[Topi][Cuda]Optimizations of global_ave_pool for NHWC layout #5450
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Outdated suggestions cannot be applied.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.
The runtime of global_ave_pool took about 14.8% in Resnet50_v2 with batchsize of 32, when Tensor Core is enabled on Tesla T4 GPU. The runtime decreased to 0.134%, after optimizations in this PR were made for NHWC layout. The results of unit tests are listed below, and the latency is reported with unit of ms. As we can see from the table, great performance improvements have been achieved.
@Hzfengsy @Laurawly @vinx13 @jwfromm Please help to review