diff options
Diffstat (limited to 'bench/tensors/README')
| -rw-r--r-- | bench/tensors/README | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/bench/tensors/README b/bench/tensors/README new file mode 100644 index 000000000..4398aa81b --- /dev/null +++ b/bench/tensors/README @@ -0,0 +1,12 @@ +Each benchmark comes in 2 flavors: one that runs on CPU, and one that runs on GPU. + +To compile the floating point CPU benchmarks, simply call: +g++ tensor_benchmarks_cpu.cc benchmark_main.cc -I ../../ -std=c++11 -O3 -DNDEBUG -pthread -mavx -o benchmarks_cpu + +To compile the floating point GPU benchmarks, simply call: +nvcc tensor_benchmarks_gpu.cu benchmark_main.cc -I ../../ -std=c++11 -O2 -DNDEBUG -arch compute_35 -o benchmarks_gpu + + +To compile the half float GPU 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 -arch compute_53 -o benchmarks_fp16_gpu + |