Add warmup_runs to TBE benchmarks and run at least 1 warmup iter #2163
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
We observe an extremely long
cudaLaunchKernel
time for the firstkernel launch after switching to CUDA 12. This causes the performance
of TBE to degrade if
warmup_runs=0
. This diff modifiesbenchmark_requests
which is used extensively in TBE benchmarks torun at least one warm up iteration even when
warmup_runs=0
toexclude the first kernel time from the profiling result. Moreover, we
add
--warmup-runs
to every TBE benchmarks to allow the users toincrease the warmup iterations.
Differential Revision: D51603915