CUDA Parallel Streams & UniformGridGPU Benchmark
- LB on GPU, Uniform Grid Benchmark app - helper class to schedule tasks to multiple CUDA streams
Showing
- apps/benchmarks/CMakeLists.txt 1 addition, 0 deletionsapps/benchmarks/CMakeLists.txt
- apps/benchmarks/UniformGridGPU/CMakeLists.txt 6 additions, 0 deletionsapps/benchmarks/UniformGridGPU/CMakeLists.txt
- apps/benchmarks/UniformGridGPU/UniformGridGPU.cpp 180 additions, 0 deletionsapps/benchmarks/UniformGridGPU/UniformGridGPU.cpp
- apps/benchmarks/UniformGridGPU/UniformGridGPU.gen.py 59 additions, 0 deletionsapps/benchmarks/UniformGridGPU/UniformGridGPU.gen.py
- apps/benchmarks/UniformGridGPU/UniformGridGPU.prm 27 additions, 0 deletionsapps/benchmarks/UniformGridGPU/UniformGridGPU.prm
- apps/benchmarks/UniformGridGPU/UniformGridGPUSmall.prm 27 additions, 0 deletionsapps/benchmarks/UniformGridGPU/UniformGridGPUSmall.prm
- src/cuda/CMakeLists.txt 1 addition, 1 deletionsrc/cuda/CMakeLists.txt
- src/cuda/CudaRAII.h 84 additions, 54 deletionssrc/cuda/CudaRAII.h
- src/cuda/ParallelStreams.cpp 113 additions, 0 deletionssrc/cuda/ParallelStreams.cpp
- src/cuda/ParallelStreams.h 100 additions, 0 deletionssrc/cuda/ParallelStreams.h
- src/cuda/communication/UniformGPUScheme.h 7 additions, 7 deletionssrc/cuda/communication/UniformGPUScheme.h
- src/cuda/communication/UniformGPUScheme.impl.h 42 additions, 44 deletionssrc/cuda/communication/UniformGPUScheme.impl.h
Please register or sign in to comment