| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Fix unlimited iterations in constant_cycles_kernel | Joshua Bakita | 2025-02-04 |
| | | |||
| * | Ensure all benchmarks support --help and cleanup | Joshua Bakita | 2024-02-26 |
| | | |||
| * | Split SAFE() macro into API-specific typed variants | Joshua Bakita | 2024-02-19 |
| | | | | | | | | | | Avoids incorrectly interpreting CUDA Driver Library error codes as though they were CUDA Runtime Library error codes (the numbering is similar, but not identical). Also cleans up how we initialize and terminate a context for capability checking in `mon_cross_ctx_copies`. | ||
| * | Add constant_cycles_kernel benchmark + header split and Makefile | Joshua Bakita | 2023-06-09 |
| Benchmark supports: => Looping on the GPU for a specified number of iterations => Looping infinitely on the GPU => Logging the sum time (ns and ms) for all iterations to complete Also splits `testbench.h` out of `copy_testbench.h` for use in other benchmarks. | |||
 |
index : gpu-microbench.git | |
| Lightweight, hyper-accurate microbenchmarks and measurement tools for GPU scheduling examination. | Joshua J Bakita |
| summaryrefslogtreecommitdiffstats |