aboutsummaryrefslogtreecommitdiff
path: root/bench/tensors/README
diff options
context:
space:
mode:
authorYi Kong <yikong@google.com>2022-02-25 15:53:09 +0000
committerAutomerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com>2022-02-25 15:53:09 +0000
commit10f298fc4175c1b8537c674f654a070c871960e5 (patch)
treefb979fb4cf4f8052c8cc66b1ec9516d91fcd859b /bench/tensors/README
parent892aea0d75825c43d5b630e2060622cbba23694c (diff)
parent79df15ea886a5fc1b85de433f9b3518c68934bae (diff)
downloadeigen-10f298fc4175c1b8537c674f654a070c871960e5.tar.gz
Original change: https://android-review.googlesource.com/c/platform/external/eigen/+/1999079 Change-Id: I0c5108390c595f0d39af8797875f2b88accb7b56
Diffstat (limited to 'bench/tensors/README')
-rw-r--r--bench/tensors/README13
1 files changed, 6 insertions, 7 deletions
diff --git a/bench/tensors/README b/bench/tensors/README
index 3a5fdbe17..dcbf0217a 100644
--- a/bench/tensors/README
+++ b/bench/tensors/README
@@ -11,11 +11,10 @@ nvcc tensor_benchmarks_gpu.cu benchmark_main.cc -I ../../ -std=c++11 -O2 -DNDEBU
We also provide a version of the generic GPU tensor benchmarks that uses half floats (aka fp16) instead of regular floats. To compile these benchmarks, simply call the command line below. You'll need a recent GPU that supports compute capability 5.3 or higher to run them and nvcc 7.5 or higher to compile the code.
nvcc tensor_benchmarks_fp16_gpu.cu benchmark_main.cc -I ../../ -std=c++11 -O2 -DNDEBUG -use_fast_math -ftz=true -arch compute_53 -o benchmarks_fp16_gpu
-last but not least, we also provide a suite of benchmarks to measure the scalability of the contraction code on CPU. To compile these benchmarks, call
-g++ contraction_benchmarks_cpu.cc benchmark_main.cc -I ../../ -std=c++11 -O3 -DNDEBUG -pthread -mavx -o benchmarks_cpu
+To compile and run the benchmark for SYCL, using ComputeCpp, simply run the
+following commands:
+1. export COMPUTECPP_PACKAGE_ROOT_DIR={PATH TO COMPUTECPP ROOT DIRECTORY}
+2. bash eigen_sycl_bench.sh
-To compile the benchmark for SYCL, using ComputeCpp you currently need 2 passes (only for translation units containing device code):
-1. The device compilation pass that generates the device code (SYCL kernels and referenced device functions) and glue code needed by the host compiler to reference the device code from host code.
-{ComputeCpp_ROOT}/bin/compute++ -I ../../ -I {ComputeCpp_ROOT}/include/ -std=c++11 -mllvm -inline-threshold=1000 -Wno-ignored-attributes -sycl -intelspirmetadata -emit-llvm -no-serial-memop -sycl-compress-name -DBUILD_PLATFORM_SPIR -DNDBUG -O3 -c tensor_benchmarks_sycl.cc
-2. The host compilation pass that generates the final host binary.
-clang++-3.7 -include tensor_benchmarks_sycl.sycl benchmark_main.cc tensor_benchmarks_sycl.cc -pthread -I ../../ -I {ComputeCpp_ROOT}/include/ -L {ComputeCpp_ROOT}/lib/ -lComputeCpp -lOpenCL -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 -o tensor_benchmark_sycl
+Last but not least, we also provide a suite of benchmarks to measure the scalability of the contraction code on CPU. To compile these benchmarks, call
+g++ contraction_benchmarks_cpu.cc benchmark_main.cc -I ../../ -std=c++11 -O3 -DNDEBUG -pthread -mavx -o benchmarks_cpu