diff --git a/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp b/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
--- a/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
+++ b/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
@@ -1284,10 +1284,6 @@
   if (!isa<linalg::GenericOp, linalg::FillOp>(op))
     return failure();
 
-  // TODO: Index vectorization assumes static shape.
-  if (op.hasIndexSemantics())
-    return failure();
-
   LDBG("Dynamically-shaped op meets vectorization pre-conditions\n");
   return success();
 }
diff --git a/mlir/test/Dialect/Linalg/vectorization.mlir b/mlir/test/Dialect/Linalg/vectorization.mlir
--- a/mlir/test/Dialect/Linalg/vectorization.mlir
+++ b/mlir/test/Dialect/Linalg/vectorization.mlir
@@ -1834,6 +1834,39 @@
 
 // -----
 
+func.func @masked_vectorize_nd_tensor_extract_with_affine_apply_contiguous(%6: tensor<80x16xf32>, %arg0: index, %extracted_slice : tensor<1x3xf32>) -> tensor<1x3xf32> {
+  %c79 = arith.constant 79 : index
+  %1 = linalg.generic {
+    indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>],
+    iterator_types = ["parallel", "parallel"]
+  } outs(%extracted_slice : tensor<1x3xf32>) {
+  ^bb0(%out: f32):
+    %2 = linalg.index 1 : index
+    %3 = affine.apply affine_map<(d0, d1) -> (d0 + d1)>(%2, %arg0)
+    %extracted = tensor.extract %6[%c79, %3] : tensor<80x16xf32>
+    linalg.yield %extracted : f32
+  } -> tensor<1x3xf32>
+  return %1 : tensor<1x3xf32>
+}
+
+// CHECK-LABEL:   func.func @masked_vectorize_nd_tensor_extract_with_affine_apply_contiguous
+// CHECK-DAG:       %[[VAL_4:.*]] = arith.constant 1 : index
+// CHECK-DAG:       %[[VAL_5:.*]] = arith.constant 3 : index
+// CHECK:           %[[VAL_8:.*]] = vector.create_mask %[[VAL_4]], %[[VAL_5]] : vector<1x4xi1>
+// CHECK:           %[[VAL_9:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read {{.*}} {in_bounds = [true, true]} : tensor<1x3xf32>, vector<1x4xf32> } : vector<1x4xi1> -> vector<1x4xf32>
+// CHECK:           %[[VAL_11:.*]] = vector.broadcast {{.*}} : index to vector<4xindex>
+// CHECK:           %[[VAL_12:.*]] = arith.addi {{.*}} : vector<4xindex>
+// CHECK:           %[[VAL_20:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read {{.*}} {in_bounds = [true, true]} : tensor<80x16xf32>, vector<1x4xf32> } : vector<1x4xi1> -> vector<1x4xf32>
+// CHECK:           %[[VAL_22:.*]] = vector.mask %[[VAL_8]] { vector.transfer_write {{.*}} {in_bounds = [true, true]} : vector<1x4xf32>, tensor<1x3xf32> } : vector<1x4xi1> -> tensor<1x3xf32>
+
+transform.sequence failures(propagate) {
+ ^bb1(%arg1: !pdl.operation):
+   %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
+   transform.structured.masked_vectorize %0 vector_sizes [1, 4] { vectorize_nd_extract }
+ }
+
+// -----
+
 // The vectorizer converts `affine.apply` so that the subsequent Ops can be vectorised based on the converted ops. Gather load.
 func.func @vectorize_nd_tensor_extract_with_affine_apply_gather(%6: tensor<80x16xf32>, %arg0: index, %extracted_slice : tensor<1x4xf32>) -> tensor<1x4xf32> {
   %c16 = arith.constant 16 : index
@@ -1878,6 +1911,44 @@
 
 // -----
 
+func.func @masked_vectorize_nd_tensor_extract_with_affine_apply_gather(%6: tensor<80x16xf32>, %arg0: index, %extracted_slice : tensor<1x3xf32>) -> tensor<1x3xf32> {
+  %c16 = arith.constant 16 : index
+  %1 = linalg.generic {
+    indexing_maps = [affine_map<(d0, d1) -> (d0, d1)>],
+    iterator_types = ["parallel", "parallel"]
+  } outs(%extracted_slice : tensor<1x3xf32>) {
+  ^bb0(%out: f32):
+    %2 = linalg.index 1 : index
+    %3 = affine.apply affine_map<(d0, d1) -> (d0 + d1)>(%2, %arg0)
+    %extracted = tensor.extract %6[%3, %c16] : tensor<80x16xf32>
+    linalg.yield %extracted : f32
+  } -> tensor<1x3xf32>
+  return %1 : tensor<1x3xf32>
+}
+
+// CHECK-LABEL:   func.func @masked_vectorize_nd_tensor_extract_with_affine_apply_gather
+// CHECK-DAG:       %[[VAL_4:.*]] = arith.constant 1 : index
+// CHECK-DAG:       %[[VAL_5:.*]] = arith.constant 3 : index
+// CHECK:           %[[VAL_8:.*]] = vector.create_mask %[[VAL_4]], %[[VAL_5]] : vector<1x4xi1>
+// CHECK:           %[[VAL_9:.*]] = vector.mask %[[VAL_8]] { vector.transfer_read {{.*}} {in_bounds = [true, true]} : tensor<1x3xf32>, vector<1x4xf32> } : vector<1x4xi1> -> vector<1x4xf32>
+// CHECK:           %[[VAL_11:.*]] = vector.broadcast {{.*}} : index to vector<4xindex>
+// CHECK:           %[[VAL_12:.*]] = arith.addi {{.*}} : vector<4xindex>
+// CHECK:           %[[VAL_16:.*]] = vector.broadcast {{.*}} : vector<4xindex> to vector<1x4xindex>
+// CHECK:           %[[VAL_18:.*]] = tensor.dim {{.*}} : tensor<80x16xf32>
+// CHECK:           %[[VAL_19:.*]] = vector.broadcast {{.*}} : index to vector<1x4xindex>
+// CHECK:           %[[VAL_20:.*]] = arith.muli {{.*}} : vector<1x4xindex>
+// CHECK:           %[[VAL_22:.*]] = arith.addi {{.*}} : vector<1x4xindex>
+// CHECK:           %[[VAL_23:.*]] = vector.mask %[[VAL_8]] { vector.gather {{.*}} : tensor<80x16xf32>, vector<1x4xindex>, vector<1x4xi1>, vector<1x4xf32> into vector<1x4xf32> } : vector<1x4xi1> -> vector<1x4xf32>
+// CHECK:           %[[VAL_25:.*]] = vector.mask %[[VAL_8]] { vector.transfer_write {{.*}} {in_bounds = [true, true]} : vector<1x4xf32>, tensor<1x3xf32> } : vector<1x4xi1> -> tensor<1x3xf32>
+
+transform.sequence failures(propagate) {
+ ^bb1(%arg1: !pdl.operation):
+   %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!pdl.operation) -> !pdl.operation
+   transform.structured.masked_vectorize %0 vector_sizes [1, 4] { vectorize_nd_extract }
+ }
+
+// -----
+
 // Make sure that non-linear arithmetic operations (e.g. arith.maxsi) are allowed when calculating indices for load operations. Gather load.
 func.func @vectorize_nd_tensor_extract_with_maxsi_gather(%arg0: tensor<80x16xf32>, %extracted_slice : tensor<1x4xf32>) -> tensor<1x4xf32> {
   %c79 = arith.constant 79 : index