[Mlir-commits] [mlir] [mlir][vector] Determine vector sizes from the result shape in the ca… (PR #88249)

[Diego Caballero]

================
@@ -812,3 +812,37 @@ func.func @test_vectorize_unpack_no_masks(%source: tensor<8x8x32x16xf32>, %dest:
     transform.yield
   } 
 }
+
+  // -----
+
+// CHECK-LABEL: test_vectorize_padded_pack_no_vector_sizes
+func.func @test_vectorize_padded_pack_no_vector_sizes(%arg0: tensor<32x7x15xf32>, %arg1: tensor<32x4x1x16x2xf32>) -> tensor<32x4x1x16x2xf32> {
+  %pad = arith.constant 0.000000e+00 : f32
+  %pack = tensor.pack %arg0 padding_value(%pad : f32) inner_dims_pos = [2, 1] inner_tiles = [16, 2] into %arg1 : tensor<32x7x15xf32> -> tensor<32x4x1x16x2xf32>
+  return %pack : tensor<32x4x1x16x2xf32>
+}
+//  CHECK-DAG: %[[cst:.*]] = arith.constant 0.000000e+00 : f32
+//  CHECK-DAG: %[[c0:.*]] = arith.constant 0 : index
+//  CHECK-DAG: %[[c32:.*]] = arith.constant 32 : index
+//  CHECK-DAG: %[[c7:.*]] = arith.constant 7 : index
+//  CHECK-DAG: %[[c15:.*]] = arith.constant 15 : index
+//      CHECK: %[[mask:.*]] = vector.create_mask %[[c32]], %[[c7]], %[[c15]] : vector<32x8x16xi1>
+//      CHECK: %[[masked_read:.*]] = vector.mask %[[mask]] {
+// CHECK-SAME:   vector.transfer_read %{{.*}}[%[[c0]], %[[c0]], %[[c0]]], %[[cst]]
+// CHECK-SAME:   {in_bounds = [true, true, true]} : tensor<32x7x15xf32>, vector<32x8x16xf32>
+// CHECK-SAME: } : vector<32x8x16xi1> -> vector<32x8x16xf32>
----------------
dcaballe wrote:

Yes, the default approach is using `in_bounds` set to false when input vector sizes are not provided. Masking should only be used when input vector sizes are provided. Eventually we may get rid of `in_bounds` that when we would have to emulate its behavior from a masked operation.

https://github.com/llvm/llvm-project/pull/88249