- User Since
- Sep 21 2022, 11:31 AM (26 w, 1 d)
@ThomasRaoux Bump on the review :)
Fri, Mar 17
Thu, Feb 23
clarify helpers and cleanup
Wed, Feb 22
Tue, Feb 21
Feb 21 2023
Use invert helper instead of specialized function
rebase and use getPosition
Feb 20 2023
Feb 15 2023
I will let others review the transform dialect piece, but I see the movement of these patterns from IREE as a step in the right direction. Also, it would probably be good to pull the FileCheck tests from IREE as well, even if the intent is to later generalize the patterns as the transform won't change.
Feb 14 2023
assert exactly one result
rebase and address comment
Feb 13 2023
Feb 7 2023
@ThomasRaoux I added changes to the GPUToNVVM lowering to support integer types. Would it be better to move those changes to a separate revision?
Add support for int8 types in lowering to nvvm and rebase
Feb 6 2023
Remove check for empty uses
The lowering to SPIRV will just take the type from the mma_matrix type so as long as the types are set properly here then there should be no problems. The lowering otherwise doesn't look any different because the ops are the same. For the lowering to NVVM I realize I'm not as certain so I can either leave support for that to another PR or try and verify correctness now.
Jan 30 2023
add back initial commit
Generalize pattern to arbitrary bit widths
This revision was erroneously opened.
Dec 14 2022
Nov 28 2022
Add description of transpose and relax check for transposed load.
Switch to OptionalAttr<UnitAttr> and update tests accordingly. Additionally changes the check for a transposed vector.transfer_read to directly check for a 2d transpose.