[Mlir-commits] [mlir] [mlir][linalg] Add support for masked vectorization of `tensor.insert_slice` (2/N) (PR #123031)

[Diego Caballero]

================
@@ -2716,56 +2716,56 @@ vectorizeAsInsertSliceOp(RewriterBase &rewriter, tensor::InsertSliceOp sliceOp,
   }
   auto vecType = VectorType::get(vecShape, sourceType.getElementType());
 
-  // 3. Generate TransferReadOp.
-  SmallVector<Value> readIndices(
-      vecType.getRank(),
-      rewriter.create<arith::ConstantIndexOp>(sliceOp.getLoc(), 0));
-  Operation *read = rewriter.create<vector::TransferReadOp>(
-      sliceOp.getLoc(), vecType, source, readIndices, padValue,
-      ArrayRef<bool>{readInBounds});
+  // 3. Generate TransferReadOp + TransferWriteOp
+  ReifiedRankedShapedTypeDims reifiedSrcSizes;
+  Value maskOp;
 
-  // If vector sizes are user provided, make sure to mask xfer_read.
+  // If vector sizes are user provided, make sure to mask. First, generate the
+  // mask.
----------------
dcaballe wrote:

Couldn't user-provided vector sizes lead to an unmasked scenario? We have a method that checks if mask is needed here (can't remember the name right now). Couldn't use it for this case?

https://github.com/llvm/llvm-project/pull/123031