Caching cudaFunctorAttributes and whether L1/Shmem prefer was set #3151
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Outdated suggestions cannot be applied.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.
This reduces launch latencies, and closes the gap between a raw CUDA
launch and Kokkos Launch to about 0.2us (empty Kernel parallel_for).
Test case comparison the different times are non-fenced, and fenced after each kernel call. In parenthesis fenced with an extra fence after the Repeats loop (doesn't matter, since I can't enqueue so many kernels anyway, so it adds like 5us/Repeats).
Old:
New