[Mlir-commits] [mlir] [mlir][Vector] Tighten up application conditions in TransferReadAfter… (PR #143869)

[Kunwar Grover]

================
@@ -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