Linear transfer without transformation but with repeat #1882
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
Coverage ReportCreated: 2024-10-24 22:09Click here for information about interpreting this report.
Generated by llvm-cov -- llvm version 14.0.0 |
hunhoffe
changed the title
hunhoffe
changed the title
hunhoffe
requested review from
stephenneuendorffer,
jgmelber,
fifield,
jackl-xilinx,
denolf and
AndraBisca
as code owners
jgmelber
approved these changes
Oct 25, 2024
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Outdated suggestions cannot be applied.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.
This PR relaxes some constraints made by checks in
AIEXDialect.cppandAIEDmaToNpu.cppto allow one to continue to special-case the linear transfer without transform but to allowrepeat_count/iteration_stride.To be specific, cases such as
size=[1, 1, 1, N], strides=[0, 0, 0, 1]were special-cased so that whenNexceeded the maximum allowable size, the transformation was still considered legal. This special case can still be done in this case:size=[repeat_count, 1, 1, N], strides=[iteration_stride, 0, 0, 1]but was previously disallowed by checks.I've relaxed the checks to allow this case and also added an example of this case in
test/npu-xrt.I also tried to fix-up some documentation to reflect the
repeat_count/iteration_strideinformation.