Slightly improving 4 bit mat mul performance through better engage ALU pipes by splitting uint to float conversion operation. #15447
+16
−18
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15447
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ No FailuresAs of commit ff1b33a with merge base 7bd34b8 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
@trivedivivek has exported this pull request. If you are a Meta employee, you can view the originating Diff in D85779855. |
trivedivivek
added
the
release notes: vulkan
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Oct 30, 2025
…U pipes by splitting uint to float conversion operation. (pytorch#15447) Summary: This diff makes a slight improvement to the performance of 4-bit matrix multiplication by better utilizing the ALU pipes. This is achieved by splitting the `uint` to `float` conversion operation. Differential Revision: D85779855
trivedivivek
force-pushed
the
export-D85779855
branch
from
9db3ed8 to
35be9f2
Compare
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Oct 30, 2025
…U pipes by splitting uint to float conversion operation. (pytorch#15447) Summary: This diff makes a slight improvement to the performance of 4-bit matrix multiplication by better utilizing the ALU pipes. This is achieved by splitting the `uint` to `float` conversion operation. Differential Revision: D85779855
trivedivivek
force-pushed
the
export-D85779855
branch
from
35be9f2 to
88efba0
Compare
Summary: This diff fixes a regression in the 8-bit quantized matrix multiplication operation, by reducing number of columns processed to 1 instead of 2 as before. Differential Revision: D85767668
…U pipes by splitting uint to float conversion operation. (pytorch#15447) Summary: This diff makes a slight improvement to the performance of 4-bit matrix multiplication by better utilizing the ALU pipes. This is achieved by splitting the `uint` to `float` conversion operation. Differential Revision: D85779855
trivedivivek
force-pushed
the
export-D85779855
branch
from
88efba0 to
ff1b33a
Compare
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
Oct 30, 2025
…U pipes by splitting uint to float conversion operation. (pytorch#15447) Summary: This diff makes a slight improvement to the performance of 4-bit matrix multiplication by better utilizing the ALU pipes. This is achieved by splitting the `uint` to `float` conversion operation. Differential Revision: D85779855
SS-JIA
approved these changes
Oct 30, 2025
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.
Summary: This diff makes a slight improvement to the performance of 4-bit matrix multiplication by better utilizing the ALU pipes. This is achieved by splitting the
uinttofloatconversion operation.Differential Revision: D85779855