diff --git a/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf-full.mlir b/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf-full.mlir
--- a/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf-full.mlir
+++ b/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-mulf-full.mlir
@@ -1,6 +1,9 @@
-// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-std -convert-vector-to-llvm="enable-amx" -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
+// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-std \
+// RUN:  -tensor-constant-bufferize -convert-vector-to-llvm="enable-amx" \
+// RUN:  -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-translate -mlir-to-llvmir | \
-// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \
+// RUN:  --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
 // Note: To run this test, your CPU must support AMX.
@@ -25,9 +28,7 @@
   %c16 = arith.constant 16: index
   %c32 = arith.constant 32: index
 
-  // Setup simple test data. Note that bf16 does not seem to work well with the
-  // tensor type yet, which is why we use vectors and transfer the data into memref.
-  // TODO: use tensors and bufferization.to_memref instead
+  // Setup simple test data.
   %0 = arith.constant dense<[
      [ 1.1, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ],
@@ -61,7 +62,7 @@
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ],
      [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.1,
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ]
-  ]> : vector<16x32xbf16>
+  ]> : tensor<16x32xbf16>
   %1 = arith.constant dense<[
      [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.1, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ],
@@ -95,14 +96,12 @@
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ],
      [ 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.1, 1.0, 1.0, 1.0, 1.0, 1.0,
        1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0 ]
-  ]> : vector<16x32xbf16>
+  ]> : tensor<16x32xbf16>
 
   // Set up memory.
-  %a = memref.alloc() : memref<16x32xbf16>
-  %b = memref.alloc() : memref<16x32xbf16>
+  %a = bufferization.to_memref %0 : memref<16x32xbf16>
+  %b = bufferization.to_memref %1 : memref<16x32xbf16>
   %c = memref.alloc() : memref<16x16xf32>
-  vector.transfer_write %0, %a[%c0, %c0] : vector<16x32xbf16>, memref<16x32xbf16>
-  vector.transfer_write %1, %b[%c0, %c0] : vector<16x32xbf16>, memref<16x32xbf16>
 
   // Call kernel.
   call @kernel(%a, %b, %c) : (memref<16x32xbf16>, memref<16x32xbf16>, memref<16x16xf32>) -> ()
@@ -133,8 +132,6 @@
   }
 
   // Release resources.
-  memref.dealloc %a : memref<16x32xbf16>
-  memref.dealloc %b : memref<16x32xbf16>
   memref.dealloc %c : memref<16x16xf32>
   %i0 = arith.constant 0 : i32
   return %i0 : i32
diff --git a/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli-full.mlir b/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli-full.mlir
new file mode 100644
--- /dev/null
+++ b/mlir/test/Integration/Dialect/Vector/CPU/AMX/test-muli-full.mlir
@@ -0,0 +1,137 @@
+// RUN: mlir-opt %s -convert-vector-to-scf -lower-affine -convert-scf-to-std \
+// RUN:  -tensor-constant-bufferize -convert-vector-to-llvm="enable-amx" \
+// RUN:  -convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
+// RUN: mlir-translate -mlir-to-llvmir | \
+// RUN: %lli --entry-function=entry --mattr="+amx-tile,+amx-int8,+amx-bf16" \
+// RUN:  --dlopen=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+
+// Note: To run this test, your CPU must support AMX.
+
+// Multiply full size tiles into zero destination.
+func @kernel(%arg0: memref<16x64xi8>,
+             %arg1: memref<16x64xi8>,
+             %arg2: memref<16x16xi32>) {
+  %0 = arith.constant 0 : index
+  %1 = amx.tile_load %arg0[%0, %0] : memref<16x64xi8>  into vector<16x64xi8>
+  %2 = amx.tile_load %arg1[%0, %0] : memref<16x64xi8>  into vector<16x64xi8>
+  %3 = amx.tile_zero : vector<16x16xi32>
+  %4 = amx.tile_muli %1 zext, %2 zext, %3 : vector<16x64xi8>, vector<16x64xi8>, vector<16x16xi32>
+  amx.tile_store %arg2[%0, %0], %4 : memref<16x16xi32>, vector<16x16xi32>
+  return
+}
+
+func @entry() -> i32 {
+  %iu = arith.constant -1: i32
+  %c0 = arith.constant 0: index
+  %c1 = arith.constant 1: index
+  %c16 = arith.constant 16: index
+
+  // Setup simple test data.
+  %0 = arith.constant dense<[
+    [ 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
+  ]> : tensor<16x64xi8>
+  %1 = arith.constant dense<[
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ],
+    [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
+  ]> : tensor<16x64xi8>
+
+  // Set up memory.
+  %a = bufferization.to_memref %0 : memref<16x64xi8>
+  %b = bufferization.to_memref %1 : memref<16x64xi8>
+  %c = memref.alloc() : memref<16x16xi32>
+
+  // Call kernel.
+  call @kernel(%a, %b, %c) : (memref<16x64xi8>, memref<16x64xi8>, memref<16x16xi32>) -> ()
+
+  //
+  // Print and verify the 16x16 result.
+  //
+  // CHECK:      ( 69, 69, 69, 69, 65, 65, 65, 65, 89, 89, 89, 89, 89, 89, 89, 75 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 72, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 72, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 72, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 72, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 75, 75, 75, 75, 71, 71, 71, 71, 95, 95, 95, 95, 95, 95, 95, 81 )
+  // CHECK-NEXT: ( 69, 69, 69, 69, 65, 65, 65, 65, 89, 89, 89, 89, 89, 89, 89, 75 )
+  //
+  scf.for %i = %c0 to %c16 step %c1 {
+    %v = vector.transfer_read %c[%i, %c0], %iu: memref<16x16xi32>, vector<16xi32>
+    vector.print %v : vector<16xi32>
+  }
+
+  // Release resources.
+  memref.dealloc %c : memref<16x16xi32>
+  %i0 = arith.constant 0 : i32
+  return %i0 : i32
+}