Allison Vacanti ef3e1594eb Implement manual timers. ...

See the new thrust/sort/basic.cu benchmark for usage.

Other notable changes:

- Updated summary column names:
  - Cold GPU -> GPU Time
  - Cold CPU -> CPU Time
  - Hot GPU  -> Batch GPU
- Removed CPU timings from measure_hot
  - They'd been hidden for a while, and aren't really useful.
- Moved the throughput calcs to measure_cold
  - `timer` will disable `hot` timings, still want throughput
  - `cold` timings make more sense for throughput, global BW numbers
    are meaningless if the data is sitting in L2.

2021-02-17 18:48:26 -05:00

nvbench

Implement manual timers.

2021-02-17 18:48:26 -05:00

testing

Update benchmark macros:

2021-02-16 16:08:38 -05:00

CMakeLists.txt

Bump CMake to 3.18.3 for NVCC/MSVC/C++17 bugfixes.

2021-01-14 17:46:09 -05:00

Description

CUDA Kernel Benchmarking Library

benchmarkcudacuda-kernelsgpukernel-benchmarknvidiaperformance

Apache-2.0 2.6 MiB

Languages

Cuda 62.6%

C++ 15%

Python 11.8%

Shell 5.4%

CMake 5.2%