Repository navigation
Remove clones that only request a memory format - #24453
Open
zonglinpeng wants to merge 1 commit into
Open
zonglinpeng wants to merge 1 commit into
zonglinpeng wants to merge 1 commit into
Conversation
Summary: `rlx_arbitrary_image_stylization` fails in the ExecuTorch emitter: `InternalError: Tensor has a memory_format that is unsupported in ExecuTorch: torch.channels_last` (`exir/tensor.py` `memory_format_enum` raises `KeyError: torch.channels_last`). Its export carries `clone(memory_format=torch.channels_last)` on ops that stay on the CPU. Cadence lowers with `_skip_dim_order=True`, and so does Helios, which runs Cadence's remove passes. Every edge tensor is therefore contiguous and a memory format has no runtime representation. The emitter accepts only contiguous and preserve. The upstream `RemoveCloneOpsTransform` deliberately keeps clones that change memory format, because with dim order they carry a real layout, and Cadence's wrapper `RemoveCloneOpsTransformImported` ran it unchanged. Nothing removed the clone. The wrapper becomes one pass, renamed `RemoveCloneOpsPass`: a `RemoveCloneOpsTransform` subclass that also treats an `aten.clone` with any memory format as a plain copy, so the clone is removed. `_clone_dim_order` keeps the upstream behavior. Dead-code elimination still runs afterwards, as it did in the wrapper. The upstream transform is unchanged. The rename touches every caller in fbcode and xplat: Cadence passes, Helios sharding transforms, Jarvis, the SAS compiler and the xr_sonic gleam export. This replaces the Helios-only `StripCloneMemoryFormat` pass from the earlier version of this diff. Differential Revision: D125145150
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24453
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 3 PendingAs of commit e34b34c with merge base 822cb60 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@zonglinpeng has exported this pull request. If you are a Meta employee, you can view the originating Diff in D125145150. |
This PR needs a
|
This branch was previously deployed
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
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:
rlx_arbitrary_image_stylizationfails in the ExecuTorch emitter:InternalError: Tensor has a memory_format that is unsupported in ExecuTorch: torch.channels_last(exir/tensor.pymemory_format_enumraisesKeyError: torch.channels_last). Its export carriesclone(memory_format=torch.channels_last)on ops that stay on the CPU.Cadence lowers with
_skip_dim_order=True, and so does Helios, which runs Cadence's remove passes. Every edge tensor is therefore contiguous and a memory format has no runtime representation. The emitter accepts only contiguous and preserve. The upstreamRemoveCloneOpsTransformdeliberately keeps clones that change memory format, because with dim order they carry a real layout, and Cadence's wrapperRemoveCloneOpsTransformImportedran it unchanged. Nothing removed the clone.The wrapper becomes one pass, renamed
RemoveCloneOpsPass: aRemoveCloneOpsTransformsubclass that also treats anaten.clonewith any memory format as a plain copy, so the clone is removed._clone_dim_orderkeeps the upstream behavior. Dead-code elimination still runs afterwards, as it did in the wrapper. The upstream transform is unchanged.The rename touches every caller in fbcode and xplat: Cadence passes, Helios sharding transforms, Jarvis, the SAS compiler and the xr_sonic gleam export. This replaces the Helios-only
StripCloneMemoryFormatpass from the earlier version of this diff.Differential Revision: D125145150