[mlir][vector] Propagate scalability in TransferWriteNonPermutationLowering (llvm#85632)

Updates `extendVectorRank` so that scalability in patterns
that use it (in particular, `TransferWriteNonPermutationLowering`),
is correctly propagated.


Closed related previous PR
llvm#85270

---------

Signed-off-by: Crefeda Rodrigues <[email protected]>
Co-authored-by: Benjamin Maxwell <[email protected]>

Author: 2 people

mlir/lib/Dialect/Vector/Transforms/LowerVectorTransfer.cpp

@@ -41,8 +41,12 @@ static Value extendVectorRank(OpBuilder &builder, Location loc, Value vec,
   SmallVector<int64_t> newShape(addedRank, 1);
   newShape.append(originalVecType.getShape().begin(),
                   originalVecType.getShape().end());
-  VectorType newVecType =
-      VectorType::get(newShape, originalVecType.getElementType());
+
+  SmallVector<bool> newScalableDims(addedRank, false);
+  newScalableDims.append(originalVecType.getScalableDims().begin(),
+                         originalVecType.getScalableDims().end());
+  VectorType newVecType = VectorType::get(
+      newShape, originalVecType.getElementType(), newScalableDims);
   return builder.create<vector::BroadcastOp>(loc, newVecType, vec);
 }
 

mlir/test/Dialect/Vector/vector-transfer-permutation-lowering.mlir

@@ -41,6 +41,24 @@ func.func @permutation_with_mask_scalable(%2: memref<?x?xf32>, %dim_1: index, %d
   return %1 : vector<8x[4]x2xf32>
 }
 
+// CHECK:           func.func @permutation_with_mask_transfer_write_scalable(
+// CHECK-SAME:        %[[ARG_0:.*]]: vector<4x[8]xi16>,
+// CHECK-SAME:        %[[ARG_1:.*]]: memref<1x4x?x1x1x1x1xi16>,
+// CHECK-SAME:        %[[MASK:.*]]: vector<4x[8]xi1>) {
+// CHECK:             %[[C0:.*]] = arith.constant 0 : index
+// CHECK:             %[[BCAST_1:.*]] = vector.broadcast %[[ARG_0]] : vector<4x[8]xi16> to vector<1x1x1x1x4x[8]xi16>
+// CHECK:             %[[BCAST_2:.*]] = vector.broadcast %[[MASK]] : vector<4x[8]xi1> to vector<1x1x1x1x4x[8]xi1>
+// CHECK:             %[[TRANSPOSE_1:.*]] = vector.transpose %[[BCAST_2]], [4, 5, 0, 1, 2, 3] : vector<1x1x1x1x4x[8]xi1> to vector<4x[8]x1x1x1x1xi1>
+// CHECK:             %[[TRANSPOSE_2:.*]] = vector.transpose %[[BCAST_1]], [4, 5, 0, 1, 2, 3] : vector<1x1x1x1x4x[8]xi16> to vector<4x[8]x1x1x1x1xi16>
+// CHECK:             vector.transfer_write %[[TRANSPOSE_2]], %[[ARG_1]]{{\[}}%[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]]], %[[TRANSPOSE_1]] {in_bounds = [true, true, true, true, true, true]} : vector<4x[8]x1x1x1x1xi16>, memref<1x4x?x1x1x1x1xi16>
+// CHECK:             return
+func.func @permutation_with_mask_transfer_write_scalable(%arg0: vector<4x[8]xi16>, %arg1: memref<1x4x?x1x1x1x1xi16>, %mask:  vector<4x[8]xi1>){
+     %c0 = arith.constant 0 : index
+      vector.transfer_write %arg0, %arg1[%c0, %c0, %c0, %c0, %c0, %c0, %c0], %mask {in_bounds = [true, true], permutation_map = affine_map<(d0, d1, d2, d3, d4, d5, d6) -> (d1, d2)>
+} : vector<4x[8]xi16>, memref<1x4x?x1x1x1x1xi16>
+
+    return
+}
 module attributes {transform.with_named_sequence} {
   transform.named_sequence @__transform_main(%module_op: !transform.any_op {transform.readonly}) {
     %f = transform.structured.match ops{["func.func"]} in %module_op