aboutsummaryrefslogtreecommitdiffhomepage
path: root/bench/tensors/README
diff options
context:
space:
mode:
Diffstat (limited to 'bench/tensors/README')
-rw-r--r--bench/tensors/README10
1 files changed, 7 insertions, 3 deletions
diff --git a/bench/tensors/README b/bench/tensors/README
index 3a5fdbe17..69342cc9c 100644
--- a/bench/tensors/README
+++ b/bench/tensors/README
@@ -14,8 +14,12 @@ nvcc tensor_benchmarks_fp16_gpu.cu benchmark_main.cc -I ../../ -std=c++11 -O2 -D
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 the benchmark for SYCL, using ComputeCpp you currently need 2 passes (only for translation units containing device code):
+To compile and run the benchmark for SYCL, using ComputeCpp you currently need following 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
+{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 -DEIGEN_USE_SYCL=1
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
+clang++ -O3 -c benchmark_main.cc -pthread -I ../../ -D_GLIBCXX_USE_CXX11_ABI=0 -DEIGEN_USE_SYCL=1 -std=c++11 -o benchmark_main.o
+clang++ -O3 tensor_benchmarks_sycl_include_headers.cc -pthread -I ../../ -I {ComputeCpp_ROOT}/include/ -L {ComputeCpp_ROOT}/lib/ -lComputeCpp -lOpenCL -D_GLIBCXX_USE_CXX11_ABI=0 -DEIGEN_USE_SYCL=1 -std=c++11 benchmark_main.o -o tensor_benchmark_sycl
+export LD_LIBRARY_PATH={ComputeCpp_ROOT}/lib
+3. Run the benchmark
+./tensor_benchmark_sycl