[DT] Unify encoding materialization pass into a single pass. #19454
Conversation
This file contains 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
bjacob
approved these changes
Dec 11, 2024
| @@ -161,6 +161,11 @@ const char *getIreeArchNameForTargetTriple(llvm::Triple triple) { | |||
| return "unknown"; | |||
| } | |||
|
|
|||
| bool isLLVMCPUBackend(IREE::HAL::ExecutableTargetAttr targetAttr) { | |||
| return targetAttr && | |||
| targetAttr.getBackend().getValue().starts_with("llvm-cpu"); | |||
There was a problem hiding this comment.
Can't you just check equality ? Why starts_with? If that was copying the vmvx case below, I might have done that out of ignorance in the past.
There was a problem hiding this comment.
Oh, yes. Thanks for pointing it out! I'm mainly following the other cases, but can definitely check equality.
Signed-off-by: hanhanW <hanhan0912@gmail.com>
also update cpu targets in llvmcpu_materialize_encoding.mlir Signed-off-by: hanhanW <hanhan0912@gmail.com>
Signed-off-by: hanhanW <hanhan0912@gmail.com>
Signed-off-by: hanhanW <hanhan0912@gmail.com>
…rns.cpp Signed-off-by: hanhanW <hanhan0912@gmail.com>
Signed-off-by: hanhanW <hanhan0912@gmail.com>
9005f5a to
0f6ac93
Compare
Signed-off-by: hanhanW <hanhan0912@gmail.com>
Signed-off-by: hanhanW <hanhan0912@gmail.com>
1a13342 to
5224968
Compare
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Outdated suggestions cannot be applied.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.
The revision creates a generic materialization pass and uses it for backends that implement data-tiling. After months of development, we identify that the needs of GPU is a superset of the needs of CPU. To be more specific, it has the additional "swizzle" field in terms of layout. It means that the GPU set_encoding/unset_encoding lowering patterns cover the needs of CPU path. The lowering of contraction ops is different. CPU lowers it to mmt4d ops, while GPU lowers it to multi_mma op. However, the lowering of contraction is implemented through attribute interface. Thus, we can have a generic pattern to lower contraction ops.
To make the review process much easier, the revision is created by 5 commits.
Common/[CPU|GPU]/testtoCommon/test.MaterializeEncodingPatterns.cpp.The revision retains the MaterializeEncodingIntoNop pass, and add a TODO item. Because it is still used by MaterializeHomogeneousEncoding pass. It can be deleted once we deprecate the early materialization path.