diff --git a/mlir/test/Dialect/Linalg/transform-patterns.mlir b/mlir/test/Dialect/Linalg/transform-patterns.mlir
--- a/mlir/test/Dialect/Linalg/transform-patterns.mlir
+++ b/mlir/test/Dialect/Linalg/transform-patterns.mlir
@@ -1,7 +1,8 @@
 // RUN: mlir-opt %s -test-linalg-transform-patterns | FileCheck %s
 
-// CHECK-DAG: #[[STRIDED_1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
-// CHECK-DAG: #[[STRIDED_2D:.*]] = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
+// CHECK-DAG: #[[STRIDED_1D:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1  + s0)>
+// CHECK-DAG: #[[STRIDED_2D_1:.*]] = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
+// CHECK-DAG: #[[STRIDED_2D:.*]] = affine_map<(d0, d1)[s0, s1, s2] -> (d0 * s1 + s0 + d1 * s2)>
 // CHECK-DAG: #[[mk:.*]] = affine_map<(d0, d1, d2) -> (d0, d2)>
 // CHECK-DAG: #[[kn:.*]] = affine_map<(d0, d1, d2) -> (d2, d1)>
 // CHECK-DAG: #[[mn:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
@@ -17,18 +18,19 @@
   return
 }
 // CHECK-LABEL: func @dot
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c8:.*]] = constant 8 : index
-// CHECK-DAG  :   %[[c8000:.*]] = constant 8000 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8]] {
-// CHECK      :       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c1]] {
-// CHECK      :         load
-// CHECK      :         load
-// CHECK      :         mulf
-// CHECK      :         load
-// CHECK      :         addf
-// CHECK      :         store
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c1:.*]] = constant 1 : index
+// CHECK-DAG:     %[[c8:.*]] = constant 8 : index
+// CHECK-DAG:     %[[c8000:.*]] = constant 8000 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8]] {
+// CHECK:             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c1]] {
+// CHECK:               load
+// CHECK:               load
+// CHECK:               mulf
+// CHECK:               load
+// CHECK:               addf
+// CHECK:               store
 
 func @matvec(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %x: memref<?xf32, offset: ?, strides: [1]>,
@@ -39,12 +41,12 @@
   return
 }
 // CHECK-LABEL: func @matvec
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c5:.*]] = constant 5 : index
-// CHECK-DAG  :   %[[c6:.*]] = constant 6 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c5]]
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c6]]
-// CHECK      :       linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c5:.*]] = constant 5 : index
+// CHECK-DAG:     %[[c6:.*]] = constant 6 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c5]]
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c6]]
+// CHECK:             linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>
 
 func @matmul(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %B: memref<?x?xf32, offset: ?, strides: [?, 1]>,
@@ -55,32 +57,32 @@
   return
 }
 // CHECK-LABEL: func @matmul
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c2:.*]] = constant 2 : index
-// CHECK-DAG  :   %[[c3:.*]] = constant 3 : index
-// CHECK-DAG  :   %[[c4:.*]] = constant 4 : index
-// CHECK-DAG  :   %[[c20:.*]] = constant 20 : index
-// CHECK-DAG  :   %[[c30:.*]] = constant 30 : index
-// CHECK-DAG  :   %[[c40:.*]] = constant 40 : index
-// CHECK-DAG  :   %[[c200:.*]] = constant 200 : index
-// CHECK-DAG  :   %[[c300:.*]] = constant 300 : index
-// CHECK-DAG  :   %[[c400:.*]] = constant 400 : index
-// CHECK-DAG  :   %[[c2000:.*]] = constant 2000 : index
-// CHECK-DAG  :   %[[c3000:.*]] = constant 3000 : index
-// CHECK-DAG  :   %[[c4000:.*]] = constant 4000 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
-// CHECK      :       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
-// CHECK      :         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
-// CHECK      :           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
-// CHECK      :             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
-// CHECK      :               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
-// CHECK      :                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
-// CHECK      :                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
-// CHECK      :                     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2]] {
-// CHECK      :                       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3]] {
-// CHECK      :                         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4]] {
-// CHECK      :                           linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c2:.*]] = constant 2 : index
+// CHECK-DAG:     %[[c3:.*]] = constant 3 : index
+// CHECK-DAG:     %[[c4:.*]] = constant 4 : index
+// CHECK-DAG:     %[[c20:.*]] = constant 20 : index
+// CHECK-DAG:     %[[c30:.*]] = constant 30 : index
+// CHECK-DAG:     %[[c40:.*]] = constant 40 : index
+// CHECK-DAG:     %[[c200:.*]] = constant 200 : index
+// CHECK-DAG:     %[[c300:.*]] = constant 300 : index
+// CHECK-DAG:     %[[c400:.*]] = constant 400 : index
+// CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index
+// CHECK-DAG:     %[[c3000:.*]] = constant 3000 : index
+// CHECK-DAG:     %[[c4000:.*]] = constant 4000 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
+// CHECK:             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
+// CHECK:               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
+// CHECK:                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
+// CHECK:                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
+// CHECK:                     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
+// CHECK:                       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
+// CHECK:                         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
+// CHECK:                           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2]] {
+// CHECK:                             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3]] {
+// CHECK:                               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4]] {
+// CHECK:                                 linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
 
 #some_generic_trait = {
   args_in = 1,
@@ -122,47 +124,47 @@
   return
 }
 // CHECK-LABEL: func @fusion_test
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c2:.*]] = constant 2 : index
-// CHECK-DAG  :   %[[c3:.*]] = constant 3 : index
-// CHECK-DAG  :   %[[c4:.*]] = constant 4 : index
-// CHECK-DAG  :   %[[c20:.*]] = constant 20 : index
-// CHECK-DAG  :   %[[c30:.*]] = constant 30 : index
-// CHECK-DAG  :   %[[c40:.*]] = constant 40 : index
-// CHECK-DAG  :   %[[c100:.*]] = constant 100 : index
-// CHECK-DAG  :   %[[c150:.*]] = constant 150 : index
-// CHECK-DAG  :   %[[c200:.*]] = constant 200 : index
-// CHECK-DAG  :   %[[c300:.*]] = constant 300 : index
-// CHECK-DAG  :   %[[c400:.*]] = constant 400 : index
-// CHECK-DAG  :   %[[c2000:.*]] = constant 2000 : index
-// CHECK-DAG  :   %[[c3000:.*]] = constant 3000 : index
-// CHECK-DAG  :   %[[c4000:.*]] = constant 4000 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
-// CHECK      :       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
-// CHECK      :         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
-// CHECK      :           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
-// CHECK      :             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
-// CHECK      :               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
-// CHECK      :                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
-// CHECK      :                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
-// CHECK      :                     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2]] {
-// CHECK      :                       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3]] {
-// CHECK      :                         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4]] {
-// CHECK      :                           linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c2:.*]] = constant 2 : index
+// CHECK-DAG:     %[[c3:.*]] = constant 3 : index
+// CHECK-DAG:     %[[c4:.*]] = constant 4 : index
+// CHECK-DAG:     %[[c20:.*]] = constant 20 : index
+// CHECK-DAG:     %[[c30:.*]] = constant 30 : index
+// CHECK-DAG:     %[[c40:.*]] = constant 40 : index
+// CHECK-DAG:     %[[c100:.*]] = constant 100 : index
+// CHECK-DAG:     %[[c150:.*]] = constant 150 : index
+// CHECK-DAG:     %[[c200:.*]] = constant 200 : index
+// CHECK-DAG:     %[[c300:.*]] = constant 300 : index
+// CHECK-DAG:     %[[c400:.*]] = constant 400 : index
+// CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index
+// CHECK-DAG:     %[[c3000:.*]] = constant 3000 : index
+// CHECK-DAG:     %[[c4000:.*]] = constant 4000 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
+// CHECK:             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
+// CHECK:               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
+// CHECK:                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
+// CHECK:                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
+// CHECK:                     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
+// CHECK:                       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
+// CHECK:                         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
+// CHECK:                           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2]] {
+// CHECK:                             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3]] {
+// CHECK:                               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4]] {
+// CHECK:                                 linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
 //
-// CHECK      :   linalg.generic
+// CHECK:         linalg.generic
 //
-// CHECK      :   loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c100]] {
-// CHECK      :     loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c150]] {
-// CHECK      :       loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c2]] {
-// CHECK      :         loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c3]] {
-// CHECK      :           loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c4]] {
-// CHECK      :             linalg.matmul(%{{.*}}, %{{.*}}, %{{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
-// CHECK      :       loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c2]] {
-// CHECK      :         loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c3]] {
-// CHECK      :           loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c4]] {
-// CHECK      :             linalg.matmul(%{{.*}}, %{{.*}}, %{{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:         loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c100]] {
+// CHECK:           loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c150]] {
+// CHECK:             loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c2]] {
+// CHECK:               loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c3]] {
+// CHECK:                 loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c4]] {
+// CHECK:                   linalg.matmul(%{{.*}}, %{{.*}}, %{{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:             loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c2]] {
+// CHECK:               loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c3]] {
+// CHECK:                 loop.for %{{.*}} = %[[c0]] to %{{.*}} step %[[c4]] {
+// CHECK:                   linalg.matmul(%{{.*}}, %{{.*}}, %{{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
 
 #matmul_trait = {
   args_in = 2,
@@ -237,15 +239,14 @@
      memref<?x?xf32, offset: ?, strides: [?, 1]>
   return
 }
-// CHECK-LABEL : func @fma
-// CHECK-LABEL : func @permute_generic
-// CHECK       : linalg.generic {args_in = 2, args_out = 1,
-// CHECK-SAME  : indexing_maps = [#[[kn]], #[[nm]], #[[km]]],
-// CHECK-SAME  : iterator_types = ["parallel", "reduction", "parallel"],
-// CHECK-SAME  : library_call = "linalg_matmul"} %{{.*}}, %{{.*}}, %{{.*}}
-// CHECK       :   memref<?x?xf32, #[[STRIDED_2D]]>,
-// CHECK-SAME  :   memref<?x?xf32, #[[STRIDED_2D]]>,
-// CHECK-SAME  :   memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK-LABEL:  func @permute_generic
+// CHECK:        linalg.generic {args_in = 2 : i64, args_out = 1 : i64,
+// CHECK-SAME:   indexing_maps = [#[[kn]], #[[nm]], #[[km]]],
+// CHECK-SAME:   iterator_types = ["parallel", "reduction", "parallel"],
+// CHECK-SAME:   library_call = "linalg_matmul"} %{{.*}}, %{{.*}}, %{{.*}}
+// CHECK:          memref<?x?xf32, #[[STRIDED_2D_1]]>,
+// CHECK-SAME:     memref<?x?xf32, #[[STRIDED_2D_1]]>,
+// CHECK-SAME:     memref<?x?xf32, #[[STRIDED_2D_1]]>
 
 #indexed_matmul_trait = {
   args_in = 2,
@@ -268,15 +269,14 @@
       memref<?x?xf32, offset: ?, strides: [?, 1]>
   return
 }
-// CHECK-LABEL : func @fma_indexed
-// CHECK-LABEL : func @permute_generic_indexed
-// CHECK       : linalg.indexed_generic {args_in = 2, args_out = 1,
-// CHECK-SAME  :   indexing_maps = [#[[kn]], #[[nm]], #[[km]]],
-// CHECK-SAME  :   iterator_types = ["parallel", "reduction", "parallel"],
-// CHECK-SAME  :   library_call = "linalg_matmul_indexed"} %{{.*}}, %{{.*}}, %{{.*}} :
-// CHECK       :     memref<?x?xf32, #[[STRIDED_2D]]>,
-// CHECK-SAME  :     memref<?x?xf32, #[[STRIDED_2D]]>,
-// CHECK-SAME  :     memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK-LABEL:  func @permute_generic_indexed
+// CHECK:        linalg.indexed_generic {args_in = 2 : i64, args_out = 1 : i64,
+// CHECK-SAME:     indexing_maps = [#[[kn]], #[[nm]], #[[km]]],
+// CHECK-SAME:     iterator_types = ["parallel", "reduction", "parallel"],
+// CHECK-SAME:     library_call = "linalg_matmul_indexed"} %{{.*}}, %{{.*}}, %{{.*}}
+// CHECK:            memref<?x?xf32, #[[STRIDED_2D_1]]>,
+// CHECK-SAME:       memref<?x?xf32, #[[STRIDED_2D_1]]>,
+// CHECK-SAME:       memref<?x?xf32, #[[STRIDED_2D_1]]>
 
 func @dot_perm(%x: memref<?xf32, offset: ?, strides: [1]>,
           %y: memref<?xf32, offset: ?, strides: [1]>,
@@ -288,12 +288,12 @@
   return
 }
 // CHECK-LABEL: func @dot_perm
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c8:.*]] = constant 8 : index
-// CHECK-DAG  :   %[[c8000:.*]] = constant 8000 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8]] {
-// CHECK      :       linalg.dot({{.*}}, {{.*}}, {{.*}}) : memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<f32>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c8:.*]] = constant 8 : index
+// CHECK-DAG:     %[[c8000:.*]] = constant 8000 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c8]] {
+// CHECK:             linalg.dot({{.*}}, {{.*}}, {{.*}}) : memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<f32>
 
 func @matvec_perm(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %x: memref<?xf32, offset: ?, strides: [1]>,
@@ -305,12 +305,12 @@
   return
 }
 // CHECK-LABEL: func @matvec_perm
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c5:.*]] = constant 5 : index
-// CHECK-DAG  :   %[[c6:.*]] = constant 6 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c6]]
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c5]]
-// CHECK      :       linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c5:.*]] = constant 5 : index
+// CHECK-DAG:     %[[c6:.*]] = constant 6 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c6]]
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c5]]
+// CHECK:             linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?xf32, #[[STRIDED_1D]]>, memref<?xf32, #[[STRIDED_1D]]>
 
 func @matmul_perm(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %B: memref<?x?xf32, offset: ?, strides: [?, 1]>,
@@ -322,29 +322,26 @@
   return
 }
 // CHECK-LABEL: func @matmul_perm
-// CHECK-DAG  :   %[[c0:.*]] = constant 0 : index
-// CHECK-DAG  :   %[[c2:.*]] = constant 2 : index
-// CHECK-DAG  :   %[[c3:.*]] = constant 3 : index
-// CHECK-DAG  :   %[[c4:.*]] = constant 4 : index
-// CHECK-DAG  :   %[[c20:.*]] = constant 20 : index
-// CHECK-DAG  :   %[[c30:.*]] = constant 30 : index
-// CHECK-DAG  :   %[[c40:.*]] = constant 40 : index
-// CHECK-DAG  :   %[[c200:.*]] = constant 200 : index
-// CHECK-DAG  :   %[[c300:.*]] = constant 300 : index
-// CHECK-DAG  :   %[[c400:.*]] = constant 400 : index
-// CHECK-DAG  :   %[[c2000:.*]] = constant 2000 : index
-// CHECK-DAG  :   %[[c3000:.*]] = constant 3000 : index
-// CHECK-DAG  :   %[[c4000:.*]] = constant 4000 : index
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
-// CHECK      :       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
-// CHECK      :         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
-// CHECK      :           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
-// CHECK      :             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
-// CHECK      :               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
-// CHECK      :                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
-// CHECK      :                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
-// CHECK      :                           linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK-DAG:     %[[c0:.*]] = constant 0 : index
+// CHECK-DAG:     %[[c20:.*]] = constant 20 : index
+// CHECK-DAG:     %[[c30:.*]] = constant 30 : index
+// CHECK-DAG:     %[[c40:.*]] = constant 40 : index
+// CHECK-DAG:     %[[c200:.*]] = constant 200 : index
+// CHECK-DAG:     %[[c300:.*]] = constant 300 : index
+// CHECK-DAG:     %[[c400:.*]] = constant 400 : index
+// CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index
+// CHECK-DAG:     %[[c3000:.*]] = constant 3000 : index
+// CHECK-DAG:     %[[c4000:.*]] = constant 4000 : index
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
+// CHECK:             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
+// CHECK:               loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
+// CHECK:                 loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
+// CHECK:                   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
+// CHECK:                     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
+// CHECK:                       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
+// CHECK:                         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
+// CHECK:                                 linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
 
 func @promote_subview_matmul(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
                              %arg1: memref<?x?xf32, offset: ?, strides: [?, 1]>,
@@ -360,11 +357,11 @@
   loop.for %arg3 = %c0 to %0 step %c2000 {
     loop.for %arg4 = %c0 to %2 step %c3000 {
       loop.for %arg5 = %c0 to %1 step %c4000 {
-        %3 = std.subview %arg0[%arg3, %arg5][%c2000, %c4000][%c1, %c1] :
+        %3 = subview %arg0[%arg3, %arg5][%c2000, %c4000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
-        %4 = std.subview %arg1[%arg5, %arg4][%c4000, %c3000][%c1, %c1] :
+        %4 = subview %arg1[%arg5, %arg4][%c4000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
-        %5 = std.subview %arg2[%arg3, %arg4][%c2000, %c3000][%c1, %c1] :
+        %5 = subview %arg2[%arg3, %arg4][%c2000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         linalg.matmul(%3, %4, %5) {__internal_linalg_transform__ = "_promote_views_"} :
                       memref<?x?xf32, offset: ?, strides: [?, ?]>,
@@ -376,22 +373,22 @@
   return
 }
 // CHECK-LABEL: func @promote_subview_matmul
-// CHECK      :   loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
-// CHECK      :     loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
-// CHECK      :       loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
-// CHECK      :         %[[s0:.*]] = std.subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
-// CHECK      :         %[[s1:.*]] = std.subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
-// CHECK      :         %[[s2:.*]] = std.subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
-// CHECK      :         %[[a0:.*]] = alloc({{%.*}}) : memref<?xi8>
-// CHECK      :         %[[v0:.*]] = std.view %[[a0]][][{{%.*}}, {{%.*}}]: memref<?xi8> to memref<?x?xf32>
-// CHECK      :         %[[l0:.*]] = linalg.slice %[[v0]][{{%.*}}, {{%.*}}] : memref<?x?xf32>, !linalg.range, !linalg.range, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         %[[a1:.*]] = alloc({{%.*}}) : memref<?xi8>
-// CHECK      :         %[[v1:.*]] = std.view %[[a1]][][{{%.*}}, {{%.*}}]: memref<?xi8> to memref<?x?xf32>
-// CHECK      :         %[[l1:.*]] = linalg.slice %[[v1]][{{%.*}}, {{%.*}}] : memref<?x?xf32>, !linalg.range, !linalg.range, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         %[[a2:.*]] = alloc({{%.*}}) : memref<?xi8>
-// CHECK      :         %[[v2:.*]] = std.view %[[a2]][][{{%.*}}, {{%.*}}]: memref<?xi8> to memref<?x?xf32>
-// CHECK      :         %[[l2:.*]] = linalg.slice %[[v2]][{{%.*}}, {{%.*}}] : memref<?x?xf32>, !linalg.range, !linalg.range, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         linalg.copy(%[[s0]], %[[l0]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         linalg.copy(%[[s1]], %[[l1]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         linalg.copy(%[[s2]], %[[l2]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
-// CHECK      :         linalg.matmul(%[[v0]], %[[v1]], %[[v2]]) : memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>, memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:         loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
+// CHECK:           loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
+// CHECK:             loop.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
+// CHECK:               %[[s0:.*]] = subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
+// CHECK:               %[[s1:.*]] = subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
+// CHECK:               %[[s2:.*]] = subview {{%.*}}[{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32, #map{{.*}}> to memref<?x?xf32, #map{{.*}}>
+// CHECK:               %[[a0:.*]] = alloc({{%.*}}) : memref<?xi8>
+// CHECK:               %[[v0:.*]] = std.view %[[a0]][][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
+// CHECK:               %[[l0:.*]] = subview %[[v0]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:               %[[a1:.*]] = alloc({{%.*}}) : memref<?xi8>
+// CHECK:               %[[v1:.*]] = std.view %[[a1]][][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
+// CHECK:               %[[l1:.*]] = subview %[[v1]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:               %[[a2:.*]] = alloc({{%.*}}) : memref<?xi8>
+// CHECK:               %[[v2:.*]] = std.view %[[a2]][][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
+// CHECK:               %[[l2:.*]] = subview %[[v2]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[STRIDED_2D]]>
+// CHECK:               linalg.copy(%[[s0]], %[[l0]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
+// CHECK:               linalg.copy(%[[s1]], %[[l1]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
+// CHECK:               linalg.copy(%[[s2]], %[[l2]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
+// CHECK:               linalg.matmul(%[[v0]], %[[v1]], %[[v2]]) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>