[CINN]Softmax optimization based on bucket splitting strategy #71263
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
xkkkkkk23
force-pushed
the
develop
branch
10 times, most recently
from
f757909 to
f13317f
Compare
lshpku
reviewed
Feb 26, 2025
lshpku
reviewed
Feb 26, 2025
lshpku
reviewed
Feb 26, 2025
xkkkkkk23
force-pushed
the
develop
branch
12 times, most recently
from
07f676a to
27490cb
Compare
lshpku
reviewed
Feb 27, 2025
lshpku
reviewed
Feb 27, 2025
lshpku
approved these changes
Feb 28, 2025
Enigmatisms
pushed a commit
to Enigmatisms/Paddle
that referenced
this pull request
Mar 6, 2025
…Paddle#71263) * [CINN]Softmax optimization based on bucket splitting strategy
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Outdated suggestions cannot be applied.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 Category
CINNPR Types
ImprovementsDescription
softmax算子初始编译后只会产生一个kernel，其中分配1024个线程，这对于小规模输入来说，有大量资源闲置浪费，修改后，细化分桶，为不同规模输入分配不同的线程组合及计算策略。其次，kernel中的for循环的判断条件需要每次重复进行计算，严重拉慢运算速度，修改后为其设置定值，提升速度。
Pcard-85711