GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-06-04 18:54:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Replace usage of CudaStreamDevice with GpuStreamDevice in tensor benchmarks GPU

Browse Source
This commit is contained in:
Alejandro Acosta 2023-05-29 17:23:58 +01:00 committed by Antonio Sánchez
parent 8c43bf2b5b
commit 07e4604b19
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
bench/tensors/tensor_benchmarks_fp16_gpu.cu
View File

@ -10,7 +10,7 @@
#define BM_FuncGPU(FUNC) \
static void BM_##FUNC(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, Eigen::half> suite(device, N); \
cudaDeviceSynchronize(); \
@ -40,7 +40,7 @@ BM_FuncGPU(fullReduction);
#define BM_FuncWithInputDimsGPU(FUNC, D1, D2, D3) \
static void BM_##FUNC##_##D1##x##D2##x##D3(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, Eigen::half> suite(device, D1, D2, D3); \
cudaDeviceSynchronize(); \
@ -59,7 +59,7 @@ BM_FuncWithInputDimsGPU(contraction, N, N, 64);
#define BM_FuncWithKernelDimsGPU(FUNC, DIM1, DIM2) \
static void BM_##FUNC##_##DIM1##x##DIM2(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, Eigen::half> suite(device, N); \
cudaDeviceSynchronize(); \

6
bench/tensors/tensor_benchmarks_gpu.cu
View File

@ -10,7 +10,7 @@
#define BM_FuncGPU(FUNC) \
static void BM_##FUNC(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, float> suite(device, N); \
cudaDeviceSynchronize(); \
@ -40,7 +40,7 @@ BM_FuncGPU(fullReduction);
#define BM_FuncWithInputDimsGPU(FUNC, D1, D2, D3) \
static void BM_##FUNC##_##D1##x##D2##x##D3(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, float> suite(device, D1, D2, D3); \
cudaDeviceSynchronize(); \
@ -59,7 +59,7 @@ BM_FuncWithInputDimsGPU(contraction, N, N, 64);
#define BM_FuncWithKernelDimsGPU(FUNC, DIM1, DIM2) \
static void BM_##FUNC##_##DIM1##x##DIM2(int iters, int N) { \
StopBenchmarkTiming(); \
Eigen::CudaStreamDevice stream; \
Eigen::GpuStreamDevice stream; \
Eigen::GpuDevice device(&stream); \
BenchmarkSuite<Eigen::GpuDevice, float> suite(device, N); \
cudaDeviceSynchronize(); \