aboutsummaryrefslogtreecommitdiff
path: root/auxprogs
AgeCommit message (Expand)Author
2007-04-05Handle some more types: {REAL,INTEGER}{4,8} and 2INT. Also a changesewardj
2007-03-29Test some Fortran types.sewardj
2007-03-26Add a variant of gsl16test which handles the newer gsl-1.9 package.sewardj
2007-03-08Horrible hacks to make 'make dist' work properly. Previously it onlysewardj
2007-02-08Handle type MPI_PACKED and associated functions PMPI_Packed andsewardj
2007-01-16Inline a bunch of helper functions, in an attempt to minimisesewardj
2007-01-08Update copyright dates.sewardj
2007-01-08Update for 2007.sewardj
2007-01-06Fixes for MPICH on amd64-linux.sewardj
2006-12-10Fix installation of libmpiwrap.so on the primary platform.sewardj
2006-11-24- remove some 'inline' directives so as to make stack backtracessewardj
2006-11-23Fix compilation warning, and partially de-leak.sewardj
2006-10-17Add a simple script which drives 'kdiff3' through a large source treesewardj
2006-10-17Merge r6201: Fix compile warning on aix.sewardj
2006-10-17Merge r6139:sewardj
2006-10-17Merge r6092 and some of r6093:sewardj
2006-10-17Merge r6086:sewardj
2006-10-14Create a new module, m_vki, and move all knowledge about the kernelsewardj
2006-07-06A patch for the "Open POSIX Test Suite"sewardj
2006-06-24handy script to decode ppc instructionscerion
2006-06-05Update copyright dates.sewardj
2006-06-05Restrict to *.[chS]; otherwise it ends up losing permissions on sewardj
2006-06-01Added a useful script.njn
2006-05-21(1) build libmpiwrap.so with -fPIC, not -fpic.sewardj
2006-04-13Not all MPI implementations define MPI_UNSIGNED_LONG_LONG.sewardj
2006-03-31Terminology change: previously in Memcheck we had the four states:njn
2006-03-28Only complain once for each missing wrapper.sewardj
2006-03-27Merge in the COMPVBITS branch to the trunk. This is a big change tonjn
2006-03-12Sigh; rename mpiwrap.c to libmpiwrap.c so that 'make dist' doesn't barfsewardj
2006-03-12LAM/MPI compile fixsewardj
2006-03-12sizeofOneNamedTy(): handle long double correctly on non-x86/amd64 platforms.sewardj
2006-03-12A 64-bit fixsewardj
2006-03-10Quadrics MPI build fixes.sewardj
2006-03-10Make sure we get the right headers, not whatever happens to be alreadysewardj
2006-03-10Add a (rather ingenious, if I do say so myself) program to test thesewardj
2006-03-10Even more MPI wrappers.sewardj
2006-03-10Add a bunch more wrappers and generally tidy up a bit.sewardj
2006-03-10* try to handle MPI_{LONG,DOUBLE,SHORT}_INT better (despite the bestsewardj
2006-03-10- Improve handling of MPI base typessewardj
2006-03-09Give *all* MPI-1.1 and MPI-2 functions a wrapper; most of them get asewardj
2006-03-09Add a 'quiet' option to make it shut up except for showing errors.sewardj
2006-03-08More MPICH build fixes.sewardj
2006-03-08Add showCombiner and move showTy to a better place.sewardj
2006-03-08New wrapper, and an MPICH build fix.sewardj
2006-03-08MPI build system refinements: just base everything off mpicc, and don'tsewardj
2006-03-08walk_type: handle all remaining MPI1 combiners ({H,}VECTOR andsewardj
2006-03-04Fix a type-size subtlety.sewardj
2006-03-03More futzing with the machinery for traversing datatypes.sewardj
2006-03-03Beginnings of proper MPI user type-walking code.sewardj
2006-03-02Detect/select 'mpicc' (from --with-mpicc=) and use that to buildsewardj