[ET-VK] Clean up vTensor member variables and expose dim order UBO and push constant
#11599
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
…O and push constant ## Changes * Add dim order to the list of tensor metadata that can be ingested by compute shaders * Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth ## Motivation > Add dim order to the list of tensor metadata that can be ingested by compute shaders Knowing the dim order is necessary to convert between a linear buffer index to N-dimensional tensor index using a tensor's strides. Technically, the dim order can be inferred from the strides by performing an index sort on the strides array; however to prevent compute shaders from having to do this operation frequently, it is more efficient to pass in the dim order directly to the compute shader. Currently, ET-VK compute shaders make strong assumptions about the dim order of buffer backed tensors so as to avoid having to dynamically generate the dim order from the strides array. However, these assumptions are not enforced and it is more correct to just account for the dim order rather than make assumptions. This will be addressed in the next diff. > Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth I realized that the purpose of these "derived metadata" is to simply convert default tensor metadata such sizes, strides, etc. to a form where they can be used in a compute shader. There is no need to store these derived metadata persistently, since they are pretty much only useful in the final `ivec4` form they exist as inside `UniformData`. So to simplify `vTensor` and to reduce the size of the class, I elected to remove these superfluous data members. ## Performance Impact * Potential memory footprint improvement from reducing the size of `vTensor`. Differential Revision: [D76393427](https://our.internmc.facebook.com/intern/diff/D76393427/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11599
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit f3d245f with merge base 4a14fdd ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Jun 12, 2025
|
This pull request was exported from Phabricator. Differential Revision: D76393427 |
This PR needs a
|
trivedivivek
approved these changes
Jun 12, 2025
…m order` UBO and push constant" ## Changes * Add dim order to the list of tensor metadata that can be ingested by compute shaders * Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth ## Motivation > Add dim order to the list of tensor metadata that can be ingested by compute shaders Knowing the dim order is necessary to convert between a linear buffer index to N-dimensional tensor index using a tensor's strides. Technically, the dim order can be inferred from the strides by performing an index sort on the strides array; however to prevent compute shaders from having to do this operation frequently, it is more efficient to pass in the dim order directly to the compute shader. Currently, ET-VK compute shaders make strong assumptions about the dim order of buffer backed tensors so as to avoid having to dynamically generate the dim order from the strides array. However, these assumptions are not enforced and it is more correct to just account for the dim order rather than make assumptions. This will be addressed in the next diff. > Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth I realized that the purpose of these "derived metadata" is to simply convert default tensor metadata such sizes, strides, etc. to a form where they can be used in a compute shader. There is no need to store these derived metadata persistently, since they are pretty much only useful in the final `ivec4` form they exist as inside `UniformData`. So to simplify `vTensor` and to reduce the size of the class, I elected to remove these superfluous data members. ## Performance Impact * Potential memory footprint improvement from reducing the size of `vTensor`. Differential Revision: [D76393427](https://our.internmc.facebook.com/intern/diff/D76393427/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76393427 |
…m order` UBO and push constant" ## Changes * Add dim order to the list of tensor metadata that can be ingested by compute shaders * Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth ## Motivation > Add dim order to the list of tensor metadata that can be ingested by compute shaders Knowing the dim order is necessary to convert between a linear buffer index to N-dimensional tensor index using a tensor's strides. Technically, the dim order can be inferred from the strides by performing an index sort on the strides array; however to prevent compute shaders from having to do this operation frequently, it is more efficient to pass in the dim order directly to the compute shader. Currently, ET-VK compute shaders make strong assumptions about the dim order of buffer backed tensors so as to avoid having to dynamically generate the dim order from the strides array. However, these assumptions are not enforced and it is more correct to just account for the dim order rather than make assumptions. This will be addressed in the next diff. > Do not persistently store derivative metadata (i.e. padded sizes, padded numel, unsqueezed strides, etc.) as members of vTensor; instead store these in `uniform_data_` and use `uniform_data_` as the source of truth I realized that the purpose of these "derived metadata" is to simply convert default tensor metadata such sizes, strides, etc. to a form where they can be used in a compute shader. There is no need to store these derived metadata persistently, since they are pretty much only useful in the final `ivec4` form they exist as inside `UniformData`. So to simplify `vTensor` and to reduce the size of the class, I elected to remove these superfluous data members. ## Performance Impact * Potential memory footprint improvement from reducing the size of `vTensor`. Differential Revision: [D76393427](https://our.internmc.facebook.com/intern/diff/D76393427/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D76393427 |
facebook-github-bot
merged commit d0c9233
into
gh/SS-JIA/240/base
94 of 98 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
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):
catoperator #11508vTensormember variables and exposedim orderUBO and push constant #11599Changes
uniform_data_and useuniform_data_as the source of truthMotivation
Knowing the dim order is necessary to convert between a linear buffer index to N-dimensional tensor index using a tensor's strides. Technically, the dim order can be inferred from the strides by performing an index sort on the strides array; however to prevent compute shaders from having to do this operation frequently, it is more efficient to pass in the dim order directly to the compute shader.
Currently, ET-VK compute shaders make strong assumptions about the dim order of buffer backed tensors so as to avoid having to dynamically generate the dim order from the strides array. However, these assumptions are not enforced and it is more correct to just account for the dim order rather than make assumptions. This will be addressed in the next diff.
I realized that the purpose of these "derived metadata" is to simply convert default tensor metadata such sizes, strides, etc. to a form where they can be used in a compute shader. There is no need to store these derived metadata persistently, since they are pretty much only useful in the final
ivec4form they exist as insideUniformData. So to simplifyvTensorand to reduce the size of the class, I elected to remove these superfluous data members.Performance Impact
vTensor.Differential Revision: D76393427