[ET-VK] Request VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT, not RANDOM #7615
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/7615
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3fd4ee4 with merge base bfebce1 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
Author
|
https://gpuopen-librariesandsdks.github.io/VulkanMemoryAllocator/html/usage_patterns.html recommends doing this for staging data to send to the GPU. It's not immediately clear to me whether we also rely on the "readback" usage pattern mentioned later on. |
SS-JIA
approved these changes
Jan 13, 2025
YIWENX14
pushed a commit
that referenced
this pull request
Jan 28, 2025
…T, not RANDOM (#7615) * [ET-VK] Request VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT, not RANDOM * fix lint
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Outdated suggestions cannot be applied.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.
Summary
It looks like we are careful to use only copy_from and copy_to with StagingBuffer on CPU, in which case we only need SEQUENTIAL_WRITE.
This matters on Raspberry Pi 5, where there appears (from debugging) to be only one memory type; that type is HOST_VISIBLE and HOST_COHERENT but not HOST_CACHED.
This is my first time working with Vulkan, so please be critical.
Test plan
Followed vulkan README.md vk_add example on Raspberry Pi 5; was failing with vmaCreateBuffer returned -8 and now succeeds.