.
+ * Simplify and fix segment insertion, trimming and mspace_destroy
+ * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x
+ * Thanks especially to Dennis Flanagan for help on these.
+
+ V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee)
+ * Fix memalign brace error.
+
+ V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee)
+ * Fix improper #endif nesting in C++
+ * Add explicit casts needed for C++
+
+ V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee)
+ * Use trees for large bins
+ * Support mspaces
+ * Use segments to unify sbrk-based and mmap-based system allocation,
+ removing need for emulation on most platforms without sbrk.
+ * Default safety checks
+ * Optional footer checks. Thanks to William Robertson for the idea.
+ * Internal code refactoring
+ * Incorporate suggestions and platform-specific changes.
+ Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas,
+ Aaron Bachmann, Emery Berger, and others.
+ * Speed up non-fastbin processing enough to remove fastbins.
+ * Remove useless cfree() to avoid conflicts with other apps.
+ * Remove internal memcpy, memset. Compilers handle builtins better.
+ * Remove some options that no one ever used and rename others.
+
+ V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee)
+ * Fix malloc_state bitmap array misdeclaration
+
+ V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee)
+ * Allow tuning of FIRST_SORTED_BIN_SIZE
+ * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte.
+ * Better detection and support for non-contiguousness of MORECORE.
+ Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger
+ * Bypass most of malloc if no frees. Thanks To Emery Berger.
+ * Fix freeing of old top non-contiguous chunk im sysmalloc.
+ * Raised default trim and map thresholds to 256K.
+ * Fix mmap-related #defines. Thanks to Lubos Lunak.
+ * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield.
+ * Branch-free bin calculation
+ * Default trim and mmap thresholds now 256K.
+
+ V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee)
+ * Introduce independent_comalloc and independent_calloc.
+ Thanks to Michael Pachos for motivation and help.
+ * Make optional .h file available
+ * Allow > 2GB requests on 32bit systems.
+ * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>.
+ Thanks also to Andreas Mueller <a.mueller at paradatec.de>,
+ and Anonymous.
+ * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for
+ helping test this.)
+ * memalign: check alignment arg
+ * realloc: don't try to shift chunks backwards, since this
+ leads to more fragmentation in some programs and doesn't
+ seem to help in any others.
+ * Collect all cases in malloc requiring system memory into sysmalloc
+ * Use mmap as backup to sbrk
+ * Place all internal state in malloc_state
+ * Introduce fastbins (although similar to 2.5.1)
+ * Many minor tunings and cosmetic improvements
+ * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK
+ * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS
+ Thanks to Tony E. Bennett <tbennett@nvidia.com> and others.
+ * Include errno.h to support default failure action.
+
+ V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee)
+ * return null for negative arguments
+ * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com>
+ * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
+ (e.g. WIN32 platforms)
+ * Cleanup header file inclusion for WIN32 platforms
+ * Cleanup code to avoid Microsoft Visual C++ compiler complaints
+ * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing
+ memory allocation routines
+ * Set 'malloc_getpagesize' for WIN32 platforms (needs more work)
+ * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to
+ usage of 'assert' in non-WIN32 code
+ * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to
+ avoid infinite loop
+ * Always call 'fREe()' rather than 'free()'
+
+ V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee)
+ * Fixed ordering problem with boundary-stamping
+
+ V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee)
+ * Added pvalloc, as recommended by H.J. Liu
+ * Added 64bit pointer support mainly from Wolfram Gloger
+ * Added anonymously donated WIN32 sbrk emulation
+ * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen
+ * malloc_extend_top: fix mask error that caused wastage after
+ foreign sbrks
+ * Add linux mremap support code from HJ Liu
+
+ V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee)
+ * Integrated most documentation with the code.
+ * Add support for mmap, with help from
+ Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+ * Use last_remainder in more cases.
+ * Pack bins using idea from colin@nyx10.cs.du.edu
+ * Use ordered bins instead of best-fit threshhold
+ * Eliminate block-local decls to simplify tracing and debugging.
+ * Support another case of realloc via move into top
+ * Fix error occuring when initial sbrk_base not word-aligned.
+ * Rely on page size for units instead of SBRK_UNIT to
+ avoid surprises about sbrk alignment conventions.
+ * Add mallinfo, mallopt. Thanks to Raymond Nijssen
+ (raymond@es.ele.tue.nl) for the suggestion.
+ * Add `pad' argument to malloc_trim and top_pad mallopt parameter.
+ * More precautions for cases where other routines call sbrk,
+ courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+ * Added macros etc., allowing use in linux libc from
+ H.J. Lu (hjl@gnu.ai.mit.edu)
+ * Inverted this history list
+
+ V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee)
+ * Re-tuned and fixed to behave more nicely with V2.6.0 changes.
+ * Removed all preallocation code since under current scheme
+ the work required to undo bad preallocations exceeds
+ the work saved in good cases for most test programs.
+ * No longer use return list or unconsolidated bins since
+ no scheme using them consistently outperforms those that don't
+ given above changes.
+ * Use best fit for very large chunks to prevent some worst-cases.
+ * Added some support for debugging
+
+ V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee)
+ * Removed footers when chunks are in use. Thanks to
+ Paul Wilson (wilson@cs.texas.edu) for the suggestion.
+
+ V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee)
+ * Added malloc_trim, with help from Wolfram Gloger
+ (wmglo@Dent.MED.Uni-Muenchen.DE).
+
+ V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g)
+
+ V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g)
+ * realloc: try to expand in both directions
+ * malloc: swap order of clean-bin strategy;
+ * realloc: only conditionally expand backwards
+ * Try not to scavenge used bins
+ * Use bin counts as a guide to preallocation
+ * Occasionally bin return list chunks in first scan
+ * Add a few optimizations from colin@nyx10.cs.du.edu
+
+ V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g)
+ * faster bin computation & slightly different binning
+ * merged all consolidations to one part of malloc proper
+ (eliminating old malloc_find_space & malloc_clean_bin)
+ * Scan 2 returns chunks (not just 1)
+ * Propagate failure in realloc if malloc returns 0
+ * Add stuff to allow compilation on non-ANSI compilers
+ from kpv@research.att.com
+
+ V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu)
+ * removed potential for odd address access in prev_chunk
+ * removed dependency on getpagesize.h
+ * misc cosmetics and a bit more internal documentation
+ * anticosmetics: mangled names in macros to evade debugger strangeness
+ * tested on sparc, hp-700, dec-mips, rs6000
+ with gcc & native cc (hp, dec only) allowing
+ Detlefs & Zorn comparison study (in SIGPLAN Notices.)
+
+ Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu)
+ * Based loosely on libg++-1.2X malloc. (It retains some of the overall
+ structure of old version, but most details differ.)
+
+*/
+
diff --git a/unsupported/test/mpreal/dlmalloc.h b/unsupported/test/mpreal/dlmalloc.h new file mode 100755 index 000000000..a90dcb6f5 --- /dev/null +++ b/unsupported/test/mpreal/dlmalloc.h @@ -0,0 +1,562 @@ +/*
+ Default header file for malloc-2.8.x, written by Doug Lea
+ and released to the public domain, as explained at
+ http://creativecommons.org/licenses/publicdomain.
+
+ last update: Wed May 27 14:25:17 2009 Doug Lea (dl at gee)
+
+ This header is for ANSI C/C++ only. You can set any of
+ the following #defines before including:
+
+ * If USE_DL_PREFIX is defined, it is assumed that malloc.c
+ was also compiled with this option, so all routines
+ have names starting with "dl".
+
+ * If HAVE_USR_INCLUDE_MALLOC_H is defined, it is assumed that this
+ file will be #included AFTER <malloc.h>. This is needed only if
+ your system defines a struct mallinfo that is incompatible with the
+ standard one declared here. Otherwise, you can include this file
+ INSTEAD of your system system <malloc.h>. At least on ANSI, all
+ declarations should be compatible with system versions
+
+ * If MSPACES is defined, declarations for mspace versions are included.
+*/
+
+#ifndef MALLOC_280_H
+#define MALLOC_280_H
+
+#define USE_DL_PREFIX
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stddef.h> /* for size_t */
+
+#ifndef ONLY_MSPACES
+#define ONLY_MSPACES 0 /* define to a value */
+#endif /* ONLY_MSPACES */
+#ifndef NO_MALLINFO
+#define NO_MALLINFO 0
+#endif /* NO_MALLINFO */
+
+
+#if !ONLY_MSPACES
+
+#ifndef USE_DL_PREFIX
+#define dlcalloc calloc
+#define dlfree free
+#define dlmalloc malloc
+#define dlmemalign memalign
+#define dlrealloc realloc
+#define dlvalloc valloc
+#define dlpvalloc pvalloc
+#define dlmallinfo mallinfo
+#define dlmallopt mallopt
+#define dlmalloc_trim malloc_trim
+#define dlmalloc_stats malloc_stats
+#define dlmalloc_usable_size malloc_usable_size
+#define dlmalloc_footprint malloc_footprint
+#define dlindependent_calloc independent_calloc
+#define dlindependent_comalloc independent_comalloc
+#endif /* USE_DL_PREFIX */
+#if !NO_MALLINFO
+#ifndef HAVE_USR_INCLUDE_MALLOC_H
+#ifndef _MALLOC_H
+#ifndef MALLINFO_FIELD_TYPE
+#define MALLINFO_FIELD_TYPE size_t
+#endif /* MALLINFO_FIELD_TYPE */
+#ifndef STRUCT_MALLINFO_DECLARED
+#define STRUCT_MALLINFO_DECLARED 1
+struct mallinfo {
+ MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */
+ MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */
+ MALLINFO_FIELD_TYPE smblks; /* always 0 */
+ MALLINFO_FIELD_TYPE hblks; /* always 0 */
+ MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */
+ MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */
+ MALLINFO_FIELD_TYPE fsmblks; /* always 0 */
+ MALLINFO_FIELD_TYPE uordblks; /* total allocated space */
+ MALLINFO_FIELD_TYPE fordblks; /* total free space */
+ MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */
+};
+#endif /* STRUCT_MALLINFO_DECLARED */
+#endif /* _MALLOC_H */
+#endif /* HAVE_USR_INCLUDE_MALLOC_H */
+#endif /* !NO_MALLINFO */
+
+/*
+ malloc(size_t n)
+ Returns a pointer to a newly allocated chunk of at least n bytes, or
+ null if no space is available, in which case errno is set to ENOMEM
+ on ANSI C systems.
+
+ If n is zero, malloc returns a minimum-sized chunk. (The minimum
+ size is 16 bytes on most 32bit systems, and 32 bytes on 64bit
+ systems.) Note that size_t is an unsigned type, so calls with
+ arguments that would be negative if signed are interpreted as
+ requests for huge amounts of space, which will often fail. The
+ maximum supported value of n differs across systems, but is in all
+ cases less than the maximum representable value of a size_t.
+*/
+void* dlmalloc(size_t);
+
+/*
+ free(void* p)
+ Releases the chunk of memory pointed to by p, that had been previously
+ allocated using malloc or a related routine such as realloc.
+ It has no effect if p is null. If p was not malloced or already
+ freed, free(p) will by default cuase the current program to abort.
+*/
+void dlfree(void*);
+
+/*
+ calloc(size_t n_elements, size_t element_size);
+ Returns a pointer to n_elements * element_size bytes, with all locations
+ set to zero.
+*/
+void* dlcalloc(size_t, size_t);
+
+/*
+ realloc(void* p, size_t n)
+ Returns a pointer to a chunk of size n that contains the same data
+ as does chunk p up to the minimum of (n, p's size) bytes, or null
+ if no space is available.
+
+ The returned pointer may or may not be the same as p. The algorithm
+ prefers extending p in most cases when possible, otherwise it
+ employs the equivalent of a malloc-copy-free sequence.
+
+ If p is null, realloc is equivalent to malloc.
+
+ If space is not available, realloc returns null, errno is set (if on
+ ANSI) and p is NOT freed.
+
+ if n is for fewer bytes than already held by p, the newly unused
+ space is lopped off and freed if possible. realloc with a size
+ argument of zero (re)allocates a minimum-sized chunk.
+
+ The old unix realloc convention of allowing the last-free'd chunk
+ to be used as an argument to realloc is not supported.
+*/
+
+void* dlrealloc(void*, size_t);
+
+/*
+ memalign(size_t alignment, size_t n);
+ Returns a pointer to a newly allocated chunk of n bytes, aligned
+ in accord with the alignment argument.
+
+ The alignment argument should be a power of two. If the argument is
+ not a power of two, the nearest greater power is used.
+ 8-byte alignment is guaranteed by normal malloc calls, so don't
+ bother calling memalign with an argument of 8 or less.
+
+ Overreliance on memalign is a sure way to fragment space.
+*/
+void* dlmemalign(size_t, size_t);
+
+/*
+ valloc(size_t n);
+ Equivalent to memalign(pagesize, n), where pagesize is the page
+ size of the system. If the pagesize is unknown, 4096 is used.
+*/
+void* dlvalloc(size_t);
+
+/*
+ mallopt(int parameter_number, int parameter_value)
+ Sets tunable parameters The format is to provide a
+ (parameter-number, parameter-value) pair. mallopt then sets the
+ corresponding parameter to the argument value if it can (i.e., so
+ long as the value is meaningful), and returns 1 if successful else
+ 0. SVID/XPG/ANSI defines four standard param numbers for mallopt,
+ normally defined in malloc.h. None of these are use in this malloc,
+ so setting them has no effect. But this malloc also supports other
+ options in mallopt:
+
+ Symbol param # default allowed param values
+ M_TRIM_THRESHOLD -1 2*1024*1024 any (-1U disables trimming)
+ M_GRANULARITY -2 page size any power of 2 >= page size
+ M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support)
+*/
+int dlmallopt(int, int);
+
+#define M_TRIM_THRESHOLD (-1)
+#define M_GRANULARITY (-2)
+#define M_MMAP_THRESHOLD (-3)
+
+
+/*
+ malloc_footprint();
+ Returns the number of bytes obtained from the system. The total
+ number of bytes allocated by malloc, realloc etc., is less than this
+ value. Unlike mallinfo, this function returns only a precomputed
+ result, so can be called frequently to monitor memory consumption.
+ Even if locks are otherwise defined, this function does not use them,
+ so results might not be up to date.
+*/
+size_t dlmalloc_footprint();
+
+#if !NO_MALLINFO
+/*
+ mallinfo()
+ Returns (by copy) a struct containing various summary statistics:
+
+ arena: current total non-mmapped bytes allocated from system
+ ordblks: the number of free chunks
+ smblks: always zero.
+ hblks: current number of mmapped regions
+ hblkhd: total bytes held in mmapped regions
+ usmblks: the maximum total allocated space. This will be greater
+ than current total if trimming has occurred.
+ fsmblks: always zero
+ uordblks: current total allocated space (normal or mmapped)
+ fordblks: total free space
+ keepcost: the maximum number of bytes that could ideally be released
+ back to system via malloc_trim. ("ideally" means that
+ it ignores page restrictions etc.)
+
+ Because these fields are ints, but internal bookkeeping may
+ be kept as longs, the reported values may wrap around zero and
+ thus be inaccurate.
+*/
+
+struct mallinfo dlmallinfo(void);
+#endif /* NO_MALLINFO */
+
+/*
+ independent_calloc(size_t n_elements, size_t element_size, void* chunks[]);
+
+ independent_calloc is similar to calloc, but instead of returning a
+ single cleared space, it returns an array of pointers to n_elements
+ independent elements that can hold contents of size elem_size, each
+ of which starts out cleared, and can be independently freed,
+ realloc'ed etc. The elements are guaranteed to be adjacently
+ allocated (this is not guaranteed to occur with multiple callocs or
+ mallocs), which may also improve cache locality in some
+ applications.
+
+ The "chunks" argument is optional (i.e., may be null, which is
+ probably the most typical usage). If it is null, the returned array
+ is itself dynamically allocated and should also be freed when it is
+ no longer needed. Otherwise, the chunks array must be of at least
+ n_elements in length. It is filled in with the pointers to the
+ chunks.
+
+ In either case, independent_calloc returns this pointer array, or
+ null if the allocation failed. If n_elements is zero and "chunks"
+ is null, it returns a chunk representing an array with zero elements
+ (which should be freed if not wanted).
+
+ Each element must be individually freed when it is no longer
+ needed. If you'd like to instead be able to free all at once, you
+ should instead use regular calloc and assign pointers into this
+ space to represent elements. (In this case though, you cannot
+ independently free elements.)
+
+ independent_calloc simplifies and speeds up implementations of many
+ kinds of pools. It may also be useful when constructing large data
+ structures that initially have a fixed number of fixed-sized nodes,
+ but the number is not known at compile time, and some of the nodes
+ may later need to be freed. For example:
+
+ struct Node { int item; struct Node* next; };
+
+ struct Node* build_list() {
+ struct Node** pool;
+ int n = read_number_of_nodes_needed();
+ if (n <= 0) return 0;
+ pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
+ if (pool == 0) die();
+ // organize into a linked list...
+ struct Node* first = pool[0];
+ for (i = 0; i < n-1; ++i)
+ pool[i]->next = pool[i+1];
+ free(pool); // Can now free the array (or not, if it is needed later)
+ return first;
+ }
+*/
+void** dlindependent_calloc(size_t, size_t, void**);
+
+/*
+ independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]);
+
+ independent_comalloc allocates, all at once, a set of n_elements
+ chunks with sizes indicated in the "sizes" array. It returns
+ an array of pointers to these elements, each of which can be
+ independently freed, realloc'ed etc. The elements are guaranteed to
+ be adjacently allocated (this is not guaranteed to occur with
+ multiple callocs or mallocs), which may also improve cache locality
+ in some applications.
+
+ The "chunks" argument is optional (i.e., may be null). If it is null
+ the returned array is itself dynamically allocated and should also
+ be freed when it is no longer needed. Otherwise, the chunks array
+ must be of at least n_elements in length. It is filled in with the
+ pointers to the chunks.
+
+ In either case, independent_comalloc returns this pointer array, or
+ null if the allocation failed. If n_elements is zero and chunks is
+ null, it returns a chunk representing an array with zero elements
+ (which should be freed if not wanted).
+
+ Each element must be individually freed when it is no longer
+ needed. If you'd like to instead be able to free all at once, you
+ should instead use a single regular malloc, and assign pointers at
+ particular offsets in the aggregate space. (In this case though, you
+ cannot independently free elements.)
+
+ independent_comallac differs from independent_calloc in that each
+ element may have a different size, and also that it does not
+ automatically clear elements.
+
+ independent_comalloc can be used to speed up allocation in cases
+ where several structs or objects must always be allocated at the
+ same time. For example:
+
+ struct Head { ... }
+ struct Foot { ... }
+
+ void send_message(char* msg) {
+ int msglen = strlen(msg);
+ size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
+ void* chunks[3];
+ if (independent_comalloc(3, sizes, chunks) == 0)
+ die();
+ struct Head* head = (struct Head*)(chunks[0]);
+ char* body = (char*)(chunks[1]);
+ struct Foot* foot = (struct Foot*)(chunks[2]);
+ // ...
+ }
+
+ In general though, independent_comalloc is worth using only for
+ larger values of n_elements. For small values, you probably won't
+ detect enough difference from series of malloc calls to bother.
+
+ Overuse of independent_comalloc can increase overall memory usage,
+ since it cannot reuse existing noncontiguous small chunks that
+ might be available for some of the elements.
+*/
+void** dlindependent_comalloc(size_t, size_t*, void**);
+
+
+/*
+ pvalloc(size_t n);
+ Equivalent to valloc(minimum-page-that-holds(n)), that is,
+ round up n to nearest pagesize.
+ */
+void* dlpvalloc(size_t);
+
+/*
+ malloc_trim(size_t pad);
+
+ If possible, gives memory back to the system (via negative arguments
+ to sbrk) if there is unused memory at the `high' end of the malloc
+ pool or in unused MMAP segments. You can call this after freeing
+ large blocks of memory to potentially reduce the system-level memory
+ requirements of a program. However, it cannot guarantee to reduce
+ memory. Under some allocation patterns, some large free blocks of
+ memory will be locked between two used chunks, so they cannot be
+ given back to the system.
+
+ The `pad' argument to malloc_trim represents the amount of free
+ trailing space to leave untrimmed. If this argument is zero, only
+ the minimum amount of memory to maintain internal data structures
+ will be left. Non-zero arguments can be supplied to maintain enough
+ trailing space to service future expected allocations without having
+ to re-obtain memory from the system.
+
+ Malloc_trim returns 1 if it actually released any memory, else 0.
+*/
+int dlmalloc_trim(size_t);
+
+/*
+ malloc_stats();
+ Prints on stderr the amount of space obtained from the system (both
+ via sbrk and mmap), the maximum amount (which may be more than
+ current if malloc_trim and/or munmap got called), and the current
+ number of bytes allocated via malloc (or realloc, etc) but not yet
+ freed. Note that this is the number of bytes allocated, not the
+ number requested. It will be larger than the number requested
+ because of alignment and bookkeeping overhead. Because it includes
+ alignment wastage as being in use, this figure may be greater than
+ zero even when no user-level chunks are allocated.
+
+ The reported current and maximum system memory can be inaccurate if
+ a program makes other calls to system memory allocation functions
+ (normally sbrk) outside of malloc.
+
+ malloc_stats prints only the most commonly interesting statistics.
+ More information can be obtained by calling mallinfo.
+*/
+void dlmalloc_stats();
+
+#endif /* !ONLY_MSPACES */
+
+/*
+ malloc_usable_size(void* p);
+
+ Returns the number of bytes you can actually use in
+ an allocated chunk, which may be more than you requested (although
+ often not) due to alignment and minimum size constraints.
+ You can use this many bytes without worrying about
+ overwriting other allocated objects. This is not a particularly great
+ programming practice. malloc_usable_size can be more useful in
+ debugging and assertions, for example:
+
+ p = malloc(n);
+ assert(malloc_usable_size(p) >= 256);
+*/
+size_t dlmalloc_usable_size(void*);
+
+
+#if MSPACES
+
+/*
+ mspace is an opaque type representing an independent
+ region of space that supports mspace_malloc, etc.
+*/
+typedef void* mspace;
+
+/*
+ create_mspace creates and returns a new independent space with the
+ given initial capacity, or, if 0, the default granularity size. It
+ returns null if there is no system memory available to create the
+ space. If argument locked is non-zero, the space uses a separate
+ lock to control access. The capacity of the space will grow
+ dynamically as needed to service mspace_malloc requests. You can
+ control the sizes of incremental increases of this space by
+ compiling with a different DEFAULT_GRANULARITY or dynamically
+ setting with mallopt(M_GRANULARITY, value).
+*/
+mspace create_mspace(size_t capacity, int locked);
+
+/*
+ destroy_mspace destroys the given space, and attempts to return all
+ of its memory back to the system, returning the total number of
+ bytes freed. After destruction, the results of access to all memory
+ used by the space become undefined.
+*/
+size_t destroy_mspace(mspace msp);
+
+/*
+ create_mspace_with_base uses the memory supplied as the initial base
+ of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this
+ space is used for bookkeeping, so the capacity must be at least this
+ large. (Otherwise 0 is returned.) When this initial space is
+ exhausted, additional memory will be obtained from the system.
+ Destroying this space will deallocate all additionally allocated
+ space (if possible) but not the initial base.
+*/
+mspace create_mspace_with_base(void* base, size_t capacity, int locked);
+
+/*
+ mspace_track_large_chunks controls whether requests for large chunks
+ are allocated in their own untracked mmapped regions, separate from
+ others in this mspace. By default large chunks are not tracked,
+ which reduces fragmentation. However, such chunks are not
+ necessarily released to the system upon destroy_mspace. Enabling
+ tracking by setting to true may increase fragmentation, but avoids
+ leakage when relying on destroy_mspace to release all memory
+ allocated using this space. The function returns the previous
+ setting.
+*/
+int mspace_track_large_chunks(mspace msp, int enable);
+
+/*
+ mspace_malloc behaves as malloc, but operates within
+ the given space.
+*/
+void* mspace_malloc(mspace msp, size_t bytes);
+
+/*
+ mspace_free behaves as free, but operates within
+ the given space.
+
+ If compiled with FOOTERS==1, mspace_free is not actually needed.
+ free may be called instead of mspace_free because freed chunks from
+ any space are handled by their originating spaces.
+*/
+void mspace_free(mspace msp, void* mem);
+
+/*
+ mspace_realloc behaves as realloc, but operates within
+ the given space.
+
+ If compiled with FOOTERS==1, mspace_realloc is not actually
+ needed. realloc may be called instead of mspace_realloc because
+ realloced chunks from any space are handled by their originating
+ spaces.
+*/
+void* mspace_realloc(mspace msp, void* mem, size_t newsize);
+
+/*
+ mspace_calloc behaves as calloc, but operates within
+ the given space.
+*/
+void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size);
+
+/*
+ mspace_memalign behaves as memalign, but operates within
+ the given space.
+*/
+void* mspace_memalign(mspace msp, size_t alignment, size_t bytes);
+
+/*
+ mspace_independent_calloc behaves as independent_calloc, but
+ operates within the given space.
+*/
+void** mspace_independent_calloc(mspace msp, size_t n_elements,
+ size_t elem_size, void* chunks[]);
+
+/*
+ mspace_independent_comalloc behaves as independent_comalloc, but
+ operates within the given space.
+*/
+void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+ size_t sizes[], void* chunks[]);
+
+/*
+ mspace_footprint() returns the number of bytes obtained from the
+ system for this space.
+*/
+size_t mspace_footprint(mspace msp);
+
+
+#if !NO_MALLINFO
+/*
+ mspace_mallinfo behaves as mallinfo, but reports properties of
+ the given space.
+*/
+struct mallinfo mspace_mallinfo(mspace msp);
+#endif /* NO_MALLINFO */
+
+/*
+ malloc_usable_size(void* p) behaves the same as malloc_usable_size;
+*/
+ size_t mspace_usable_size(void* mem);
+
+/*
+ mspace_malloc_stats behaves as malloc_stats, but reports
+ properties of the given space.
+*/
+void mspace_malloc_stats(mspace msp);
+
+/*
+ mspace_trim behaves as malloc_trim, but
+ operates within the given space.
+*/
+int mspace_trim(mspace msp, size_t pad);
+
+/*
+ An alias for mallopt.
+*/
+int mspace_mallopt(int, int);
+
+#endif /* MSPACES */
+
+#ifdef __cplusplus
+}; /* end of extern "C" */
+#endif
+
+#endif /* MALLOC_280_H */
diff --git a/unsupported/test/mpreal/mpreal.cpp b/unsupported/test/mpreal/mpreal.cpp new file mode 100644 index 000000000..5c23544ef --- /dev/null +++ b/unsupported/test/mpreal/mpreal.cpp @@ -0,0 +1,597 @@ +/*
+ Multi-precision real number class. C++ interface fo MPFR library.
+ Project homepage: http://www.holoborodko.com/pavel/
+ Contact e-mail: pavel@holoborodko.com
+
+ Copyright (c) 2008-2011 Pavel Holoborodko
+
+ Core Developers:
+ Pavel Holoborodko, Dmitriy Gubanov, Konstantin Holoborodko.
+
+ Contributors:
+ Brian Gladman, Helmut Jarausch, Fokko Beekhof, Ulrich Mutze,
+ Heinz van Saanen, Pere Constans, Peter van Hoof, Gael Guennebaud,
+ Tsai Chia Cheng, Alexei Zubanov.
+
+ ****************************************************************************
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+ ****************************************************************************
+ ****************************************************************************
+ Redistribution and use in source and binary forms, with or without
+ modification, are permitted provided that the following conditions
+ are met:
+
+ 1. Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ 2. Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+ 3. The name of the author may be used to endorse or promote products
+ derived from this software without specific prior written permission.
+
+ THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGE.
+*/
+#include <cstring>
+#include "mpreal.h"
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+#include "dlmalloc.h"
+#endif
+
+using std::ws;
+using std::cerr;
+using std::endl;
+using std::string;
+using std::ostream;
+using std::istream;
+
+namespace mpfr{
+
+mp_rnd_t mpreal::default_rnd = MPFR_RNDN; //(mpfr_get_default_rounding_mode)();
+mp_prec_t mpreal::default_prec = 64; //(mpfr_get_default_prec)();
+int mpreal::default_base = 10;
+int mpreal::double_bits = -1;
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+bool mpreal::is_custom_malloc = false;
+#endif
+
+// Default constructor: creates mp number and initializes it to 0.
+mpreal::mpreal()
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,default_prec);
+ mpfr_set_ui(mp,0,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const mpreal& u)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,mpfr_get_prec(u.mp));
+ mpfr_set(mp,u.mp,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const mpfr_t u)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,mpfr_get_prec(u));
+ mpfr_set(mp,u,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const mpf_t u)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,(mp_prec_t) mpf_get_prec(u)); // (gmp: mp_bitcnt_t) unsigned long -> long (mpfr: mp_prec_t)
+ mpfr_set_f(mp,u,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const mpz_t u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_z(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const mpq_t u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_q(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const double u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ if(double_bits == -1 || fits_in_bits(u, double_bits))
+ {
+ mpfr_init2(mp,prec);
+ mpfr_set_d(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ }
+ else
+ throw conversion_overflow();
+}
+
+mpreal::mpreal(const long double u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_ld(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const unsigned long int u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_ui(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const unsigned int u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_ui(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const long int u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_si(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const int u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_si(mp,u,mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+mpreal::mpreal(const uint64_t u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_uj(mp, u, mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const int64_t u, mp_prec_t prec, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_sj(mp, u, mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+#endif
+
+mpreal::mpreal(const char* s, mp_prec_t prec, int base, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_str(mp, s, base, mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::mpreal(const std::string& s, mp_prec_t prec, int base, mp_rnd_t mode)
+{
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ mpfr_init2(mp,prec);
+ mpfr_set_str(mp, s.c_str(), base, mode);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+mpreal::~mpreal()
+{
+ mpfr_clear(mp);
+}
+
+// Operators - Assignment
+mpreal& mpreal::operator=(const char* s)
+{
+ mpfr_t t;
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ if(0==mpfr_init_set_str(t,s,default_base,default_rnd))
+ {
+ // We will rewrite mp anyway, so flash it and resize
+ mpfr_set_prec(mp,mpfr_get_prec(t));
+ mpfr_set(mp,t,mpreal::default_rnd);
+ mpfr_clear(t);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+
+ }else{
+ mpfr_clear(t);
+ }
+
+ return *this;
+}
+
+const mpreal fma (const mpreal& v1, const mpreal& v2, const mpreal& v3, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t p1, p2, p3;
+
+ p1 = v1.get_prec();
+ p2 = v2.get_prec();
+ p3 = v3.get_prec();
+
+ a.set_prec(p3>p2?(p3>p1?p3:p1):(p2>p1?p2:p1));
+
+ mpfr_fma(a.mp,v1.mp,v2.mp,v3.mp,rnd_mode);
+ return a;
+}
+
+const mpreal fms (const mpreal& v1, const mpreal& v2, const mpreal& v3, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t p1, p2, p3;
+
+ p1 = v1.get_prec();
+ p2 = v2.get_prec();
+ p3 = v3.get_prec();
+
+ a.set_prec(p3>p2?(p3>p1?p3:p1):(p2>p1?p2:p1));
+
+ mpfr_fms(a.mp,v1.mp,v2.mp,v3.mp,rnd_mode);
+ return a;
+}
+
+const mpreal agm (const mpreal& v1, const mpreal& v2, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t p1, p2;
+
+ p1 = v1.get_prec();
+ p2 = v2.get_prec();
+
+ a.set_prec(p1>p2?p1:p2);
+
+ mpfr_agm(a.mp, v1.mp, v2.mp, rnd_mode);
+
+ return a;
+}
+
+const mpreal sum (const mpreal tab[], unsigned long int n, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ mpfr_ptr* t;
+ unsigned long int i;
+
+ t = new mpfr_ptr[n];
+ for (i=0;i<n;i++) t[i] = (mpfr_ptr)tab[i].mp;
+ mpfr_sum(x.mp,t,n,rnd_mode);
+ delete[] t;
+ return x;
+}
+
+const mpreal remquo (long* q, const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t yp, xp;
+
+ yp = y.get_prec();
+ xp = x.get_prec();
+
+ a.set_prec(yp>xp?yp:xp);
+
+ mpfr_remquo(a.mp,q, x.mp, y.mp, rnd_mode);
+
+ return a;
+}
+
+template <class T>
+std::string toString(T t, std::ios_base & (*f)(std::ios_base&))
+{
+ std::ostringstream oss;
+ oss << f << t;
+ return oss.str();
+}
+
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+
+std::string mpreal::toString(const std::string& format) const
+{
+ char *s = NULL;
+ string out;
+
+ if( !format.empty() )
+ {
+ if(!(mpfr_asprintf(&s,format.c_str(),mp) < 0))
+ {
+ out = std::string(s);
+
+ mpfr_free_str(s);
+ }
+ }
+
+ return out;
+}
+
+#endif
+
+std::string mpreal::toString(int n, int b, mp_rnd_t mode) const
+{
+ (void)b;
+ (void)mode;
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+
+ // Use MPFR native function for output
+ char format[128];
+ int digits;
+
+ digits = n > 0 ? n : bits2digits(mpfr_get_prec(mp));
+
+ sprintf(format,"%%.%dRNg",digits); // Default format
+
+ return toString(std::string(format));
+
+#else
+
+ char *s, *ns = NULL;
+ size_t slen, nslen;
+ mp_exp_t exp;
+ string out;
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ set_custom_malloc();
+#endif
+
+ if(mpfr_inf_p(mp))
+ {
+ if(mpfr_sgn(mp)>0) return "+Inf";
+ else return "-Inf";
+ }
+
+ if(mpfr_zero_p(mp)) return "0";
+ if(mpfr_nan_p(mp)) return "NaN";
+
+ s = mpfr_get_str(NULL,&exp,b,0,mp,mode);
+ ns = mpfr_get_str(NULL,&exp,b,n,mp,mode);
+
+ if(s!=NULL && ns!=NULL)
+ {
+ slen = strlen(s);
+ nslen = strlen(ns);
+ if(nslen<=slen)
+ {
+ mpfr_free_str(s);
+ s = ns;
+ slen = nslen;
+ }
+ else {
+ mpfr_free_str(ns);
+ }
+
+ // Make human eye-friendly formatting if possible
+ if (exp>0 && static_cast<size_t>(exp)<slen)
+ {
+ if(s[0]=='-')
+ {
+ // Remove zeros starting from right end
+ char* ptr = s+slen-1;
+ while (*ptr=='0' && ptr>s+exp) ptr--;
+
+ if(ptr==s+exp) out = string(s,exp+1);
+ else out = string(s,exp+1)+'.'+string(s+exp+1,ptr-(s+exp+1)+1);
+
+ //out = string(s,exp+1)+'.'+string(s+exp+1);
+ }
+ else
+ {
+ // Remove zeros starting from right end
+ char* ptr = s+slen-1;
+ while (*ptr=='0' && ptr>s+exp-1) ptr--;
+
+ if(ptr==s+exp-1) out = string(s,exp);
+ else out = string(s,exp)+'.'+string(s+exp,ptr-(s+exp)+1);
+
+ //out = string(s,exp)+'.'+string(s+exp);
+ }
+
+ }else{ // exp<0 || exp>slen
+ if(s[0]=='-')
+ {
+ // Remove zeros starting from right end
+ char* ptr = s+slen-1;
+ while (*ptr=='0' && ptr>s+1) ptr--;
+
+ if(ptr==s+1) out = string(s,2);
+ else out = string(s,2)+'.'+string(s+2,ptr-(s+2)+1);
+
+ //out = string(s,2)+'.'+string(s+2);
+ }
+ else
+ {
+ // Remove zeros starting from right end
+ char* ptr = s+slen-1;
+ while (*ptr=='0' && ptr>s) ptr--;
+
+ if(ptr==s) out = string(s,1);
+ else out = string(s,1)+'.'+string(s+1,ptr-(s+1)+1);
+
+ //out = string(s,1)+'.'+string(s+1);
+ }
+
+ // Make final string
+ if(--exp)
+ {
+ if(exp>0) out += "e+"+mpfr::toString<mp_exp_t>(exp,std::dec);
+ else out += "e"+mpfr::toString<mp_exp_t>(exp,std::dec);
+ }
+ }
+
+ mpfr_free_str(s);
+ return out;
+ }else{
+ return "conversion error!";
+ }
+#endif
+}
+
+
+//////////////////////////////////////////////////////////////////////////
+// I/O
+ostream& operator<<(ostream& os, const mpreal& v)
+{
+ return os<<v.toString(static_cast<int>(os.precision()));
+}
+
+istream& operator>>(istream &is, mpreal& v)
+{
+ string tmp;
+ is >> tmp;
+ mpfr_set_str(v.mp, tmp.c_str(),mpreal::default_base,mpreal::default_rnd);
+ return is;
+}
+
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+ // Optimized dynamic memory allocation/(re-)deallocation.
+ void * mpreal::mpreal_allocate(size_t alloc_size)
+ {
+ return(dlmalloc(alloc_size));
+ }
+
+ void * mpreal::mpreal_reallocate(void *ptr, size_t old_size, size_t new_size)
+ {
+ return(dlrealloc(ptr,new_size));
+ }
+
+ void mpreal::mpreal_free(void *ptr, size_t size)
+ {
+ dlfree(ptr);
+ }
+
+ inline void mpreal::set_custom_malloc(void)
+ {
+ if(!is_custom_malloc)
+ {
+ mp_set_memory_functions(mpreal_allocate,mpreal_reallocate,mpreal_free);
+ is_custom_malloc = true;
+ }
+ }
+#endif
+
+}
+
diff --git a/unsupported/test/mpreal/mpreal.h b/unsupported/test/mpreal/mpreal.h new file mode 100644 index 000000000..c640af947 --- /dev/null +++ b/unsupported/test/mpreal/mpreal.h @@ -0,0 +1,2735 @@ +/*
+ Multi-precision real number class. C++ interface for MPFR library.
+ Project homepage: http://www.holoborodko.com/pavel/
+ Contact e-mail: pavel@holoborodko.com
+
+ Copyright (c) 2008-2012 Pavel Holoborodko
+
+ Core Developers:
+ Pavel Holoborodko, Dmitriy Gubanov, Konstantin Holoborodko.
+
+ Contributors:
+ Brian Gladman, Helmut Jarausch, Fokko Beekhof, Ulrich Mutze,
+ Heinz van Saanen, Pere Constans, Peter van Hoof, Gael Guennebaud,
+ Tsai Chia Cheng, Alexei Zubanov.
+
+ ****************************************************************************
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+ ****************************************************************************
+ Redistribution and use in source and binary forms, with or without
+ modification, are permitted provided that the following conditions
+ are met:
+
+ 1. Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ 2. Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+ 3. The name of the author may be used to endorse or promote products
+ derived from this software without specific prior written permission.
+
+ THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+ FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGE.
+*/
+
+#ifndef __MPREAL_H__
+#define __MPREAL_H__
+
+#include <string>
+#include <iostream>
+#include <sstream>
+#include <stdexcept>
+#include <cfloat>
+#include <cmath>
+
+// Options
+#define MPREAL_HAVE_INT64_SUPPORT // int64_t support: available only for MSVC 2010 & GCC
+#define MPREAL_HAVE_MSVC_DEBUGVIEW // Enable Debugger Visualizer (valid only for MSVC in "Debug" builds)
+
+// Detect compiler using signatures from http://predef.sourceforge.net/
+#if defined(__GNUC__) && defined(__INTEL_COMPILER)
+ #define IsInf(x) isinf(x) // Intel ICC compiler on Linux
+
+#elif defined(_MSC_VER) // Microsoft Visual C++
+ #define IsInf(x) (!_finite(x))
+
+#elif defined(__GNUC__)
+ #define IsInf(x) std::isinf(x) // GNU C/C++
+
+#else
+ #define IsInf(x) std::isinf(x) // Unknown compiler, just hope for C99 conformance
+#endif
+
+#if defined(MPREAL_HAVE_INT64_SUPPORT)
+
+ #define MPFR_USE_INTMAX_T // should be defined before mpfr.h
+
+ #if defined(_MSC_VER) // <stdint.h> is available only in msvc2010!
+ #if (_MSC_VER >= 1600)
+ #include <stdint.h>
+ #else // MPFR relies on intmax_t which is available only in msvc2010
+ #undef MPREAL_HAVE_INT64_SUPPORT // Besides, MPFR - MPIR have to be compiled with msvc2010
+ #undef MPFR_USE_INTMAX_T // Since we cannot detect this, disable x64 by default
+ // Someone should change this manually if needed.
+ #endif
+ #endif
+
+ #if defined (__MINGW32__) || defined(__MINGW64__)
+ #include <stdint.h> // equivalent to msvc2010
+ #elif defined (__GNUC__)
+ #if defined(__amd64__) || defined(__amd64) || defined(__x86_64__) || defined(__x86_64)
+ #undef MPREAL_HAVE_INT64_SUPPORT // remove all shaman dances for x64 builds since
+ #undef MPFR_USE_INTMAX_T // GCC already support x64 as of "long int" is 64-bit integer, nothing left to do
+ #else
+ #include <stdint.h> // use int64_t, uint64_t otherwise.
+ #endif
+ #endif
+
+#endif
+
+#if defined(MPREAL_HAVE_MSVC_DEBUGVIEW) && defined(_MSC_VER) && defined(_DEBUG)
+#define MPREAL_MSVC_DEBUGVIEW_CODE DebugView = toString()
+ #define MPREAL_MSVC_DEBUGVIEW_DATA std::string DebugView
+#else
+ #define MPREAL_MSVC_DEBUGVIEW_CODE
+ #define MPREAL_MSVC_DEBUGVIEW_DATA
+#endif
+
+#include <mpfr.h>
+
+#if (MPFR_VERSION < MPFR_VERSION_NUM(3,0,0))
+ #include <cstdlib> // needed for random()
+#endif
+
+namespace mpfr {
+
+class mpreal {
+private:
+ mpfr_t mp;
+
+public:
+ static mp_rnd_t default_rnd;
+ static mp_prec_t default_prec;
+ static int default_base;
+ static int double_bits;
+
+public:
+ // Constructors && type conversion
+ mpreal();
+ mpreal(const mpreal& u);
+ mpreal(const mpfr_t u);
+ mpreal(const mpf_t u);
+ mpreal(const mpz_t u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const mpq_t u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const double u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const long double u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const unsigned long int u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const unsigned int u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const long int u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const int u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+ mpreal(const uint64_t u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+ mpreal(const int64_t u, mp_prec_t prec = default_prec, mp_rnd_t mode = default_rnd);
+#endif
+
+ mpreal(const char* s, mp_prec_t prec = default_prec, int base = default_base, mp_rnd_t mode = default_rnd);
+ mpreal(const std::string& s, mp_prec_t prec = default_prec, int base = default_base, mp_rnd_t mode = default_rnd);
+
+ ~mpreal();
+
+ // Operations
+ // =
+ // +, -, *, /, ++, --, <<, >>
+ // *=, +=, -=, /=,
+ // <, >, ==, <=, >=
+
+ // =
+ mpreal& operator=(const mpreal& v);
+ mpreal& operator=(const mpf_t v);
+ mpreal& operator=(const mpz_t v);
+ mpreal& operator=(const mpq_t v);
+ mpreal& operator=(const long double v);
+ mpreal& operator=(const double v);
+ mpreal& operator=(const unsigned long int v);
+ mpreal& operator=(const unsigned int v);
+ mpreal& operator=(const long int v);
+ mpreal& operator=(const int v);
+ mpreal& operator=(const char* s);
+
+ // +
+ mpreal& operator+=(const mpreal& v);
+ mpreal& operator+=(const mpf_t v);
+ mpreal& operator+=(const mpz_t v);
+ mpreal& operator+=(const mpq_t v);
+ mpreal& operator+=(const long double u);
+ mpreal& operator+=(const double u);
+ mpreal& operator+=(const unsigned long int u);
+ mpreal& operator+=(const unsigned int u);
+ mpreal& operator+=(const long int u);
+ mpreal& operator+=(const int u);
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+ mpreal& operator+=(const int64_t u);
+ mpreal& operator+=(const uint64_t u);
+ mpreal& operator-=(const int64_t u);
+ mpreal& operator-=(const uint64_t u);
+ mpreal& operator*=(const int64_t u);
+ mpreal& operator*=(const uint64_t u);
+ mpreal& operator/=(const int64_t u);
+ mpreal& operator/=(const uint64_t u);
+#endif
+
+ const mpreal operator+() const;
+ mpreal& operator++ ();
+ const mpreal operator++ (int);
+
+ // -
+ mpreal& operator-=(const mpreal& v);
+ mpreal& operator-=(const mpz_t v);
+ mpreal& operator-=(const mpq_t v);
+ mpreal& operator-=(const long double u);
+ mpreal& operator-=(const double u);
+ mpreal& operator-=(const unsigned long int u);
+ mpreal& operator-=(const unsigned int u);
+ mpreal& operator-=(const long int u);
+ mpreal& operator-=(const int u);
+ const mpreal operator-() const;
+ friend const mpreal operator-(const unsigned long int b, const mpreal& a);
+ friend const mpreal operator-(const unsigned int b, const mpreal& a);
+ friend const mpreal operator-(const long int b, const mpreal& a);
+ friend const mpreal operator-(const int b, const mpreal& a);
+ friend const mpreal operator-(const double b, const mpreal& a);
+ mpreal& operator-- ();
+ const mpreal operator-- (int);
+
+ // *
+ mpreal& operator*=(const mpreal& v);
+ mpreal& operator*=(const mpz_t v);
+ mpreal& operator*=(const mpq_t v);
+ mpreal& operator*=(const long double v);
+ mpreal& operator*=(const double v);
+ mpreal& operator*=(const unsigned long int v);
+ mpreal& operator*=(const unsigned int v);
+ mpreal& operator*=(const long int v);
+ mpreal& operator*=(const int v);
+
+ // /
+ mpreal& operator/=(const mpreal& v);
+ mpreal& operator/=(const mpz_t v);
+ mpreal& operator/=(const mpq_t v);
+ mpreal& operator/=(const long double v);
+ mpreal& operator/=(const double v);
+ mpreal& operator/=(const unsigned long int v);
+ mpreal& operator/=(const unsigned int v);
+ mpreal& operator/=(const long int v);
+ mpreal& operator/=(const int v);
+ friend const mpreal operator/(const unsigned long int b, const mpreal& a);
+ friend const mpreal operator/(const unsigned int b, const mpreal& a);
+ friend const mpreal operator/(const long int b, const mpreal& a);
+ friend const mpreal operator/(const int b, const mpreal& a);
+ friend const mpreal operator/(const double b, const mpreal& a);
+
+ //<<= Fast Multiplication by 2^u
+ mpreal& operator<<=(const unsigned long int u);
+ mpreal& operator<<=(const unsigned int u);
+ mpreal& operator<<=(const long int u);
+ mpreal& operator<<=(const int u);
+
+ //>>= Fast Division by 2^u
+ mpreal& operator>>=(const unsigned long int u);
+ mpreal& operator>>=(const unsigned int u);
+ mpreal& operator>>=(const long int u);
+ mpreal& operator>>=(const int u);
+
+ // Boolean Operators
+ friend bool operator > (const mpreal& a, const mpreal& b);
+ friend bool operator >= (const mpreal& a, const mpreal& b);
+ friend bool operator < (const mpreal& a, const mpreal& b);
+ friend bool operator <= (const mpreal& a, const mpreal& b);
+ friend bool operator == (const mpreal& a, const mpreal& b);
+ friend bool operator != (const mpreal& a, const mpreal& b);
+
+ // Optimized specializations for boolean operators
+ friend bool operator == (const mpreal& a, const unsigned long int b);
+ friend bool operator == (const mpreal& a, const unsigned int b);
+ friend bool operator == (const mpreal& a, const long int b);
+ friend bool operator == (const mpreal& a, const int b);
+ friend bool operator == (const mpreal& a, const long double b);
+ friend bool operator == (const mpreal& a, const double b);
+
+ // Type Conversion operators
+ long toLong() const;
+ unsigned long toULong() const;
+ double toDouble() const;
+ long double toLDouble() const;
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+ int64_t toInt64() const;
+ uint64_t toUInt64() const;
+#endif
+
+ // Get raw pointers
+ ::mpfr_ptr mpfr_ptr();
+ ::mpfr_srcptr mpfr_srcptr() const;
+
+ // Convert mpreal to string with n significant digits in base b
+ // n = 0 -> convert with the maximum available digits
+ std::string toString(int n = 0, int b = default_base, mp_rnd_t mode = default_rnd) const;
+
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ std::string toString(const std::string& format) const;
+#endif
+
+ // Math Functions
+ friend const mpreal sqr (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sqrt(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sqrt(const unsigned long int v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal cbrt(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal root(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const mpreal& a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const mpreal& a, const mpz_t b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const mpreal& a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const mpreal& a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const unsigned long int a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal pow (const unsigned long int a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal fabs(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal abs(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal dim(const mpreal& a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend inline const mpreal mul_2ui(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend inline const mpreal mul_2si(const mpreal& v, long int k, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend inline const mpreal div_2ui(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend inline const mpreal div_2si(const mpreal& v, long int k, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend int cmpabs(const mpreal& a,const mpreal& b);
+
+ friend const mpreal log (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal log2 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal log10(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal exp (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal exp2 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal exp10(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal log1p(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal expm1(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal cos(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sin(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal tan(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sec(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal csc(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal cot(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend int sin_cos(mpreal& s, mpreal& c, const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal acos (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal asin (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal atan (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal atan2 (const mpreal& y, const mpreal& x, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal acot (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal asec (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal acsc (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal cosh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sinh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal tanh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sech (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal csch (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal coth (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal acosh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal asinh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal atanh (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal acoth (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal asech (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal acsch (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal hypot (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal fac_ui (unsigned long int v, mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal eint (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ friend const mpreal gamma (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal lngamma (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal lgamma (const mpreal& v, int *signp = 0, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal zeta (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal erf (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal erfc (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal besselj0 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal besselj1 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal besseljn (long n, const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal bessely0 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal bessely1 (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal besselyn (long n, const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal fma (const mpreal& v1, const mpreal& v2, const mpreal& v3, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal fms (const mpreal& v1, const mpreal& v2, const mpreal& v3, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal agm (const mpreal& v1, const mpreal& v2, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal sum (const mpreal tab[], unsigned long int n, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend int sgn(const mpreal& v); // -1 or +1
+
+// MPFR 2.4.0 Specifics
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ friend int sinh_cosh(mpreal& s, mpreal& c, const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal li2(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal fmod (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal rec_sqrt(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+#endif
+
+// MPFR 3.0.0 Specifics
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(3,0,0))
+ friend const mpreal digamma(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal ai(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal urandom (gmp_randstate_t& state,mp_rnd_t rnd_mode = mpreal::default_rnd); // use gmp_randinit_default() to init state, gmp_randclear() to clear
+ friend bool isregular(const mpreal& v);
+#endif
+
+ // Uniformly distributed random number generation in [0,1] using
+ // Mersenne-Twister algorithm by default.
+ // Use parameter to setup seed, e.g.: random((unsigned)time(NULL))
+ // Check urandom() for more precise control.
+ friend const mpreal random(unsigned int seed = 0);
+
+ // Exponent and mantissa manipulation
+ friend const mpreal frexp(const mpreal& v, mp_exp_t* exp);
+ friend const mpreal ldexp(const mpreal& v, mp_exp_t exp);
+
+ // Splits mpreal value into fractional and integer parts.
+ // Returns fractional part and stores integer part in n.
+ friend const mpreal modf(const mpreal& v, mpreal& n);
+
+ // Constants
+ // don't forget to call mpfr_free_cache() for every thread where you are using const-functions
+ friend const mpreal const_log2 (mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal const_pi (mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal const_euler (mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal const_catalan (mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ // returns +inf iff sign>=0 otherwise -inf
+ friend const mpreal const_infinity(int sign = 1, mp_prec_t prec = mpreal::default_prec, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ // Output/ Input
+ friend std::ostream& operator<<(std::ostream& os, const mpreal& v);
+ friend std::istream& operator>>(std::istream& is, mpreal& v);
+
+ // Integer Related Functions
+ friend const mpreal rint (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal ceil (const mpreal& v);
+ friend const mpreal floor(const mpreal& v);
+ friend const mpreal round(const mpreal& v);
+ friend const mpreal trunc(const mpreal& v);
+ friend const mpreal rint_ceil (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal rint_floor(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal rint_round(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal rint_trunc(const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal frac (const mpreal& v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal remainder (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = mpreal::default_rnd);
+ friend const mpreal remquo (long* q, const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+ // Miscellaneous Functions
+ friend const mpreal nexttoward (const mpreal& x, const mpreal& y);
+ friend const mpreal nextabove (const mpreal& x);
+ friend const mpreal nextbelow (const mpreal& x);
+
+ // use gmp_randinit_default() to init state, gmp_randclear() to clear
+ friend const mpreal urandomb (gmp_randstate_t& state);
+
+// MPFR < 2.4.2 Specifics
+#if (MPFR_VERSION <= MPFR_VERSION_NUM(2,4,2))
+ friend const mpreal random2 (mp_size_t size, mp_exp_t exp);
+#endif
+
+ // Instance Checkers
+ friend bool isnan (const mpreal& v);
+ friend bool isinf (const mpreal& v);
+ friend bool isfinite(const mpreal& v);
+
+ friend bool isnum(const mpreal& v);
+ friend bool iszero(const mpreal& v);
+ friend bool isint(const mpreal& v);
+
+ // Set/Get instance properties
+ inline mp_prec_t get_prec() const;
+ inline void set_prec(mp_prec_t prec, mp_rnd_t rnd_mode = default_rnd); // Change precision with rounding mode
+
+ // Aliases for get_prec(), set_prec() - needed for compatibility with std::complex<mpreal> interface
+ inline mpreal& setPrecision(int Precision, mp_rnd_t RoundingMode = (mpfr_get_default_rounding_mode)());
+ inline int getPrecision() const;
+
+ // Set mpreal to +/- inf, NaN, +/-0
+ mpreal& setInf (int Sign = +1);
+ mpreal& setNan ();
+ mpreal& setZero (int Sign = +1);
+ mpreal& setSign (int Sign, mp_rnd_t RoundingMode = (mpfr_get_default_rounding_mode)());
+
+ //Exponent
+ mp_exp_t get_exp();
+ int set_exp(mp_exp_t e);
+ int check_range (int t, mp_rnd_t rnd_mode = default_rnd);
+ int subnormalize (int t,mp_rnd_t rnd_mode = default_rnd);
+
+ // Inexact conversion from float
+ inline bool fits_in_bits(double x, int n);
+
+ // Set/Get global properties
+ static void set_default_prec(mp_prec_t prec);
+ static mp_prec_t get_default_prec();
+ static void set_default_base(int base);
+ static int get_default_base();
+ static void set_double_bits(int dbits);
+ static int get_double_bits();
+ static void set_default_rnd(mp_rnd_t rnd_mode);
+ static mp_rnd_t get_default_rnd();
+ static mp_exp_t get_emin (void);
+ static mp_exp_t get_emax (void);
+ static mp_exp_t get_emin_min (void);
+ static mp_exp_t get_emin_max (void);
+ static mp_exp_t get_emax_min (void);
+ static mp_exp_t get_emax_max (void);
+ static int set_emin (mp_exp_t exp);
+ static int set_emax (mp_exp_t exp);
+
+ // Efficient swapping of two mpreal values
+ friend void swap(mpreal& x, mpreal& y);
+
+ //Min Max - macros is evil. Needed for systems which defines max and min globally as macros (e.g. Windows)
+ //Hope that globally defined macros use > < operations only
+ friend const mpreal fmax(const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = default_rnd);
+ friend const mpreal fmin(const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode = default_rnd);
+
+#if defined (MPREAL_HAVE_CUSTOM_MPFR_MALLOC)
+
+private:
+ // Optimized dynamic memory allocation/(re-)deallocation.
+ static bool is_custom_malloc;
+ static void *mpreal_allocate (size_t alloc_size);
+ static void *mpreal_reallocate (void *ptr, size_t old_size, size_t new_size);
+ static void mpreal_free (void *ptr, size_t size);
+ inline static void set_custom_malloc (void);
+
+#endif
+
+
+private:
+ // Human friendly Debug Preview in Visual Studio.
+ // Put one of these lines:
+ //
+ // mpfr::mpreal=<DebugView> ; Show value only
+ // mpfr::mpreal=<DebugView>, <mp[0]._mpfr_prec,u>bits ; Show value & precision
+ //
+ // at the beginning of
+ // [Visual Studio Installation Folder]\Common7\Packages\Debugger\autoexp.dat
+ MPREAL_MSVC_DEBUGVIEW_DATA
+};
+
+//////////////////////////////////////////////////////////////////////////
+// Exceptions
+class conversion_overflow : public std::exception {
+public:
+ std::string why() { return "inexact conversion from floating point"; }
+};
+
+namespace internal{
+
+ // Use SFINAE to restrict arithmetic operations instantiation only for numeric types
+ // This is needed for smooth integration with libraries based on expression templates
+ template <typename ArgumentType> struct result_type {};
+
+ template <> struct result_type<mpreal> {typedef mpreal type;};
+ template <> struct result_type<mpz_t> {typedef mpreal type;};
+ template <> struct result_type<mpq_t> {typedef mpreal type;};
+ template <> struct result_type<long double> {typedef mpreal type;};
+ template <> struct result_type<double> {typedef mpreal type;};
+ template <> struct result_type<unsigned long int> {typedef mpreal type;};
+ template <> struct result_type<unsigned int> {typedef mpreal type;};
+ template <> struct result_type<long int> {typedef mpreal type;};
+ template <> struct result_type<int> {typedef mpreal type;};
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+ template <> struct result_type<int64_t > {typedef mpreal type;};
+ template <> struct result_type<uint64_t > {typedef mpreal type;};
+#endif
+}
+
+// + Addition
+template <typename Rhs>
+inline const typename internal::result_type<Rhs>::type
+ operator+(const mpreal& lhs, const Rhs& rhs){ return mpreal(lhs) += rhs; }
+
+template <typename Lhs>
+inline const typename internal::result_type<Lhs>::type
+ operator+(const Lhs& lhs, const mpreal& rhs){ return mpreal(rhs) += lhs; }
+
+// - Subtraction
+template <typename Rhs>
+inline const typename internal::result_type<Rhs>::type
+ operator-(const mpreal& lhs, const Rhs& rhs){ return mpreal(lhs) -= rhs; }
+
+template <typename Lhs>
+inline const typename internal::result_type<Lhs>::type
+ operator-(const Lhs& lhs, const mpreal& rhs){ return mpreal(lhs) -= rhs; }
+
+// * Multiplication
+template <typename Rhs>
+inline const typename internal::result_type<Rhs>::type
+ operator*(const mpreal& lhs, const Rhs& rhs){ return mpreal(lhs) *= rhs; }
+
+template <typename Lhs>
+inline const typename internal::result_type<Lhs>::type
+ operator*(const Lhs& lhs, const mpreal& rhs){ return mpreal(rhs) *= lhs; }
+
+// / Division
+template <typename Rhs>
+inline const typename internal::result_type<Rhs>::type
+ operator/(const mpreal& lhs, const Rhs& rhs){ return mpreal(lhs) /= rhs; }
+
+template <typename Lhs>
+inline const typename internal::result_type<Lhs>::type
+ operator/(const Lhs& lhs, const mpreal& rhs){ return mpreal(lhs) /= rhs; }
+
+//////////////////////////////////////////////////////////////////////////
+// sqrt
+const mpreal sqrt(const unsigned int v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal sqrt(const long int v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal sqrt(const int v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal sqrt(const long double v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal sqrt(const double v, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+//////////////////////////////////////////////////////////////////////////
+// pow
+const mpreal pow(const mpreal& a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const mpreal& a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const mpreal& a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const mpreal& a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const unsigned int a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long double a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const double a, const mpreal& b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const unsigned long int a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned long int a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned long int a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned long int a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned long int a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const unsigned int a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned int a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned int a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned int a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned int a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const unsigned int a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const long int a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long int a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const int a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const int a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const long double a, const long double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long double a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long double a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long double a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const long double a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+const mpreal pow(const double a, const double b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const double a, const unsigned long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const double a, const unsigned int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const double a, const long int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+const mpreal pow(const double a, const int b, mp_rnd_t rnd_mode = mpreal::default_rnd);
+
+//////////////////////////////////////////////////////////////////////////
+// Estimate machine epsilon for the given precision
+// Returns smallest eps such that 1.0 + eps != 1.0
+inline const mpreal machine_epsilon(mp_prec_t prec = mpreal::get_default_prec());
+
+// Returns the positive distance from abs(x) to the next larger in magnitude floating point number of the same precision as x
+inline const mpreal machine_epsilon(const mpreal& x);
+
+inline const mpreal mpreal_min(mp_prec_t prec = mpreal::get_default_prec());
+inline const mpreal mpreal_max(mp_prec_t prec = mpreal::get_default_prec());
+inline bool isEqualFuzzy(const mpreal& a, const mpreal& b, const mpreal& eps);
+inline bool isEqualUlps(const mpreal& a, const mpreal& b, int maxUlps);
+
+//////////////////////////////////////////////////////////////////////////
+// Bits - decimal digits relation
+// bits = ceil(digits*log[2](10))
+// digits = floor(bits*log[10](2))
+
+inline mp_prec_t digits2bits(int d);
+inline int bits2digits(mp_prec_t b);
+
+//////////////////////////////////////////////////////////////////////////
+// min, max
+const mpreal (max)(const mpreal& x, const mpreal& y);
+const mpreal (min)(const mpreal& x, const mpreal& y);
+
+//////////////////////////////////////////////////////////////////////////
+// Implementation
+//////////////////////////////////////////////////////////////////////////
+
+//////////////////////////////////////////////////////////////////////////
+// Operators - Assignment
+inline mpreal& mpreal::operator=(const mpreal& v)
+{
+ if (this != &v)
+ {
+ mpfr_clear(mp);
+ mpfr_init2(mp,mpfr_get_prec(v.mp));
+ mpfr_set(mp,v.mp,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ }
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const mpf_t v)
+{
+ mpfr_set_f(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const mpz_t v)
+{
+ mpfr_set_z(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const mpq_t v)
+{
+ mpfr_set_q(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const long double v)
+{
+ mpfr_set_ld(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const double v)
+{
+ if(double_bits == -1 || fits_in_bits(v, double_bits))
+ {
+ mpfr_set_d(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ }
+ else
+ throw conversion_overflow();
+
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const unsigned long int v)
+{
+ mpfr_set_ui(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const unsigned int v)
+{
+ mpfr_set_ui(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const long int v)
+{
+ mpfr_set_si(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator=(const int v)
+{
+ mpfr_set_si(mp,v,default_rnd);
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// + Addition
+inline mpreal& mpreal::operator+=(const mpreal& v)
+{
+ mpfr_add(mp,mp,v.mp,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const mpf_t u)
+{
+ *this += mpreal(u);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const mpz_t u)
+{
+ mpfr_add_z(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const mpq_t u)
+{
+ mpfr_add_q(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+= (const long double u)
+{
+ *this += mpreal(u);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+= (const double u)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpfr_add_d(mp,mp,u,default_rnd);
+#else
+ *this += mpreal(u);
+#endif
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const unsigned long int u)
+{
+ mpfr_add_ui(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const unsigned int u)
+{
+ mpfr_add_ui(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const long int u)
+{
+ mpfr_add_si(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator+=(const int u)
+{
+ mpfr_add_si(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+inline mpreal& mpreal::operator+=(const int64_t u){ *this += mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator+=(const uint64_t u){ *this += mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator-=(const int64_t u){ *this -= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator-=(const uint64_t u){ *this -= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator*=(const int64_t u){ *this *= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator*=(const uint64_t u){ *this *= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator/=(const int64_t u){ *this /= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+inline mpreal& mpreal::operator/=(const uint64_t u){ *this /= mpreal(u); MPREAL_MSVC_DEBUGVIEW_CODE; return *this; }
+#endif
+
+inline const mpreal mpreal::operator+()const { return mpreal(*this); }
+
+inline const mpreal operator+(const mpreal& a, const mpreal& b)
+{
+ // prec(a+b) = max(prec(a),prec(b))
+ if(a.get_prec()>b.get_prec()) return mpreal(a) += b;
+ else return mpreal(b) += a;
+}
+
+inline mpreal& mpreal::operator++()
+{
+ return *this += 1;
+}
+
+inline const mpreal mpreal::operator++ (int)
+{
+ mpreal x(*this);
+ *this += 1;
+ return x;
+}
+
+inline mpreal& mpreal::operator--()
+{
+ return *this -= 1;
+}
+
+inline const mpreal mpreal::operator-- (int)
+{
+ mpreal x(*this);
+ *this -= 1;
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// - Subtraction
+inline mpreal& mpreal::operator-= (const mpreal& v)
+{
+ mpfr_sub(mp,mp,v.mp,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const mpz_t v)
+{
+ mpfr_sub_z(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const mpq_t v)
+{
+ mpfr_sub_q(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const long double v)
+{
+ *this -= mpreal(v);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const double v)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpfr_sub_d(mp,mp,v,default_rnd);
+#else
+ *this -= mpreal(v);
+#endif
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const unsigned long int v)
+{
+ mpfr_sub_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const unsigned int v)
+{
+ mpfr_sub_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const long int v)
+{
+ mpfr_sub_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator-=(const int v)
+{
+ mpfr_sub_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline const mpreal mpreal::operator-()const
+{
+ mpreal u(*this);
+ mpfr_neg(u.mp,u.mp,default_rnd);
+ return u;
+}
+
+inline const mpreal operator-(const mpreal& a, const mpreal& b)
+{
+ // prec(a-b) = max(prec(a),prec(b))
+ if(a.getPrecision() >= b.getPrecision())
+ {
+ return mpreal(a) -= b;
+ }else{
+ mpreal x(a);
+ x.setPrecision(b.getPrecision());
+ return x -= b;
+ }
+}
+
+inline const mpreal operator-(const double b, const mpreal& a)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpreal x(a);
+ mpfr_d_sub(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+#else
+ return mpreal(b) -= a;
+#endif
+}
+
+inline const mpreal operator-(const unsigned long int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_ui_sub(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator-(const unsigned int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_ui_sub(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator-(const long int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_si_sub(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator-(const int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_si_sub(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// * Multiplication
+inline mpreal& mpreal::operator*= (const mpreal& v)
+{
+ mpfr_mul(mp,mp,v.mp,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const mpz_t v)
+{
+ mpfr_mul_z(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const mpq_t v)
+{
+ mpfr_mul_q(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const long double v)
+{
+ *this *= mpreal(v);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const double v)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpfr_mul_d(mp,mp,v,default_rnd);
+#else
+ *this *= mpreal(v);
+#endif
+
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const unsigned long int v)
+{
+ mpfr_mul_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const unsigned int v)
+{
+ mpfr_mul_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const long int v)
+{
+ mpfr_mul_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator*=(const int v)
+{
+ mpfr_mul_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline const mpreal operator*(const mpreal& a, const mpreal& b)
+{
+ // prec(a*b) = max(prec(a),prec(b))
+ if(a.getPrecision() >= b.getPrecision()) return mpreal(a) *= b;
+ else return mpreal(b) *= a;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// / Division
+inline mpreal& mpreal::operator/=(const mpreal& v)
+{
+ mpfr_div(mp,mp,v.mp,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const mpz_t v)
+{
+ mpfr_div_z(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const mpq_t v)
+{
+ mpfr_div_q(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const long double v)
+{
+ *this /= mpreal(v);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const double v)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpfr_div_d(mp,mp,v,default_rnd);
+#else
+ *this /= mpreal(v);
+#endif
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const unsigned long int v)
+{
+ mpfr_div_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const unsigned int v)
+{
+ mpfr_div_ui(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const long int v)
+{
+ mpfr_div_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator/=(const int v)
+{
+ mpfr_div_si(mp,mp,v,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline const mpreal operator/(const mpreal& a, const mpreal& b)
+{
+ // prec(a/b) = max(prec(a),prec(b))
+ if(a.getPrecision() >= b.getPrecision())
+ {
+ return mpreal(a) /= b;
+ }else{
+
+ mpreal x(a);
+ x.setPrecision(b.getPrecision());
+ return x /= b;
+ }
+}
+
+inline const mpreal operator/(const unsigned long int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_ui_div(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator/(const unsigned int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_ui_div(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator/(const long int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_si_div(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator/(const int b, const mpreal& a)
+{
+ mpreal x(a);
+ mpfr_si_div(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal operator/(const double b, const mpreal& a)
+{
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+ mpreal x(a);
+ mpfr_d_div(x.mp,b,a.mp,mpreal::default_rnd);
+ return x;
+#else
+ return mpreal(b) /= a;
+#endif
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Shifts operators - Multiplication/Division by power of 2
+inline mpreal& mpreal::operator<<=(const unsigned long int u)
+{
+ mpfr_mul_2ui(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator<<=(const unsigned int u)
+{
+ mpfr_mul_2ui(mp,mp,static_cast<unsigned long int>(u),default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator<<=(const long int u)
+{
+ mpfr_mul_2si(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator<<=(const int u)
+{
+ mpfr_mul_2si(mp,mp,static_cast<long int>(u),default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator>>=(const unsigned long int u)
+{
+ mpfr_div_2ui(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator>>=(const unsigned int u)
+{
+ mpfr_div_2ui(mp,mp,static_cast<unsigned long int>(u),default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator>>=(const long int u)
+{
+ mpfr_div_2si(mp,mp,u,default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::operator>>=(const int u)
+{
+ mpfr_div_2si(mp,mp,static_cast<long int>(u),default_rnd);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline const mpreal operator<<(const mpreal& v, const unsigned long int k)
+{
+ return mul_2ui(v,k);
+}
+
+inline const mpreal operator<<(const mpreal& v, const unsigned int k)
+{
+ return mul_2ui(v,static_cast<unsigned long int>(k));
+}
+
+inline const mpreal operator<<(const mpreal& v, const long int k)
+{
+ return mul_2si(v,k);
+}
+
+inline const mpreal operator<<(const mpreal& v, const int k)
+{
+ return mul_2si(v,static_cast<long int>(k));
+}
+
+inline const mpreal operator>>(const mpreal& v, const unsigned long int k)
+{
+ return div_2ui(v,k);
+}
+
+inline const mpreal operator>>(const mpreal& v, const long int k)
+{
+ return div_2si(v,k);
+}
+
+inline const mpreal operator>>(const mpreal& v, const unsigned int k)
+{
+ return div_2ui(v,static_cast<unsigned long int>(k));
+}
+
+inline const mpreal operator>>(const mpreal& v, const int k)
+{
+ return div_2si(v,static_cast<long int>(k));
+}
+
+// mul_2ui
+inline const mpreal mul_2ui(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_mul_2ui(x.mp,v.mp,k,rnd_mode);
+ return x;
+}
+
+// mul_2si
+inline const mpreal mul_2si(const mpreal& v, long int k, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_mul_2si(x.mp,v.mp,k,rnd_mode);
+ return x;
+}
+
+inline const mpreal div_2ui(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_div_2ui(x.mp,v.mp,k,rnd_mode);
+ return x;
+}
+
+inline const mpreal div_2si(const mpreal& v, long int k, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_div_2si(x.mp,v.mp,k,rnd_mode);
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+//Boolean operators
+inline bool operator > (const mpreal& a, const mpreal& b){ return (mpfr_greater_p(a.mp,b.mp) !=0); }
+inline bool operator >= (const mpreal& a, const mpreal& b){ return (mpfr_greaterequal_p(a.mp,b.mp) !=0); }
+inline bool operator < (const mpreal& a, const mpreal& b){ return (mpfr_less_p(a.mp,b.mp) !=0); }
+inline bool operator <= (const mpreal& a, const mpreal& b){ return (mpfr_lessequal_p(a.mp,b.mp) !=0); }
+inline bool operator == (const mpreal& a, const mpreal& b){ return (mpfr_equal_p(a.mp,b.mp) !=0); }
+inline bool operator != (const mpreal& a, const mpreal& b){ return (mpfr_lessgreater_p(a.mp,b.mp) !=0); }
+
+inline bool operator == (const mpreal& a, const unsigned long int b ){ return (mpfr_cmp_ui(a.mp,b) == 0); }
+inline bool operator == (const mpreal& a, const unsigned int b ){ return (mpfr_cmp_ui(a.mp,b) == 0); }
+inline bool operator == (const mpreal& a, const long int b ){ return (mpfr_cmp_si(a.mp,b) == 0); }
+inline bool operator == (const mpreal& a, const int b ){ return (mpfr_cmp_si(a.mp,b) == 0); }
+inline bool operator == (const mpreal& a, const long double b ){ return (mpfr_cmp_ld(a.mp,b) == 0); }
+inline bool operator == (const mpreal& a, const double b ){ return (mpfr_cmp_d(a.mp,b) == 0); }
+
+
+inline bool isnan (const mpreal& v){ return (mpfr_nan_p(v.mp) != 0); }
+inline bool isinf (const mpreal& v){ return (mpfr_inf_p(v.mp) != 0); }
+inline bool isfinite(const mpreal& v){ return (mpfr_number_p(v.mp) != 0); }
+inline bool iszero (const mpreal& v){ return (mpfr_zero_p(v.mp) != 0); }
+inline bool isint (const mpreal& v){ return (mpfr_integer_p(v.mp) != 0); }
+
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(3,0,0))
+inline bool isregular(const mpreal& v){ return (mpfr_regular_p(v.mp));}
+#endif
+
+//////////////////////////////////////////////////////////////////////////
+// Type Converters
+inline long mpreal::toLong() const { return mpfr_get_si(mp,GMP_RNDZ); }
+inline unsigned long mpreal::toULong() const { return mpfr_get_ui(mp,GMP_RNDZ); }
+inline double mpreal::toDouble() const { return mpfr_get_d(mp,default_rnd); }
+inline long double mpreal::toLDouble() const { return mpfr_get_ld(mp,default_rnd); }
+
+#if defined (MPREAL_HAVE_INT64_SUPPORT)
+inline int64_t mpreal::toInt64() const{ return mpfr_get_sj(mp,GMP_RNDZ); }
+inline uint64_t mpreal::toUInt64() const{ return mpfr_get_uj(mp,GMP_RNDZ); }
+#endif
+
+inline ::mpfr_ptr mpreal::mpfr_ptr() { return mp; }
+inline ::mpfr_srcptr mpreal::mpfr_srcptr() const { return const_cast< ::mpfr_srcptr >(mp); }
+
+//////////////////////////////////////////////////////////////////////////
+// Bits - decimal digits relation
+// bits = ceil(digits*log[2](10))
+// digits = floor(bits*log[10](2))
+
+inline mp_prec_t digits2bits(int d)
+{
+ const double LOG2_10 = 3.3219280948873624;
+
+ d = 10>d?10:d;
+
+ return (mp_prec_t)std::ceil((d)*LOG2_10);
+}
+
+inline int bits2digits(mp_prec_t b)
+{
+ const double LOG10_2 = 0.30102999566398119;
+
+ b = 34>b?34:b;
+
+ return (int)std::floor((b)*LOG10_2);
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Set/Get number properties
+inline int sgn(const mpreal& v)
+{
+ int r = mpfr_signbit(v.mp);
+ return (r>0?-1:1);
+}
+
+inline mpreal& mpreal::setSign(int sign, mp_rnd_t RoundingMode)
+{
+ mpfr_setsign(mp,mp,(sign<0?1:0),RoundingMode);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline int mpreal::getPrecision() const
+{
+ return mpfr_get_prec(mp);
+}
+
+inline mpreal& mpreal::setPrecision(int Precision, mp_rnd_t RoundingMode)
+{
+ mpfr_prec_round(mp,Precision, RoundingMode);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::setInf(int sign)
+{
+ mpfr_set_inf(mp,sign);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::setNan()
+{
+ mpfr_set_nan(mp);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mpreal& mpreal::setZero(int sign)
+{
+ mpfr_set_zero(mp,sign);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return *this;
+}
+
+inline mp_prec_t mpreal::get_prec() const
+{
+ return mpfr_get_prec(mp);
+}
+
+inline void mpreal::set_prec(mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpfr_prec_round(mp,prec,rnd_mode);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+}
+
+inline mp_exp_t mpreal::get_exp ()
+{
+ return mpfr_get_exp(mp);
+}
+
+inline int mpreal::set_exp (mp_exp_t e)
+{
+ int x = mpfr_set_exp(mp, e);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return x;
+}
+
+inline const mpreal frexp(const mpreal& v, mp_exp_t* exp)
+{
+ mpreal x(v);
+ *exp = x.get_exp();
+ x.set_exp(0);
+ return x;
+}
+
+inline const mpreal ldexp(const mpreal& v, mp_exp_t exp)
+{
+ mpreal x(v);
+
+ // rounding is not important since we just increasing the exponent
+ mpfr_mul_2si(x.mp,x.mp,exp,mpreal::default_rnd);
+ return x;
+}
+
+inline const mpreal machine_epsilon(mp_prec_t prec)
+{
+ // the smallest eps such that 1.0+eps != 1.0
+ // depends (of cause) on the precision
+ return machine_epsilon(mpreal(1,prec));
+}
+
+inline const mpreal machine_epsilon(const mpreal& x)
+{
+ if( x < 0)
+ {
+ return nextabove(-x)+x;
+ }else{
+ return nextabove(x)-x;
+ }
+}
+
+inline const mpreal mpreal_min(mp_prec_t prec)
+{
+ // min = 1/2*2^emin = 2^(emin-1)
+
+ return mpreal(1,prec) << mpreal::get_emin()-1;
+}
+
+inline const mpreal mpreal_max(mp_prec_t prec)
+{
+ // max = (1-eps)*2^emax, assume eps = 0?,
+ // and use emax-1 to prevent value to be +inf
+ // max = 2^(emax-1)
+
+ return mpreal(1,prec) << mpreal::get_emax()-1;
+}
+
+inline bool isEqualUlps(const mpreal& a, const mpreal& b, int maxUlps)
+{
+ /*
+ maxUlps - a and b can be apart by maxUlps binary numbers.
+ */
+ return abs(a - b) <= machine_epsilon((max)(abs(a), abs(b))) * maxUlps;
+}
+
+inline bool isEqualFuzzy(const mpreal& a, const mpreal& b, const mpreal& eps)
+{
+ return abs(a - b) <= (min)(abs(a), abs(b)) * eps;
+}
+
+inline bool isEqualFuzzy(const mpreal& a, const mpreal& b)
+{
+ return isEqualFuzzy(a,b,machine_epsilon((std::min)(abs(a), abs(b))));
+}
+
+inline const mpreal modf(const mpreal& v, mpreal& n)
+{
+ mpreal frac(v);
+
+ // rounding is not important since we are using the same number
+ mpfr_frac(frac.mp,frac.mp,mpreal::default_rnd);
+ mpfr_trunc(n.mp,v.mp);
+ return frac;
+}
+
+inline int mpreal::check_range (int t, mp_rnd_t rnd_mode)
+{
+ return mpfr_check_range(mp,t,rnd_mode);
+}
+
+inline int mpreal::subnormalize (int t,mp_rnd_t rnd_mode)
+{
+ int r = mpfr_subnormalize(mp,t,rnd_mode);
+ MPREAL_MSVC_DEBUGVIEW_CODE;
+ return r;
+}
+
+inline mp_exp_t mpreal::get_emin (void)
+{
+ return mpfr_get_emin();
+}
+
+inline int mpreal::set_emin (mp_exp_t exp)
+{
+ return mpfr_set_emin(exp);
+}
+
+inline mp_exp_t mpreal::get_emax (void)
+{
+ return mpfr_get_emax();
+}
+
+inline int mpreal::set_emax (mp_exp_t exp)
+{
+ return mpfr_set_emax(exp);
+}
+
+inline mp_exp_t mpreal::get_emin_min (void)
+{
+ return mpfr_get_emin_min();
+}
+
+inline mp_exp_t mpreal::get_emin_max (void)
+{
+ return mpfr_get_emin_max();
+}
+
+inline mp_exp_t mpreal::get_emax_min (void)
+{
+ return mpfr_get_emax_min();
+}
+
+inline mp_exp_t mpreal::get_emax_max (void)
+{
+ return mpfr_get_emax_max();
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Mathematical Functions
+//////////////////////////////////////////////////////////////////////////
+inline const mpreal sqr(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sqr(x.mp,x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sqrt(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sqrt(x.mp,x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sqrt(const unsigned long int v, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ mpfr_sqrt_ui(x.mp,v,rnd_mode);
+ return x;
+}
+
+inline const mpreal sqrt(const unsigned int v, mp_rnd_t rnd_mode)
+{
+ return sqrt(static_cast<unsigned long int>(v),rnd_mode);
+}
+
+inline const mpreal sqrt(const long int v, mp_rnd_t rnd_mode)
+{
+ if (v>=0) return sqrt(static_cast<unsigned long int>(v),rnd_mode);
+ else return mpreal().setNan(); // NaN
+}
+
+inline const mpreal sqrt(const int v, mp_rnd_t rnd_mode)
+{
+ if (v>=0) return sqrt(static_cast<unsigned long int>(v),rnd_mode);
+ else return mpreal().setNan(); // NaN
+}
+
+inline const mpreal sqrt(const long double v, mp_rnd_t rnd_mode)
+{
+ return sqrt(mpreal(v),rnd_mode);
+}
+
+inline const mpreal sqrt(const double v, mp_rnd_t rnd_mode)
+{
+ return sqrt(mpreal(v),rnd_mode);
+}
+
+inline const mpreal cbrt(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_cbrt(x.mp,x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal root(const mpreal& v, unsigned long int k, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_root(x.mp,x.mp,k,rnd_mode);
+ return x;
+}
+
+inline const mpreal fabs(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_abs(x.mp,x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal abs(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_abs(x.mp,x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal dim(const mpreal& a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_dim(x.mp,a.mp,b.mp,rnd_mode);
+ return x;
+}
+
+inline int cmpabs(const mpreal& a,const mpreal& b)
+{
+ return mpfr_cmpabs(a.mp,b.mp);
+}
+
+inline const mpreal log (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_log(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal log2(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_log2(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal log10(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_log10(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal exp(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_exp(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal exp2(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_exp2(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal exp10(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_exp10(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal cos(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_cos(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sin(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sin(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal tan(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_tan(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sec(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sec(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal csc(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_csc(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal cot(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_cot(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline int sin_cos(mpreal& s, mpreal& c, const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return mpfr_sin_cos(s.mp,c.mp,v.mp,rnd_mode);
+}
+
+inline const mpreal acos (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_acos(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal asin (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_asin(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal atan (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_atan(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal acot (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return atan(1/v, rnd_mode);
+}
+
+inline const mpreal asec (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return acos(1/v, rnd_mode);
+}
+
+inline const mpreal acsc (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return asin(1/v, rnd_mode);
+}
+
+inline const mpreal acoth (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return atanh(1/v, rnd_mode);
+}
+
+inline const mpreal asech (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return acosh(1/v, rnd_mode);
+}
+
+inline const mpreal acsch (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return asinh(1/v, rnd_mode);
+}
+
+inline const mpreal atan2 (const mpreal& y, const mpreal& x, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t yp, xp;
+
+ yp = y.get_prec();
+ xp = x.get_prec();
+
+ a.set_prec(yp>xp?yp:xp);
+
+ mpfr_atan2(a.mp, y.mp, x.mp, rnd_mode);
+
+ return a;
+}
+
+inline const mpreal cosh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_cosh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sinh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sinh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal tanh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_tanh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal sech (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_sech(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal csch (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_csch(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal coth (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_coth(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal acosh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_acosh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal asinh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_asinh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal atanh (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_atanh(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal hypot (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t yp, xp;
+
+ yp = y.get_prec();
+ xp = x.get_prec();
+
+ a.set_prec(yp>xp?yp:xp);
+
+ mpfr_hypot(a.mp, x.mp, y.mp, rnd_mode);
+
+ return a;
+}
+
+inline const mpreal remainder (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t yp, xp;
+
+ yp = y.get_prec();
+ xp = x.get_prec();
+
+ a.set_prec(yp>xp?yp:xp);
+
+ mpfr_remainder(a.mp, x.mp, y.mp, rnd_mode);
+
+ return a;
+}
+
+inline const mpreal fac_ui (unsigned long int v, mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x(0,prec);
+ mpfr_fac_ui(x.mp,v,rnd_mode);
+ return x;
+}
+
+inline const mpreal log1p (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_log1p(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal expm1 (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_expm1(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal eint (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_eint(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal gamma (const mpreal& x, mp_rnd_t rnd_mode)
+{
+ mpreal FunctionValue(x);
+
+ // x < 0: gamma(-x) = -pi/(x * gamma(x) * sin(pi*x))
+
+ mpfr_gamma(FunctionValue.mp, x.mp, rnd_mode);
+
+ return FunctionValue;
+}
+
+inline const mpreal lngamma (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_lngamma(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal lgamma (const mpreal& v, int *signp, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ int tsignp;
+
+ if(signp)
+ mpfr_lgamma(x.mp,signp,v.mp,rnd_mode);
+ else
+ mpfr_lgamma(x.mp,&tsignp,v.mp,rnd_mode);
+
+ return x;
+}
+
+inline const mpreal zeta (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_zeta(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal erf (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_erf(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal erfc (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_erfc(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal besselj0 (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_j0(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal besselj1 (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_j1(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal besseljn (long n, const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_jn(x.mp,n,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal bessely0 (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_y0(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal bessely1 (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_y1(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal besselyn (long n, const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_yn(x.mp,n,v.mp,rnd_mode);
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// MPFR 2.4.0 Specifics
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(2,4,0))
+
+inline int sinh_cosh(mpreal& s, mpreal& c, const mpreal& v, mp_rnd_t rnd_mode)
+{
+ return mpfr_sinh_cosh(s.mp,c.mp,v.mp,rnd_mode);
+}
+
+inline const mpreal li2(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_li2(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal fmod (const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mp_prec_t yp, xp;
+
+ yp = y.get_prec();
+ xp = x.get_prec();
+
+ a.set_prec(yp>xp?yp:xp);
+
+ mpfr_fmod(a.mp, x.mp, y.mp, rnd_mode);
+
+ return a;
+}
+
+inline const mpreal rec_sqrt(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rec_sqrt(x.mp,v.mp,rnd_mode);
+ return x;
+}
+#endif // MPFR 2.4.0 Specifics
+
+//////////////////////////////////////////////////////////////////////////
+// MPFR 3.0.0 Specifics
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(3,0,0))
+
+inline const mpreal digamma(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_digamma(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal ai(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_ai(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+#endif // MPFR 3.0.0 Specifics
+
+//////////////////////////////////////////////////////////////////////////
+// Constants
+inline const mpreal const_log2 (mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ x.set_prec(prec);
+ mpfr_const_log2(x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal const_pi (mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ x.set_prec(prec);
+ mpfr_const_pi(x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal const_euler (mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ x.set_prec(prec);
+ mpfr_const_euler(x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal const_catalan (mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ x.set_prec(prec);
+ mpfr_const_catalan(x.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal const_infinity (int sign, mp_prec_t prec, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ x.set_prec(prec,rnd_mode);
+ mpfr_set_inf(x.mp, sign);
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Integer Related Functions
+inline const mpreal rint(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rint(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal ceil(const mpreal& v)
+{
+ mpreal x(v);
+ mpfr_ceil(x.mp,v.mp);
+ return x;
+
+}
+
+inline const mpreal floor(const mpreal& v)
+{
+ mpreal x(v);
+ mpfr_floor(x.mp,v.mp);
+ return x;
+}
+
+inline const mpreal round(const mpreal& v)
+{
+ mpreal x(v);
+ mpfr_round(x.mp,v.mp);
+ return x;
+}
+
+inline const mpreal trunc(const mpreal& v)
+{
+ mpreal x(v);
+ mpfr_trunc(x.mp,v.mp);
+ return x;
+}
+
+inline const mpreal rint_ceil (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rint_ceil(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal rint_floor(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rint_floor(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal rint_round(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rint_round(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal rint_trunc(const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_rint_trunc(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal frac (const mpreal& v, mp_rnd_t rnd_mode)
+{
+ mpreal x(v);
+ mpfr_frac(x.mp,v.mp,rnd_mode);
+ return x;
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Miscellaneous Functions
+inline void swap(mpreal& a, mpreal& b)
+{
+ mpfr_swap(a.mp,b.mp);
+}
+
+inline const mpreal (max)(const mpreal& x, const mpreal& y)
+{
+ return (x>y?x:y);
+}
+
+inline const mpreal (min)(const mpreal& x, const mpreal& y)
+{
+ return (x<y?x:y);
+}
+
+inline const mpreal fmax(const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mpfr_max(a.mp,x.mp,y.mp,rnd_mode);
+ return a;
+}
+
+inline const mpreal fmin(const mpreal& x, const mpreal& y, mp_rnd_t rnd_mode)
+{
+ mpreal a;
+ mpfr_min(a.mp,x.mp,y.mp,rnd_mode);
+ return a;
+}
+
+inline const mpreal nexttoward (const mpreal& x, const mpreal& y)
+{
+ mpreal a(x);
+ mpfr_nexttoward(a.mp,y.mp);
+ return a;
+}
+
+inline const mpreal nextabove (const mpreal& x)
+{
+ mpreal a(x);
+ mpfr_nextabove(a.mp);
+ return a;
+}
+
+inline const mpreal nextbelow (const mpreal& x)
+{
+ mpreal a(x);
+ mpfr_nextbelow(a.mp);
+ return a;
+}
+
+inline const mpreal urandomb (gmp_randstate_t& state)
+{
+ mpreal x;
+ mpfr_urandomb(x.mp,state);
+ return x;
+}
+
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(3,0,0))
+// use gmp_randinit_default() to init state, gmp_randclear() to clear
+inline const mpreal urandom (gmp_randstate_t& state, mp_rnd_t rnd_mode)
+{
+ mpreal x;
+ mpfr_urandom(x.mp,state,rnd_mode);
+ return x;
+}
+#endif
+
+#if (MPFR_VERSION <= MPFR_VERSION_NUM(2,4,2))
+inline const mpreal random2 (mp_size_t size, mp_exp_t exp)
+{
+ mpreal x;
+ mpfr_random2(x.mp,size,exp);
+ return x;
+}
+#endif
+
+// Uniformly distributed random number generation
+// a = random(seed); <- initialization & first random number generation
+// a = random(); <- next random numbers generation
+// seed != 0
+inline const mpreal random(unsigned int seed)
+{
+
+#if (MPFR_VERSION >= MPFR_VERSION_NUM(3,0,0))
+ static gmp_randstate_t state;
+ static bool isFirstTime = true;
+
+ if(isFirstTime)
+ {
+ gmp_randinit_default(state);
+ gmp_randseed_ui(state,0);
+ isFirstTime = false;
+ }
+
+ if(seed != 0) gmp_randseed_ui(state,seed);
+
+ return mpfr::urandom(state);
+#else
+ if(seed != 0) std::srand(seed);
+ return mpfr::mpreal(std::rand()/(double)RAND_MAX);
+#endif
+
+}
+
+//////////////////////////////////////////////////////////////////////////
+// Set/Get global properties
+inline void mpreal::set_default_prec(mp_prec_t prec)
+{
+ default_prec = prec;
+ mpfr_set_default_prec(prec);
+}
+
+inline mp_prec_t mpreal::get_default_prec()
+{
+ return (mpfr_get_default_prec)();
+}
+
+inline void mpreal::set_default_base(int base)
+{
+ default_base = base;
+}
+
+inline int mpreal::get_default_base()
+{
+ return default_base;
+}
+
+inline void mpreal::set_default_rnd(mp_rnd_t rnd_mode)
+{
+ default_rnd = rnd_mode;
+ mpfr_set_default_rounding_mode(rnd_mode);
+}
+
+inline mp_rnd_t mpreal::get_default_rnd()
+{
+ return static_cast<mp_rnd_t>((mpfr_get_default_rounding_mode)());
+}
+
+inline void mpreal::set_double_bits(int dbits)
+{
+ double_bits = dbits;
+}
+
+inline int mpreal::get_double_bits()
+{
+ return double_bits;
+}
+
+inline bool mpreal::fits_in_bits(double x, int n)
+{
+ int i;
+ double t;
+ return IsInf(x) || (std::modf ( std::ldexp ( std::frexp ( x, &i ), n ), &t ) == 0.0);
+}
+
+inline const mpreal pow(const mpreal& a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_pow(x.mp,x.mp,b.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const mpreal& a, const mpz_t b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_pow_z(x.mp,x.mp,b,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const mpreal& a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_pow_ui(x.mp,x.mp,b,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const mpreal& a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ return pow(a,static_cast<unsigned long int>(b),rnd_mode);
+}
+
+inline const mpreal pow(const mpreal& a, const long int b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_pow_si(x.mp,x.mp,b,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const mpreal& a, const int b, mp_rnd_t rnd_mode)
+{
+ return pow(a,static_cast<long int>(b),rnd_mode);
+}
+
+inline const mpreal pow(const mpreal& a, const long double b, mp_rnd_t rnd_mode)
+{
+ return pow(a,mpreal(b),rnd_mode);
+}
+
+inline const mpreal pow(const mpreal& a, const double b, mp_rnd_t rnd_mode)
+{
+ return pow(a,mpreal(b),rnd_mode);
+}
+
+inline const mpreal pow(const unsigned long int a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_ui_pow(x.mp,a,b.mp,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const unsigned int a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ return pow(static_cast<unsigned long int>(a),b,rnd_mode);
+}
+
+inline const mpreal pow(const long int a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),b,rnd_mode);
+ else return pow(mpreal(a),b,rnd_mode);
+}
+
+inline const mpreal pow(const int a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),b,rnd_mode);
+ else return pow(mpreal(a),b,rnd_mode);
+}
+
+inline const mpreal pow(const long double a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode);
+}
+
+inline const mpreal pow(const double a, const mpreal& b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode);
+}
+
+// pow unsigned long int
+inline const mpreal pow(const unsigned long int a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ mpreal x(a);
+ mpfr_ui_pow_ui(x.mp,a,b,rnd_mode);
+ return x;
+}
+
+inline const mpreal pow(const unsigned long int a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ return pow(a,static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+}
+
+inline const mpreal pow(const unsigned long int a, const long int b, mp_rnd_t rnd_mode)
+{
+ if(b>0) return pow(a,static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(a,mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned long int a, const int b, mp_rnd_t rnd_mode)
+{
+ if(b>0) return pow(a,static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(a,mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned long int a, const long double b, mp_rnd_t rnd_mode)
+{
+ return pow(a,mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned long int a, const double b, mp_rnd_t rnd_mode)
+{
+ return pow(a,mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+// pow unsigned int
+inline const mpreal pow(const unsigned int a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ return pow(static_cast<unsigned long int>(a),b,rnd_mode); //mpfr_ui_pow_ui
+}
+
+inline const mpreal pow(const unsigned int a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+}
+
+inline const mpreal pow(const unsigned int a, const long int b, mp_rnd_t rnd_mode)
+{
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned int a, const int b, mp_rnd_t rnd_mode)
+{
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned int a, const long double b, mp_rnd_t rnd_mode)
+{
+ return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+inline const mpreal pow(const unsigned int a, const double b, mp_rnd_t rnd_mode)
+{
+ return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+}
+
+// pow long int
+inline const mpreal pow(const long int a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ if (a>0) return pow(static_cast<unsigned long int>(a),b,rnd_mode); //mpfr_ui_pow_ui
+ else return pow(mpreal(a),b,rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const long int a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ if (a>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(mpreal(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const long int a, const long int b, mp_rnd_t rnd_mode)
+{
+ if (a>0)
+ {
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ }else{
+ return pow(mpreal(a),b,rnd_mode); // mpfr_pow_si
+ }
+}
+
+inline const mpreal pow(const long int a, const int b, mp_rnd_t rnd_mode)
+{
+ if (a>0)
+ {
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ }else{
+ return pow(mpreal(a),static_cast<long int>(b),rnd_mode); // mpfr_pow_si
+ }
+}
+
+inline const mpreal pow(const long int a, const long double b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ else return pow(mpreal(a),mpreal(b),rnd_mode); //mpfr_pow
+}
+
+inline const mpreal pow(const long int a, const double b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ else return pow(mpreal(a),mpreal(b),rnd_mode); //mpfr_pow
+}
+
+// pow int
+inline const mpreal pow(const int a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ if (a>0) return pow(static_cast<unsigned long int>(a),b,rnd_mode); //mpfr_ui_pow_ui
+ else return pow(mpreal(a),b,rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const int a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ if (a>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(mpreal(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const int a, const long int b, mp_rnd_t rnd_mode)
+{
+ if (a>0)
+ {
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ }else{
+ return pow(mpreal(a),b,rnd_mode); // mpfr_pow_si
+ }
+}
+
+inline const mpreal pow(const int a, const int b, mp_rnd_t rnd_mode)
+{
+ if (a>0)
+ {
+ if(b>0) return pow(static_cast<unsigned long int>(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_ui_pow_ui
+ else return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ }else{
+ return pow(mpreal(a),static_cast<long int>(b),rnd_mode); // mpfr_pow_si
+ }
+}
+
+inline const mpreal pow(const int a, const long double b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ else return pow(mpreal(a),mpreal(b),rnd_mode); //mpfr_pow
+}
+
+inline const mpreal pow(const int a, const double b, mp_rnd_t rnd_mode)
+{
+ if (a>=0) return pow(static_cast<unsigned long int>(a),mpreal(b),rnd_mode); //mpfr_ui_pow
+ else return pow(mpreal(a),mpreal(b),rnd_mode); //mpfr_pow
+}
+
+// pow long double
+inline const mpreal pow(const long double a, const long double b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),mpreal(b),rnd_mode);
+}
+
+inline const mpreal pow(const long double a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const long double a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),static_cast<unsigned long int>(b),rnd_mode); //mpfr_pow_ui
+}
+
+inline const mpreal pow(const long double a, const long int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode); // mpfr_pow_si
+}
+
+inline const mpreal pow(const long double a, const int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),static_cast<long int>(b),rnd_mode); // mpfr_pow_si
+}
+
+inline const mpreal pow(const double a, const double b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),mpreal(b),rnd_mode);
+}
+
+inline const mpreal pow(const double a, const unsigned long int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode); // mpfr_pow_ui
+}
+
+inline const mpreal pow(const double a, const unsigned int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),static_cast<unsigned long int>(b),rnd_mode); // mpfr_pow_ui
+}
+
+inline const mpreal pow(const double a, const long int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),b,rnd_mode); // mpfr_pow_si
+}
+
+inline const mpreal pow(const double a, const int b, mp_rnd_t rnd_mode)
+{
+ return pow(mpreal(a),static_cast<long int>(b),rnd_mode); // mpfr_pow_si
+}
+} // End of mpfr namespace
+
+// Explicit specialization of std::swap for mpreal numbers
+// Thus standard algorithms will use efficient version of swap (due to Koenig lookup)
+// Non-throwing swap C++ idiom: http://en.wikibooks.org/wiki/More_C%2B%2B_Idioms/Non-throwing_swap
+namespace std
+{
+ template <>
+ inline void swap(mpfr::mpreal& x, mpfr::mpreal& y)
+ {
+ return mpfr::swap(x, y);
+ }
+}
+
+#endif /* __MPREAL_H__ */
diff --git a/unsupported/test/mpreal_support.cpp b/unsupported/test/mpreal_support.cpp new file mode 100644 index 000000000..551af9db8 --- /dev/null +++ b/unsupported/test/mpreal_support.cpp @@ -0,0 +1,64 @@ +#include "main.h" +#include <Eigen/MPRealSupport> +#include <Eigen/LU> +#include <Eigen/Eigenvalues> +#include <sstream> + +using namespace mpfr; +using namespace std; +using namespace Eigen; + +void test_mpreal_support() +{ + // set precision to 256 bits (double has only 53 bits) + mpreal::set_default_prec(256); + typedef Matrix<mpreal,Eigen::Dynamic,Eigen::Dynamic> MatrixXmp; + + std::cerr << "epsilon = " << NumTraits<mpreal>::epsilon() << "\n"; + std::cerr << "dummy_precision = " << NumTraits<mpreal>::dummy_precision() << "\n"; + std::cerr << "highest = " << NumTraits<mpreal>::highest() << "\n"; + std::cerr << "lowest = " << NumTraits<mpreal>::lowest() << "\n"; + + for(int i = 0; i < g_repeat; i++) { + int s = Eigen::internal::random<int>(1,100); + MatrixXmp A = MatrixXmp::Random(s,s); + MatrixXmp B = MatrixXmp::Random(s,s); + MatrixXmp S = A.adjoint() * A; + MatrixXmp X; + + // Basic stuffs + VERIFY_IS_APPROX(A.real(), A); + VERIFY(Eigen::internal::isApprox(A.array().abs2().sum(), A.squaredNorm())); + VERIFY_IS_APPROX(A.array().exp(), exp(A.array())); + VERIFY_IS_APPROX(A.array().abs2().sqrt(), A.array().abs()); + VERIFY_IS_APPROX(A.array().sin(), sin(A.array())); + VERIFY_IS_APPROX(A.array().cos(), cos(A.array())); + + + // Cholesky + X = S.selfadjointView<Lower>().llt().solve(B); + VERIFY_IS_APPROX((S.selfadjointView<Lower>()*X).eval(),B); + + // partial LU + X = A.lu().solve(B); + VERIFY_IS_APPROX((A*X).eval(),B); + + // symmetric eigenvalues + SelfAdjointEigenSolver<MatrixXmp> eig(S); + VERIFY_IS_EQUAL(eig.info(), Success); + VERIFY_IS_APPROX((S.selfadjointView<Lower>() * eig.eigenvectors()), + eig.eigenvectors() * eig.eigenvalues().asDiagonal()); + } + + { + MatrixXmp A(8,3); A.setRandom(); + // test output (interesting things happen in this code) + std::stringstream stream; + stream << A; + } +} + +extern "C" { +#include "mpreal/dlmalloc.c" +} +#include "mpreal/mpreal.cpp" diff --git a/unsupported/test/openglsupport.cpp b/unsupported/test/openglsupport.cpp new file mode 100644 index 000000000..706a816f7 --- /dev/null +++ b/unsupported/test/openglsupport.cpp @@ -0,0 +1,337 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2010 Gael Guennebaud <gael.guennebaud@inria.fr> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include <main.h> +#include <iostream> +#include <GL/glew.h> +#include <Eigen/OpenGLSupport> +#include <GL/glut.h> +using namespace Eigen; + + + + +#define VERIFY_MATRIX(CODE,REF) { \ + glLoadIdentity(); \ + CODE; \ + Matrix<float,4,4,ColMajor> m; m.setZero(); \ + glGet(GL_MODELVIEW_MATRIX, m); \ + if(!(REF).cast<float>().isApprox(m)) { \ + std::cerr << "Expected:\n" << ((REF).cast<float>()) << "\n" << "got\n" << m << "\n\n"; \ + } \ + VERIFY_IS_APPROX((REF).cast<float>(), m); \ + } + +#define VERIFY_UNIFORM(SUFFIX,NAME,TYPE) { \ + TYPE value; value.setRandom(); \ + TYPE data; \ + int loc = glGetUniformLocation(prg_id, #NAME); \ + VERIFY((loc!=-1) && "uniform not found"); \ + glUniform(loc,value); \ + EIGEN_CAT(glGetUniform,SUFFIX)(prg_id,loc,data.data()); \ + if(!value.isApprox(data)) { \ + std::cerr << "Expected:\n" << value << "\n" << "got\n" << data << "\n\n"; \ + } \ + VERIFY_IS_APPROX(value, data); \ + } + +#define VERIFY_UNIFORMi(NAME,TYPE) { \ + TYPE value = TYPE::Random().eval().cast<float>().cast<TYPE::Scalar>(); \ + TYPE data; \ + int loc = glGetUniformLocation(prg_id, #NAME); \ + VERIFY((loc!=-1) && "uniform not found"); \ + glUniform(loc,value); \ + glGetUniformiv(prg_id,loc,(GLint*)data.data()); \ + if(!value.isApprox(data)) { \ + std::cerr << "Expected:\n" << value << "\n" << "got\n" << data << "\n\n"; \ + } \ + VERIFY_IS_APPROX(value, data); \ + } + +void printInfoLog(GLuint objectID) +{ + int infologLength, charsWritten; + GLchar *infoLog; + glGetProgramiv(objectID,GL_INFO_LOG_LENGTH, &infologLength); + if(infologLength > 0) + { + infoLog = new GLchar[infologLength]; + glGetProgramInfoLog(objectID, infologLength, &charsWritten, infoLog); + if (charsWritten>0) + std::cerr << "Shader info : \n" << infoLog << std::endl; + delete[] infoLog; + } +} + +GLint createShader(const char* vtx, const char* frg) +{ + GLint prg_id = glCreateProgram(); + GLint vtx_id = glCreateShader(GL_VERTEX_SHADER); + GLint frg_id = glCreateShader(GL_FRAGMENT_SHADER); + GLint ok; + + glShaderSource(vtx_id, 1, &vtx, 0); + glCompileShader(vtx_id); + glGetShaderiv(vtx_id,GL_COMPILE_STATUS,&ok); + if(!ok) + { + std::cerr << "vtx compilation failed\n"; + } + + glShaderSource(frg_id, 1, &frg, 0); + glCompileShader(frg_id); + glGetShaderiv(frg_id,GL_COMPILE_STATUS,&ok); + if(!ok) + { + std::cerr << "frg compilation failed\n"; + } + + glAttachShader(prg_id, vtx_id); + glAttachShader(prg_id, frg_id); + glLinkProgram(prg_id); + glGetProgramiv(prg_id,GL_LINK_STATUS,&ok); + if(!ok) + { + std::cerr << "linking failed\n"; + } + printInfoLog(prg_id); + + glUseProgram(prg_id); + return prg_id; +} + +void test_openglsupport() +{ + int argc = 0; + glutInit(&argc, 0); + glutInitDisplayMode(GLUT_DOUBLE | GLUT_RGB | GLUT_DEPTH); + glutInitWindowPosition (0,0); + glutInitWindowSize(10, 10); + + if(glutCreateWindow("Eigen") <= 0) + { + std::cerr << "Error: Unable to create GLUT Window.\n"; + exit(1); + } + + glewExperimental = GL_TRUE; + if(glewInit() != GLEW_OK) + { + std::cerr << "Warning: Failed to initialize GLEW\n"; + } + + Vector3f v3f; + Matrix3f rot; + glBegin(GL_POINTS); + + glVertex(v3f); + glVertex(2*v3f+v3f); + glVertex(rot*v3f); + + glEnd(); + + // 4x4 matrices + Matrix4f mf44; mf44.setRandom(); + VERIFY_MATRIX(glLoadMatrix(mf44), mf44); + VERIFY_MATRIX(glMultMatrix(mf44), mf44); + Matrix4d md44; md44.setRandom(); + VERIFY_MATRIX(glLoadMatrix(md44), md44); + VERIFY_MATRIX(glMultMatrix(md44), md44); + + // Quaternion + Quaterniond qd(AngleAxisd(internal::random<double>(), Vector3d::Random())); + VERIFY_MATRIX(glRotate(qd), Projective3d(qd).matrix()); + + Quaternionf qf(AngleAxisf(internal::random<double>(), Vector3f::Random())); + VERIFY_MATRIX(glRotate(qf), Projective3f(qf).matrix()); + + // 3D Transform + Transform<float,3,AffineCompact> acf3; acf3.matrix().setRandom(); + VERIFY_MATRIX(glLoadMatrix(acf3), Projective3f(acf3).matrix()); + VERIFY_MATRIX(glMultMatrix(acf3), Projective3f(acf3).matrix()); + + Transform<float,3,Affine> af3(acf3); + VERIFY_MATRIX(glLoadMatrix(af3), Projective3f(af3).matrix()); + VERIFY_MATRIX(glMultMatrix(af3), Projective3f(af3).matrix()); + + Transform<float,3,Projective> pf3; pf3.matrix().setRandom(); + VERIFY_MATRIX(glLoadMatrix(pf3), Projective3f(pf3).matrix()); + VERIFY_MATRIX(glMultMatrix(pf3), Projective3f(pf3).matrix()); + + Transform<double,3,AffineCompact> acd3; acd3.matrix().setRandom(); + VERIFY_MATRIX(glLoadMatrix(acd3), Projective3d(acd3).matrix()); + VERIFY_MATRIX(glMultMatrix(acd3), Projective3d(acd3).matrix()); + + Transform<double,3,Affine> ad3(acd3); + VERIFY_MATRIX(glLoadMatrix(ad3), Projective3d(ad3).matrix()); + VERIFY_MATRIX(glMultMatrix(ad3), Projective3d(ad3).matrix()); + + Transform<double,3,Projective> pd3; pd3.matrix().setRandom(); + VERIFY_MATRIX(glLoadMatrix(pd3), Projective3d(pd3).matrix()); + VERIFY_MATRIX(glMultMatrix(pd3), Projective3d(pd3).matrix()); + + // translations (2D and 3D) + { + Vector2f vf2; vf2.setRandom(); Vector3f vf23; vf23 << vf2, 0; + VERIFY_MATRIX(glTranslate(vf2), Projective3f(Translation3f(vf23)).matrix()); + Vector2d vd2; vd2.setRandom(); Vector3d vd23; vd23 << vd2, 0; + VERIFY_MATRIX(glTranslate(vd2), Projective3d(Translation3d(vd23)).matrix()); + + Vector3f vf3; vf3.setRandom(); + VERIFY_MATRIX(glTranslate(vf3), Projective3f(Translation3f(vf3)).matrix()); + Vector3d vd3; vd3.setRandom(); + VERIFY_MATRIX(glTranslate(vd3), Projective3d(Translation3d(vd3)).matrix()); + + Translation<float,3> tf3; tf3.vector().setRandom(); + VERIFY_MATRIX(glTranslate(tf3), Projective3f(tf3).matrix()); + + Translation<double,3> td3; td3.vector().setRandom(); + VERIFY_MATRIX(glTranslate(td3), Projective3d(td3).matrix()); + } + + // scaling (2D and 3D) + { + Vector2f vf2; vf2.setRandom(); Vector3f vf23; vf23 << vf2, 1; + VERIFY_MATRIX(glScale(vf2), Projective3f(Scaling(vf23)).matrix()); + Vector2d vd2; vd2.setRandom(); Vector3d vd23; vd23 << vd2, 1; + VERIFY_MATRIX(glScale(vd2), Projective3d(Scaling(vd23)).matrix()); + + Vector3f vf3; vf3.setRandom(); + VERIFY_MATRIX(glScale(vf3), Projective3f(Scaling(vf3)).matrix()); + Vector3d vd3; vd3.setRandom(); + VERIFY_MATRIX(glScale(vd3), Projective3d(Scaling(vd3)).matrix()); + + UniformScaling<float> usf(internal::random<float>()); + VERIFY_MATRIX(glScale(usf), Projective3f(usf).matrix()); + + UniformScaling<double> usd(internal::random<double>()); + VERIFY_MATRIX(glScale(usd), Projective3d(usd).matrix()); + } + + // uniform + { + const char* vtx = "void main(void) { gl_Position = gl_Vertex; }\n"; + + if(GLEW_VERSION_2_0) + { + #ifdef GL_VERSION_2_0 + const char* frg = "" + "uniform vec2 v2f;\n" + "uniform vec3 v3f;\n" + "uniform vec4 v4f;\n" + "uniform ivec2 v2i;\n" + "uniform ivec3 v3i;\n" + "uniform ivec4 v4i;\n" + "uniform mat2 m2f;\n" + "uniform mat3 m3f;\n" + "uniform mat4 m4f;\n" + "void main(void) { gl_FragColor = vec4(v2f[0]+v3f[0]+v4f[0])+vec4(v2i[0]+v3i[0]+v4i[0])+vec4(m2f[0][0]+m3f[0][0]+m4f[0][0]); }\n"; + + GLint prg_id = createShader(vtx,frg); + + VERIFY_UNIFORM(fv,v2f, Vector2f); + VERIFY_UNIFORM(fv,v3f, Vector3f); + VERIFY_UNIFORM(fv,v4f, Vector4f); + VERIFY_UNIFORMi(v2i, Vector2i); + VERIFY_UNIFORMi(v3i, Vector3i); + VERIFY_UNIFORMi(v4i, Vector4i); + VERIFY_UNIFORM(fv,m2f, Matrix2f); + VERIFY_UNIFORM(fv,m3f, Matrix3f); + VERIFY_UNIFORM(fv,m4f, Matrix4f); + #endif + } + else + std::cerr << "Warning: opengl 2.0 was not tested\n"; + + if(GLEW_VERSION_2_1) + { + #ifdef GL_VERSION_2_1 + const char* frg = "#version 120\n" + "uniform mat2x3 m23f;\n" + "uniform mat3x2 m32f;\n" + "uniform mat2x4 m24f;\n" + "uniform mat4x2 m42f;\n" + "uniform mat3x4 m34f;\n" + "uniform mat4x3 m43f;\n" + "void main(void) { gl_FragColor = vec4(m23f[0][0]+m32f[0][0]+m24f[0][0]+m42f[0][0]+m34f[0][0]+m43f[0][0]); }\n"; + + GLint prg_id = createShader(vtx,frg); + + typedef Matrix<float,2,3> Matrix23f; + typedef Matrix<float,3,2> Matrix32f; + typedef Matrix<float,2,4> Matrix24f; + typedef Matrix<float,4,2> Matrix42f; + typedef Matrix<float,3,4> Matrix34f; + typedef Matrix<float,4,3> Matrix43f; + + VERIFY_UNIFORM(fv,m23f, Matrix23f); + VERIFY_UNIFORM(fv,m32f, Matrix32f); + VERIFY_UNIFORM(fv,m24f, Matrix24f); + VERIFY_UNIFORM(fv,m42f, Matrix42f); + VERIFY_UNIFORM(fv,m34f, Matrix34f); + VERIFY_UNIFORM(fv,m43f, Matrix43f); + #endif + } + else + std::cerr << "Warning: opengl 2.1 was not tested\n"; + + if(GLEW_VERSION_3_0) + { + #ifdef GL_VERSION_3_0 + const char* frg = "#version 150\n" + "uniform uvec2 v2ui;\n" + "uniform uvec3 v3ui;\n" + "uniform uvec4 v4ui;\n" + "out vec4 data;\n" + "void main(void) { data = vec4(v2ui[0]+v3ui[0]+v4ui[0]); }\n"; + + GLint prg_id = createShader(vtx,frg); + + typedef Matrix<unsigned int,2,1> Vector2ui; + typedef Matrix<unsigned int,3,1> Vector3ui; + typedef Matrix<unsigned int,4,1> Vector4ui; + + VERIFY_UNIFORMi(v2ui, Vector2ui); + VERIFY_UNIFORMi(v3ui, Vector3ui); + VERIFY_UNIFORMi(v4ui, Vector4ui); + #endif + } + else + std::cerr << "Warning: opengl 3.0 was not tested\n"; + + #ifdef GLEW_ARB_gpu_shader_fp64 + if(GLEW_ARB_gpu_shader_fp64) + { + #ifdef GL_ARB_gpu_shader_fp64 + const char* frg = "#version 150\n" + "uniform dvec2 v2d;\n" + "uniform dvec3 v3d;\n" + "uniform dvec4 v4d;\n" + "out vec4 data;\n" + "void main(void) { data = vec4(v2d[0]+v3d[0]+v4d[0]); }\n"; + + GLint prg_id = createShader(vtx,frg); + + typedef Vector2d Vector2d; + typedef Vector3d Vector3d; + typedef Vector4d Vector4d; + + VERIFY_UNIFORM(dv,v2d, Vector2d); + VERIFY_UNIFORM(dv,v3d, Vector3d); + VERIFY_UNIFORM(dv,v4d, Vector4d); + #endif + } + else + std::cerr << "Warning: GLEW_ARB_gpu_shader_fp64 was not tested\n"; + #else + std::cerr << "Warning: GLEW_ARB_gpu_shader_fp64 was not tested\n"; + #endif + } + +} diff --git a/unsupported/test/polynomialsolver.cpp b/unsupported/test/polynomialsolver.cpp new file mode 100644 index 000000000..fefeaff01 --- /dev/null +++ b/unsupported/test/polynomialsolver.cpp @@ -0,0 +1,217 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2010 Manuel Yguel <manuel.yguel@gmail.com> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/Polynomials> +#include <iostream> +#include <algorithm> + +using namespace std; + +namespace Eigen { +namespace internal { +template<int Size> +struct increment_if_fixed_size +{ + enum { + ret = (Size == Dynamic) ? Dynamic : Size+1 + }; +}; +} +} + + +template<int Deg, typename POLYNOMIAL, typename SOLVER> +bool aux_evalSolver( const POLYNOMIAL& pols, SOLVER& psolve ) +{ + typedef typename POLYNOMIAL::Index Index; + typedef typename POLYNOMIAL::Scalar Scalar; + + typedef typename SOLVER::RootsType RootsType; + typedef Matrix<Scalar,Deg,1> EvalRootsType; + + const Index deg = pols.size()-1; + + psolve.compute( pols ); + const RootsType& roots( psolve.roots() ); + EvalRootsType evr( deg ); + for( int i=0; i<roots.size(); ++i ){ + evr[i] = std::abs( poly_eval( pols, roots[i] ) ); } + + bool evalToZero = evr.isZero( test_precision<Scalar>() ); + if( !evalToZero ) + { + cerr << "WRONG root: " << endl; + cerr << "Polynomial: " << pols.transpose() << endl; + cerr << "Roots found: " << roots.transpose() << endl; + cerr << "Abs value of the polynomial at the roots: " << evr.transpose() << endl; + cerr << endl; + } + + std::vector<Scalar> rootModuli( roots.size() ); + Map< EvalRootsType > aux( &rootModuli[0], roots.size() ); + aux = roots.array().abs(); + std::sort( rootModuli.begin(), rootModuli.end() ); + bool distinctModuli=true; + for( size_t i=1; i<rootModuli.size() && distinctModuli; ++i ) + { + if( internal::isApprox( rootModuli[i], rootModuli[i-1] ) ){ + distinctModuli = false; } + } + VERIFY( evalToZero || !distinctModuli ); + + return distinctModuli; +} + + + + + + + +template<int Deg, typename POLYNOMIAL> +void evalSolver( const POLYNOMIAL& pols ) +{ + typedef typename POLYNOMIAL::Scalar Scalar; + + typedef PolynomialSolver<Scalar, Deg > PolynomialSolverType; + + PolynomialSolverType psolve; + aux_evalSolver<Deg, POLYNOMIAL, PolynomialSolverType>( pols, psolve ); +} + + + + +template< int Deg, typename POLYNOMIAL, typename ROOTS, typename REAL_ROOTS > +void evalSolverSugarFunction( const POLYNOMIAL& pols, const ROOTS& roots, const REAL_ROOTS& real_roots ) +{ + typedef typename POLYNOMIAL::Scalar Scalar; + + typedef PolynomialSolver<Scalar, Deg > PolynomialSolverType; + + PolynomialSolverType psolve; + if( aux_evalSolver<Deg, POLYNOMIAL, PolynomialSolverType>( pols, psolve ) ) + { + //It is supposed that + // 1) the roots found are correct + // 2) the roots have distinct moduli + + typedef typename POLYNOMIAL::Scalar Scalar; + typedef typename REAL_ROOTS::Scalar Real; + + typedef PolynomialSolver<Scalar, Deg > PolynomialSolverType; + typedef typename PolynomialSolverType::RootsType RootsType; + typedef Matrix<Scalar,Deg,1> EvalRootsType; + + //Test realRoots + std::vector< Real > calc_realRoots; + psolve.realRoots( calc_realRoots ); + VERIFY( calc_realRoots.size() == (size_t)real_roots.size() ); + + const Scalar psPrec = internal::sqrt( test_precision<Scalar>() ); + + for( size_t i=0; i<calc_realRoots.size(); ++i ) + { + bool found = false; + for( size_t j=0; j<calc_realRoots.size()&& !found; ++j ) + { + if( internal::isApprox( calc_realRoots[i], real_roots[j] ), psPrec ){ + found = true; } + } + VERIFY( found ); + } + + //Test greatestRoot + VERIFY( internal::isApprox( roots.array().abs().maxCoeff(), + internal::abs( psolve.greatestRoot() ), psPrec ) ); + + //Test smallestRoot + VERIFY( internal::isApprox( roots.array().abs().minCoeff(), + internal::abs( psolve.smallestRoot() ), psPrec ) ); + + bool hasRealRoot; + //Test absGreatestRealRoot + Real r = psolve.absGreatestRealRoot( hasRealRoot ); + VERIFY( hasRealRoot == (real_roots.size() > 0 ) ); + if( hasRealRoot ){ + VERIFY( internal::isApprox( real_roots.array().abs().maxCoeff(), internal::abs(r), psPrec ) ); } + + //Test absSmallestRealRoot + r = psolve.absSmallestRealRoot( hasRealRoot ); + VERIFY( hasRealRoot == (real_roots.size() > 0 ) ); + if( hasRealRoot ){ + VERIFY( internal::isApprox( real_roots.array().abs().minCoeff(), internal::abs( r ), psPrec ) ); } + + //Test greatestRealRoot + r = psolve.greatestRealRoot( hasRealRoot ); + VERIFY( hasRealRoot == (real_roots.size() > 0 ) ); + if( hasRealRoot ){ + VERIFY( internal::isApprox( real_roots.array().maxCoeff(), r, psPrec ) ); } + + //Test smallestRealRoot + r = psolve.smallestRealRoot( hasRealRoot ); + VERIFY( hasRealRoot == (real_roots.size() > 0 ) ); + if( hasRealRoot ){ + VERIFY( internal::isApprox( real_roots.array().minCoeff(), r, psPrec ) ); } + } +} + + +template<typename _Scalar, int _Deg> +void polynomialsolver(int deg) +{ + typedef internal::increment_if_fixed_size<_Deg> Dim; + typedef Matrix<_Scalar,Dim::ret,1> PolynomialType; + typedef Matrix<_Scalar,_Deg,1> EvalRootsType; + + cout << "Standard cases" << endl; + PolynomialType pols = PolynomialType::Random(deg+1); + evalSolver<_Deg,PolynomialType>( pols ); + + cout << "Hard cases" << endl; + _Scalar multipleRoot = internal::random<_Scalar>(); + EvalRootsType allRoots = EvalRootsType::Constant(deg,multipleRoot); + roots_to_monicPolynomial( allRoots, pols ); + evalSolver<_Deg,PolynomialType>( pols ); + + cout << "Test sugar" << endl; + EvalRootsType realRoots = EvalRootsType::Random(deg); + roots_to_monicPolynomial( realRoots, pols ); + evalSolverSugarFunction<_Deg>( + pols, + realRoots.template cast < + std::complex< + typename NumTraits<_Scalar>::Real + > + >(), + realRoots ); +} + +void test_polynomialsolver() +{ + for(int i = 0; i < g_repeat; i++) + { + CALL_SUBTEST_1( (polynomialsolver<float,1>(1)) ); + CALL_SUBTEST_2( (polynomialsolver<double,2>(2)) ); + CALL_SUBTEST_3( (polynomialsolver<double,3>(3)) ); + CALL_SUBTEST_4( (polynomialsolver<float,4>(4)) ); + CALL_SUBTEST_5( (polynomialsolver<double,5>(5)) ); + CALL_SUBTEST_6( (polynomialsolver<float,6>(6)) ); + CALL_SUBTEST_7( (polynomialsolver<float,7>(7)) ); + CALL_SUBTEST_8( (polynomialsolver<double,8>(8)) ); + + CALL_SUBTEST_9( (polynomialsolver<float,Dynamic>( + internal::random<int>(9,13) + )) ); + CALL_SUBTEST_10((polynomialsolver<double,Dynamic>( + internal::random<int>(9,13) + )) ); + } +} diff --git a/unsupported/test/polynomialutils.cpp b/unsupported/test/polynomialutils.cpp new file mode 100644 index 000000000..5fc968402 --- /dev/null +++ b/unsupported/test/polynomialutils.cpp @@ -0,0 +1,113 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2010 Manuel Yguel <manuel.yguel@gmail.com> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" +#include <unsupported/Eigen/Polynomials> +#include <iostream> + +using namespace std; + +namespace Eigen { +namespace internal { +template<int Size> +struct increment_if_fixed_size +{ + enum { + ret = (Size == Dynamic) ? Dynamic : Size+1 + }; +}; +} +} + +template<typename _Scalar, int _Deg> +void realRoots_to_monicPolynomial_test(int deg) +{ + typedef internal::increment_if_fixed_size<_Deg> Dim; + typedef Matrix<_Scalar,Dim::ret,1> PolynomialType; + typedef Matrix<_Scalar,_Deg,1> EvalRootsType; + + PolynomialType pols(deg+1); + EvalRootsType roots = EvalRootsType::Random(deg); + roots_to_monicPolynomial( roots, pols ); + + EvalRootsType evr( deg ); + for( int i=0; i<roots.size(); ++i ){ + evr[i] = std::abs( poly_eval( pols, roots[i] ) ); } + + bool evalToZero = evr.isZero( test_precision<_Scalar>() ); + if( !evalToZero ){ + cerr << evr.transpose() << endl; } + VERIFY( evalToZero ); +} + +template<typename _Scalar> void realRoots_to_monicPolynomial_scalar() +{ + CALL_SUBTEST_2( (realRoots_to_monicPolynomial_test<_Scalar,2>(2)) ); + CALL_SUBTEST_3( (realRoots_to_monicPolynomial_test<_Scalar,3>(3)) ); + CALL_SUBTEST_4( (realRoots_to_monicPolynomial_test<_Scalar,4>(4)) ); + CALL_SUBTEST_5( (realRoots_to_monicPolynomial_test<_Scalar,5>(5)) ); + CALL_SUBTEST_6( (realRoots_to_monicPolynomial_test<_Scalar,6>(6)) ); + CALL_SUBTEST_7( (realRoots_to_monicPolynomial_test<_Scalar,7>(7)) ); + CALL_SUBTEST_8( (realRoots_to_monicPolynomial_test<_Scalar,17>(17)) ); + + CALL_SUBTEST_9( (realRoots_to_monicPolynomial_test<_Scalar,Dynamic>( + internal::random<int>(18,26) )) ); +} + + + + +template<typename _Scalar, int _Deg> +void CauchyBounds(int deg) +{ + typedef internal::increment_if_fixed_size<_Deg> Dim; + typedef Matrix<_Scalar,Dim::ret,1> PolynomialType; + typedef Matrix<_Scalar,_Deg,1> EvalRootsType; + + PolynomialType pols(deg+1); + EvalRootsType roots = EvalRootsType::Random(deg); + roots_to_monicPolynomial( roots, pols ); + _Scalar M = cauchy_max_bound( pols ); + _Scalar m = cauchy_min_bound( pols ); + _Scalar Max = roots.array().abs().maxCoeff(); + _Scalar min = roots.array().abs().minCoeff(); + bool eval = (M >= Max) && (m <= min); + if( !eval ) + { + cerr << "Roots: " << roots << endl; + cerr << "Bounds: (" << m << ", " << M << ")" << endl; + cerr << "Min,Max: (" << min << ", " << Max << ")" << endl; + } + VERIFY( eval ); +} + +template<typename _Scalar> void CauchyBounds_scalar() +{ + CALL_SUBTEST_2( (CauchyBounds<_Scalar,2>(2)) ); + CALL_SUBTEST_3( (CauchyBounds<_Scalar,3>(3)) ); + CALL_SUBTEST_4( (CauchyBounds<_Scalar,4>(4)) ); + CALL_SUBTEST_5( (CauchyBounds<_Scalar,5>(5)) ); + CALL_SUBTEST_6( (CauchyBounds<_Scalar,6>(6)) ); + CALL_SUBTEST_7( (CauchyBounds<_Scalar,7>(7)) ); + CALL_SUBTEST_8( (CauchyBounds<_Scalar,17>(17)) ); + + CALL_SUBTEST_9( (CauchyBounds<_Scalar,Dynamic>( + internal::random<int>(18,26) )) ); +} + +void test_polynomialutils() +{ + for(int i = 0; i < g_repeat; i++) + { + realRoots_to_monicPolynomial_scalar<double>(); + realRoots_to_monicPolynomial_scalar<float>(); + CauchyBounds_scalar<double>(); + CauchyBounds_scalar<float>(); + } +} diff --git a/unsupported/test/sparse_extra.cpp b/unsupported/test/sparse_extra.cpp new file mode 100644 index 000000000..5dc333424 --- /dev/null +++ b/unsupported/test/sparse_extra.cpp @@ -0,0 +1,149 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2008-2010 Gael Guennebaud <g.gael@free.fr> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + + +// import basic and product tests for deprectaed DynamicSparseMatrix +#define EIGEN_NO_DEPRECATED_WARNING +#include "sparse_basic.cpp" +#include "sparse_product.cpp" +#include <Eigen/SparseExtra> + +template<typename SetterType,typename DenseType, typename Scalar, int Options> +bool test_random_setter(SparseMatrix<Scalar,Options>& sm, const DenseType& ref, const std::vector<Vector2i>& nonzeroCoords) +{ + typedef SparseMatrix<Scalar,Options> SparseType; + { + sm.setZero(); + SetterType w(sm); + std::vector<Vector2i> remaining = nonzeroCoords; + while(!remaining.empty()) + { + int i = internal::random<int>(0,static_cast<int>(remaining.size())-1); + w(remaining[i].x(),remaining[i].y()) = ref.coeff(remaining[i].x(),remaining[i].y()); + remaining[i] = remaining.back(); + remaining.pop_back(); + } + } + return sm.isApprox(ref); +} + +template<typename SetterType,typename DenseType, typename T> +bool test_random_setter(DynamicSparseMatrix<T>& sm, const DenseType& ref, const std::vector<Vector2i>& nonzeroCoords) +{ + sm.setZero(); + std::vector<Vector2i> remaining = nonzeroCoords; + while(!remaining.empty()) + { + int i = internal::random<int>(0,static_cast<int>(remaining.size())-1); + sm.coeffRef(remaining[i].x(),remaining[i].y()) = ref.coeff(remaining[i].x(),remaining[i].y()); + remaining[i] = remaining.back(); + remaining.pop_back(); + } + return sm.isApprox(ref); +} + +template<typename SparseMatrixType> void sparse_extra(const SparseMatrixType& ref) +{ + typedef typename SparseMatrixType::Index Index; + const Index rows = ref.rows(); + const Index cols = ref.cols(); + typedef typename SparseMatrixType::Scalar Scalar; + enum { Flags = SparseMatrixType::Flags }; + + double density = (std::max)(8./(rows*cols), 0.01); + typedef Matrix<Scalar,Dynamic,Dynamic> DenseMatrix; + typedef Matrix<Scalar,Dynamic,1> DenseVector; + Scalar eps = 1e-6; + + SparseMatrixType m(rows, cols); + DenseMatrix refMat = DenseMatrix::Zero(rows, cols); + DenseVector vec1 = DenseVector::Random(rows); + + std::vector<Vector2i> zeroCoords; + std::vector<Vector2i> nonzeroCoords; + initSparse<Scalar>(density, refMat, m, 0, &zeroCoords, &nonzeroCoords); + + if (zeroCoords.size()==0 || nonzeroCoords.size()==0) + return; + + // test coeff and coeffRef + for (int i=0; i<(int)zeroCoords.size(); ++i) + { + VERIFY_IS_MUCH_SMALLER_THAN( m.coeff(zeroCoords[i].x(),zeroCoords[i].y()), eps ); + if(internal::is_same<SparseMatrixType,SparseMatrix<Scalar,Flags> >::value) + VERIFY_RAISES_ASSERT( m.coeffRef(zeroCoords[0].x(),zeroCoords[0].y()) = 5 ); + } + VERIFY_IS_APPROX(m, refMat); + + m.coeffRef(nonzeroCoords[0].x(), nonzeroCoords[0].y()) = Scalar(5); + refMat.coeffRef(nonzeroCoords[0].x(), nonzeroCoords[0].y()) = Scalar(5); + + VERIFY_IS_APPROX(m, refMat); + + // random setter +// { +// m.setZero(); +// VERIFY_IS_NOT_APPROX(m, refMat); +// SparseSetter<SparseMatrixType, RandomAccessPattern> w(m); +// std::vector<Vector2i> remaining = nonzeroCoords; +// while(!remaining.empty()) +// { +// int i = internal::random<int>(0,remaining.size()-1); +// w->coeffRef(remaining[i].x(),remaining[i].y()) = refMat.coeff(remaining[i].x(),remaining[i].y()); +// remaining[i] = remaining.back(); +// remaining.pop_back(); +// } +// } +// VERIFY_IS_APPROX(m, refMat); + + VERIFY(( test_random_setter<RandomSetter<SparseMatrixType, StdMapTraits> >(m,refMat,nonzeroCoords) )); + #ifdef EIGEN_UNORDERED_MAP_SUPPORT + VERIFY(( test_random_setter<RandomSetter<SparseMatrixType, StdUnorderedMapTraits> >(m,refMat,nonzeroCoords) )); + #endif + #ifdef _DENSE_HASH_MAP_H_ + VERIFY(( test_random_setter<RandomSetter<SparseMatrixType, GoogleDenseHashMapTraits> >(m,refMat,nonzeroCoords) )); + #endif + #ifdef _SPARSE_HASH_MAP_H_ + VERIFY(( test_random_setter<RandomSetter<SparseMatrixType, GoogleSparseHashMapTraits> >(m,refMat,nonzeroCoords) )); + #endif + + + // test RandomSetter + /*{ + SparseMatrixType m1(rows,cols), m2(rows,cols); + DenseMatrix refM1 = DenseMatrix::Zero(rows, rows); + initSparse<Scalar>(density, refM1, m1); + { + Eigen::RandomSetter<SparseMatrixType > setter(m2); + for (int j=0; j<m1.outerSize(); ++j) + for (typename SparseMatrixType::InnerIterator i(m1,j); i; ++i) + setter(i.index(), j) = i.value(); + } + VERIFY_IS_APPROX(m1, m2); + }*/ + + +} + +void test_sparse_extra() +{ + for(int i = 0; i < g_repeat; i++) { + int s = Eigen::internal::random<int>(1,50); + CALL_SUBTEST_1( sparse_extra(SparseMatrix<double>(8, 8)) ); + CALL_SUBTEST_2( sparse_extra(SparseMatrix<std::complex<double> >(s, s)) ); + CALL_SUBTEST_1( sparse_extra(SparseMatrix<double>(s, s)) ); + + CALL_SUBTEST_3( sparse_extra(DynamicSparseMatrix<double>(s, s)) ); +// CALL_SUBTEST_3(( sparse_basic(DynamicSparseMatrix<double>(s, s)) )); +// CALL_SUBTEST_3(( sparse_basic(DynamicSparseMatrix<double,ColMajor,long int>(s, s)) )); + + CALL_SUBTEST_3( (sparse_product<DynamicSparseMatrix<float, ColMajor> >()) ); + CALL_SUBTEST_3( (sparse_product<DynamicSparseMatrix<float, RowMajor> >()) ); + } +} diff --git a/unsupported/test/splines.cpp b/unsupported/test/splines.cpp new file mode 100644 index 000000000..1043453dc --- /dev/null +++ b/unsupported/test/splines.cpp @@ -0,0 +1,240 @@ +// This file is part of Eigen, a lightweight C++ template library +// for linear algebra. +// +// Copyright (C) 2010-2011 Hauke Heibel <heibel@gmail.com> +// +// This Source Code Form is subject to the terms of the Mozilla +// Public License v. 2.0. If a copy of the MPL was not distributed +// with this file, You can obtain one at http://mozilla.org/MPL/2.0/. + +#include "main.h" + +#include <unsupported/Eigen/Splines> + +// lets do some explicit instantiations and thus +// force the compilation of all spline functions... +template class Spline<double, 2, Dynamic>; +template class Spline<double, 3, Dynamic>; + +template class Spline<double, 2, 2>; +template class Spline<double, 2, 3>; +template class Spline<double, 2, 4>; +template class Spline<double, 2, 5>; + +template class Spline<float, 2, Dynamic>; +template class Spline<float, 3, Dynamic>; + +template class Spline<float, 3, 2>; +template class Spline<float, 3, 3>; +template class Spline<float, 3, 4>; +template class Spline<float, 3, 5>; + +Spline<double, 2, Dynamic> closed_spline2d() +{ + RowVectorXd knots(12); + knots << 0, + 0, + 0, + 0, + 0.867193179093898, + 1.660330955342408, + 2.605084834823134, + 3.484154586374428, + 4.252699478956276, + 4.252699478956276, + 4.252699478956276, + 4.252699478956276; + + MatrixXd ctrls(8,2); + ctrls << -0.370967741935484, 0.236842105263158, + -0.231401860693277, 0.442245185027632, + 0.344361228532831, 0.773369994120753, + 0.828990216203802, 0.106550882647595, + 0.407270163678382, -1.043452922172848, + -0.488467813584053, -0.390098582530090, + -0.494657189446427, 0.054804824897884, + -0.370967741935484, 0.236842105263158; + ctrls.transposeInPlace(); + + return Spline<double, 2, Dynamic>(knots, ctrls); +} + +/* create a reference spline */ +Spline<double, 3, Dynamic> spline3d() +{ + RowVectorXd knots(11); + knots << 0, + 0, + 0, + 0.118997681558377, + 0.162611735194631, + 0.498364051982143, + 0.655098003973841, + 0.679702676853675, + 1.000000000000000, + 1.000000000000000, + 1.000000000000000; + + MatrixXd ctrls(8,3); + ctrls << 0.959743958516081, 0.340385726666133, 0.585267750979777, + 0.223811939491137, 0.751267059305653, 0.255095115459269, + 0.505957051665142, 0.699076722656686, 0.890903252535799, + 0.959291425205444, 0.547215529963803, 0.138624442828679, + 0.149294005559057, 0.257508254123736, 0.840717255983663, + 0.254282178971531, 0.814284826068816, 0.243524968724989, + 0.929263623187228, 0.349983765984809, 0.196595250431208, + 0.251083857976031, 0.616044676146639, 0.473288848902729; + ctrls.transposeInPlace(); + + return Spline<double, 3, Dynamic>(knots, ctrls); +} + +/* compares evaluations against known results */ +void eval_spline3d() +{ + Spline3d spline = spline3d(); + + RowVectorXd u(10); + u << 0.351659507062997, + 0.830828627896291, + 0.585264091152724, + 0.549723608291140, + 0.917193663829810, + 0.285839018820374, + 0.757200229110721, + 0.753729094278495, + 0.380445846975357, + 0.567821640725221; + + MatrixXd pts(10,3); + pts << 0.707620811535916, 0.510258911240815, 0.417485437023409, + 0.603422256426978, 0.529498282727551, 0.270351549348981, + 0.228364197569334, 0.423745615677815, 0.637687289287490, + 0.275556796335168, 0.350856706427970, 0.684295784598905, + 0.514519311047655, 0.525077224890754, 0.351628308305896, + 0.724152914315666, 0.574461155457304, 0.469860285484058, + 0.529365063753288, 0.613328702656816, 0.237837040141739, + 0.522469395136878, 0.619099658652895, 0.237139665242069, + 0.677357023849552, 0.480655768435853, 0.422227610314397, + 0.247046593173758, 0.380604672404750, 0.670065791405019; + pts.transposeInPlace(); + + for (int i=0; i<u.size(); ++i) + { + Vector3d pt = spline(u(i)); + VERIFY( (pt - pts.col(i)).norm() < 1e-14 ); + } +} + +/* compares evaluations on corner cases */ +void eval_spline3d_onbrks() +{ + Spline3d spline = spline3d(); + + RowVectorXd u = spline.knots(); + + MatrixXd pts(11,3); + pts << 0.959743958516081, 0.340385726666133, 0.585267750979777, + 0.959743958516081, 0.340385726666133, 0.585267750979777, + 0.959743958516081, 0.340385726666133, 0.585267750979777, + 0.430282980289940, 0.713074680056118, 0.720373307943349, + 0.558074875553060, 0.681617921034459, 0.804417124839942, + 0.407076008291750, 0.349707710518163, 0.617275937419545, + 0.240037008286602, 0.738739390398014, 0.324554153129411, + 0.302434111480572, 0.781162443963899, 0.240177089094644, + 0.251083857976031, 0.616044676146639, 0.473288848902729, + 0.251083857976031, 0.616044676146639, 0.473288848902729, + 0.251083857976031, 0.616044676146639, 0.473288848902729; + pts.transposeInPlace(); + + for (int i=0; i<u.size(); ++i) + { + Vector3d pt = spline(u(i)); + VERIFY( (pt - pts.col(i)).norm() < 1e-14 ); + } +} + +void eval_closed_spline2d() +{ + Spline2d spline = closed_spline2d(); + + RowVectorXd u(12); + u << 0, + 0.332457030395796, + 0.356467130532952, + 0.453562180176215, + 0.648017921874804, + 0.973770235555003, + 1.882577647219307, + 2.289408593930498, + 3.511951429883045, + 3.884149321369450, + 4.236261590369414, + 4.252699478956276; + + MatrixXd pts(12,2); + pts << -0.370967741935484, 0.236842105263158, + -0.152576775123250, 0.448975001279334, + -0.133417538277668, 0.461615613865667, + -0.053199060826740, 0.507630360006299, + 0.114249591147281, 0.570414135097409, + 0.377810316891987, 0.560497102875315, + 0.665052120135908, -0.157557441109611, + 0.516006487053228, -0.559763292174825, + -0.379486035348887, -0.331959640488223, + -0.462034726249078, -0.039105670080824, + -0.378730600917982, 0.225127015099919, + -0.370967741935484, 0.236842105263158; + pts.transposeInPlace(); + + for (int i=0; i<u.size(); ++i) + { + Vector2d pt = spline(u(i)); + VERIFY( (pt - pts.col(i)).norm() < 1e-14 ); + } +} + +void check_global_interpolation2d() +{ + typedef Spline2d::PointType PointType; + typedef Spline2d::KnotVectorType KnotVectorType; + typedef Spline2d::ControlPointVectorType ControlPointVectorType; + + ControlPointVectorType points = ControlPointVectorType::Random(2,100); + + KnotVectorType chord_lengths; // knot parameters + Eigen::ChordLengths(points, chord_lengths); + + // interpolation without knot parameters + { + const Spline2d spline = SplineFitting<Spline2d>::Interpolate(points,3); + + for (Eigen::DenseIndex i=0; i<points.cols(); ++i) + { + PointType pt = spline( chord_lengths(i) ); + PointType ref = points.col(i); + VERIFY( (pt - ref).matrix().norm() < 1e-14 ); + } + } + + // interpolation with given knot parameters + { + const Spline2d spline = SplineFitting<Spline2d>::Interpolate(points,3,chord_lengths); + + for (Eigen::DenseIndex i=0; i<points.cols(); ++i) + { + PointType pt = spline( chord_lengths(i) ); + PointType ref = points.col(i); + VERIFY( (pt - ref).matrix().norm() < 1e-14 ); + } + } +} + + +void test_splines() +{ + CALL_SUBTEST( eval_spline3d() ); + CALL_SUBTEST( eval_spline3d_onbrks() ); + CALL_SUBTEST( eval_closed_spline2d() ); + CALL_SUBTEST( check_global_interpolation2d() ); +} |