[mlir][linalg] Move vectorization tests for Tensor Ops (nfc) (#140877)

This patch reorganises vectorisation tests for tensor ops:

  * Tests for `tensor.pad` and `tensor.insert_slice` are extracted into
    dedicated files under a new `vectorization/` subdirectory.
  * Test files for `tensor.extract` are renamed and moved to the same
    subdirectory.

Goals:
* Unify test file naming.
* Better organise the growing set of tests, which are currently hard to
  navigate.

This is also a preparatory step for upcoming changes. I’ll soon be updating the
vectorisation logic for `tensor.pad` and `tensor.insert_slice`. With the new
structure in place, follow-up changes will be easier to review:
  * Only tests related to those ops will be updated.
  * Changes (e.g., to masking logic) will be isolated to the relevant tests.

This patch implements part of #141025 - please see the ticket for full context.

8 files changed, 599 insertions, 593 deletions

diff --git a/mlir/test/Dialect/Linalg/vectorization-with-patterns.mlir b/mlir/test/Dialect/Linalg/vectorization-with-patterns.mlir
index 9f2ee47..b282c57 100644
--- a/mlir/test/Dialect/Linalg/vectorization-with-patterns.mlir
+++ b/mlir/test/Dialect/Linalg/vectorization-with-patterns.mlir
@@ -889,207 +889,6 @@ module attributes {transform.with_named_sequence} {
 
 // -----
 
-// CHECK-LABEL: func @pad_static(
-//  CHECK-SAME:                  %[[ARG0:.*]]: tensor<2x?x2xf32>, %[[PAD:.*]]: f32
-//   CHECK-NOT:   tensor.pad
-//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
-//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
-//   CHECK-DAG:   %[[INIT:.*]] = tensor.empty() : tensor<2x3x4xf32>
-//   CHECK-DAG:   %[[VEC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<2x3x4xf32>
-//       CHECK:   %[[FILL:.*]] = vector.transfer_write %[[VEC]], %[[INIT]]{{.*}} : vector<2x3x4xf32>, tensor<2x3x4xf32>
-//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]], %[[C0]]], %[[PAD]] {in_bounds = [true, false, true]} : tensor<2x?x2xf32>, vector<2x3x2xf32>
-//       CHECK:   %[[RESULT:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C0]], %[[C0]], %[[C2]]] {in_bounds = [true, true, true]} : vector<2x3x2xf32>, tensor<2x3x4xf32>
-//       CHECK:   return %[[RESULT]]
-func.func @pad_static(%arg0: tensor<2x?x2xf32>, %pad_value: f32) -> tensor<2x3x4xf32> {
-  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
-    ^bb0(%arg1: index, %arg2: index, %arg3: index):
-      tensor.yield %pad_value : f32
-    } : tensor<2x?x2xf32> to tensor<2x3x4xf32>
-  return %0 : tensor<2x3x4xf32>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-// CHECK-LABEL: func @pad_static_source(
-//  CHECK-SAME:                  %[[ARG0:.*]]: tensor<2x5x2xf32>, %[[PAD:.*]]: f32
-//   CHECK-NOT:   tensor.pad
-//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
-//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
-//       CHECK:   %[[INIT:.*]] = tensor.empty() : tensor<2x6x4xf32>
-//       CHECK:   %[[VEC:.*]] =  vector.broadcast %[[PAD]] : f32 to vector<2x6x4xf32>
-//       CHECK:   %[[FILL:.*]] = vector.transfer_write %[[VEC]], %[[INIT]][%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<2x6x4xf32>, tensor<2x6x4xf32>
-//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]], %[[C0]]], %{{.*}} {in_bounds = [true, true, true]} : tensor<2x5x2xf32>, vector<2x5x2xf32>
-//       CHECK:   %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C0]], %[[C0]], %[[C2]]] {in_bounds = [true, true, true]} : vector<2x5x2xf32>, tensor<2x6x4xf32>
-//       CHECK:   return %[[WRITE]]
-func.func @pad_static_source(%arg0: tensor<2x5x2xf32>, %pad_value: f32) -> tensor<2x6x4xf32> {
-  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
-    ^bb0(%arg1: index, %arg2: index, %arg3: index):
-      tensor.yield %pad_value : f32
-    } : tensor<2x5x2xf32> to tensor<2x6x4xf32>
-  return %0 : tensor<2x6x4xf32>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-
-// -----
-
-// CHECK-LABEL: func @pad_static_dynamic(
-//  CHECK-SAME:                          %[[SRC:.*]]: tensor<1x2x2x?xf32>, %[[LOW:.*]]: index, %[[HIGH:.*]]: index
-//   CHECK-NOT:   tensor.pad
-//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
-//   CHECK-DAG:   %[[C3:.*]] = arith.constant 3 : index
-//   CHECK-DAG:   %[[C5:.*]] = arith.constant 5 : index
-//       CHECK:   %[[V0:.*]] = arith.addi %[[LOW]], %[[C2]] : index
-//       CHECK:   %[[V1:.*]] = arith.addi %[[V0]], %[[C3]] : index
-//       CHECK:   %[[V2:.*]] = arith.addi %[[HIGH]], %[[C5]] : index
-//       CHECK:   %[[DIM3:.*]] = tensor.dim %[[SRC]], %[[C3]] : tensor<1x2x2x?xf32>
-//       CHECK:   %[[V4:.*]] = arith.addi %[[DIM3]], %[[C3]] : index
-//       CHECK:   %[[V5:.*]] = arith.addi %[[V4]], %[[C2]] : index
-//       CHECK:   %[[INIT:.*]] = tensor.empty(%[[V1]], %[[V2]], %[[V5]]) : tensor<6x?x?x?xf32>
-//       CHECK:   %[[FILL:.*]] = linalg.fill ins(%{{.*}} : f32) outs(%[[INIT]] : tensor<6x?x?x?xf32>) -> tensor<6x?x?x?xf32>
-//       CHECK:   %[[SRCDIM:.*]] = tensor.dim %[[SRC]], %[[C3]] : tensor<1x2x2x?xf32>
-//       CHECK:   %[[RESULT:.*]] = tensor.insert_slice %[[SRC]] into %[[FILL]][2, %[[LOW]], 3, 3] [1, 2, 2, %[[SRCDIM]]] [1, 1, 1, 1] : tensor<1x2x2x?xf32> into tensor<6x?x?x?xf32>
-//       CHECK:   return %[[RESULT]]
-func.func @pad_static_dynamic(%arg0: tensor<1x2x2x?xf32>, %low: index, %high: index,
-                  %pad_value: f32) -> tensor<6x?x?x?xf32> {
-  %0 = tensor.pad %arg0 low[2, %low, 3, 3] high[3, 3, %high, 2] {
-    ^bb0(%arg1: index, %arg2: index, %arg3: index, %arg4: index):
-      tensor.yield %pad_value : f32
-    } : tensor<1x2x2x?xf32> to tensor<6x?x?x?xf32>
-  return %0 : tensor<6x?x?x?xf32>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-// CHECK-LABEL: func @pad_static_complex(
-//   CHECK-NOT:   vector<
-func.func @pad_static_complex(%arg0: tensor<2x5x2xcomplex<f32>>, %pad_value: complex<f32>) -> tensor<2x6x4xcomplex<f32>> {
-  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
-    ^bb0(%arg1: index, %arg2: index, %arg3: index):
-      tensor.yield %pad_value : complex<f32>
-    } : tensor<2x5x2xcomplex<f32>> to tensor<2x6x4xcomplex<f32>>
-  return %0 : tensor<2x6x4xcomplex<f32>>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-func.func private @make_vector() -> tensor<12x13xf32>
-
-// CHECK-LABEL:   func.func @pad_and_insert_slice_dest(
-// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x5x6xf32>) -> tensor<1x12x13xf32> {
-// CHECK:           %[[C0:.*]] = arith.constant 0.000000e+00 : f32
-// CHECK:           %[[CST:.*]] = arith.constant dense<5.000000e+00> : vector<1x12x13xf32>
-// CHECK:           %[[C0_IDX:.*]] = arith.constant 0 : index
-// CHECK:           %[[PAD_VAL:.*]] = arith.constant 5.000000e+00 : f32
-// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<1x12x13xf32>
-// CHECK:           %[[WRITE_1:.*]] = vector.transfer_write %[[CST]], %[[EMPTY]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true, true]} : vector<1x12x13xf32>, tensor<1x12x13xf32>
-// CHECK:           %[[READ_1:.*]] = vector.transfer_read %[[ARG_0]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]], %[[PAD_VAL]] {in_bounds = [true, true, true]} : tensor<1x5x6xf32>, vector<1x5x6xf32>
-// CHECK:           %[[WRITE_2:.*]] = vector.transfer_write %[[READ_1]], %[[WRITE_1]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true, true]} : vector<1x5x6xf32>, tensor<1x12x13xf32>
-// CHECK:           %[[MAKE_VEC:.*]] = call @make_vector() : () -> tensor<12x13xf32>
-// CHECK:           %[[READ_2:.*]] = vector.transfer_read %[[MAKE_VEC]]{{\[}}%[[C0_IDX]], %[[C0_IDX]]], %[[C0]] {in_bounds = [true, true]} : tensor<12x13xf32>, vector<12x13xf32>
-// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ_2]], %[[WRITE_2]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true]} : vector<12x13xf32>, tensor<1x12x13xf32>
-// CHECK:           return %[[RES]] : tensor<1x12x13xf32>
-func.func @pad_and_insert_slice_dest(
-    %arg0: tensor<1x5x6xf32>) -> tensor<1x12x13xf32> {
-  %c5 = arith.constant 5.0 : f32
-  %0 = tensor.pad %arg0 low[0, 0, 0] high[0, 7, 7] {
-    ^bb0(%arg2: index, %arg3: index, %arg4: index):
-      tensor.yield %c5 : f32
-  } : tensor<1x5x6xf32> to tensor<1x12x13xf32>
-  %1 = call @make_vector() : () -> tensor<12x13xf32>
-  %r = tensor.insert_slice %1 into %0[0, 0, 0][1, 12, 13][1, 1, 1] : tensor<12x13xf32> into tensor<1x12x13xf32>
-  return %r : tensor<1x12x13xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %3 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %4 = transform.get_parent_op %3 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %5 = transform.structured.vectorize_children_and_apply_patterns %4  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-// CHECK-LABEL: func @pad_tensor_non_const_pad_value
-//  CHECK-SAME:     %[[ARG0:.*]]: tensor<5x6xf32>
-//   CHECK-NOT:   tensor.pad
-//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
-//   CHECK-DAG:   %[[C3:.*]] = arith.constant 3 : index
-//   CHECK-DAG:   %[[C4:.*]] = arith.constant 4 : index
-//       CHECK:   %[[FILL:.*]] = tensor.generate
-//       CHECK:     %[[RES:.*]] = arith.mulf
-//       CHECK:     tensor.yield %[[RES]] : f32
-//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]]], %{{.*}} {in_bounds = [true, true]} : tensor<5x6xf32>, vector<5x6xf32>
-//       CHECK:   %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C3]], %[[C4]]] {in_bounds = [true, true]} : vector<5x6xf32>, tensor<12x13xf32>
-//       CHECK:   return %[[WRITE]]
-func.func @pad_tensor_non_const_pad_value(%arg0: tensor<5x6xf32>) -> tensor<12x13xf32> {
-  %c0 = arith.constant 0 : index
-  %c5 = arith.constant 5.0 : f32
-  %0 = tensor.pad %arg0 low[3, 4] high[4, 3] {
-    ^bb0(%arg1: index, %arg2: index):
-      %i1 = arith.index_cast %arg1 : index to i32
-      %i2 = arith.index_cast %arg2 : index to i32
-      %f1 = arith.sitofp %i1 : i32 to f32
-      %f2 = arith.sitofp %i2 : i32 to f32
-      %m = arith.mulf %f1, %f2 : f32
-      tensor.yield %m : f32
-  } : tensor<5x6xf32> to tensor<12x13xf32>
-  return %0 : tensor<12x13xf32>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %3 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %4 = transform.get_parent_op %3 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %5 = transform.structured.vectorize_children_and_apply_patterns %4  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
 // CHECK-LABEL: func @sum_exp
 func.func @sum_exp(%input: tensor<4x16x8xf32>, %output: tensor<4x16xf32>)
   -> tensor<4x16xf32>
@@ -1805,29 +1604,6 @@ module attributes {transform.with_named_sequence} {
 
 // -----
 
-// CHECK-LABEL: func @test_masked_pad_static_dynamic
-func.func @test_masked_pad_static_dynamic(%arg0: tensor<1x2x2x?xf32>, %low: index, %high: index,
-                  %pad_value: f32) -> tensor<6x?x?x?xf32> {
-  // CHECK: tensor.pad
-  %0 = tensor.pad %arg0 low[2, %low, 3, 3] high[3, 3, %high, 2] {
-    ^bb0(%arg1: index, %arg2: index, %arg3: index, %arg4: index):
-      tensor.yield %pad_value : f32
-    } : tensor<1x2x2x?xf32> to tensor<6x?x?x?xf32>
-  return %0 : tensor<6x?x?x?xf32>
-}
-
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
 func.func @zero_dim_tensor(%input: tensor<f32>, %output: tensor<f32>) -> tensor<f32>
 {
   %0 = linalg.generic { indexing_maps = [ affine_map<() -> ()>, affine_map<() -> ()> ],
@@ -2001,94 +1777,3 @@ module attributes {transform.with_named_sequence} {
     transform.yield
   }
 }
-
-// -----
-
-///----------------------------------------------------------------------------------------
-/// tensor.insert_slice
-///----------------------------------------------------------------------------------------
-
-// The pad value for xfer-read is neither needed nor available - use the default (0.0).
-
-// CHECK-LABEL: func @insert_static_slice_default_pad
-// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x2x3xf32>,
-// CHECK-SAME:      %[[ARG_1:.*]]: tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32> {
-// CHECK:           %[[PAD:.*]] = arith.constant 0.000000e+00 : f32
-// CHECK:           %[[C0:.*]] = arith.constant 0 : index
-// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{\[}}%[[C0]], %[[C0]], %[[C0]]], %[[PAD]] {in_bounds = [true, true, true]} : tensor<1x2x3xf32>, vector<1x2x3xf32>
-// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[ARG_1]]{{\[}}%[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
-// CHECK:           return %[[WRITE]] : tensor<9x8x7x1x2x3xf32>
-func.func @insert_static_slice_default_pad(%arg0: tensor<1x2x3xf32>, %arg1: tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32> {
-  %res = tensor.insert_slice %arg0 into %arg1[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, 2, 3][1, 1, 1, 1, 1, 1] : tensor<1x2x3xf32> into tensor<9x8x7x1x2x3xf32>
-  return %res : tensor<9x8x7x1x2x3xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_padding } : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-// Same as above, but there's a pad value available that should be used instead of the default value.
-
-// CHECK-LABEL:   func.func @insert_static_slice_non_zero_pad
-// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x2x3xf32>,
-// CHECK-SAME:      %[[PAD:.*]]: f32) -> tensor<9x8x7x1x2x3xf32> {
-// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<9x8x7x1x2x3xf32>
-// CHECK:           %[[BC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<9x8x7x1x2x3xf32>
-// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[BC]], %[[EMPTY]]{{.*}} {in_bounds = [true, true, true, true, true, true]} : vector<9x8x7x1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
-// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{.*}}, %[[PAD]] {in_bounds = [true, true, true]} : tensor<1x2x3xf32>, vector<1x2x3xf32>
-// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ]], %[[WRITE]]{{.*}} {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
-// CHECK:           return %[[RES]] : tensor<9x8x7x1x2x3xf32>
-func.func @insert_static_slice_non_zero_pad(%arg0: tensor<1x2x3xf32>, %pad : f32) -> tensor<9x8x7x1x2x3xf32> {
-  %init = tensor.empty() : tensor<9x8x7x1x2x3xf32>
-  %fill = linalg.fill ins(%pad : f32) outs(%init : tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32>
-  %res = tensor.insert_slice %arg0 into %fill[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, 2, 3][1, 1, 1, 1, 1, 1] : tensor<1x2x3xf32> into tensor<9x8x7x1x2x3xf32>
-  return %res : tensor<9x8x7x1x2x3xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1 : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-// Same as above, but the source type has is dynamically shaped. This means
-// that the pad value is now required and the vector dim corresponding to the
-// dynamic shape has to be inferred from the shape of the destination tensor.
-
-// CHECK-LABEL:   func.func @insert_dynamic_slice_non_zero_pad(
-// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x?x3xf32>,
-// CHECK-SAME:      %[[PAD:.*]]: f32,
-// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<9x8x7x1x2x3xf32> {
-// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<9x8x7x1x2x3xf32>
-// CHECK:           %[[BC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<9x8x7x1x2x3xf32>
-// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[BC]], %[[EMPTY]]{{.*}} {in_bounds = [true, true, true, true, true, true]} : vector<9x8x7x1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
-// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{.*}}, %[[PAD]] {in_bounds = [true, false, true]} : tensor<1x?x3xf32>, vector<1x2x3xf32>
-// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ]], %[[WRITE]]{{.*}} {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
-// CHECK:           return %[[RES]] : tensor<9x8x7x1x2x3xf32>
-func.func @insert_dynamic_slice_non_zero_pad(%arg0: tensor<1x?x3xf32>, %pad : f32, %size: index) -> tensor<9x8x7x1x2x3xf32> {
-  %init = tensor.empty() : tensor<9x8x7x1x2x3xf32>
-  %fill = linalg.fill ins(%pad : f32) outs(%init : tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32>
-  %res = tensor.insert_slice %arg0 into %fill[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, %size, 3][1, 1, 1, 1, 1, 1] : tensor<1x?x3xf32> into tensor<9x8x7x1x2x3xf32>
-  return %res : tensor<9x8x7x1x2x3xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
-    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
-    %2 = transform.structured.vectorize_children_and_apply_patterns %1 : (!transform.any_op) -> !transform.any_op
-    transform.yield
-  }
-}
diff --git a/mlir/test/Dialect/Linalg/vectorization.mlir b/mlir/test/Dialect/Linalg/vectorization.mlir
index 6b760a1..8c6760f 100644
--- a/mlir/test/Dialect/Linalg/vectorization.mlir
+++ b/mlir/test/Dialect/Linalg/vectorization.mlir
@@ -580,133 +580,6 @@ module attributes {transform.with_named_sequence} {
   }
 }
 
-// -----
-
-// CHECK-LABEL: func @test_masked_vectorize_pad
-func.func @test_masked_vectorize_pad(
-  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index)
-    -> tensor<2x4xf32>
-{
-  //  CHECK-DAG: %[[c42:.*]] = arith.constant 4.243000e+01 : f32
-  //  CHECK-DAG: %[[c0:.*]] = arith.constant 0 : index
-  //  CHECK-DAG: %[[c0_0:.*]] = arith.constant 0 : index
-  //      CHECK: %[[d0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[d1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[mask:.*]] = vector.create_mask %[[d0]], %[[d1]] : vector<2x4xi1>
-  //      CHECK: %[[masked_read:.*]] = vector.mask %[[mask]] {
-  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[c0_0]], %[[c0_0]]], %[[c42]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<2x4xf32>
-  // CHECK-SAME: } : vector<2x4xi1> -> vector<2x4xf32>
-  //  CHECK-DAG: %[[c0_1:.*]] = arith.constant 0 : index
-  //  CHECK-DAG: %[[empty:.*]] = tensor.empty() : tensor<2x4xf32>
-  //      CHECK: vector.transfer_write %[[masked_read]], %[[empty]][%[[c0_1]], %[[c0_1]]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : vector<2x4xf32>, tensor<2x4xf32>
-  %cst = arith.constant 42.43 : f32
-  %c0 = arith.constant 0 : index
-  %1 = tensor.pad %0 low[0, %c0] high[%h0, %h1]  {
-    ^bb0(%hh1: index, %hh2: index):
-      tensor.yield %cst : f32
-    } : tensor<?x?xf32> to tensor<2x4xf32>
-  return %1: tensor<2x4xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
-      : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [2, 4] : !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-
-//       CHECK: #[[MAP:.+]] = affine_map<()[s0, s1] -> (s0 + s1)>
-//       CHECK: func @test_masked_vectorize_dynamic_pad
-func.func @test_masked_vectorize_dynamic_pad(
-  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index)
-    -> tensor<?x?xf32>
-{
-  //  CHECK-DAG: %[[c42:.*]] = arith.constant 4.243000e+01 : f32
-  //  CHECK-DAG: %[[c0:.*]] = arith.constant 0 : index
-  //  CHECK-DAG: %[[res_d0:.+]] = affine.apply #[[MAP]]()
-  //  CHECK-DAG: %[[res_d1:.+]] = affine.apply #[[MAP]]()
-  //      CHECK: %[[c0_2:.*]] = arith.constant 0 : index
-  //      CHECK: %[[d0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[d1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[mask:.*]] = vector.create_mask %[[d0]], %[[d1]] : vector<2x4xi1>
-  //      CHECK: %[[masked_read:.*]] = vector.mask %[[mask]] {
-  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[c0_2]], %[[c0_2]]], %[[c42]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<2x4xf32>
-  // CHECK-SAME: } : vector<2x4xi1> -> vector<2x4xf32>
-  //  CHECK-DAG: %[[empty:.*]] = tensor.empty(%[[res_d0]], %[[res_d1]]) : tensor<?x?xf32>
-  //  CHECK-DAG: %[[c0_3:.*]] = arith.constant 0 : index
-  //  CHECK-DAG: %[[d2:.*]] = tensor.dim %[[empty]], {{.*}} : tensor<?x?xf32>
-  //  CHECK-DAG: %[[d3:.*]] = tensor.dim %[[empty]], {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[mask_2:.*]] = vector.create_mask %[[d2]], %[[d3]] : vector<2x4xi1>
-  //      CHECK: %[[masked_write:.*]] = vector.mask %[[mask_2]] {
-  // CHECK-SAME: vector.transfer_write %[[masked_read]], %[[empty]][%[[c0_3]], %[[c0_3]]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : vector<2x4xf32>, tensor<?x?xf32>
-  //      CHECK: return %[[masked_write]] : tensor<?x?xf32>
-  %cst = arith.constant 42.43 : f32
-  %c0 = arith.constant 0 : index
-  %1 = tensor.pad %0 low[0, %c0] high[%h0, %h1]  {
-    ^bb0(%hh1: index, %hh2: index):
-      tensor.yield %cst : f32
-    } : tensor<?x?xf32> to tensor<?x?xf32>
-  return %1: tensor<?x?xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
-      : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [2, 4] : !transform.any_op
-    transform.yield
-  }
-}
-
-// -----
-// This case is supported because low padding `%l0` is applied on
-// a unit dimension which is supported, non unit result dimension low
-// padding is currently unsupported.
-//  CHECK-LABEL: func @test_masked_vectorize_non_zero_low_pad_unit_res_dim
-func.func @test_masked_vectorize_non_zero_low_pad_unit_res_dim(
-  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index, %l0 : index)
-    -> tensor<1x4xf32>
-{
-  //  CHECK-DAG: %[[C42:.*]] = arith.constant 4.243000e+01 : f32
-  //  CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
-  //      CHECK: %[[C0_1:.*]] = arith.constant 0 : index
-  //  CHECK-DAG: %[[D0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //  CHECK-DAG: %[[D1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
-  //      CHECK: %[[MASK:.*]] = vector.create_mask %[[D0]], %[[D1]] : vector<1x4xi1>
-  //      CHECK: %[[MASKED_READ:.*]] = vector.mask %[[MASK]] {
-  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[C0_1]], %[[C0_1]]], %[[C42]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<1x4xf32>
-  // CHECK-SAME: } : vector<1x4xi1> -> vector<1x4xf32>
-  //  CHECK-DAG: %[[EMPTY:.*]] = tensor.empty() : tensor<1x4xf32>
-  //  CHECK-DAG: %[[C0_2:.*]] = arith.constant 0 : index
-  //      CHECK: %[[MASKED_WRITE:.*]] = vector.transfer_write %[[MASKED_READ]], %[[EMPTY]][%[[C0_2]], %[[C0_2]]]
-  // CHECK-SAME:   {in_bounds = [true, true]} : vector<1x4xf32>, tensor<1x4xf32>
-  //      CHECK: return %[[MASKED_WRITE]] : tensor<1x4xf32>
-  %cst = arith.constant 42.43 : f32
-  %c0 = arith.constant 0 : index
-  %1 = tensor.pad %0 low[%l0, %c0] high[%h0, %h1]  {
-    ^bb0(%hh1: index, %hh2: index):
-      tensor.yield %cst : f32
-    } : tensor<?x?xf32> to tensor<1x4xf32>
-  return %1: tensor<1x4xf32>
-}
-
-module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
-      : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [1, 4] : !transform.any_op
-    transform.yield
-  }
-}
 
 // -----
 
@@ -1155,153 +1028,3 @@ func.func @test_vectorize_unpack_no_vector_sizes_permute(%source: tensor<4x7x4xf
   }
  }
 
-// -----
-
-///----------------------------------------------------------------------------------------
-/// tensor.insert_slice
-///----------------------------------------------------------------------------------------
-
-func.func private @insert_slice_static_sizes(%source: tensor<?x3x?x1xi32>) -> tensor<5x3xi32> {
-  %c2 = arith.constant 2 : index
-  %init = tensor.empty() : tensor<5x3xi32>
-
-  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
-  %res = tensor.insert_slice %source_slice into %init[0, %c2] [5, 1] [1, 1] : tensor<5x1xi32> into tensor<5x3xi32>
-
-  return %res : tensor<5x3xi32>
-}
-
-// CHECK-LABEL:   func.func private @insert_slice_static_sizes(
-// CHECK-SAME:      %[[SEC:.*]]: tensor<?x3x?x1xi32>) -> tensor<5x3xi32> {
-// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
-// CHECK:           %[[INIT:.*]] = tensor.empty() : tensor<5x3xi32>
-// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SEC]][0, %[[C_2]], 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
-// CHECK-DAG:       %[[PAD:.*]] = arith.constant 0 : i32
-// CHECK-DAG:       %[[C_5:.*]] = arith.constant 5 : index
-// CHECK-DAG:       %[[C_1:.*]] = arith.constant 1 : index
-// CHECK:           %[[MASK:.*]] = vector.create_mask %[[C_5]], %[[C_1]] : vector<8x1xi1>
-// CHECK:           %[[C0:.*]] = arith.constant 0 : index
-// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C0]], %[[C0]]], %[[PAD]] : tensor<5x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
-// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
-// CHECK:           %[[RES:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0]], %[[C_2]]] : vector<8x1xi32>, tensor<5x3xi32> } : vector<8x1xi1> -> tensor<5x3xi32>
-// CHECK:           return %[[RES]] : tensor<5x3xi32>
-
- module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
-    transform.yield
-  }
- }
-
-// -----
-
-// One of the _source_ dimensions is dynamic (but _destination_ dimensions are static).
-
-func.func private @insert_slice_dynamic_src_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<5x3xi32> {
-  %c2 = arith.constant 2 : index
-  %init = tensor.empty() : tensor<5x3xi32>
-
-  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, %size, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
-  %res = tensor.insert_slice %source_slice into %init[0, %c2] [%size, 1] [1, 1] : tensor<?x1xi32> into tensor<5x3xi32>
-
-  return %res : tensor<5x3xi32>
-}
-
-// CHECK-LABEL:   func.func private @insert_slice_dynamic_src_dim(
-// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
-// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<5x3xi32> {
-// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
-// CHECK:           %[[INIT:.*]] = tensor.empty() : tensor<5x3xi32>
-// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, %[[SIZE]], 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
-// CHECK-DAG:       %[[PAD:.*]] = arith.constant 0 : i32
-// CHECK-DAG:       %[[C_1:.*]] = arith.constant 1 : index
-// CHECK:           %[[MASK:.*]] = vector.create_mask %[[SIZE]], %[[C_1]] : vector<8x1xi1>
-// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
-// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C_0]], %[[C_0]]], %[[PAD]] : tensor<?x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
-// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
-// CHECK:           %[[RES:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<5x3xi32> } : vector<8x1xi1> -> tensor<5x3xi32>
-// CHECK:           return %[[RES]] : tensor<5x3xi32>
-
- module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
-    transform.yield
-  }
- }
-
-// -----
-
-// One of the _destination_ dimensions is dynamic (but _source_ dimensions are static).
-
-func.func private @insert_slice_dynamic_dest_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<?x3xi32> {
-  %c2 = arith.constant 2 : index
-  %init = tensor.empty(%size) : tensor<?x3xi32>
-
-  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
-  %res = tensor.insert_slice %source_slice into %init[0, %c2] [5, 1] [1, 1] : tensor<5x1xi32> into tensor<?x3xi32>
-
-  return %res : tensor<?x3xi32>
-}
-
-// CHECK-LABEL:   func.func private @insert_slice_dynamic_dest_dim(
-// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
-// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<?x3xi32> {
-// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
-// CHECK:           %[[INIT:.*]] = tensor.empty(%[[SIZE]]) : tensor<?x3xi32>
-// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
-// CHECK:           %[[PAD:.*]] = arith.constant 0 : i32
-// CHECK:           %[[C_5:.*]] = arith.constant 5 : index
-// CHECK:           %[[C_1:.*]] = arith.constant 1 : index
-// CHECK:           %[[MASK:.*]] = vector.create_mask %[[C_5]], %[[C_1]] : vector<8x1xi1>
-// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
-// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C_0]], %[[C_0]]], %[[PAD]] : tensor<5x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
-// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
-// CHECK:           %[[WRITE:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<?x3xi32> } : vector<8x1xi1> -> tensor<?x3xi32>
-// CHECK:           return %[[WRITE]] : tensor<?x3xi32>
-
- module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
-    transform.yield
-  }
- }
-
-// -----
-
-// At least one _source_ and one _destination_ dimensions are dynamic.
-
-func.func private @insert_slice_dynamic_source_and_dest_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<?x3xi32> {
-  %c2 = arith.constant 2 : index
-  %init = tensor.empty(%size) : tensor<?x3xi32>
-
-  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, %size, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
-  %res = tensor.insert_slice %source_slice into %init[0, %c2] [%size, 1] [1, 1] : tensor<?x1xi32> into tensor<?x3xi32>
-
-  return %res : tensor<?x3xi32>
-}
-
-// CHECK-LABEL:   func.func private @insert_slice_dynamic_source_and_dest_dim(
-// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
-// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<?x3xi32> {
-// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
-// CHECK:           %[[INIT:.*]] = tensor.empty(%[[SIZE]]) : tensor<?x3xi32>
-// CHECK:           %[[SRC_SIZE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, %[[SIZE]], 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
-// CHECK:           %[[PAD:.*]] = arith.constant 0 : i32
-// CHECK:           %[[C1:.*]] = arith.constant 1 : index
-// CHECK:           %[[MASK:.*]] = vector.create_mask %[[SIZE]], %[[C1]] : vector<8x1xi1>
-// CHECK:           %[[C0:.*]] = arith.constant 0 : index
-// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SIZE]]{{\[}}%[[C0]], %[[C0]]], %[[PAD]] : tensor<?x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
-// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
-// CHECK:           %[[WRITE:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]]{{\[}}%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<?x3xi32> } : vector<8x1xi1> -> tensor<?x3xi32>
-// CHECK:           return %[[WRITE]] : tensor<?x3xi32>
-
- module attributes {transform.with_named_sequence} {
-  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
-    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
-    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
-    transform.yield
-  }
- }
diff --git a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir b/mlir/test/Dialect/Linalg/vectorization/extract-with-patterns.mlir
index 01eafaf..f62e257 100644
--- a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
+++ b/mlir/test/Dialect/Linalg/vectorization/extract-with-patterns.mlir
@@ -1,5 +1,5 @@
 // RUN: mlir-opt -split-input-file \
-// RUN: -transform-preload-library='transform-library-paths=%p/td/vectorize-with-patterns.mlir' \
+// RUN: -transform-preload-library='transform-library-paths=%p/../td/vectorize-with-patterns.mlir' \
 // RUN: -transform-interpreter=entry-point=vectorize_with_patterns %s | FileCheck %s
 
 //===----------------------------------------------------------------------===//
diff --git a/mlir/test/Dialect/Linalg/vectorize-tensor-extract-masked.mlir b/mlir/test/Dialect/Linalg/vectorization/extract.mlir
index d0d3b58..d0d3b58 100644
--- a/mlir/test/Dialect/Linalg/vectorize-tensor-extract-masked.mlir
+++ b/mlir/test/Dialect/Linalg/vectorization/extract.mlir
diff --git a/mlir/test/Dialect/Linalg/vectorization/insert-slice-with-patterns.mlir b/mlir/test/Dialect/Linalg/vectorization/insert-slice-with-patterns.mlir
new file mode 100644
index 0000000..f7764be
--- /dev/null
+++ b/mlir/test/Dialect/Linalg/vectorization/insert-slice-with-patterns.mlir
@@ -0,0 +1,90 @@
+// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s
+
+///----------------------------------------------------------------------------------------
+/// Tests for tensor.insert_slice
+///----------------------------------------------------------------------------------------
+
+// The pad value for xfer-read is neither needed nor available - use the default (0.0).
+
+// CHECK-LABEL: func @insert_static_slice_default_pad
+// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x2x3xf32>,
+// CHECK-SAME:      %[[ARG_1:.*]]: tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32> {
+// CHECK:           %[[PAD:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[C0:.*]] = arith.constant 0 : index
+// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{\[}}%[[C0]], %[[C0]], %[[C0]]], %[[PAD]] {in_bounds = [true, true, true]} : tensor<1x2x3xf32>, vector<1x2x3xf32>
+// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[ARG_1]]{{\[}}%[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
+// CHECK:           return %[[WRITE]] : tensor<9x8x7x1x2x3xf32>
+func.func @insert_static_slice_default_pad(%arg0: tensor<1x2x3xf32>, %arg1: tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32> {
+  %res = tensor.insert_slice %arg0 into %arg1[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, 2, 3][1, 1, 1, 1, 1, 1] : tensor<1x2x3xf32> into tensor<9x8x7x1x2x3xf32>
+  return %res : tensor<9x8x7x1x2x3xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// Same as above, but there's a pad value available that should be used instead of the default value.
+
+// CHECK-LABEL:   func.func @insert_static_slice_non_zero_pad
+// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x2x3xf32>,
+// CHECK-SAME:      %[[PAD:.*]]: f32) -> tensor<9x8x7x1x2x3xf32> {
+// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<9x8x7x1x2x3xf32>
+// CHECK:           %[[BC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<9x8x7x1x2x3xf32>
+// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[BC]], %[[EMPTY]]{{.*}} {in_bounds = [true, true, true, true, true, true]} : vector<9x8x7x1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
+// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{.*}}, %[[PAD]] {in_bounds = [true, true, true]} : tensor<1x2x3xf32>, vector<1x2x3xf32>
+// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ]], %[[WRITE]]{{.*}} {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
+// CHECK:           return %[[RES]] : tensor<9x8x7x1x2x3xf32>
+func.func @insert_static_slice_non_zero_pad(%arg0: tensor<1x2x3xf32>, %pad : f32) -> tensor<9x8x7x1x2x3xf32> {
+  %init = tensor.empty() : tensor<9x8x7x1x2x3xf32>
+  %fill = linalg.fill ins(%pad : f32) outs(%init : tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32>
+  %res = tensor.insert_slice %arg0 into %fill[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, 2, 3][1, 1, 1, 1, 1, 1] : tensor<1x2x3xf32> into tensor<9x8x7x1x2x3xf32>
+  return %res : tensor<9x8x7x1x2x3xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1 : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// Same as above, but the source type has is dynamically shaped. This means
+// that the pad value is now required and the vector dim corresponding to the
+// dynamic shape has to be inferred from the shape of the destination tensor.
+
+// CHECK-LABEL:   func.func @insert_dynamic_slice_non_zero_pad(
+// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x?x3xf32>,
+// CHECK-SAME:      %[[PAD:.*]]: f32,
+// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<9x8x7x1x2x3xf32> {
+// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<9x8x7x1x2x3xf32>
+// CHECK:           %[[BC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<9x8x7x1x2x3xf32>
+// CHECK:           %[[WRITE:.*]] = vector.transfer_write %[[BC]], %[[EMPTY]]{{.*}} {in_bounds = [true, true, true, true, true, true]} : vector<9x8x7x1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
+// CHECK:           %[[READ:.*]] = vector.transfer_read %[[ARG_0]]{{.*}}, %[[PAD]] {in_bounds = [true, false, true]} : tensor<1x?x3xf32>, vector<1x2x3xf32>
+// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ]], %[[WRITE]]{{.*}} {in_bounds = [true, true, true]} : vector<1x2x3xf32>, tensor<9x8x7x1x2x3xf32>
+// CHECK:           return %[[RES]] : tensor<9x8x7x1x2x3xf32>
+func.func @insert_dynamic_slice_non_zero_pad(%arg0: tensor<1x?x3xf32>, %pad : f32, %size: index) -> tensor<9x8x7x1x2x3xf32> {
+  %init = tensor.empty() : tensor<9x8x7x1x2x3xf32>
+  %fill = linalg.fill ins(%pad : f32) outs(%init : tensor<9x8x7x1x2x3xf32>) -> tensor<9x8x7x1x2x3xf32>
+  %res = tensor.insert_slice %arg0 into %fill[0, 0, 0, 0, 0, 0] [1, 1, 1, 1, %size, 3][1, 1, 1, 1, 1, 1] : tensor<1x?x3xf32> into tensor<9x8x7x1x2x3xf32>
+  return %res : tensor<9x8x7x1x2x3xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1 : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
diff --git a/mlir/test/Dialect/Linalg/vectorization/insert-slice.mlir b/mlir/test/Dialect/Linalg/vectorization/insert-slice.mlir
new file mode 100644
index 0000000..ddd4f43
--- /dev/null
+++ b/mlir/test/Dialect/Linalg/vectorization/insert-slice.mlir
@@ -0,0 +1,150 @@
+// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s
+
+///----------------------------------------------------------------------------------------
+/// Tests for tensor.insert_slice
+///----------------------------------------------------------------------------------------
+
+func.func private @insert_slice_static_sizes(%source: tensor<?x3x?x1xi32>) -> tensor<5x3xi32> {
+  %c2 = arith.constant 2 : index
+  %init = tensor.empty() : tensor<5x3xi32>
+
+  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
+  %res = tensor.insert_slice %source_slice into %init[0, %c2] [5, 1] [1, 1] : tensor<5x1xi32> into tensor<5x3xi32>
+
+  return %res : tensor<5x3xi32>
+}
+
+// CHECK-LABEL:   func.func private @insert_slice_static_sizes(
+// CHECK-SAME:      %[[SEC:.*]]: tensor<?x3x?x1xi32>) -> tensor<5x3xi32> {
+// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
+// CHECK:           %[[INIT:.*]] = tensor.empty() : tensor<5x3xi32>
+// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SEC]][0, %[[C_2]], 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
+// CHECK-DAG:       %[[PAD:.*]] = arith.constant 0 : i32
+// CHECK-DAG:       %[[C_5:.*]] = arith.constant 5 : index
+// CHECK-DAG:       %[[C_1:.*]] = arith.constant 1 : index
+// CHECK:           %[[MASK:.*]] = vector.create_mask %[[C_5]], %[[C_1]] : vector<8x1xi1>
+// CHECK:           %[[C0:.*]] = arith.constant 0 : index
+// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C0]], %[[C0]]], %[[PAD]] : tensor<5x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
+// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
+// CHECK:           %[[RES:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0]], %[[C_2]]] : vector<8x1xi32>, tensor<5x3xi32> } : vector<8x1xi1> -> tensor<5x3xi32>
+// CHECK:           return %[[RES]] : tensor<5x3xi32>
+
+ module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
+    transform.yield
+  }
+ }
+
+// -----
+
+// One of the _source_ dimensions is dynamic (but _destination_ dimensions are static).
+
+func.func private @insert_slice_dynamic_src_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<5x3xi32> {
+  %c2 = arith.constant 2 : index
+  %init = tensor.empty() : tensor<5x3xi32>
+
+  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, %size, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
+  %res = tensor.insert_slice %source_slice into %init[0, %c2] [%size, 1] [1, 1] : tensor<?x1xi32> into tensor<5x3xi32>
+
+  return %res : tensor<5x3xi32>
+}
+
+// CHECK-LABEL:   func.func private @insert_slice_dynamic_src_dim(
+// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
+// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<5x3xi32> {
+// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
+// CHECK:           %[[INIT:.*]] = tensor.empty() : tensor<5x3xi32>
+// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, %[[SIZE]], 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
+// CHECK-DAG:       %[[PAD:.*]] = arith.constant 0 : i32
+// CHECK-DAG:       %[[C_1:.*]] = arith.constant 1 : index
+// CHECK:           %[[MASK:.*]] = vector.create_mask %[[SIZE]], %[[C_1]] : vector<8x1xi1>
+// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
+// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C_0]], %[[C_0]]], %[[PAD]] : tensor<?x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
+// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
+// CHECK:           %[[RES:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<5x3xi32> } : vector<8x1xi1> -> tensor<5x3xi32>
+// CHECK:           return %[[RES]] : tensor<5x3xi32>
+
+ module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
+    transform.yield
+  }
+ }
+
+// -----
+
+// One of the _destination_ dimensions is dynamic (but _source_ dimensions are static).
+
+func.func private @insert_slice_dynamic_dest_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<?x3xi32> {
+  %c2 = arith.constant 2 : index
+  %init = tensor.empty(%size) : tensor<?x3xi32>
+
+  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
+  %res = tensor.insert_slice %source_slice into %init[0, %c2] [5, 1] [1, 1] : tensor<5x1xi32> into tensor<?x3xi32>
+
+  return %res : tensor<?x3xi32>
+}
+
+// CHECK-LABEL:   func.func private @insert_slice_dynamic_dest_dim(
+// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
+// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<?x3xi32> {
+// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
+// CHECK:           %[[INIT:.*]] = tensor.empty(%[[SIZE]]) : tensor<?x3xi32>
+// CHECK:           %[[SRC_SLICE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, 5, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<5x1xi32>
+// CHECK:           %[[PAD:.*]] = arith.constant 0 : i32
+// CHECK:           %[[C_5:.*]] = arith.constant 5 : index
+// CHECK:           %[[C_1:.*]] = arith.constant 1 : index
+// CHECK:           %[[MASK:.*]] = vector.create_mask %[[C_5]], %[[C_1]] : vector<8x1xi1>
+// CHECK:           %[[C_0:.*]] = arith.constant 0 : index
+// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SLICE]][%[[C_0]], %[[C_0]]], %[[PAD]] : tensor<5x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
+// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
+// CHECK:           %[[WRITE:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]][%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<?x3xi32> } : vector<8x1xi1> -> tensor<?x3xi32>
+// CHECK:           return %[[WRITE]] : tensor<?x3xi32>
+
+ module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
+    transform.yield
+  }
+ }
+
+// -----
+
+// At least one _source_ and one _destination_ dimensions are dynamic.
+
+func.func private @insert_slice_dynamic_source_and_dest_dim(%source: tensor<?x3x?x1xi32>, %size: index) -> tensor<?x3xi32> {
+  %c2 = arith.constant 2 : index
+  %init = tensor.empty(%size) : tensor<?x3xi32>
+
+  %source_slice = tensor.extract_slice %source[0, %c2, 0, 0] [1, 1, %size, 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
+  %res = tensor.insert_slice %source_slice into %init[0, %c2] [%size, 1] [1, 1] : tensor<?x1xi32> into tensor<?x3xi32>
+
+  return %res : tensor<?x3xi32>
+}
+
+// CHECK-LABEL:   func.func private @insert_slice_dynamic_source_and_dest_dim(
+// CHECK-SAME:      %[[SRC:.*]]: tensor<?x3x?x1xi32>,
+// CHECK-SAME:      %[[SIZE:.*]]: index) -> tensor<?x3xi32> {
+// CHECK:           %[[C_2:.*]] = arith.constant 2 : index
+// CHECK:           %[[INIT:.*]] = tensor.empty(%[[SIZE]]) : tensor<?x3xi32>
+// CHECK:           %[[SRC_SIZE:.*]] = tensor.extract_slice %[[SRC]][0, %[[C_2]], 0, 0] [1, 1, %[[SIZE]], 1] [1, 1, 1, 1] : tensor<?x3x?x1xi32> to tensor<?x1xi32>
+// CHECK:           %[[PAD:.*]] = arith.constant 0 : i32
+// CHECK:           %[[C1:.*]] = arith.constant 1 : index
+// CHECK:           %[[MASK:.*]] = vector.create_mask %[[SIZE]], %[[C1]] : vector<8x1xi1>
+// CHECK:           %[[C0:.*]] = arith.constant 0 : index
+// CHECK:           %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[SRC_SIZE]]{{\[}}%[[C0]], %[[C0]]], %[[PAD]] : tensor<?x1xi32>, vector<8x1xi32> } : vector<8x1xi1> -> vector<8x1xi32>
+// CHECK:           %[[C_0_1:.*]] = arith.constant 0 : index
+// CHECK:           %[[WRITE:.*]] = vector.mask %[[MASK]] { vector.transfer_write %[[READ]], %[[INIT]]{{\[}}%[[C_0_1]], %[[C_2]]] : vector<8x1xi32>, tensor<?x3xi32> } : vector<8x1xi1> -> tensor<?x3xi32>
+// CHECK:           return %[[WRITE]] : tensor<?x3xi32>
+
+ module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.insert_slice"]} in %arg0 : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [8, 1] : !transform.any_op
+    transform.yield
+  }
+ }
diff --git a/mlir/test/Dialect/Linalg/vectorization/pad-with-patterns.mlir b/mlir/test/Dialect/Linalg/vectorization/pad-with-patterns.mlir
new file mode 100644
index 0000000..4086d54
--- /dev/null
+++ b/mlir/test/Dialect/Linalg/vectorization/pad-with-patterns.mlir
@@ -0,0 +1,227 @@
+// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s
+
+///----------------------------------------------------------------------------------------
+/// Tests for tensor.pad
+///----------------------------------------------------------------------------------------
+
+// CHECK-LABEL: func @pad_static(
+//  CHECK-SAME:                  %[[ARG0:.*]]: tensor<2x?x2xf32>, %[[PAD:.*]]: f32
+//   CHECK-NOT:   tensor.pad
+//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
+//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
+//   CHECK-DAG:   %[[INIT:.*]] = tensor.empty() : tensor<2x3x4xf32>
+//   CHECK-DAG:   %[[VEC:.*]] = vector.broadcast %[[PAD]] : f32 to vector<2x3x4xf32>
+//       CHECK:   %[[FILL:.*]] = vector.transfer_write %[[VEC]], %[[INIT]]{{.*}} : vector<2x3x4xf32>, tensor<2x3x4xf32>
+//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]], %[[C0]]], %[[PAD]] {in_bounds = [true, false, true]} : tensor<2x?x2xf32>, vector<2x3x2xf32>
+//       CHECK:   %[[RESULT:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C0]], %[[C0]], %[[C2]]] {in_bounds = [true, true, true]} : vector<2x3x2xf32>, tensor<2x3x4xf32>
+//       CHECK:   return %[[RESULT]]
+func.func @pad_static(%arg0: tensor<2x?x2xf32>, %pad_value: f32) -> tensor<2x3x4xf32> {
+  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
+    ^bb0(%arg1: index, %arg2: index, %arg3: index):
+      tensor.yield %pad_value : f32
+    } : tensor<2x?x2xf32> to tensor<2x3x4xf32>
+  return %0 : tensor<2x3x4xf32>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// CHECK-LABEL: func @pad_static_source(
+//  CHECK-SAME:                  %[[ARG0:.*]]: tensor<2x5x2xf32>, %[[PAD:.*]]: f32
+//   CHECK-NOT:   tensor.pad
+//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
+//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
+//       CHECK:   %[[INIT:.*]] = tensor.empty() : tensor<2x6x4xf32>
+//       CHECK:   %[[VEC:.*]] =  vector.broadcast %[[PAD]] : f32 to vector<2x6x4xf32>
+//       CHECK:   %[[FILL:.*]] = vector.transfer_write %[[VEC]], %[[INIT]][%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<2x6x4xf32>, tensor<2x6x4xf32>
+//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]], %[[C0]]], %{{.*}} {in_bounds = [true, true, true]} : tensor<2x5x2xf32>, vector<2x5x2xf32>
+//       CHECK:   %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C0]], %[[C0]], %[[C2]]] {in_bounds = [true, true, true]} : vector<2x5x2xf32>, tensor<2x6x4xf32>
+//       CHECK:   return %[[WRITE]]
+func.func @pad_static_source(%arg0: tensor<2x5x2xf32>, %pad_value: f32) -> tensor<2x6x4xf32> {
+  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
+    ^bb0(%arg1: index, %arg2: index, %arg3: index):
+      tensor.yield %pad_value : f32
+    } : tensor<2x5x2xf32> to tensor<2x6x4xf32>
+  return %0 : tensor<2x6x4xf32>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+
+// -----
+
+// CHECK-LABEL: func @pad_static_dynamic(
+//  CHECK-SAME:                          %[[SRC:.*]]: tensor<1x2x2x?xf32>, %[[LOW:.*]]: index, %[[HIGH:.*]]: index
+//   CHECK-NOT:   tensor.pad
+//   CHECK-DAG:   %[[C2:.*]] = arith.constant 2 : index
+//   CHECK-DAG:   %[[C3:.*]] = arith.constant 3 : index
+//   CHECK-DAG:   %[[C5:.*]] = arith.constant 5 : index
+//       CHECK:   %[[V0:.*]] = arith.addi %[[LOW]], %[[C2]] : index
+//       CHECK:   %[[V1:.*]] = arith.addi %[[V0]], %[[C3]] : index
+//       CHECK:   %[[V2:.*]] = arith.addi %[[HIGH]], %[[C5]] : index
+//       CHECK:   %[[DIM3:.*]] = tensor.dim %[[SRC]], %[[C3]] : tensor<1x2x2x?xf32>
+//       CHECK:   %[[V4:.*]] = arith.addi %[[DIM3]], %[[C3]] : index
+//       CHECK:   %[[V5:.*]] = arith.addi %[[V4]], %[[C2]] : index
+//       CHECK:   %[[INIT:.*]] = tensor.empty(%[[V1]], %[[V2]], %[[V5]]) : tensor<6x?x?x?xf32>
+//       CHECK:   %[[FILL:.*]] = linalg.fill ins(%{{.*}} : f32) outs(%[[INIT]] : tensor<6x?x?x?xf32>) -> tensor<6x?x?x?xf32>
+//       CHECK:   %[[SRCDIM:.*]] = tensor.dim %[[SRC]], %[[C3]] : tensor<1x2x2x?xf32>
+//       CHECK:   %[[RESULT:.*]] = tensor.insert_slice %[[SRC]] into %[[FILL]][2, %[[LOW]], 3, 3] [1, 2, 2, %[[SRCDIM]]] [1, 1, 1, 1] : tensor<1x2x2x?xf32> into tensor<6x?x?x?xf32>
+//       CHECK:   return %[[RESULT]]
+func.func @pad_static_dynamic(%arg0: tensor<1x2x2x?xf32>, %low: index, %high: index,
+                  %pad_value: f32) -> tensor<6x?x?x?xf32> {
+  %0 = tensor.pad %arg0 low[2, %low, 3, 3] high[3, 3, %high, 2] {
+    ^bb0(%arg1: index, %arg2: index, %arg3: index, %arg4: index):
+      tensor.yield %pad_value : f32
+    } : tensor<1x2x2x?xf32> to tensor<6x?x?x?xf32>
+  return %0 : tensor<6x?x?x?xf32>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// CHECK-LABEL: func @pad_static_complex(
+//   CHECK-NOT:   vector<
+func.func @pad_static_complex(%arg0: tensor<2x5x2xcomplex<f32>>, %pad_value: complex<f32>) -> tensor<2x6x4xcomplex<f32>> {
+  %0 = tensor.pad %arg0 low[0, 0, 2] high[0, 1, 0] {
+    ^bb0(%arg1: index, %arg2: index, %arg3: index):
+      tensor.yield %pad_value : complex<f32>
+    } : tensor<2x5x2xcomplex<f32>> to tensor<2x6x4xcomplex<f32>>
+  return %0 : tensor<2x6x4xcomplex<f32>>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+func.func private @make_vector() -> tensor<12x13xf32>
+
+// CHECK-LABEL:   func.func @pad_and_insert_slice_dest(
+// CHECK-SAME:      %[[ARG_0:.*]]: tensor<1x5x6xf32>) -> tensor<1x12x13xf32> {
+// CHECK:           %[[C0:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK:           %[[CST:.*]] = arith.constant dense<5.000000e+00> : vector<1x12x13xf32>
+// CHECK:           %[[C0_IDX:.*]] = arith.constant 0 : index
+// CHECK:           %[[PAD_VAL:.*]] = arith.constant 5.000000e+00 : f32
+// CHECK:           %[[EMPTY:.*]] = tensor.empty() : tensor<1x12x13xf32>
+// CHECK:           %[[WRITE_1:.*]] = vector.transfer_write %[[CST]], %[[EMPTY]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true, true]} : vector<1x12x13xf32>, tensor<1x12x13xf32>
+// CHECK:           %[[READ_1:.*]] = vector.transfer_read %[[ARG_0]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]], %[[PAD_VAL]] {in_bounds = [true, true, true]} : tensor<1x5x6xf32>, vector<1x5x6xf32>
+// CHECK:           %[[WRITE_2:.*]] = vector.transfer_write %[[READ_1]], %[[WRITE_1]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true, true]} : vector<1x5x6xf32>, tensor<1x12x13xf32>
+// CHECK:           %[[MAKE_VEC:.*]] = call @make_vector() : () -> tensor<12x13xf32>
+// CHECK:           %[[READ_2:.*]] = vector.transfer_read %[[MAKE_VEC]]{{\[}}%[[C0_IDX]], %[[C0_IDX]]], %[[C0]] {in_bounds = [true, true]} : tensor<12x13xf32>, vector<12x13xf32>
+// CHECK:           %[[RES:.*]] = vector.transfer_write %[[READ_2]], %[[WRITE_2]]{{\[}}%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]] {in_bounds = [true, true]} : vector<12x13xf32>, tensor<1x12x13xf32>
+// CHECK:           return %[[RES]] : tensor<1x12x13xf32>
+func.func @pad_and_insert_slice_dest(
+    %arg0: tensor<1x5x6xf32>) -> tensor<1x12x13xf32> {
+  %c5 = arith.constant 5.0 : f32
+  %0 = tensor.pad %arg0 low[0, 0, 0] high[0, 7, 7] {
+    ^bb0(%arg2: index, %arg3: index, %arg4: index):
+      tensor.yield %c5 : f32
+  } : tensor<1x5x6xf32> to tensor<1x12x13xf32>
+  %1 = call @make_vector() : () -> tensor<12x13xf32>
+  %r = tensor.insert_slice %1 into %0[0, 0, 0][1, 12, 13][1, 1, 1] : tensor<12x13xf32> into tensor<1x12x13xf32>
+  return %r : tensor<1x12x13xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %3 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %4 = transform.get_parent_op %3 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %5 = transform.structured.vectorize_children_and_apply_patterns %4  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// CHECK-LABEL: func @pad_tensor_non_const_pad_value
+//  CHECK-SAME:     %[[ARG0:.*]]: tensor<5x6xf32>
+//   CHECK-NOT:   tensor.pad
+//   CHECK-DAG:   %[[C0:.*]] = arith.constant 0 : index
+//   CHECK-DAG:   %[[C3:.*]] = arith.constant 3 : index
+//   CHECK-DAG:   %[[C4:.*]] = arith.constant 4 : index
+//       CHECK:   %[[FILL:.*]] = tensor.generate
+//       CHECK:     %[[RES:.*]] = arith.mulf
+//       CHECK:     tensor.yield %[[RES]] : f32
+//       CHECK:   %[[READ:.*]] = vector.transfer_read %[[ARG0]][%[[C0]], %[[C0]]], %{{.*}} {in_bounds = [true, true]} : tensor<5x6xf32>, vector<5x6xf32>
+//       CHECK:   %[[WRITE:.*]] = vector.transfer_write %[[READ]], %[[FILL]][%[[C3]], %[[C4]]] {in_bounds = [true, true]} : vector<5x6xf32>, tensor<12x13xf32>
+//       CHECK:   return %[[WRITE]]
+func.func @pad_tensor_non_const_pad_value(%arg0: tensor<5x6xf32>) -> tensor<12x13xf32> {
+  %c0 = arith.constant 0 : index
+  %c5 = arith.constant 5.0 : f32
+  %0 = tensor.pad %arg0 low[3, 4] high[4, 3] {
+    ^bb0(%arg1: index, %arg2: index):
+      %i1 = arith.index_cast %arg1 : index to i32
+      %i2 = arith.index_cast %arg2 : index to i32
+      %f1 = arith.sitofp %i1 : i32 to f32
+      %f2 = arith.sitofp %i2 : i32 to f32
+      %m = arith.mulf %f1, %f2 : f32
+      tensor.yield %m : f32
+  } : tensor<5x6xf32> to tensor<12x13xf32>
+  return %0 : tensor<12x13xf32>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %3 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %4 = transform.get_parent_op %3 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %5 = transform.structured.vectorize_children_and_apply_patterns %4  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+// CHECK-LABEL: func @test_masked_pad_static_dynamic
+func.func @test_masked_pad_static_dynamic(%arg0: tensor<1x2x2x?xf32>, %low: index, %high: index,
+                  %pad_value: f32) -> tensor<6x?x?x?xf32> {
+  // CHECK: tensor.pad
+  %0 = tensor.pad %arg0 low[2, %low, 3, 3] high[3, 3, %high, 2] {
+    ^bb0(%arg1: index, %arg2: index, %arg3: index, %arg4: index):
+      tensor.yield %pad_value : f32
+    } : tensor<1x2x2x?xf32> to tensor<6x?x?x?xf32>
+  return %0 : tensor<6x?x?x?xf32>
+}
+
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+    %2 = transform.structured.vectorize_children_and_apply_patterns %1  { vectorize_padding } : (!transform.any_op) -> !transform.any_op
+    transform.yield
+  }
+}
diff --git a/mlir/test/Dialect/Linalg/vectorization/pad.mlir b/mlir/test/Dialect/Linalg/vectorization/pad.mlir
new file mode 100644
index 0000000..6bbb7ab
--- /dev/null
+++ b/mlir/test/Dialect/Linalg/vectorization/pad.mlir
@@ -0,0 +1,131 @@
+// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s
+
+///----------------------------------------------------------------------------------------
+/// Tests for tensor.pad
+///----------------------------------------------------------------------------------------
+
+// CHECK-LABEL: func @test_masked_vectorize_pad
+func.func @test_masked_vectorize_pad(
+  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index)
+    -> tensor<2x4xf32>
+{
+  //  CHECK-DAG: %[[c42:.*]] = arith.constant 4.243000e+01 : f32
+  //  CHECK-DAG: %[[c0:.*]] = arith.constant 0 : index
+  //  CHECK-DAG: %[[c0_0:.*]] = arith.constant 0 : index
+  //      CHECK: %[[d0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[d1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[mask:.*]] = vector.create_mask %[[d0]], %[[d1]] : vector<2x4xi1>
+  //      CHECK: %[[masked_read:.*]] = vector.mask %[[mask]] {
+  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[c0_0]], %[[c0_0]]], %[[c42]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<2x4xf32>
+  // CHECK-SAME: } : vector<2x4xi1> -> vector<2x4xf32>
+  //  CHECK-DAG: %[[c0_1:.*]] = arith.constant 0 : index
+  //  CHECK-DAG: %[[empty:.*]] = tensor.empty() : tensor<2x4xf32>
+  //      CHECK: vector.transfer_write %[[masked_read]], %[[empty]][%[[c0_1]], %[[c0_1]]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : vector<2x4xf32>, tensor<2x4xf32>
+  %cst = arith.constant 42.43 : f32
+  %c0 = arith.constant 0 : index
+  %1 = tensor.pad %0 low[0, %c0] high[%h0, %h1]  {
+    ^bb0(%hh1: index, %hh2: index):
+      tensor.yield %cst : f32
+    } : tensor<?x?xf32> to tensor<2x4xf32>
+  return %1: tensor<2x4xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
+      : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [2, 4] : !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+
+//       CHECK: #[[MAP:.+]] = affine_map<()[s0, s1] -> (s0 + s1)>
+//       CHECK: func @test_masked_vectorize_dynamic_pad
+func.func @test_masked_vectorize_dynamic_pad(
+  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index)
+    -> tensor<?x?xf32>
+{
+  //  CHECK-DAG: %[[c42:.*]] = arith.constant 4.243000e+01 : f32
+  //  CHECK-DAG: %[[c0:.*]] = arith.constant 0 : index
+  //  CHECK-DAG: %[[res_d0:.+]] = affine.apply #[[MAP]]()
+  //  CHECK-DAG: %[[res_d1:.+]] = affine.apply #[[MAP]]()
+  //      CHECK: %[[c0_2:.*]] = arith.constant 0 : index
+  //      CHECK: %[[d0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[d1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[mask:.*]] = vector.create_mask %[[d0]], %[[d1]] : vector<2x4xi1>
+  //      CHECK: %[[masked_read:.*]] = vector.mask %[[mask]] {
+  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[c0_2]], %[[c0_2]]], %[[c42]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<2x4xf32>
+  // CHECK-SAME: } : vector<2x4xi1> -> vector<2x4xf32>
+  //  CHECK-DAG: %[[empty:.*]] = tensor.empty(%[[res_d0]], %[[res_d1]]) : tensor<?x?xf32>
+  //  CHECK-DAG: %[[c0_3:.*]] = arith.constant 0 : index
+  //  CHECK-DAG: %[[d2:.*]] = tensor.dim %[[empty]], {{.*}} : tensor<?x?xf32>
+  //  CHECK-DAG: %[[d3:.*]] = tensor.dim %[[empty]], {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[mask_2:.*]] = vector.create_mask %[[d2]], %[[d3]] : vector<2x4xi1>
+  //      CHECK: %[[masked_write:.*]] = vector.mask %[[mask_2]] {
+  // CHECK-SAME: vector.transfer_write %[[masked_read]], %[[empty]][%[[c0_3]], %[[c0_3]]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : vector<2x4xf32>, tensor<?x?xf32>
+  //      CHECK: return %[[masked_write]] : tensor<?x?xf32>
+  %cst = arith.constant 42.43 : f32
+  %c0 = arith.constant 0 : index
+  %1 = tensor.pad %0 low[0, %c0] high[%h0, %h1]  {
+    ^bb0(%hh1: index, %hh2: index):
+      tensor.yield %cst : f32
+    } : tensor<?x?xf32> to tensor<?x?xf32>
+  return %1: tensor<?x?xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
+      : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [2, 4] : !transform.any_op
+    transform.yield
+  }
+}
+
+// -----
+// This case is supported because low padding `%l0` is applied on
+// a unit dimension which is supported, non unit result dimension low
+// padding is currently unsupported.
+//  CHECK-LABEL: func @test_masked_vectorize_non_zero_low_pad_unit_res_dim
+func.func @test_masked_vectorize_non_zero_low_pad_unit_res_dim(
+  %0 : tensor<?x?xf32>, %h0 : index, %h1 : index, %l0 : index)
+    -> tensor<1x4xf32>
+{
+  //  CHECK-DAG: %[[C42:.*]] = arith.constant 4.243000e+01 : f32
+  //  CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
+  //      CHECK: %[[C0_1:.*]] = arith.constant 0 : index
+  //  CHECK-DAG: %[[D0:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //  CHECK-DAG: %[[D1:.*]] = tensor.dim {{.*}} : tensor<?x?xf32>
+  //      CHECK: %[[MASK:.*]] = vector.create_mask %[[D0]], %[[D1]] : vector<1x4xi1>
+  //      CHECK: %[[MASKED_READ:.*]] = vector.mask %[[MASK]] {
+  // CHECK-SAME:   vector.transfer_read %{{.*}}[%[[C0_1]], %[[C0_1]]], %[[C42]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : tensor<?x?xf32>, vector<1x4xf32>
+  // CHECK-SAME: } : vector<1x4xi1> -> vector<1x4xf32>
+  //  CHECK-DAG: %[[EMPTY:.*]] = tensor.empty() : tensor<1x4xf32>
+  //  CHECK-DAG: %[[C0_2:.*]] = arith.constant 0 : index
+  //      CHECK: %[[MASKED_WRITE:.*]] = vector.transfer_write %[[MASKED_READ]], %[[EMPTY]][%[[C0_2]], %[[C0_2]]]
+  // CHECK-SAME:   {in_bounds = [true, true]} : vector<1x4xf32>, tensor<1x4xf32>
+  //      CHECK: return %[[MASKED_WRITE]] : tensor<1x4xf32>
+  %cst = arith.constant 42.43 : f32
+  %c0 = arith.constant 0 : index
+  %1 = tensor.pad %0 low[%l0, %c0] high[%h0, %h1]  {
+    ^bb0(%hh1: index, %hh2: index):
+      tensor.yield %cst : f32
+    } : tensor<?x?xf32> to tensor<1x4xf32>
+  return %1: tensor<1x4xf32>
+}
+
+module attributes {transform.with_named_sequence} {
+  transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
+    %0 = transform.structured.match ops{["tensor.pad"]} in %arg1
+      : (!transform.any_op) -> !transform.any_op
+    transform.structured.vectorize %0 vector_sizes [1, 4] : !transform.any_op
+    transform.yield
+  }
+}