Go to file
2015-07-31 15:35:40 +01:00
CL new files 2015-07-28 11:37:50 +01:00
results Fix opencl result file binary errors 2015-07-31 15:26:22 +01:00
.gitignore new files 2015-07-28 11:37:50 +01:00
common.cpp Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
common.h Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
cuda-stream.cu Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
LICENSE Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
Makefile Add common.h to dependancy of common.o 2015-07-31 14:58:05 +01:00
ocl-stream-kernels.cl Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
ocl-stream.cpp Remove trailing whitespaces 2015-07-31 15:35:40 +01:00
README.md Update README 2015-07-16 18:23:28 +01:00

GPU-STREAM

Measure memory transfer rates to/from global device memory on GPUs. This benchmark is similar in spirit, and based on, the STREAM benchmark [1] for CPUs.

Unlike other GPU memory bandwidth benchmarks this does not include the PCIe transfer time.

Usage

Build the OpenCL and CUDA binaries with make

Run the OpenCL version with ./gpu-stream-ocl and the CUDA version with ./gpu-stream-cuda

Results

Sample results can be found in the results subdirectory. If you would like to submit updated results, please submit a Pull Request.

[1]: McCalpin, John D., 1995: "Memory Bandwidth and Machine Balance in Current High Performance Computers", IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, December 1995.