cory-master/BabelStream
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
49 Commits 1 Branch 0 Tags 2.5 MiB
C++ 52.4%
Fortran 10.1%
CMake 9.7%
Java 7.3%
Shell 5.5%
Other 15%
ec9d73b8d5
Go to file
Tom Deakin ec9d73b8d5 CUDA bug: ARRAY_SIZE on CLI not being resized 
The ARRAY_SIZE was being resized before the CLI args were read
2015-07-27 16:49:36 +01:00
results Add S9150 result 2015-07-22 12:44:07 +01:00
.gitignore Add .gitignore file 2015-07-16 17:35:39 +01:00
cl.hpp Add cl.hpp from Khronos website 2015-07-15 23:20:19 +01:00
cuda-stream.cu CUDA bug: ARRAY_SIZE on CLI not being resized 2015-07-27 16:49:36 +01:00
LICENSE Add 3-clause BSD license file 2015-07-15 23:36:08 +01:00
Makefile Update Makefile with all and cuda stuff 2015-07-16 18:16:27 +01:00
ocl-stream-kernels.cl Add a float option to the kernel 2015-07-23 12:12:02 +01:00
ocl-stream.cpp Bug fix: sizes array wasn't updating with ARRAY_SIZE argument 2015-07-27 13:44:07 +01:00
README.md Update README 2015-07-16 18:23:28 +01:00

README.md

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.