[mlir][test] Fix filecheck annotation typos [2/n] (#93476)

klensy · klensy · web-flow · commit a5985ca51dd7 · 2024-06-14T17:16:02.000+02:00
Few more fixes previous: #92897 pr Issues from #93154 unfixed. --------- Co-authored-by: klensy <nightouser@gmail.com>
diff --git a/mlir/test/Analysis/test-liveness.mlir b/mlir/test/Analysis/test-liveness.mlir
@@ -40,7 +40,7 @@ func.func @func_simpleBranch(%arg0: i32, %arg1 : i32) -> i32 {
   // CHECK-SAME:    arg0@0 arg1@0 val_2
   // CHECK: return
   // CHECK-SAME:    val_2
-  // CHECK-NEXT EndCurrentlyLive
+  // CHECK-NEXT:EndCurrentlyLive
   %result = arith.addi %arg0, %arg1 : i32
   return %result : i32
 }
@@ -197,9 +197,9 @@ func.func @func_ranges(%cond : i1, %arg1 : i32, %arg2 : i32, %arg3 : i32) -> i32
   // CHECK-NEXT:    %2 = arith.addi
   // CHECK-NEXT:    %3 = arith.muli
   // CHECK-NEXT: val_7
-  // CHECK-NEXT    %2 = arith.addi
-  // CHECK-NEXT    %3 = arith.muli
-  // CHECK-NEXT    %4 = arith.muli
+  // CHECK-NEXT:   %2 = arith.addi
+  // CHECK-NEXT:   %3 = arith.muli
+  // CHECK-NEXT:   %4 = arith.muli
   // CHECK:      val_8
   // CHECK-NEXT:    %3 = arith.muli
   // CHECK-NEXT:    %4 = arith.muli
diff --git a/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
@@ -638,7 +638,7 @@ gpu.module @test_module_30 {
   }
   // CHECK-LABEL: @subgroup_reduce_xor
   gpu.func @subgroup_reduce_xor(%arg0 : i32) {
-    // CHECK nvvm.redux.sync xor {{.*}}
+    // CHECK: nvvm.redux.sync xor {{.*}}
     %result = gpu.subgroup_reduce xor %arg0 uniform {} : (i32) -> (i32)
     gpu.return
   }
diff --git a/mlir/test/Conversion/MemRefToLLVM/convert-dynamic-memref-ops.mlir b/mlir/test/Conversion/MemRefToLLVM/convert-dynamic-memref-ops.mlir
@@ -378,14 +378,14 @@ func.func @memref_cast_ranked_to_unranked(%arg : memref<42x2x?xf32>) {
 // CHECK-DAG:  %[[p:.*]] = llvm.alloca %[[c]] x !llvm.struct<(ptr, ptr, i64, array<3 x i64>, array<3 x i64>)> : (i64) -> !llvm.ptr
 // CHECK-DAG:  llvm.store %{{.*}}, %[[p]] : !llvm.struct<(ptr, ptr, i64, array<3 x i64>, array<3 x i64>)>, !llvm.ptr
 // CHECK-DAG:  %[[r:.*]] = llvm.mlir.constant(3 : index) : i64
-// CHECK    :  llvm.mlir.undef : !llvm.struct<(i64, ptr)>
+//     CHECK:  llvm.mlir.undef : !llvm.struct<(i64, ptr)>
 // CHECK-DAG:  llvm.insertvalue %[[r]], %{{.*}}[0] : !llvm.struct<(i64, ptr)>
 // CHECK-DAG:  llvm.insertvalue %[[p]], %{{.*}}[1] : !llvm.struct<(i64, ptr)>
 // CHECK32-DAG:  %[[c:.*]] = llvm.mlir.constant(1 : index) : i64
 // CHECK32-DAG:  %[[p:.*]] = llvm.alloca %[[c]] x !llvm.struct<(ptr, ptr, i32, array<3 x i32>, array<3 x i32>)> : (i64) -> !llvm.ptr
 // CHECK32-DAG:  llvm.store %{{.*}}, %[[p]] : !llvm.struct<(ptr, ptr, i32, array<3 x i32>, array<3 x i32>)>, !llvm.ptr
 // CHECK32-DAG:  %[[r:.*]] = llvm.mlir.constant(3 : index) : i32
-// CHECK32    :  llvm.mlir.undef : !llvm.struct<(i32, ptr)>
+//     CHECK32:  llvm.mlir.undef : !llvm.struct<(i32, ptr)>
 // CHECK32-DAG:  llvm.insertvalue %[[r]], %{{.*}}[0] : !llvm.struct<(i32, ptr)>
 // CHECK32-DAG:  llvm.insertvalue %[[p]], %{{.*}}[1] : !llvm.struct<(i32, ptr)>
   %0 = memref.cast %arg : memref<42x2x?xf32> to memref<*xf32>
diff --git a/mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir b/mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir
@@ -11,7 +11,7 @@ func.func @m16n8k16_fp16(%arg0: vector<4x2xf16>, %arg1: vector<2x2xf16>, %arg2:
   // CHECK: llvm.extractvalue %{{.*}}[1] : !llvm.array<2 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[0] : !llvm.array<2 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[1] : !llvm.array<2 x vector<2xf16>>
-  // CHECK-NOT llvm.extractvalue
+  // CHECK-NOT: llvm.extractvalue
   // CHECK: [[d:%.+]] = nvvm.mma.sync
   // CHECK-SAME: shape = #nvvm.shape<m = 16, n = 8, k = 16>
   %d = nvgpu.mma.sync (%arg0, %arg1, %arg2) {mmaShape = [16, 8, 16]} : (vector<4x2xf16>, vector<2x2xf16>, vector<2x2xf16>) -> vector<2x2xf16>
@@ -56,7 +56,7 @@ func.func @m16n8k8_fp16(%arg0: vector<2x2xf16>, %arg1: vector<1x2xf16>, %arg2: v
   // CHECK: llvm.extractvalue %{{.*}}[0] : !llvm.array<1 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[0] : !llvm.array<2 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[1] : !llvm.array<2 x vector<2xf16>>
-  // CHECK-NOT llvm.extractvalue
+  // CHECK-NOT: llvm.extractvalue
   // CHECK: [[d:%.+]] = nvvm.mma.sync
   // CHECK-SAME: shape = #nvvm.shape<m = 16, n = 8, k = 8>
   %d = nvgpu.mma.sync (%arg0, %arg1, %arg2) {mmaShape = [16, 8, 8]} : (vector<2x2xf16>, vector<1x2xf16>, vector<2x2xf16>) -> vector<2x2xf16>
@@ -360,7 +360,7 @@ func.func @mma_sp_sync_f16_16832(%arg0: vector<4x2xf16>,
   // CHECK: llvm.extractvalue %{{.*}}[0] : !llvm.array<2 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[1] : !llvm.array<2 x vector<2xf16>>
 
-  // CHECK-NOT llvm.extractvalue
+  // CHECK-NOT: llvm.extractvalue
 
   // CHECK: %[[sparseMetadata:.+]] = llvm.bitcast %{{.+}} : vector<2xi16> to i32
 
@@ -396,7 +396,7 @@ func.func @mma_sp_sync_f16_16816(%arg0: vector<2x2xf16>,
   // CHECK: llvm.extractvalue %{{.*}}[0] : !llvm.array<2 x vector<2xf16>>
   // CHECK: llvm.extractvalue %{{.*}}[1] : !llvm.array<2 x vector<2xf16>>
 
-  // CHECK-NOT llvm.extractvalue
+  // CHECK-NOT: llvm.extractvalue
 
   // CHECK: %[[sparseMetadata:.+]] = llvm.bitcast %{{.+}} : vector<2xi16> to i32
 
@@ -455,7 +455,7 @@ func.func @mma_sp_sync_i8_16864(%arg0: vector<4x4xi8>,
   // CHECK: llvm.extractvalue %{{.*}}[{{.*}}] : !llvm.array<2 x vector<2xi32>>
   // CHECK: llvm.extractvalue %{{.*}}[{{.*}}] : !llvm.array<2 x vector<2xi32>>
 
-  // CHECK-NOT llvm.extractvalue
+  // CHECK-NOT: llvm.extractvalue
 
   // CHECK: %[[sparseMetadata:.+]] = llvm.bitcast %{{.+}} : vector<2xi16> to i32
 
diff --git a/mlir/test/Dialect/AMX/roundtrip.mlir b/mlir/test/Dialect/AMX/roundtrip.mlir
@@ -2,7 +2,7 @@
 
 // CHECK-LABEL: tzero
 // CHECK: amx.tile_zero : vector<16x16xbf16>
-// CHECK amx.tile_store %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} : memref<?x?xbf16>, vector<16x16xbf16>
+// CHECK: amx.tile_store %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} : memref<?x?xbf16>, vector<16x16xbf16>
 func.func @tzero(%arg0: memref<?x?xbf16>) {
   %0 = arith.constant 0 : index
   %1 = amx.tile_zero : vector<16x16xbf16>
diff --git a/mlir/test/Dialect/Affine/loop-fusion-3.mlir b/mlir/test/Dialect/Affine/loop-fusion-3.mlir
@@ -889,7 +889,7 @@ func.func @reduce_add_non_innermost(%arg0: memref<64x64xf32, 1>, %arg1: memref<1
 // CHECK:         affine.for
 // CHECK-NEXT:      affine.for
 // CHECK-NEXT:        affine.for
-// CHECK             affine.for
+// CHECK:            affine.for
 
 
 
diff --git a/mlir/test/Dialect/Affine/unroll.mlir b/mlir/test/Dialect/Affine/unroll.mlir
@@ -616,7 +616,7 @@ func.func @loop_nest_non_trivial_multiple_upper_bound_alt(%M : index, %N : index
   // UNROLL-BY-4-NEXT: "foo"
   // UNROLL-BY-4-NEXT: "foo"
   // UNROLL-BY-4-NEXT: "foo"
-  // UNROLL-BY-4-NOT for
+  // UNROLL-BY-4-NOT: for
   // UNROLL-BY-4: return
   return
 }
diff --git a/mlir/test/Dialect/ArmSME/tile-allocation-liveness.mlir b/mlir/test/Dialect/ArmSME/tile-allocation-liveness.mlir
@@ -406,7 +406,7 @@ func.func @avoidable_spill(%a: vector<[4]xf32>, %b: vector<[4]xf32>, %c: vector<
 // CHECK: arm_sme.get_tile {tile_id = 2 : i32} : vector<[4]x[4]xf32>
 // CHECK: arm_sme.get_tile {tile_id = 3 : i32} : vector<[4]x[4]xf32>
 // CHECK: arm_sme.move_vector_to_tile_slice {{.*}} {tile_id = 0 : i32} : vector<[4]xf32> into vector<[4]x[4]xf32>
-// CHECK-NOT tile_id = 16
+// CHECK-NOT: tile_id = 16
 func.func @cond_branch_with_backedge(%slice: vector<[4]xf32>) {
   %tileA = arm_sme.get_tile : vector<[4]x[4]xf32>
   %tileB = arm_sme.get_tile : vector<[4]x[4]xf32>
diff --git a/mlir/test/Dialect/Linalg/drop-unit-extent-dims.mlir b/mlir/test/Dialect/Linalg/drop-unit-extent-dims.mlir
@@ -881,7 +881,7 @@ func.func @input_stays_same(%arg0 : memref<?x1x?xf32, strided<[?, 1, 1]>>, %arg1
 // CHECK:     func @input_stays_same(
 // CHECK-SAME:  %[[ARG0:.*]]: memref<?x1x?xf32, strided<[?, 1, 1]>>,
 // CHECK-SAME:  %[[ARG1:.*]]: f32, %[[ARG2:.*]]: memref<?x1x?x1x?xf32>)
-// CHECK-SAME   -> memref<?x1x?x1x?xf32> {
+// CHECK-SAME:  -> memref<?x1x?x1x?xf32> {
 // CHECK:      %[[OUT:.*]] = memref.collapse_shape %[[ARG2]] {{\[}}[0, 1], [2, 3], [4]]
 // CHECK-SAME:   : memref<?x1x?x1x?xf32> into memref<?x?x?xf32>
 // CHECK:      linalg.generic
diff --git a/mlir/test/Dialect/Linalg/fusion-elementwise-ops.mlir b/mlir/test/Dialect/Linalg/fusion-elementwise-ops.mlir
@@ -532,7 +532,7 @@ func.func @scalar_generic_fusion
 //  CHECK-SAME:     ins(%[[ARG1]] : tensor<i32>)
 //       CHECK:     tensor.extract %[[ARG0]]
 //       CHECK:     linalg.yield
-//       CHECK   return %[[T0]]
+//       CHECK:  return %[[T0]]
 
 // -----
 
diff --git a/mlir/test/Dialect/Linalg/transform-ops.mlir b/mlir/test/Dialect/Linalg/transform-ops.mlir
@@ -2,17 +2,17 @@
 
 transform.sequence failures(propagate) {
 ^bb1(%arg0: !transform.any_op):
-  // CHECK %{{.*}}, %{{.*}}:2 = transform.structured.tile
+  // CHECK: %{{.*}}, %{{.*}}:2 = transform.structured.tile
   %0, %1:2 = transform.structured.tile_using_for %arg0 tile_sizes [2, 0, 3] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op)
 }
 
 // check that the Attributes of `tile_using_for` are preserved through printing
 // and parsing with and without use of the optional `interchange` Attribute.
 transform.sequence failures(propagate) {
 ^bb1(%arg0: !transform.any_op):
-  // CHECK %{{.*}}, %{{.*}}:2 = transform.structured.tile %arg0 [2, 0, 3] interchange = [2, 1] {test_attr1 = 1 : i64, test_attr2}
+  // CHECK: %{{.*}}, %{{.*}}:2 = transform.structured.tile_using_for %arg0 tile_sizes [2, 0, 3] interchange = [2, 1] {test_attr1 = 1 : i64, test_attr2}
   %0, %1:2 = transform.structured.tile_using_for %arg0 tile_sizes [2, 0, 3] interchange = [2, 1] {test_attr1 = 1 : i64, test_attr2}: (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op)
-  // CHECK %{{.*}}, %{{.*}}:2 = transform.structured.tile %arg0 [4, 5, 3] {test_attr3 = 1 : i64, test_attr4}
+  // CHECK: %{{.*}}, %{{.*}}:2 = transform.structured.tile_using_for %tiled_linalg_op tile_sizes [0, 5, 3] {test_attr3 = 1 : i64, test_attr4}
   %2, %3:2 = transform.structured.tile_using_for %0 tile_sizes [0, 5, 3] {test_attr3 = 1 : i64, test_attr4}: (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op)
 }
 
diff --git a/mlir/test/Dialect/OpenMP/ops.mlir b/mlir/test/Dialect/OpenMP/ops.mlir
@@ -142,7 +142,7 @@ func.func @omp_parallel_pretty(%data_var : memref<i32>, %if_cond : i1, %num_thre
    omp.terminator
  }
 
- // CHECK omp.parallel if(%{{.*}}) num_threads(%{{.*}} : i32) private(%{{.*}} : memref<i32>) proc_bind(close)
+ // CHECK: omp.parallel if(%{{.*}}) num_threads(%{{.*}} : i32) proc_bind(close)
  omp.parallel num_threads(%num_threads : i32) if(%if_cond: i1) proc_bind(close) {
    omp.terminator
  }
diff --git a/mlir/test/Dialect/SparseTensor/sparse_reshape.mlir b/mlir/test/Dialect/SparseTensor/sparse_reshape.mlir
@@ -76,9 +76,9 @@ func.func @sparse_expand(%arg0: tensor<100xf64, #SparseVector>) -> tensor<10x10x
 // CHECK:             %[[T:.*]] = arith.muli %[[SI0]], %[[C10]] : index
 // CHECK:             %[[DI:.*]] = arith.addi %[[T]], %[[SI1]] : index
 // CHECK:             %[[R1:.*]] = tensor.insert %[[SV]] into %[[A1]]{{\[}}%[[DI]]]
-// CHECK              scf.yield %[[R1]]
-// CHECK            }
-// CHECK            scf.yield %[[RET_1]]
+// CHECK:             scf.yield %[[R1]]
+// CHECK:           }
+// CHECK:           scf.yield %[[RET_1]]
 // CHECK:         }
 // CHECK:        %[[NT1:.*]] = sparse_tensor.load %[[RET]] hasInserts
 // CHECK-NOT:    sparse_tensor.convert
@@ -170,9 +170,9 @@ func.func @dynamic_sparse_expand(%arg0: tensor<?xf64, #SparseVector>, %sz0: inde
 // CHECK:             %[[T4:.*]] = arith.muli %[[SI1]], %[[T3]] : index
 // CHECK:             %[[DI:.*]] = arith.addi %[[T2]], %[[T4]] : index
 // CHECK:             %[[NT:.*]] = tensor.insert %[[SV]] into %[[R1]]{{\[}}%[[DI]]]
-// CHECK              scf.yield %[[NT]]
-// CHECK            }
-// CHECK            scf.yield %[[RET_1]]
+// CHECK:             scf.yield %[[NT]]
+// CHECK:           }
+// CHECK:           scf.yield %[[RET_1]]
 // CHECK:        }
 // CHECK:        %[[NT1:.*]] = sparse_tensor.load %[[RET]] hasInserts
 // CHECK-NOT:    sparse_tensor.convert
diff --git a/mlir/test/Dialect/Tensor/canonicalize.mlir b/mlir/test/Dialect/Tensor/canonicalize.mlir
@@ -1120,8 +1120,8 @@ func.func @compose_expand_of_expand_of_zero_dim(%arg0 : tensor<f32>)
 // CHECK-LABEL: func.func @collapse_of_cast(
 // CHECK-SAME:         %[[IN:.*]]: tensor<8x12x32xf32>) -> tensor<?x32xf32> {
 // CHECK-NEXT:    %[[COLLAPSE:.*]] = tensor.collapse_shape %[[IN]] {{\[}}[0, 1], [2]] : tensor<8x12x32xf32> into tensor<96x32xf32>
-// CHECK-NEXT     %[[CAST:.*]] = tensor.cast %[[COLLAPSE]] : tensor<96x32xf32> to tensor<?x32xf32>
-// CHECK-NEXT     return %[[CAST]] : tensor<?x32xf32>
+// CHECK-NEXT:    %[[CAST:.*]] = tensor.cast %[[COLLAPSE]] : tensor<96x32xf32> to tensor<?x32xf32>
+// CHECK-NEXT:    return %[[CAST]] : tensor<?x32xf32>
 func.func @collapse_of_cast(%t: tensor<8x12x32xf32>) -> tensor<?x32xf32> {
   %0 = tensor.cast %t : tensor<8x12x32xf32> to tensor<?x?x?xf32>
   %1 = tensor.collapse_shape %0 [[0, 1], [2]] : tensor<?x?x?xf32> into tensor<?x?xf32>
diff --git a/mlir/test/Dialect/Tosa/canonicalize.mlir b/mlir/test/Dialect/Tosa/canonicalize.mlir
@@ -684,7 +684,7 @@ func.func @canonicalize_concat_slice_on_non_concat_axis(%arg0 : tensor<1x12x12xf
 
 // -----
 
-// CHECK-LABEL
+// CHECK-LABEL: @fold_log_exp
 func.func @fold_log_exp(%arg0: tensor<?x1xf32>) -> tensor<?x1xf32> {
   // CHECK: return %arg{{.*}} : tensor<?x1xf32>
   %0 = tosa.exp %arg0 : (tensor<?x1xf32>) -> tensor<?x1xf32>
diff --git a/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir b/mlir/test/Dialect/Tosa/tosa-infer-shapes.mlir
@@ -222,13 +222,13 @@ func.func @test_binary_i32(%arg0 : tensor<4xi32>, %arg1 : tensor<i32>) -> () {
 
 // CHECK-LABEL: @test_binary_i1
 func.func @test_binary_i1(%arg0 : tensor<4xi1>, %arg1 : tensor<i1>) -> () {
-  // CHECK tosa.logical_and %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<4xi1>
+  // CHECK: tosa.logical_and %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<4xi1>
   %0 = tosa.logical_and %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<*xi1>
 
-  // CHECK tosa.logical_or %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<4xi1>
+  // CHECK: tosa.logical_or %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<4xi1>
   %1 = tosa.logical_or %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<*xi1>
 
-  // CHECK tosa.logical_xor %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<*4i1>
+  // CHECK: tosa.logical_xor %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<4xi1>
   %2 = tosa.logical_xor %arg0, %arg1 : (tensor<4xi1>, tensor<i1>) -> tensor<*xi1>
 
   return
diff --git a/mlir/test/Dialect/Vector/vector-dropleadunitdim-transforms.mlir b/mlir/test/Dialect/Vector/vector-dropleadunitdim-transforms.mlir
@@ -241,7 +241,7 @@ func.func @cast_away_contraction_leading_one_dims_nonleadingunitdim_rank4_acctra
 // -----
 
 // CHECK-LABEL:   func.func @cast_away_contraction_does_not_transpose_leading_unit_dims
-// CHECK-NOT   vector.transpose
+// CHECK-NOT:  vector.transpose
 // CHECK:           vector.contract
 func.func @cast_away_contraction_does_not_transpose_leading_unit_dims(%lhs: vector<1x1x8xi32>,
                           %rhs: vector<1x8x8xi32>,
diff --git a/mlir/test/IR/parser.mlir b/mlir/test/IR/parser.mlir
@@ -342,40 +342,40 @@ func.func @loop_bounds(%N : index) {
 
 // CHECK-LABEL: func @ifinst(%{{.*}}: index) {
 func.func @ifinst(%N: index) {
-  %c = arith.constant 200 : index // CHECK   %{{.*}} = arith.constant 200
-  affine.for %i = 1 to 10 {           // CHECK   affine.for %{{.*}} = 1 to 10 {
-    affine.if #set0(%i)[%N, %c] {     // CHECK     affine.if #set0(%{{.*}})[%{{.*}}, %{{.*}}] {
+  %c = arith.constant 200 : index // CHECK:  %{{.*}} = arith.constant 200
+  affine.for %i = 1 to 10 {           // CHECK:  affine.for %{{.*}} = 1 to 10 {
+    affine.if #set0(%i)[%N, %c] {     // CHECK:    affine.if #set(%{{.*}})[%{{.*}}, %{{.*}}] {
       %x = arith.constant 1 : i32
        // CHECK: %{{.*}} = arith.constant 1 : i32
       %y = "add"(%x, %i) : (i32, index) -> i32 // CHECK: %{{.*}} = "add"(%{{.*}}, %{{.*}}) : (i32, index) -> i32
       %z = "mul"(%y, %y) : (i32, i32) -> i32 // CHECK: %{{.*}} = "mul"(%{{.*}}, %{{.*}}) : (i32, i32) -> i32
     } else { // CHECK } else {
-      affine.if affine_set<(i)[N] : (i - 2 >= 0, 4 - i >= 0)>(%i)[%N]  {      // CHECK  affine.if (#set1(%{{.*}})[%{{.*}}]) {
+      affine.if affine_set<(i)[N] : (i - 2 >= 0, 4 - i >= 0)>(%i)[%N]  {      // CHECK: affine.if #set1(%{{.*}})[%{{.*}}] {
         // CHECK: %{{.*}} = arith.constant 1 : index
         %u = arith.constant 1 : index
         // CHECK: %{{.*}} = affine.apply #map{{.*}}(%{{.*}}, %{{.*}})[%{{.*}}]
         %w = affine.apply affine_map<(d0,d1)[s0] -> (d0+d1+s0)> (%i, %i) [%u]
       } else {            // CHECK     } else {
         %v = arith.constant 3 : i32 // %c3_i32 = arith.constant 3 : i32
       }
-    }       // CHECK     }
-  }         // CHECK   }
-  return    // CHECK   return
-}           // CHECK }
+    }       // CHECK:    }
+  }         // CHECK:  }
+  return    // CHECK:  return
+}           // CHECK:}
 
 // CHECK-LABEL: func @simple_ifinst(%{{.*}}: index) {
 func.func @simple_ifinst(%N: index) {
-  %c = arith.constant 200 : index // CHECK   %{{.*}} = arith.constant 200
-  affine.for %i = 1 to 10 {           // CHECK   affine.for %{{.*}} = 1 to 10 {
-    affine.if #set0(%i)[%N, %c] {     // CHECK     affine.if #set0(%{{.*}})[%{{.*}}, %{{.*}}] {
+  %c = arith.constant 200 : index // CHECK:  %{{.*}} = arith.constant 200
+  affine.for %i = 1 to 10 {           // CHECK:  affine.for %{{.*}} = 1 to 10 {
+    affine.if #set0(%i)[%N, %c] {     // CHECK:    affine.if #set(%{{.*}})[%{{.*}}, %{{.*}}] {
       %x = arith.constant 1 : i32
        // CHECK: %{{.*}} = arith.constant 1 : i32
       %y = "add"(%x, %i) : (i32, index) -> i32 // CHECK: %{{.*}} = "add"(%{{.*}}, %{{.*}}) : (i32, index) -> i32
       %z = "mul"(%y, %y) : (i32, i32) -> i32 // CHECK: %{{.*}} = "mul"(%{{.*}}, %{{.*}}) : (i32, i32) -> i32
-    }       // CHECK     }
-  }         // CHECK   }
-  return    // CHECK   return
-}           // CHECK }
+    }       // CHECK:    }
+  }         // CHECK:  }
+  return    // CHECK:  return
+}           // CHECK:}
 
 // CHECK-LABEL: func @attributes() {
 func.func @attributes() {
diff --git a/mlir/test/Target/LLVMIR/llvmir.mlir b/mlir/test/Target/LLVMIR/llvmir.mlir
@@ -2330,39 +2330,47 @@ llvm.func @streaming_compatible_func() attributes {arm_streaming_compatible} {
 // -----
 
 // CHECK-LABEL: @new_za_func
-// CHECK: #[[ATTR:[0-9]*]]
+// CHECK-SAME: #[[ATTR:[0-9]*]]
 llvm.func @new_za_func() attributes {arm_new_za} {
   llvm.return
 }
-// CHECK #[[ATTR]] = { "aarch64_new_za" }
+// CHECK: #[[ATTR]] = { "aarch64_new_za" }
+
+// -----
 
 // CHECK-LABEL: @in_za_func
-// CHECK: #[[ATTR:[0-9]*]]
+// CHECK-SAME: #[[ATTR:[0-9]*]]
 llvm.func @in_za_func() attributes {arm_in_za } {
   llvm.return
 }
-// CHECK #[[ATTR]] = { "aarch64_in_za" }
+// CHECK: #[[ATTR]] = { "aarch64_in_za" }
+
+// -----
 
 // CHECK-LABEL: @out_za_func
-// CHECK: #[[ATTR:[0-9]*]]
+// CHECK-SAME: #[[ATTR:[0-9]*]]
 llvm.func @out_za_func() attributes {arm_out_za } {
   llvm.return
 }
-// CHECK #[[ATTR]] = { "aarch64_out_za" }
+// CHECK: #[[ATTR]] = { "aarch64_out_za" }
+
+// -----
 
 // CHECK-LABEL: @inout_za_func
-// CHECK: #[[ATTR:[0-9]*]]
+// CHECK-SAME: #[[ATTR:[0-9]*]]
 llvm.func @inout_za_func() attributes {arm_inout_za } {
   llvm.return
 }
-// CHECK #[[ATTR]] = { "aarch64_inout_za" }
+// CHECK: #[[ATTR]] = { "aarch64_inout_za" }
+
+// -----
 
 // CHECK-LABEL: @preserves_za_func
-// CHECK: #[[ATTR:[0-9]*]]
+// CHECK-SAME: #[[ATTR:[0-9]*]]
 llvm.func @preserves_za_func() attributes {arm_preserves_za} {
   llvm.return
 }
-// CHECK #[[ATTR]] = { "aarch64_preserves_za" }
+// CHECK: #[[ATTR]] = { "aarch64_preserves_za" }
 
 // -----
 
diff --git a/mlir/test/Target/LLVMIR/openmp-llvm.mlir b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
diff --git a/mlir/test/Transforms/canonicalize.mlir b/mlir/test/Transforms/canonicalize.mlir
diff --git a/mlir/test/mlir-cpu-runner/copy.mlir b/mlir/test/mlir-cpu-runner/copy.mlir
diff --git a/mlir/test/mlir-tblgen/bytecode-reserved.td b/mlir/test/mlir-tblgen/bytecode-reserved.td
diff --git a/mlir/test/python/ir/attributes.py b/mlir/test/python/ir/attributes.py

Original file line number	Diff line number	Diff line change
`@@ -638,7 +638,7 @@ gpu.module @test_module_30 {`
`638`	`638`	`}`
`639`	`639`	`// CHECK-LABEL: @subgroup_reduce_xor`
`640`	`640`	`gpu.func @subgroup_reduce_xor(%arg0 : i32) {`
`641`		`- // CHECK nvvm.redux.sync xor {{.*}}`
	`641`	`+ // CHECK: nvvm.redux.sync xor {{.*}}`
`642`	`642`	`%result = gpu.subgroup_reduce xor %arg0 uniform {} : (i32) -> (i32)`
`643`	`643`	`gpu.return`
`644`	`644`	`}`
Original file line number	Diff line number	Diff line change
`@@ -616,7 +616,7 @@ func.func @loop_nest_non_trivial_multiple_upper_bound_alt(%M : index, %N : index`
`616`	`616`	`// UNROLL-BY-4-NEXT: "foo"`
`617`	`617`	`// UNROLL-BY-4-NEXT: "foo"`
`618`	`618`	`// UNROLL-BY-4-NEXT: "foo"`
`619`		`- // UNROLL-BY-4-NOT for`
	`619`	`+ // UNROLL-BY-4-NOT: for`
`620`	`620`	`// UNROLL-BY-4: return`
`621`	`621`	`return`
`622`	`622`	`}`