Skip to content

Conversation

@trivedivivek
Copy link
Contributor

Summary:
This diff changes the default image layout for a tensor from TILING_OPTIMAL to TILING_LINEAR.
Linear tiling helps improve memory utilization by minimizing texture padding and give better control over texture caching.

q_8w_linear op shader and dispatch settings are modified to utilize linearity of texture.

Differential Revision: D65912644

@pytorch-bot
Copy link

pytorch-bot bot commented Nov 13, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6838

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

✅ No Failures

As of commit 5ba6845 with merge base 6f63893 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Nov 13, 2024
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65912644

trivedivivek added a commit to trivedivivek/executorch that referenced this pull request Nov 14, 2024
…orch#6838)

Summary:

This diff changes the default image layout for a tensor from TILING_OPTIMAL to TILING_LINEAR.
Linear tiling helps improve memory utilization by minimizing texture padding and give better control over texture caching.

q_8w_linear op shader and dispatch settings are modified to utilize linearity of texture.

Reviewed By: nathanaelsee

Differential Revision: D65912644
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65912644

…orch#6838)

Summary:

This diff changes the default image layout for a tensor from TILING_OPTIMAL to TILING_LINEAR.
Linear tiling helps improve memory utilization by minimizing texture padding and give better control over texture caching.

q_8w_linear op shader and dispatch settings are modified to utilize linearity of texture.

Reviewed By: nathanaelsee

Differential Revision: D65912644
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D65912644

@facebook-github-bot facebook-github-bot merged commit ecdc007 into pytorch:main Nov 14, 2024
41 checks passed
@trivedivivek trivedivivek changed the title Linear tiling experiment Use Linear tiling by default for executorch vulkan tensor images Nov 14, 2024
@pytorch-bot pytorch-bot bot added ciflow/periodic module: vulkan Issues related to the Vulkan delegate and code under backends/vulkan/ labels Nov 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/periodic CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported module: vulkan Issues related to the Vulkan delegate and code under backends/vulkan/

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants