| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Add measure_launch_oh benchmark and make target | Joshua Bakita | 2024-02-26 |
| | | | | | | | | Benchmark supports: => Warms up the GPU and kernel code before sampling => Uses a flag in zero-copy memory to track when a kernel begins => Outputs summary statistics to stderr, and sample data to stdout | ||
| * | Allow custom nvcc location when running make + ignore gdb history | Joshua Bakita | 2023-10-25 |
| | | | | | | To specify a custom path to nvcc when building: `make NVCC=/my/path/to/nvcc` | ||
| * | Add preemption_logger benchmark, make target, and fix d82c60c | Joshua Bakita | 2023-07-06 |
| Benchmark supports: => Spinning on-GPU until some number of preemptions have occured => Monitoring GPU scheduling by logging preempt and resume times => Logging the above as raw GPU, or converted CPU, times => Measuring launch overheads Also imports task_host_utilities.cu from cuda_scheduling_examiner as of commit 9fc0ca898ef64b82cbc3734c60405723650bc66f. This is needed for timing logic used in both preemption_logger and mon_cross_ctx_copies, thus the latter would not compile prior to this commit. Also adds a new testbench helper, and a .gitignore for binaries. | |||
 |
index : gpu-microbench.git | |
| Lightweight, hyper-accurate microbenchmarks and measurement tools for GPU scheduling examination. | Joshua J Bakita |
| summaryrefslogtreecommitdiffstats |
path: root/.gitignore