[Mlir-commits] [mlir] [mlir][linalg] Vectorize unpack op without masking (PR #89067)

[Andrzej Warzyński]

================
@@ -1560,40 +1575,61 @@ vectorizeAsTensorUnpackOp(RewriterBase &rewriter, tensor::UnPackOp unpackOp,
 
   ArrayRef<int64_t> innerDimPos = unpackOp.getInnerDimsPos();
   ArrayRef<int64_t> innerTiles = unpackOp.getStaticInnerTiles();
-
-  SmallVector<int64_t> readMaskShape(inputVectorSizes.begin(),
-                                     inputVectorSizes.end());
-  ArrayRef<int64_t> outerDimsPerm = unpackOp.getOuterDimsPerm();
   ArrayRef<int64_t> sourceShape = unpackTensorType.getShape();
+  bool useInBoundsInsteadOfMasking = false;
+  ArrayRef<int64_t> outerDimsPerm = unpackOp.getOuterDimsPerm();
+
+  auto destSize = unpackOp.getDestRank();
 
-  // ReadMask is the size of tensor used to read and apply mask. It is
+  // vectorSizes is the shape of the vector that will be used to do final
+  // write on the destination tensor. It is set like this: Let's say the
+  // sourceShape is 'M' and the vectorSize (VS) array is size 'N' where N <= M.
+  // Thus:
+  // - vectorSizes = sourceShape.take_front(N)
+  // - if outer_dims_perms is present: do that permutation on initVectorShape.
+  // - Multiply all the locations pointed by innerDimPos by the innerTileSize
+  //  attribute value.
+  SmallVector<int64_t> vectorSizes(inputVectorSizes);
+  if (vectorSizes.empty()) {
+    llvm::append_range(vectorSizes, sourceShape.take_front(destSize));
+    if (!outerDimsPerm.empty())
+      applyPermutationToVector(vectorSizes, outerDimsPerm);
+    for (auto [i, pos] : llvm::enumerate(innerDimPos))
+      vectorSizes[pos] *= innerTiles[i];
+
+    useInBoundsInsteadOfMasking = true;
+  }
+
+  SmallVector<int64_t> readVectorSizes(vectorSizes.begin(), vectorSizes.end());
----------------
banach-space wrote:

[nit] Move below the comment that documents what `readVectorSizes` is (L1623).

https://github.com/llvm/llvm-project/pull/89067