Improve build time by ~30% #539
Merged
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
[ghstack-poisoned]
danthe3rd
pushed a commit
that referenced
this pull request
Nov 24, 2022
ghstack-source-id: 504b6d0a01cf4df9daa82264544e01da466f83a3 Pull Request resolved: #539
facebook-github-bot
added
the
CLA Signed
[ghstack-poisoned]
danthe3rd
pushed a commit
that referenced
this pull request
Nov 24, 2022
ghstack-source-id: 4b2445fe3c83eef3282643862ed83cef85dc5997 Pull Request resolved: #539
[ghstack-poisoned]
danthe3rd
pushed a commit
that referenced
this pull request
Nov 24, 2022
ghstack-source-id: eee2e10144ca54bb23e34d6ff5988faa3308c08d Pull Request resolved: #539
[ghstack-poisoned]
danthe3rd
pushed a commit
that referenced
this pull request
Nov 24, 2022
ghstack-source-id: bb993fcd50536e112fcb478e7128d76da3b1f195 Pull Request resolved: #539
Codecov ReportBase: 89.79% // Head: 89.79% // No change to project coverage 👍
Additional details and impacted files@@ Coverage Diff @@
## gh/danthe3rd/56/base #539 +/- ##
=====================================================
Coverage 89.79% 89.79%
=====================================================
Files 80 80
Lines 4839 4839
=====================================================
Hits 4345 4345
Misses 494 494
Flags with carried forward coverage won't be shown. Click here to find out more. Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report at Codecov. |
... by reducing the number of ATen imports, and skipping them altogether when building the actual kernels 13mn -> 9mn on Sm61 (CI, does not build flash) [ghstack-poisoned]
fmassa
approved these changes
Nov 25, 2022
| @@ -384,7 +384,7 @@ class MmaPipelinedFromSharedMemory : public MmaBaseFromSharedMemory< | |||
| // but not supported as it worsens perf: older gpus < sm80 don't | |||
| // support async tranfers and have to waste registers | |||
| CUTLASS_DEVICE | |||
| bool set_prologue_done(bool value) {} | |||
| void set_prologue_done(bool value) {} | |||
There was a problem hiding this comment.
Those changes are unrelated, right?
| @@ -676,18 +671,19 @@ struct AttentionBackwardKernel { | |||
| } | |||
| }; | |||
|
|
|||
| static void __host__ check_supported(Params const& p) { | |||
| static bool __host__ check_supported(Params const& p) { | |||
There was a problem hiding this comment.
This change is also unrelated, right?
... by reducing the number of ATen imports, and skipping them altogether when building the actual kernels 13mn -> 9mn on Sm61 (CI, does not build flash) [ghstack-poisoned]
... by reducing the number of ATen imports, and skipping them altogether when building the actual kernels 13mn -> 9mn on Sm61 (CI, does not build flash) [ghstack-poisoned]
danthe3rd
pushed a commit
that referenced
this pull request
Nov 29, 2022
ghstack-source-id: a083a9494486298191eea001ff480a82af6966c7 Pull Request resolved: #539
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.
Stack from ghstack (oldest at bottom):
... by reducing the number of ATen imports, and skipping them altogether when building the actual kernels
13mn -> 9mn on Sm61 (CI, does not build flash)