[PATCH] D76014: [mlir][Vector]Lower vector.contract to llvm.intr.matrix_multiply

[River Riddle via Phabricator via llvm-commits]

rriddle added inline comments.


================
Comment at: mlir/lib/Dialect/VectorOps/VectorTransforms.cpp:46
+static llvm::cl::opt<bool> lowerToLLVMMatrixIntrinsics(
+    "vector-lower-matrix-intrinsics",
+    llvm::cl::desc("Lower vector.contract to llvm.intr.matrix.multiply"),
----------------
Can we please avoid global cl opts?


================
Comment at: mlir/lib/Dialect/VectorOps/VectorTransforms.cpp:922
+      if (elementType.isIntOrFloat()) {
+        if (elementType.isSignedInteger() || elementType.isSignedInteger())
+          rewriter.replaceOpWithNewOp<AddIOp>(op, op.acc(), mul);
----------------
This check is duplicated, are you trying to check elementType.isa<IntegerType>()


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76014/new/

https://reviews.llvm.org/D76014