[Operator] Make Convolution gemms fusible by resolving to batch_matmul#279
Merged
yaoyaoding merged 2 commits intohidet-org:mainfrom Jun 16, 2023
Merged
[Operator] Make Convolution gemms fusible by resolving to batch_matmul#279yaoyaoding merged 2 commits intohidet-org:mainfrom
yaoyaoding merged 2 commits intohidet-org:mainfrom
Conversation
Member
|
Thanks @hjjq ! |
vadiklyutiy
added a commit
that referenced
this pull request
Jul 22, 2024
Right now we have sufficient fixed overhead for model run (#279). **no cudagraph** Below: run of an empty model, no cudagraph times in ms. Before. Inductor overhead is 0.052 = 0.032 + 0.02 where 0.02 is overhead before entering in compiler and 0.032 directly inductor overhead. Hidet overhead is 0.205 = 0.185 + 0.02 After. Hidet overhead is 0.068 = 0.048 + 0.02 Overhead reduced from 0.185ms -> 0.048ms or by 3.85x **cudagraph** Before 0.162ms After 0.124ms Inductor 0.88ms For cudagraph there is one more room for improvement(left TODO in code).
vadiklyutiy
added a commit
that referenced
this pull request
Jul 23, 2024
Right now we have sufficient fixed overhead for model run (#279). **no cudagraph** Below: run of an empty model, no cudagraph times in ms. Before. Inductor overhead is 0.052 = 0.032 + 0.02 where 0.02 is overhead before entering in compiler and 0.032 directly inductor overhead. Hidet overhead is 0.205 = 0.185 + 0.02 After. Hidet overhead is 0.068 = 0.048 + 0.02 Overhead reduced from 0.185ms -> 0.048ms or by 3.85x **cudagraph** Before 0.162ms After 0.124ms Inductor 0.88ms For cudagraph there is one more room for improvement(left TODO in code).
vadiklyutiy
added a commit
that referenced
this pull request
Dec 26, 2024
Right now we have sufficient fixed overhead for model run (#279). **no cudagraph** Below: run of an empty model, no cudagraph times in ms. Before. Inductor overhead is 0.052 = 0.032 + 0.02 where 0.02 is overhead before entering in compiler and 0.032 directly inductor overhead. Hidet overhead is 0.205 = 0.185 + 0.02 After. Hidet overhead is 0.068 = 0.048 + 0.02 Overhead reduced from 0.185ms -> 0.048ms or by 3.85x **cudagraph** Before 0.162ms After 0.124ms Inductor 0.88ms For cudagraph there is one more room for improvement(left TODO in code).
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
No description provided.