[ET-VK] Integrate axis mapping into naive matrix multiplication shaders #5277
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
## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5277
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit c315784 with merge base 9845019 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D62518403 |
SS-JIA
added a commit
that referenced
this pull request
Sep 11, 2024
## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) ghstack-source-id: 242059485 Pull Request resolved: #5277
…ation shaders" ## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Sep 12, 2024
Pull Request resolved: #5277 ## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. ghstack-source-id: 242137430 @exported-using-ghexport Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/)
|
This pull request was exported from Phabricator. Differential Revision: D62518403 |
…ation shaders" ## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D62518403 |
…ation shaders" ## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D62518403 |
…ation shaders" ## Context Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability. ## Performance impact Running the matrix multiplication operator benchmark, we can observe the following results: | commit | matmul_naive_texture3d_float | linear_naive_texture3d_float | |-------------|------------------------------|------------------------------| | master | 6.53645 | 6.98834 | | this commit | 6.61293 | 6.34905 | Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency. Differential Revision: [D62518403](https://our.internmc.facebook.com/intern/diff/D62518403/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D62518403 |
jorgep31415
approved these changes
Sep 13, 2024
|
This pull request has been merged in 31e652d. |
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):
virtual_transpose()tovTensorfor no copy transposition #5353Context
Give similar treatment as #5223 to integrate axis mapping into the naive matrix multiplication shaders. As with the previous diff, code cleanup is performed as well to consolidate shaders and improve code readability.
Performance impact
Running the matrix multiplication operator benchmark, we can observe the following results:
Evidently, accounting for axis mapping did not have any significant adverse impact on shader latency.
Differential Revision: D62518403