Advance llvm-project and stablehlo. #2619
Merged
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
llvm-project: bbd2b08 stablehlo: ab709fe48de88c67717abfbd7ef17425eb95ddaf These commits were chosen in order to account for an MLIR API break from llvm/llvm-project@3dbac2c which required a patch to stablehlo. We integrate a bit beyond that commit to deal with some revert/reapply cycles in the intervening range which were discovered in another downstream. Further, it requires adaptation to the stablehlo API breaks introduced from openxla/stablehlo#1872 which are along for the ride.
antiagainst
approved these changes
Dec 8, 2023
|
Hey @eric-k256, can you or someone more familiar with these TOSA lowerings look at what is going on here? I got a CI run that said that 5 tests were unexpectedly passing, so I added them. Then it said they failed. I might have done it wrong: the commits are above. If you fix it, feel free to land. This is otherwise ready to go. This integrate picked up a handful of patches that look like they would be implicated: |
|
I don't see anything wrong in what you've done. I built this PR locally, and can see the 5 tests unexpectedly pass. Switching to your commit adding them to the pass list and everything runs with no failures. I retriggered the github checks to make sure it wasn't a weird glitch specific to that build. |
stellaraccident
force-pushed
the
integrate_llvm_stablehlo_20231207
branch
from
cc910f7 to
5b6535b
Compare
I think this is a difference between nightly PT and stable. Trying something else. |
This was referenced Dec 8, 2023
mgehre-amd
pushed a commit
to Xilinx/torch-mlir
that referenced
this pull request
Feb 23, 2024
llvm-project: bbd2b08 stablehlo: ab709fe48de88c67717abfbd7ef17425eb95ddaf These commits were chosen in order to account for an MLIR API break from llvm/llvm-project@3dbac2c which required a patch to stablehlo. We integrate a bit beyond that commit to deal with some revert/reapply cycles in the intervening range which were discovered in another downstream. Further, it requires adaptation to the stablehlo API breaks introduced from openxla/stablehlo#1872 which are along for the ride. Since some stablehlo builders were changed to directly take int64_t array refs, also traced that up some call stacks to eliminate some signed/unsigned mismatches that result. Also adds a few TOSA tests to the passing set that seem to work now.
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.
llvm-project: bbd2b08
stablehlo: ab709fe48de88c67717abfbd7ef17425eb95ddaf
These commits were chosen in order to account for an MLIR API break from llvm/llvm-project@3dbac2c which required a patch to stablehlo. We integrate a bit beyond that commit to deal with some revert/reapply cycles in the intervening range which were discovered in another downstream.
Further, it requires adaptation to the stablehlo API breaks introduced from openxla/stablehlo#1872 which are along for the ride.
Since some stablehlo builders were changed to directly take int64_t array refs, also traced that up some call stacks to eliminate some signed/unsigned mismatches that result.
Also adds a few TOSA tests to the passing set that seem to work now.