[Mlir-commits] [mlir] [mlir][Vector] Tighten up application conditions in TransferReadAfter… (PR #143869)
Kunwar Grover
llvmlistbot at llvm.org
Thu Jun 12 05:08:30 PDT 2025
================
@@ -4684,15 +4687,27 @@ struct TransferReadAfterWriteToBroadcast
if (getUnusedDimsBitVector({readOp.getPermutationMap()}) !=
getUnusedDimsBitVector({defWrite.getPermutationMap()}))
return failure();
- if (readOp.getIndices() != defWrite.getIndices() ||
- readOp.getMask() != defWrite.getMask())
+ // This pattern should only catch the broadcast case, the non-broadcast case
+ // should be done separately to keep application conditions clean and
+ // separate.
----------------
Groverkss wrote:
I'm okay with this, as long as we can document in the PR description, so someone relying on this downstream can get a signal.
https://github.com/llvm/llvm-project/pull/143869
More information about the Mlir-commits
mailing list