[DT][NFC] Internalize transposeNarrowN logic to LayoutAttrInterface Impl #19453
+72
−132
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
hanhanW
requested review from
antiagainst,
qedawkins and
MaheshRavishankar
as code owners
hanhanW
force-pushed
the
data-tiling-cleanups-narrow-n
branch
from
75e6979 to
00c3e8e
Compare
hanhanW
changed the base branch from
users/hanhanW/data-tiling-cleanups-3-upstream-diff
to
main
Whether apply transposion from narrow-N to narrow-M is backend implementation details, and we do not need to expose it to the type converter. The encoding itself has enough information, like indexing maps, narrow dimensions, etc., to infer the shapes and encoding info. Instead of updating the RankedTensorTypes and the attached encoding in type converter, we can just cook the logic in `getEncodingInfo` methods. From the encoding, we know that whether it is narrow-N case, and we can update the MaterializeEncodingInfo correspondingly. The type converter can infer the transposed tensor type from it. Thus, we can simplify the logic in the type conversion. The documentation of `transposeNarrowN` is moved to [CPU|GPU]EncodingExternalModels.cpp because all the implementaion locates at the files. Signed-off-by: hanhanW <[email protected]>
hanhanW
force-pushed
the
data-tiling-cleanups-narrow-n
branch
from
00c3e8e to
dd92fd3
Compare
hanhanW
requested review from
Max191
and removed request for
antiagainst and
qedawkins
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Outdated suggestions cannot be applied.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.
Whether applying transposition from narrow-N to narrow-M is backend
implementation details, and we do not need to expose it to the type
converter. The encoding itself has enough information, like indexing
maps, narrow dimensions, etc., to infer the shapes and encoding info.
Instead of updating the RankedTensorType and the attached encoding in
type converter, we can just cook the logic in
getEncodingInfomethods.From the encoding, we know that whether it is narrow-N case, and we can
update the MaterializeEncodingInfo correspondingly. The type converter
can infer the transposed tensor type from it. Thus, we can simplify the
logic in the type conversion.
The documentation of
transposeNarrowNis moved to[CPU|GPU]EncodingExternalModels.cppbecause all the implementationlocates at the files.