Unify the block/grid strategy and implementation of ReduceLastDim and ReduceAny. #34436
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
✅ This PR's description meets the template requirements! |
|
Thanks for your contribution! |
|
LGTM |
Xreki
changed the title
Xreki
approved these changes
Aug 2, 2021
| @@ -524,18 +531,20 @@ static __device__ T WarpReduce(T val, ReduceOp reducer) { | |||
| template <typename T, typename ReduceOp> | |||
| static __device__ T BlockXReduce(T val, ReduceOp reducer) { | |||
| using detail::kWarpSize; | |||
| __shared__ T shared[kWarpSize]; | |||
| __shared__ T shared[2 * kWarpSize]; | |||
There was a problem hiding this comment.
为什么是2 * kWarpSize？后续可以考虑继续优化下这个函数，使得它可以作为一个基础函数，可以适用于如softmax、batch_norm等算子的使用场景。
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
PR types
Performance optimization
PR changes
OPs
Describe
Unify the block/grid strategy and implementation of ReduceLastDim and ReduceAny
解决了在brocast反向时，reduce最后一维很小时性能差的问题，且优化了 ReduceLastDim的实现，提升了部分case性能。