onnxruntime
Patching cuda profiler with enhancements
#9214
Merged

Patching cuda profiler with enhancements #9214

RandySheriffH merged 6 commits into master from ProfileConcurrentCudaKernel
RandySheriffH
RandySheriffH profiler concurrent cuda kernel to keep parallelism
ff6f166b
pranavsharma
pranavsharma dismissed these changes on 2021-09-29
RandySheriffH RandySheriffH changed the title [WIP] Profiler concurrent cuda kernel to keep multi-stream parallelism Profiler concurrent cuda kernel to keep multi-stream parallelism 4 years ago
RandySheriffH exclude cuda version < 11.0
474b6a85
RandySheriffH RandySheriffH dismissed their stale review via 474b6a85 4 years ago
RandySheriffH adjust logic
0c4c6053
RandySheriffH fix test
59297b3e
RandySheriffH adjust macro
ddf208a6
RandySheriffH move macro to cc file
31e0ba11
RandySheriffH RandySheriffH changed the title Profiler concurrent cuda kernel to keep multi-stream parallelism Patching cuda profiler with enhancements 4 years ago
stevenlix
RandySheriffH
stevenlix
stevenlix stevenlix requested a review from stevenlix stevenlix 4 years ago
stevenlix
stevenlix approved these changes on 2021-09-30
RandySheriffH RandySheriffH merged ffca0b77 into master 4 years ago
RandySheriffH RandySheriffH deleted the ProfileConcurrentCudaKernel branch 4 years ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone