[Mlir-commits] [mlir] 8af0ccf - [sparse][mlir] give all sparse kernels an explicit "output" tensor

Aart Bik llvmlistbot at llvm.org
Thu Jan 28 10:50:19 PST 2021


Author: Aart Bik
Date: 2021-01-28T10:41:17-08:00
New Revision: 8af0ccf5a498fb75f13aef0e3bd5c00bc348693f

URL: https://github.com/llvm/llvm-project/commit/8af0ccf5a498fb75f13aef0e3bd5c00bc348693f
DIFF: https://github.com/llvm/llvm-project/commit/8af0ccf5a498fb75f13aef0e3bd5c00bc348693f.diff

LOG: [sparse][mlir] give all sparse kernels an explicit "output" tensor

Rationale:
Providing an output tensor, even if one is not used as input to
the kernel provides the right pattern for using lingalg sparse
kernels (in contrast with reusing a tensor just to provide the shape).
This prepares proper bufferization that will follow.

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D95587

Added: 
    

Modified: 
    mlir/test/Dialect/Linalg/sparse_1d.mlir
    mlir/test/Dialect/Linalg/sparse_2d.mlir
    mlir/test/Dialect/Linalg/sparse_3d.mlir
    mlir/test/Dialect/Linalg/sparse_invalid.mlir
    mlir/test/Dialect/Linalg/sparse_nd.mlir
    mlir/test/Dialect/Linalg/sparse_parallel.mlir
    mlir/test/Dialect/Linalg/sparse_storage.mlir
    mlir/test/Dialect/Linalg/sparse_vector.mlir

Removed: 
    


################################################################################
diff  --git a/mlir/test/Dialect/Linalg/sparse_1d.mlir b/mlir/test/Dialect/Linalg/sparse_1d.mlir
index 9f7fbe471409..18357afa2718 100644
--- a/mlir/test/Dialect/Linalg/sparse_1d.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_1d.mlir
@@ -16,26 +16,27 @@
 
 // CHECK-LABEL:   func @add_d(
 // CHECK-SAME:                %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                %[[VAL_1:.*]]: f32) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                %[[VAL_1:.*]]: f32,
+// CHECK-SAME:                %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
 // CHECK:           %[[VAL_6:.*]] = alloca() : memref<32xf32>
-// CHECK:           scf.for %[[VAL_7:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_8:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_7]]] : memref<32xf32>
-// CHECK:             %[[VAL_9:.*]] = addf %[[VAL_8]], %[[VAL_1]] : f32
-// CHECK:             store %[[VAL_9]], %[[VAL_6]]{{\[}}%[[VAL_7]]] : memref<32xf32>
+// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
+// CHECK:           scf.for %[[VAL_8:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_9:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32>
+// CHECK:             %[[VAL_10:.*]] = addf %[[VAL_9]], %[[VAL_1]] : f32
+// CHECK:             store %[[VAL_10]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_10:.*]] = tensor_load %[[VAL_6]] : memref<32xf32>
-// CHECK:           return %[[VAL_10]] : tensor<32xf32>
+// CHECK:           %[[VAL_11:.*]] = tensor_load %[[VAL_7]] : memref<32xf32>
+// CHECK:           return %[[VAL_11]] : tensor<32xf32>
 // CHECK:         }
-func @add_d(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @add_d(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_d
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s : f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -43,26 +44,27 @@ func @add_d(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
 
 // CHECK-LABEL:   func @mul_d(
 // CHECK-SAME:                %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                %[[VAL_1:.*]]: f32) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                %[[VAL_1:.*]]: f32,
+// CHECK-SAME:                %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
 // CHECK:           %[[VAL_6:.*]] = alloca() : memref<32xf32>
-// CHECK:           scf.for %[[VAL_7:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_8:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_7]]] : memref<32xf32>
-// CHECK:             %[[VAL_9:.*]] = mulf %[[VAL_8]], %[[VAL_1]] : f32
-// CHECK:             store %[[VAL_9]], %[[VAL_6]]{{\[}}%[[VAL_7]]] : memref<32xf32>
+// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
+// CHECK:           scf.for %[[VAL_8:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_9:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32>
+// CHECK:             %[[VAL_10:.*]] = mulf %[[VAL_9]], %[[VAL_1]] : f32
+// CHECK:             store %[[VAL_10]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_10:.*]] = tensor_load %[[VAL_6]] : memref<32xf32>
-// CHECK:           return %[[VAL_10]] : tensor<32xf32>
+// CHECK:           %[[VAL_11:.*]] = tensor_load %[[VAL_7]] : memref<32xf32>
+// CHECK:           return %[[VAL_11]] : tensor<32xf32>
 // CHECK:         }
-func @mul_d(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @mul_d(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_d
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s : f32):
-        %0 = mulf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = mulf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -83,99 +85,62 @@ func @mul_d(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
 
 // CHECK-LABEL:   func @add_s(
 // CHECK-SAME:                %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                %[[VAL_1:.*]]: f32) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant true
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]]:2 = scf.while (%[[VAL_14:.*]] = %[[VAL_11]], %[[VAL_15:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_16:.*]] = cmpi ult, %[[VAL_14]], %[[VAL_12]] : index
-// CHECK:             scf.condition(%[[VAL_16]]) %[[VAL_14]], %[[VAL_15]] : index, index
+// CHECK-SAME:                %[[VAL_1:.*]]: f32,
+// CHECK-SAME:                %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant true
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_12:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_17:.*]] = cmpi ult, %[[VAL_15]], %[[VAL_13]] : index
+// CHECK:             scf.condition(%[[VAL_17]]) %[[VAL_15]], %[[VAL_16]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_17:.*]]: index, %[[VAL_18:.*]]: index):
-// CHECK:             %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:             %[[VAL_20:.*]] = cmpi eq, %[[VAL_19]], %[[VAL_18]] : index
-// CHECK:             scf.if %[[VAL_20]] {
-// CHECK:               %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref<?xf32>
-// CHECK:               %[[VAL_22:.*]] = addf %[[VAL_21]], %[[VAL_1]] : f32
-// CHECK:               store %[[VAL_22]], %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<32xf32>
+// CHECK:           ^bb0(%[[VAL_18:.*]]: index, %[[VAL_19:.*]]: index):
+// CHECK:             %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:             %[[VAL_21:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
+// CHECK:             scf.if %[[VAL_21]] {
+// CHECK:               %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<?xf32>
+// CHECK:               %[[VAL_23:.*]] = addf %[[VAL_22]], %[[VAL_1]] : f32
+// CHECK:               store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_5]] {
-// CHECK:                 store %[[VAL_1]], %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<32xf32>
+// CHECK:               scf.if %[[VAL_6]] {
+// CHECK:                 store %[[VAL_1]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_23:.*]] = cmpi eq, %[[VAL_19]], %[[VAL_18]] : index
-// CHECK:             %[[VAL_24:.*]] = addi %[[VAL_17]], %[[VAL_6]] : index
-// CHECK:             %[[VAL_25:.*]] = select %[[VAL_23]], %[[VAL_24]], %[[VAL_17]] : index
-// CHECK:             %[[VAL_26:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index
-// CHECK:             scf.yield %[[VAL_25]], %[[VAL_26]] : index, index
+// CHECK:             %[[VAL_24:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
+// CHECK:             %[[VAL_25:.*]] = addi %[[VAL_18]], %[[VAL_7]] : index
+// CHECK:             %[[VAL_26:.*]] = select %[[VAL_24]], %[[VAL_25]], %[[VAL_18]] : index
+// CHECK:             %[[VAL_27:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index
+// CHECK:             scf.yield %[[VAL_26]], %[[VAL_27]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_27:.*]] = %[[VAL_28:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:             store %[[VAL_1]], %[[VAL_10]]{{\[}}%[[VAL_27]]] : memref<32xf32>
+// CHECK:           scf.for %[[VAL_28:.*]] = %[[VAL_29:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:             store %[[VAL_1]], %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_29:.*]] = tensor_load %[[VAL_10]] : memref<32xf32>
-// CHECK:           return %[[VAL_29]] : tensor<32xf32>
+// CHECK:           %[[VAL_30:.*]] = tensor_load %[[VAL_11]] : memref<32xf32>
+// CHECK:           return %[[VAL_30]] : tensor<32xf32>
 // CHECK:         }
-func @add_s(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @add_s(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_s
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s : f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
 }
 
 // CHECK-LABEL:   func @repeated_add_s(
-// CHECK-SAME:                         %[[VAL_0:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_1:.*]] = constant 999 : index
-// CHECK:           %[[VAL_2:.*]] = constant 0 : index
-// CHECK:           %[[VAL_3:.*]] = constant 1 : index
-// CHECK:           %[[VAL_4:.*]] = alloca(%[[VAL_1]]) : memref<?xindex>
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_1]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_1]]) : memref<?xf32>
-// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_8:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_2]]] : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = load %[[VAL_4]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_3]] {
-// CHECK:             %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_10]]] : memref<?xindex>
-// CHECK:             %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xf32>
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xf32>
-// CHECK:             %[[VAL_14:.*]] = addf %[[VAL_12]], %[[VAL_13]] : f32
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xf32>
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xf32>
-// CHECK:             %[[VAL_17:.*]] = addf %[[VAL_15]], %[[VAL_16]] : f32
-// CHECK:             %[[VAL_18:.*]] = addf %[[VAL_14]], %[[VAL_17]] : f32
-// CHECK:             store %[[VAL_18]], %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref<32xf32>
-// CHECK:           }
-// CHECK:           %[[VAL_19:.*]] = tensor_load %[[VAL_7]] : memref<32xf32>
-// CHECK:           return %[[VAL_19]] : tensor<32xf32>
-// CHECK:         }
-func @repeated_add_s(%arga: tensor<32xf32>) -> tensor<32xf32> {
-  %0 = linalg.generic #trait_s
-     ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s : f32):
-        %0 = addf %a, %a  : f32  // same tensor
-        %1 = addf %a, %a  : f32  // should yield
-        %2 = addf %0, %1  : f32  // one guard
-        linalg.yield %2 : f32
-  } -> tensor<32xf32>
-  return %0 : tensor<32xf32>
-}
-
-// CHECK-LABEL:   func @mul_s(
-// CHECK-SAME:                %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                %[[VAL_1:.*]]: f32) -> tensor<32xf32> {
+// CHECK-SAME:                         %[[VAL_0:.*]]: tensor<32xf32>,
+// CHECK-SAME:                         %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
 // CHECK:           %[[VAL_2:.*]] = constant 999 : index
 // CHECK:           %[[VAL_3:.*]] = constant 0 : index
 // CHECK:           %[[VAL_4:.*]] = constant 1 : index
@@ -188,18 +153,58 @@ func @repeated_add_s(%arga: tensor<32xf32>) -> tensor<32xf32> {
 // CHECK:           scf.for %[[VAL_11:.*]] = %[[VAL_9]] to %[[VAL_10]] step %[[VAL_4]] {
 // CHECK:             %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref<?xindex>
 // CHECK:             %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref<?xf32>
-// CHECK:             %[[VAL_14:.*]] = mulf %[[VAL_13]], %[[VAL_1]] : f32
-// CHECK:             store %[[VAL_14]], %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<32xf32>
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref<?xf32>
+// CHECK:             %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref<?xf32>
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_11]]] : memref<?xf32>
+// CHECK:             %[[VAL_18:.*]] = addf %[[VAL_16]], %[[VAL_17]] : f32
+// CHECK:             %[[VAL_19:.*]] = addf %[[VAL_15]], %[[VAL_18]] : f32
+// CHECK:             store %[[VAL_19]], %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_15:.*]] = tensor_load %[[VAL_8]] : memref<32xf32>
-// CHECK:           return %[[VAL_15]] : tensor<32xf32>
+// CHECK:           %[[VAL_20:.*]] = tensor_load %[[VAL_8]] : memref<32xf32>
+// CHECK:           return %[[VAL_20]] : tensor<32xf32>
 // CHECK:         }
-func @mul_s(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @repeated_add_s(%arga: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_s
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s : f32):
-        %0 = mulf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %a : f32  // same tensor
+        %1 = addf %a, %a : f32  // should yield
+        %2 = addf %0, %1 : f32  // one guard
+        linalg.yield %2 : f32
+  } -> tensor<32xf32>
+  return %0 : tensor<32xf32>
+}
+
+// CHECK-LABEL:   func @mul_s(
+// CHECK-SAME:                %[[VAL_0:.*]]: tensor<32xf32>,
+// CHECK-SAME:                %[[VAL_1:.*]]: f32,
+// CHECK-SAME:                %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xindex>
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<?xf32>
+// CHECK:             %[[VAL_15:.*]] = mulf %[[VAL_14]], %[[VAL_1]] : f32
+// CHECK:             store %[[VAL_15]], %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<32xf32>
+// CHECK:           }
+// CHECK:           %[[VAL_16:.*]] = tensor_load %[[VAL_9]] : memref<32xf32>
+// CHECK:           return %[[VAL_16]] : tensor<32xf32>
+// CHECK:         }
+func @mul_s(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
+  %0 = linalg.generic #trait_s
+     ins(%arga: tensor<32xf32>)
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = mulf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -221,58 +226,60 @@ func @mul_s(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
 }
 
 // CHECK-LABEL:   func @add_dd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
 // CHECK:           %[[VAL_6:.*]] = alloca() : memref<32xf32>
 // CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
-// CHECK:           scf.for %[[VAL_8:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_8]]] : memref<32xf32>
-// CHECK:             %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32>
-// CHECK:             %[[VAL_11:.*]] = addf %[[VAL_9]], %[[VAL_10]] : f32
-// CHECK:             store %[[VAL_11]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32>
+// CHECK:           %[[VAL_8:.*]] = alloca() : memref<32xf32>
+// CHECK:           scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32>
+// CHECK:             %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]]] : memref<32xf32>
+// CHECK:             %[[VAL_12:.*]] = addf %[[VAL_10]], %[[VAL_11]] : f32
+// CHECK:             store %[[VAL_12]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_12:.*]] = tensor_load %[[VAL_7]] : memref<32xf32>
-// CHECK:           return %[[VAL_12]] : tensor<32xf32>
+// CHECK:           %[[VAL_13:.*]] = tensor_load %[[VAL_8]] : memref<32xf32>
+// CHECK:           return %[[VAL_13]] : tensor<32xf32>
 // CHECK:         }
-func @add_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @add_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_dd
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
 }
 
 // CHECK-LABEL:   func @mul_dd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
 // CHECK:           %[[VAL_6:.*]] = alloca() : memref<32xf32>
 // CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
-// CHECK:           scf.for %[[VAL_8:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_8]]] : memref<32xf32>
-// CHECK:             %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_8]]] : memref<32xf32>
-// CHECK:             %[[VAL_11:.*]] = mulf %[[VAL_9]], %[[VAL_10]] : f32
-// CHECK:             store %[[VAL_11]], %[[VAL_7]]{{\[}}%[[VAL_8]]] : memref<32xf32>
+// CHECK:           %[[VAL_8:.*]] = alloca() : memref<32xf32>
+// CHECK:           scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<32xf32>
+// CHECK:             %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]]] : memref<32xf32>
+// CHECK:             %[[VAL_12:.*]] = mulf %[[VAL_10]], %[[VAL_11]] : f32
+// CHECK:             store %[[VAL_12]], %[[VAL_8]]{{\[}}%[[VAL_9]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_12:.*]] = tensor_load %[[VAL_7]] : memref<32xf32>
-// CHECK:           return %[[VAL_12]] : tensor<32xf32>
+// CHECK:           %[[VAL_13:.*]] = tensor_load %[[VAL_8]] : memref<32xf32>
+// CHECK:           return %[[VAL_13]] : tensor<32xf32>
 // CHECK:         }
-func @mul_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @mul_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_dd
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -294,92 +301,94 @@ func @mul_dd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
 }
 
 // CHECK-LABEL:   func @add_ds(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant true
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_17:.*]] = cmpi ult, %[[VAL_15]], %[[VAL_13]] : index
-// CHECK:             scf.condition(%[[VAL_17]]) %[[VAL_15]], %[[VAL_16]] : index, index
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant true
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index
+// CHECK:             scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_18:.*]]: index, %[[VAL_19:.*]]: index):
-// CHECK:             %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex>
-// CHECK:             %[[VAL_21:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:             scf.if %[[VAL_21]] {
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_19]]] : memref<32xf32>
-// CHECK:               %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<?xf32>
-// CHECK:               %[[VAL_24:.*]] = addf %[[VAL_22]], %[[VAL_23]] : f32
-// CHECK:               store %[[VAL_24]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
+// CHECK:           ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index):
+// CHECK:             %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref<?xindex>
+// CHECK:             %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:             scf.if %[[VAL_22]] {
+// CHECK:               %[[VAL_23:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<32xf32>
+// CHECK:               %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<?xf32>
+// CHECK:               %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32
+// CHECK:               store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32>
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_5]] {
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_19]]] : memref<32xf32>
-// CHECK:                 store %[[VAL_25]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
+// CHECK:               scf.if %[[VAL_6]] {
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<32xf32>
+// CHECK:                 store %[[VAL_26]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32>
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_26:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_27:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index
-// CHECK:             %[[VAL_28:.*]] = select %[[VAL_26]], %[[VAL_27]], %[[VAL_18]] : index
-// CHECK:             %[[VAL_29:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index
-// CHECK:             scf.yield %[[VAL_28]], %[[VAL_29]] : index, index
+// CHECK:             %[[VAL_27:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index
+// CHECK:             %[[VAL_29:.*]] = select %[[VAL_27]], %[[VAL_28]], %[[VAL_19]] : index
+// CHECK:             %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index
+// CHECK:             scf.yield %[[VAL_29]], %[[VAL_30]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_30:.*]] = %[[VAL_31:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:             %[[VAL_32:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_30]]] : memref<32xf32>
-// CHECK:             store %[[VAL_32]], %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref<32xf32>
+// CHECK:           scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:             %[[VAL_33:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_31]]] : memref<32xf32>
+// CHECK:             store %[[VAL_33]], %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_33:.*]] = tensor_load %[[VAL_11]] : memref<32xf32>
-// CHECK:           return %[[VAL_33]] : tensor<32xf32>
+// CHECK:           %[[VAL_34:.*]] = tensor_load %[[VAL_12]] : memref<32xf32>
+// CHECK:           return %[[VAL_34]] : tensor<32xf32>
 // CHECK:         }
-func @add_ds(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @add_ds(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_ds
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
 }
 
 // CHECK-LABEL:   func @mul_ds(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xindex>
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_13]]] : memref<32xf32>
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<?xf32>
-// CHECK:             %[[VAL_16:.*]] = mulf %[[VAL_14]], %[[VAL_15]] : f32
-// CHECK:             store %[[VAL_16]], %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<32xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_11:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<?xindex>
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<32xf32>
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<?xf32>
+// CHECK:             %[[VAL_17:.*]] = mulf %[[VAL_15]], %[[VAL_16]] : f32
+// CHECK:             store %[[VAL_17]], %[[VAL_10]]{{\[}}%[[VAL_14]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_17:.*]] = tensor_load %[[VAL_9]] : memref<32xf32>
-// CHECK:           return %[[VAL_17]] : tensor<32xf32>
+// CHECK:           %[[VAL_18:.*]] = tensor_load %[[VAL_10]] : memref<32xf32>
+// CHECK:           return %[[VAL_18]] : tensor<32xf32>
 // CHECK:         }
-func @mul_ds(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @mul_ds(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_ds
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -401,92 +410,94 @@ func @mul_ds(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
 }
 
 // CHECK-LABEL:   func @add_sd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant true
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant true
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_11:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_17:.*]] = cmpi ult, %[[VAL_15]], %[[VAL_13]] : index
-// CHECK:             scf.condition(%[[VAL_17]]) %[[VAL_15]], %[[VAL_16]] : index, index
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index
+// CHECK:             scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_18:.*]]: index, %[[VAL_19:.*]]: index):
-// CHECK:             %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
-// CHECK:             %[[VAL_21:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:             scf.if %[[VAL_21]] {
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xf32>
-// CHECK:               %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref<32xf32>
-// CHECK:               %[[VAL_24:.*]] = addf %[[VAL_22]], %[[VAL_23]] : f32
-// CHECK:               store %[[VAL_24]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
+// CHECK:           ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index):
+// CHECK:             %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
+// CHECK:             %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:             scf.if %[[VAL_22]] {
+// CHECK:               %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref<?xf32>
+// CHECK:               %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]]] : memref<32xf32>
+// CHECK:               %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32
+// CHECK:               store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32>
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_5]] {
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref<32xf32>
-// CHECK:                 store %[[VAL_25]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<32xf32>
+// CHECK:               scf.if %[[VAL_6]] {
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]]] : memref<32xf32>
+// CHECK:                 store %[[VAL_26]], %[[VAL_12]]{{\[}}%[[VAL_20]]] : memref<32xf32>
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_26:.*]] = cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_27:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index
-// CHECK:             %[[VAL_28:.*]] = select %[[VAL_26]], %[[VAL_27]], %[[VAL_18]] : index
-// CHECK:             %[[VAL_29:.*]] = addi %[[VAL_19]], %[[VAL_6]] : index
-// CHECK:             scf.yield %[[VAL_28]], %[[VAL_29]] : index, index
+// CHECK:             %[[VAL_27:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_28:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index
+// CHECK:             %[[VAL_29:.*]] = select %[[VAL_27]], %[[VAL_28]], %[[VAL_19]] : index
+// CHECK:             %[[VAL_30:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index
+// CHECK:             scf.yield %[[VAL_29]], %[[VAL_30]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_30:.*]] = %[[VAL_31:.*]]#1 to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:             %[[VAL_32:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_30]]] : memref<32xf32>
-// CHECK:             store %[[VAL_32]], %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref<32xf32>
+// CHECK:           scf.for %[[VAL_31:.*]] = %[[VAL_32:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:             %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_31]]] : memref<32xf32>
+// CHECK:             store %[[VAL_33]], %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_33:.*]] = tensor_load %[[VAL_11]] : memref<32xf32>
-// CHECK:           return %[[VAL_33]] : tensor<32xf32>
+// CHECK:           %[[VAL_34:.*]] = tensor_load %[[VAL_12]] : memref<32xf32>
+// CHECK:           return %[[VAL_34]] : tensor<32xf32>
 // CHECK:         }
-func @add_sd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @add_sd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_sd
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
 }
 
 // CHECK-LABEL:   func @mul_sd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_8:.*]] = alloca() : memref<32xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_9:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xf32>
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<32xf32>
-// CHECK:             %[[VAL_16:.*]] = mulf %[[VAL_14]], %[[VAL_15]] : f32
-// CHECK:             store %[[VAL_16]], %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<32xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref<?xindex>
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<?xf32>
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<32xf32>
+// CHECK:             %[[VAL_17:.*]] = mulf %[[VAL_15]], %[[VAL_16]] : f32
+// CHECK:             store %[[VAL_17]], %[[VAL_10]]{{\[}}%[[VAL_14]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_17:.*]] = tensor_load %[[VAL_9]] : memref<32xf32>
-// CHECK:           return %[[VAL_17]] : tensor<32xf32>
+// CHECK:           %[[VAL_18:.*]] = tensor_load %[[VAL_10]] : memref<32xf32>
+// CHECK:           return %[[VAL_18]] : tensor<32xf32>
 // CHECK:         }
-func @mul_sd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @mul_sd(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_sd
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -508,142 +519,144 @@ func @mul_sd(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
 }
 
 // CHECK-LABEL:   func @add_ss(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_12]], %[[VAL_18:.*]] = %[[VAL_14]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_13]] : index
-// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_15]] : index
-// CHECK:             %[[VAL_21:.*]] = and %[[VAL_19]], %[[VAL_20]] : i1
-// CHECK:             scf.condition(%[[VAL_21]]) %[[VAL_17]], %[[VAL_18]] : index, index
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index
+// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index
+// CHECK:             %[[VAL_22:.*]] = and %[[VAL_20]], %[[VAL_21]] : i1
+// CHECK:             scf.condition(%[[VAL_22]]) %[[VAL_18]], %[[VAL_19]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
-// CHECK:             %[[VAL_24:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:             %[[VAL_25:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref<?xindex>
-// CHECK:             %[[VAL_26:.*]] = cmpi ult, %[[VAL_25]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_27:.*]] = select %[[VAL_26]], %[[VAL_25]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_28:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_30:.*]] = and %[[VAL_28]], %[[VAL_29]] : i1
-// CHECK:             scf.if %[[VAL_30]] {
-// CHECK:               %[[VAL_31:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_22]]] : memref<?xf32>
-// CHECK:               %[[VAL_32:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref<?xf32>
-// CHECK:               %[[VAL_33:.*]] = addf %[[VAL_31]], %[[VAL_32]] : f32
-// CHECK:               store %[[VAL_33]], %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<32xf32>
+// CHECK:           ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index):
+// CHECK:             %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:             %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xindex>
+// CHECK:             %[[VAL_27:.*]] = cmpi ult, %[[VAL_26]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_28:.*]] = select %[[VAL_27]], %[[VAL_26]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1
+// CHECK:             scf.if %[[VAL_31]] {
+// CHECK:               %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref<?xf32>
+// CHECK:               %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xf32>
+// CHECK:               %[[VAL_34:.*]] = addf %[[VAL_32]], %[[VAL_33]] : f32
+// CHECK:               store %[[VAL_34]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32>
 // CHECK:             } else {
-// CHECK:               %[[VAL_34:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_27]] : index
-// CHECK:               scf.if %[[VAL_34]] {
-// CHECK:                 %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_22]]] : memref<?xf32>
-// CHECK:                 store %[[VAL_35]], %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<32xf32>
+// CHECK:               %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index
+// CHECK:               scf.if %[[VAL_35]] {
+// CHECK:                 %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref<?xf32>
+// CHECK:                 store %[[VAL_36]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32>
 // CHECK:               } else {
-// CHECK:                 %[[VAL_36:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_27]] : index
-// CHECK:                 scf.if %[[VAL_36]] {
-// CHECK:                   %[[VAL_37:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref<?xf32>
-// CHECK:                   store %[[VAL_37]], %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<32xf32>
+// CHECK:                 %[[VAL_37:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index
+// CHECK:                 scf.if %[[VAL_37]] {
+// CHECK:                   %[[VAL_38:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xf32>
+// CHECK:                   store %[[VAL_38]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32>
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_38:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_39:.*]] = addi %[[VAL_22]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_40:.*]] = select %[[VAL_38]], %[[VAL_39]], %[[VAL_22]] : index
-// CHECK:             %[[VAL_41:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_42:.*]] = addi %[[VAL_23]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_43:.*]] = select %[[VAL_41]], %[[VAL_42]], %[[VAL_23]] : index
-// CHECK:             scf.yield %[[VAL_40]], %[[VAL_43]] : index, index
+// CHECK:             %[[VAL_39:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_40:.*]] = addi %[[VAL_23]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_41:.*]] = select %[[VAL_39]], %[[VAL_40]], %[[VAL_23]] : index
+// CHECK:             %[[VAL_42:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_43:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_44:.*]] = select %[[VAL_42]], %[[VAL_43]], %[[VAL_24]] : index
+// CHECK:             scf.yield %[[VAL_41]], %[[VAL_44]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_44:.*]] = %[[VAL_45:.*]]#0 to %[[VAL_13]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_46:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_44]]] : memref<?xindex>
-// CHECK:             %[[VAL_47:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_44]]] : memref<?xf32>
-// CHECK:             store %[[VAL_47]], %[[VAL_11]]{{\[}}%[[VAL_46]]] : memref<32xf32>
+// CHECK:           scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#0 to %[[VAL_14]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_47:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_45]]] : memref<?xindex>
+// CHECK:             %[[VAL_48:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_45]]] : memref<?xf32>
+// CHECK:             store %[[VAL_48]], %[[VAL_12]]{{\[}}%[[VAL_47]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_48:.*]] = %[[VAL_49:.*]]#1 to %[[VAL_15]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xindex>
-// CHECK:             %[[VAL_51:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:             store %[[VAL_51]], %[[VAL_11]]{{\[}}%[[VAL_50]]] : memref<32xf32>
+// CHECK:           scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_16]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_51:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_49]]] : memref<?xindex>
+// CHECK:             %[[VAL_52:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:             store %[[VAL_52]], %[[VAL_12]]{{\[}}%[[VAL_51]]] : memref<32xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_52:.*]] = tensor_load %[[VAL_11]] : memref<32xf32>
-// CHECK:           return %[[VAL_52]] : tensor<32xf32>
+// CHECK:           %[[VAL_53:.*]] = tensor_load %[[VAL_12]] : memref<32xf32>
+// CHECK:           return %[[VAL_53]] : tensor<32xf32>
 // CHECK:         }
-func @add_ss(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @add_ss(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_ss
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
 }
 
 // CHECK-LABEL:   func @mul_ss(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>) -> tensor<32xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_12]], %[[VAL_18:.*]] = %[[VAL_14]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_13]] : index
-// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_15]] : index
-// CHECK:             %[[VAL_21:.*]] = and %[[VAL_19]], %[[VAL_20]] : i1
-// CHECK:             scf.condition(%[[VAL_21]]) %[[VAL_17]], %[[VAL_18]] : index, index
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32xf32>) -> tensor<32xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index
+// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index
+// CHECK:             %[[VAL_22:.*]] = and %[[VAL_20]], %[[VAL_21]] : i1
+// CHECK:             scf.condition(%[[VAL_22]]) %[[VAL_18]], %[[VAL_19]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
-// CHECK:             %[[VAL_24:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:             %[[VAL_25:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref<?xindex>
-// CHECK:             %[[VAL_26:.*]] = cmpi ult, %[[VAL_25]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_27:.*]] = select %[[VAL_26]], %[[VAL_25]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_28:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_30:.*]] = and %[[VAL_28]], %[[VAL_29]] : i1
-// CHECK:             scf.if %[[VAL_30]] {
-// CHECK:               %[[VAL_31:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_22]]] : memref<?xf32>
-// CHECK:               %[[VAL_32:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref<?xf32>
-// CHECK:               %[[VAL_33:.*]] = mulf %[[VAL_31]], %[[VAL_32]] : f32
-// CHECK:               store %[[VAL_33]], %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<32xf32>
+// CHECK:           ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index):
+// CHECK:             %[[VAL_25:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:             %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xindex>
+// CHECK:             %[[VAL_27:.*]] = cmpi ult, %[[VAL_26]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_28:.*]] = select %[[VAL_27]], %[[VAL_26]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1
+// CHECK:             scf.if %[[VAL_31]] {
+// CHECK:               %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref<?xf32>
+// CHECK:               %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xf32>
+// CHECK:               %[[VAL_34:.*]] = mulf %[[VAL_32]], %[[VAL_33]] : f32
+// CHECK:               store %[[VAL_34]], %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<32xf32>
 // CHECK:             } else {
 // CHECK:             }
-// CHECK:             %[[VAL_34:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_35:.*]] = addi %[[VAL_22]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_36:.*]] = select %[[VAL_34]], %[[VAL_35]], %[[VAL_22]] : index
-// CHECK:             %[[VAL_37:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_27]] : index
-// CHECK:             %[[VAL_38:.*]] = addi %[[VAL_23]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_39:.*]] = select %[[VAL_37]], %[[VAL_38]], %[[VAL_23]] : index
-// CHECK:             scf.yield %[[VAL_36]], %[[VAL_39]] : index, index
+// CHECK:             %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_37:.*]] = select %[[VAL_35]], %[[VAL_36]], %[[VAL_23]] : index
+// CHECK:             %[[VAL_38:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_28]] : index
+// CHECK:             %[[VAL_39:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_40:.*]] = select %[[VAL_38]], %[[VAL_39]], %[[VAL_24]] : index
+// CHECK:             scf.yield %[[VAL_37]], %[[VAL_40]] : index, index
 // CHECK:           }
-// CHECK:           %[[VAL_40:.*]] = tensor_load %[[VAL_11]] : memref<32xf32>
-// CHECK:           return %[[VAL_40]] : tensor<32xf32>
+// CHECK:           %[[VAL_41:.*]] = tensor_load %[[VAL_12]] : memref<32xf32>
+// CHECK:           return %[[VAL_41]] : tensor<32xf32>
 // CHECK:         }
-func @mul_ss(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
+func @mul_ss(%arga: tensor<32xf32>, %argb: tensor<32xf32>, %argx: tensor<32xf32>) -> tensor<32xf32> {
   %0 = linalg.generic #trait_ss
      ins(%arga, %argb: tensor<32xf32>, tensor<32xf32>)
-    outs(%arga : tensor<32xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -667,89 +680,89 @@ func @mul_ss(%arga: tensor<32xf32>, %argb: tensor<32xf32>) -> tensor<32xf32> {
 // CHECK-LABEL:   func @two_way_inv(
 // CHECK-SAME:                      %[[VAL_0:.*0]]: tensor<16xf32>,
 // CHECK-SAME:                      %[[VAL_1:.*1]]: tensor<16xf32>,
-// CHECK-SAME:                      %[[VAL_2:.*2]]: f32) -> tensor<16xf32> {
-// CHECK:           %[[VAL_3:.*]] = constant 999 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<16xf32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]]:3 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) {
-// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index
-// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index
-// CHECK:             %[[VAL_23:.*]] = and %[[VAL_21]], %[[VAL_22]] : i1
-// CHECK:             scf.condition(%[[VAL_23]]) %[[VAL_18]], %[[VAL_19]], %[[VAL_20]] : index, index, index
+// CHECK-SAME:                      %[[VAL_2:.*2]]: f32,
+// CHECK-SAME:                      %[[VAL_3:.*3]]: tensor<16xf32>) -> tensor<16xf32> {
+// CHECK:           %[[VAL_4:.*]] = constant 999 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref<?xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_4]]) : memref<?xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<16xf32>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_5]]) : (index, index, index) -> (index, index, index) {
+// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_15]] : index
+// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_17]] : index
+// CHECK:             %[[VAL_24:.*]] = and %[[VAL_22]], %[[VAL_23]] : i1
+// CHECK:             scf.condition(%[[VAL_24]]) %[[VAL_19]], %[[VAL_20]], %[[VAL_21]] : index, index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index):
-// CHECK:             %[[VAL_27:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1
-// CHECK:             scf.if %[[VAL_31]] {
-// CHECK:               %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref<?xf32>
-// CHECK:               %[[VAL_33:.*]] = mulf %[[VAL_32]], %[[VAL_2]] : f32
-// CHECK:               %[[VAL_34:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:               %[[VAL_35:.*]] = mulf %[[VAL_34]], %[[VAL_2]] : f32
-// CHECK:               %[[VAL_36:.*]] = addf %[[VAL_33]], %[[VAL_35]] : f32
-// CHECK:               store %[[VAL_36]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:           ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
+// CHECK:             %[[VAL_28:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_31:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_32:.*]] = and %[[VAL_30]], %[[VAL_31]] : i1
+// CHECK:             scf.if %[[VAL_32]] {
+// CHECK:               %[[VAL_33:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref<?xf32>
+// CHECK:               %[[VAL_34:.*]] = mulf %[[VAL_33]], %[[VAL_2]] : f32
+// CHECK:               %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:               %[[VAL_36:.*]] = mulf %[[VAL_35]], %[[VAL_2]] : f32
+// CHECK:               %[[VAL_37:.*]] = addf %[[VAL_34]], %[[VAL_36]] : f32
+// CHECK:               store %[[VAL_37]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:             } else {
-// CHECK:               %[[VAL_37:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:               scf.if %[[VAL_37]] {
-// CHECK:                 %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref<?xf32>
-// CHECK:                 %[[VAL_39:.*]] = mulf %[[VAL_38]], %[[VAL_2]] : f32
-// CHECK:                 store %[[VAL_39]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:               %[[VAL_38:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:               scf.if %[[VAL_38]] {
+// CHECK:                 %[[VAL_39:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref<?xf32>
+// CHECK:                 %[[VAL_40:.*]] = mulf %[[VAL_39]], %[[VAL_2]] : f32
+// CHECK:                 store %[[VAL_40]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:               } else {
-// CHECK:                 %[[VAL_40:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:                 scf.if %[[VAL_40]] {
-// CHECK:                   %[[VAL_41:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:                   %[[VAL_42:.*]] = mulf %[[VAL_41]], %[[VAL_2]] : f32
-// CHECK:                   store %[[VAL_42]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:                 %[[VAL_41:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:                 scf.if %[[VAL_41]] {
+// CHECK:                   %[[VAL_42:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:                   %[[VAL_43:.*]] = mulf %[[VAL_42]], %[[VAL_2]] : f32
+// CHECK:                   store %[[VAL_43]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_43:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_44:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_45:.*]] = select %[[VAL_43]], %[[VAL_44]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_46:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_47:.*]] = addi %[[VAL_25]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_25]] : index
-// CHECK:             %[[VAL_49:.*]] = addi %[[VAL_26]], %[[VAL_5]] : index
-// CHECK:             scf.yield %[[VAL_45]], %[[VAL_48]], %[[VAL_49]] : index, index, index
+// CHECK:             %[[VAL_44:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_45:.*]] = addi %[[VAL_25]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_46:.*]] = select %[[VAL_44]], %[[VAL_45]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_47:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_48:.*]] = addi %[[VAL_26]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_49:.*]] = select %[[VAL_47]], %[[VAL_48]], %[[VAL_26]] : index
+// CHECK:             %[[VAL_50:.*]] = addi %[[VAL_27]], %[[VAL_6]] : index
+// CHECK:             scf.yield %[[VAL_46]], %[[VAL_49]], %[[VAL_50]] : index, index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#0 to %[[VAL_14]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_52:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_50]]] : memref<?xf32>
-// CHECK:             %[[VAL_53:.*]] = mulf %[[VAL_52]], %[[VAL_2]] : f32
-// CHECK:             store %[[VAL_53]], %[[VAL_12]]{{\[}}%[[VAL_51]]#2] : memref<16xf32>
+// CHECK:           scf.for %[[VAL_51:.*]] = %[[VAL_52:.*]]#0 to %[[VAL_15]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_53:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_51]]] : memref<?xf32>
+// CHECK:             %[[VAL_54:.*]] = mulf %[[VAL_53]], %[[VAL_2]] : f32
+// CHECK:             store %[[VAL_54]], %[[VAL_13]]{{\[}}%[[VAL_52]]#2] : memref<16xf32>
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_16]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_56:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_54]]] : memref<?xindex>
-// CHECK:             %[[VAL_57:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_54]]] : memref<?xf32>
-// CHECK:             %[[VAL_58:.*]] = mulf %[[VAL_57]], %[[VAL_2]] : f32
-// CHECK:             store %[[VAL_58]], %[[VAL_12]]{{\[}}%[[VAL_56]]] : memref<16xf32>
+// CHECK:           scf.for %[[VAL_55:.*]] = %[[VAL_56:.*]]#1 to %[[VAL_17]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_57:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_55]]] : memref<?xindex>
+// CHECK:             %[[VAL_58:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_55]]] : memref<?xf32>
+// CHECK:             %[[VAL_59:.*]] = mulf %[[VAL_58]], %[[VAL_2]] : f32
+// CHECK:             store %[[VAL_59]], %[[VAL_13]]{{\[}}%[[VAL_57]]] : memref<16xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_59:.*]] = tensor_load %[[VAL_12]] : memref<16xf32>
-// CHECK:           return %[[VAL_59]] : tensor<16xf32>
+// CHECK:           %[[VAL_60:.*]] = tensor_load %[[VAL_13]] : memref<16xf32>
+// CHECK:           return %[[VAL_60]] : tensor<16xf32>
 // CHECK:         }
-func @two_way_inv(%arga: tensor<16xf32>,
-                  %argb: tensor<16xf32>, %argc: f32) -> tensor<16xf32> {
+func @two_way_inv(%arga: tensor<16xf32>, %argb: tensor<16xf32>, %argc: f32, %argx: tensor<16xf32>) -> tensor<16xf32> {
   %0 = linalg.generic #trait_two_way_inv
-    ins(%arga, %argb : tensor<16xf32>, tensor<16xf32>)
-    outs(%argb : tensor<16xf32>) {
-      ^bb(%a : f32, %b : f32, %c : f32):
+    ins(%arga, %argb: tensor<16xf32>, tensor<16xf32>)
+    outs(%argx: tensor<16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = mulf %a, %argc : f32
         %1 = mulf %b, %argc : f32
         %2 = addf %0, %1 : f32
-        linalg.yield %2: f32
+        linalg.yield %2 : f32
   } -> tensor<16xf32>
   return %0 : tensor<16xf32>
 }
@@ -757,88 +770,89 @@ func @two_way_inv(%arga: tensor<16xf32>,
 // CHECK-LABEL:   func @two_way_inv_alt(
 // CHECK-SAME:                          %[[VAL_0:.*0]]: tensor<16xf32>,
 // CHECK-SAME:                          %[[VAL_1:.*1]]: tensor<16xf32>,
-// CHECK-SAME:                          %[[VAL_2:.*2]]: f32) -> tensor<16xf32> {
-// CHECK:           %[[VAL_3:.*]] = constant 999 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<16xf32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]]:3 = scf.while (%[[VAL_18:.*]] = %[[VAL_13]], %[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_4]]) : (index, index, index) -> (index, index, index) {
-// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_14]] : index
-// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_16]] : index
-// CHECK:             %[[VAL_23:.*]] = and %[[VAL_21]], %[[VAL_22]] : i1
-// CHECK:             scf.condition(%[[VAL_23]]) %[[VAL_18]], %[[VAL_19]], %[[VAL_20]] : index, index, index
+// CHECK-SAME:                          %[[VAL_2:.*2]]: f32,
+// CHECK-SAME:                          %[[VAL_3:.*3]]: tensor<16xf32>) -> tensor<16xf32> {
+// CHECK:           %[[VAL_4:.*]] = constant 999 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref<?xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_4]]) : memref<?xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<16xf32>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]]:3 = scf.while (%[[VAL_19:.*]] = %[[VAL_14]], %[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_5]]) : (index, index, index) -> (index, index, index) {
+// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_15]] : index
+// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_17]] : index
+// CHECK:             %[[VAL_24:.*]] = and %[[VAL_22]], %[[VAL_23]] : i1
+// CHECK:             scf.condition(%[[VAL_24]]) %[[VAL_19]], %[[VAL_20]], %[[VAL_21]] : index, index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index):
-// CHECK:             %[[VAL_27:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_31:.*]] = and %[[VAL_29]], %[[VAL_30]] : i1
-// CHECK:             scf.if %[[VAL_31]] {
-// CHECK:               %[[VAL_32:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref<?xf32>
-// CHECK:               %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:               %[[VAL_34:.*]] = addf %[[VAL_32]], %[[VAL_33]] : f32
-// CHECK:               %[[VAL_35:.*]] = mulf %[[VAL_34]], %[[VAL_2]] : f32
-// CHECK:               store %[[VAL_35]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:           ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
+// CHECK:             %[[VAL_28:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_31:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_32:.*]] = and %[[VAL_30]], %[[VAL_31]] : i1
+// CHECK:             scf.if %[[VAL_32]] {
+// CHECK:               %[[VAL_33:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref<?xf32>
+// CHECK:               %[[VAL_34:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:               %[[VAL_35:.*]] = addf %[[VAL_33]], %[[VAL_34]] : f32
+// CHECK:               %[[VAL_36:.*]] = mulf %[[VAL_35]], %[[VAL_2]] : f32
+// CHECK:               store %[[VAL_36]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:             } else {
-// CHECK:               %[[VAL_36:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:               scf.if %[[VAL_36]] {
-// CHECK:                 %[[VAL_37:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_24]]] : memref<?xf32>
-// CHECK:                 %[[VAL_38:.*]] = mulf %[[VAL_37]], %[[VAL_2]] : f32
-// CHECK:                 store %[[VAL_38]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:               %[[VAL_37:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:               scf.if %[[VAL_37]] {
+// CHECK:                 %[[VAL_38:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_25]]] : memref<?xf32>
+// CHECK:                 %[[VAL_39:.*]] = mulf %[[VAL_38]], %[[VAL_2]] : f32
+// CHECK:                 store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:               } else {
-// CHECK:                 %[[VAL_39:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:                 scf.if %[[VAL_39]] {
-// CHECK:                   %[[VAL_40:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:                   %[[VAL_41:.*]] = mulf %[[VAL_40]], %[[VAL_2]] : f32
-// CHECK:                   store %[[VAL_41]], %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<16xf32>
+// CHECK:                 %[[VAL_40:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:                 scf.if %[[VAL_40]] {
+// CHECK:                   %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:                   %[[VAL_42:.*]] = mulf %[[VAL_41]], %[[VAL_2]] : f32
+// CHECK:                   store %[[VAL_42]], %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<16xf32>
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_42:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_43:.*]] = addi %[[VAL_24]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_44:.*]] = select %[[VAL_42]], %[[VAL_43]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_45:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_46:.*]] = addi %[[VAL_25]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_25]] : index
-// CHECK:             %[[VAL_48:.*]] = addi %[[VAL_26]], %[[VAL_5]] : index
-// CHECK:             scf.yield %[[VAL_44]], %[[VAL_47]], %[[VAL_48]] : index, index, index
+// CHECK:             %[[VAL_43:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_44:.*]] = addi %[[VAL_25]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_45:.*]] = select %[[VAL_43]], %[[VAL_44]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_46:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_47:.*]] = addi %[[VAL_26]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_26]] : index
+// CHECK:             %[[VAL_49:.*]] = addi %[[VAL_27]], %[[VAL_6]] : index
+// CHECK:             scf.yield %[[VAL_45]], %[[VAL_48]], %[[VAL_49]] : index, index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#0 to %[[VAL_14]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_51:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_49]]] : memref<?xf32>
-// CHECK:             %[[VAL_52:.*]] = mulf %[[VAL_51]], %[[VAL_2]] : f32
-// CHECK:             store %[[VAL_52]], %[[VAL_12]]{{\[}}%[[VAL_50]]#2] : memref<16xf32>
+// CHECK:           scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#0 to %[[VAL_15]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_52:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_50]]] : memref<?xf32>
+// CHECK:             %[[VAL_53:.*]] = mulf %[[VAL_52]], %[[VAL_2]] : f32
+// CHECK:             store %[[VAL_53]], %[[VAL_13]]{{\[}}%[[VAL_51]]#2] : memref<16xf32>
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_53:.*]] = %[[VAL_54:.*]]#1 to %[[VAL_16]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_55:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_53]]] : memref<?xindex>
-// CHECK:             %[[VAL_56:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_53]]] : memref<?xf32>
-// CHECK:             %[[VAL_57:.*]] = mulf %[[VAL_56]], %[[VAL_2]] : f32
-// CHECK:             store %[[VAL_57]], %[[VAL_12]]{{\[}}%[[VAL_55]]] : memref<16xf32>
+// CHECK:           scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_17]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_56:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_54]]] : memref<?xindex>
+// CHECK:             %[[VAL_57:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_54]]] : memref<?xf32>
+// CHECK:             %[[VAL_58:.*]] = mulf %[[VAL_57]], %[[VAL_2]] : f32
+// CHECK:             store %[[VAL_58]], %[[VAL_13]]{{\[}}%[[VAL_56]]] : memref<16xf32>
 // CHECK:           }
-// CHECK:           %[[VAL_58:.*]] = tensor_load %[[VAL_12]] : memref<16xf32>
-// CHECK:           return %[[VAL_58]] : tensor<16xf32>
+// CHECK:           %[[VAL_59:.*]] = tensor_load %[[VAL_13]] : memref<16xf32>
+// CHECK:           return %[[VAL_59]] : tensor<16xf32>
 // CHECK:         }
 func @two_way_inv_alt(%arga: tensor<16xf32>,
-                      %argb: tensor<16xf32>, %argc: f32) -> tensor<16xf32> {
+                      %argb: tensor<16xf32>, %argc: f32, %argx: tensor<16xf32>) -> tensor<16xf32> {
   // Same kernel, but now expressed as "x(i) = (a(i) + b(i)) * c".
   %0 = linalg.generic #trait_two_way_inv
-    ins(%arga, %argb : tensor<16xf32>, tensor<16xf32>)
-    outs(%argb : tensor<16xf32>) {
-      ^bb(%a : f32, %b : f32, %c : f32):
+    ins(%arga, %argb: tensor<16xf32>, tensor<16xf32>)
+    outs(%argx: tensor<16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = addf %a, %b : f32
         %1 = mulf %0, %argc : f32
-        linalg.yield %1: f32
+        linalg.yield %1 : f32
   } -> tensor<16xf32>
   return %0 : tensor<16xf32>
 }
@@ -863,27 +877,27 @@ func @two_way_inv_alt(%arga: tensor<16xf32>,
 // CHECK:           %[[VAL_3:.*]] = constant 0 : index
 // CHECK:           %[[VAL_4:.*]] = constant 1 : index
 // CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_8:.*]] = alloca() : memref<f32>
-// CHECK:           %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = load %[[VAL_8]][] : memref<f32>
-// CHECK:           %[[VAL_12:.*]] = scf.for %[[VAL_13:.*]] = %[[VAL_9]] to %[[VAL_10]] step %[[VAL_4]] iter_args(%[[VAL_14:.*]] = %[[VAL_11]]) -> (f32) {
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref<?xf32>
-// CHECK:             %[[VAL_16:.*]] = addf %[[VAL_14]], %[[VAL_15]] : f32
-// CHECK:             scf.yield %[[VAL_16]] : f32
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
+// CHECK:           %[[VAL_7:.*]] = alloca() : memref<f32>
+// CHECK:           %[[VAL_8:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = load %[[VAL_7]][] : memref<f32>
+// CHECK:           %[[VAL_11:.*]] = scf.for %[[VAL_12:.*]] = %[[VAL_8]] to %[[VAL_9]] step %[[VAL_4]] iter_args(%[[VAL_13:.*]] = %[[VAL_10]]) -> (f32) {
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xf32>
+// CHECK:             %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32
+// CHECK:             scf.yield %[[VAL_15]] : f32
 // CHECK:           }
-// CHECK:           store %[[VAL_17:.*]], %[[VAL_8]][] : memref<f32>
-// CHECK:           %[[VAL_18:.*]] = tensor_load %[[VAL_8]] : memref<f32>
-// CHECK:           return %[[VAL_18]] : tensor<f32>
+// CHECK:           store %[[VAL_16:.*]], %[[VAL_7]][] : memref<f32>
+// CHECK:           %[[VAL_17:.*]] = tensor_load %[[VAL_7]] : memref<f32>
+// CHECK:           return %[[VAL_17]] : tensor<f32>
 // CHECK:         }
 func @sum_reduction(%arga: tensor<?xf32>, %argx: tensor<f32>) -> tensor<f32> {
   %0 = linalg.generic #trait_sum_reduction
-    ins(%arga : tensor<?xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %x : f32):
-        %0 = addf %x, %a  : f32
-        linalg.yield %0: f32
+    ins(%arga: tensor<?xf32>)
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %x, %a : f32
+        linalg.yield %0 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }
@@ -989,11 +1003,11 @@ func @sum_reduction_ss(%arga: tensor<16xf32>,
   // as two separate reductions kernels.
   %0 = linalg.generic #trait_sum_reduction_ss
     ins(%arga, %argb: tensor<16xf32>, tensor<16xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %b : f32, %x : f32):
-        %0 = addf %a, %b  : f32
-        %1 = addf %x, %0  : f32
-        linalg.yield %1: f32
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
+        %1 = addf %x, %0 : f32
+        linalg.yield %1 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }
@@ -1108,12 +1122,12 @@ func @sum_reduction_inv(%arga: tensor<16xf32>,
   // as two separate reductions kernels.
   %0 = linalg.generic #trait_sum_reduction_inv_ss
     ins(%arga, %argb, %argc : tensor<16xf32>, tensor<f32>, tensor<16xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %b : f32, %c : f32, %x : f32):
-        %0 = mulf %a, %b  : f32
-        %1 = addf %0, %c  : f32
-        %2 = addf %x, %1  : f32
-        linalg.yield %2: f32
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %b: f32, %c: f32, %x: f32):
+        %0 = mulf %a, %b : f32
+        %1 = addf %0, %c : f32
+        %2 = addf %x, %1 : f32
+        linalg.yield %2 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }

diff  --git a/mlir/test/Dialect/Linalg/sparse_2d.mlir b/mlir/test/Dialect/Linalg/sparse_2d.mlir
index 957c3b6e1589..438644debcc9 100644
--- a/mlir/test/Dialect/Linalg/sparse_2d.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_2d.mlir
@@ -17,64 +17,66 @@
 }
 
 // CHECK-LABEL:   func @add_dd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
 // CHECK:           %[[VAL_7:.*]] = alloca() : memref<32x16xf32>
 // CHECK:           %[[VAL_8:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_2]] step %[[VAL_5]] {
-// CHECK:             scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_13:.*]] = addf %[[VAL_11]], %[[VAL_12]] : f32
-// CHECK:               store %[[VAL_13]], %[[VAL_8]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
+// CHECK:             scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_14:.*]] = addf %[[VAL_12]], %[[VAL_13]] : f32
+// CHECK:               store %[[VAL_14]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_14:.*]] = tensor_load %[[VAL_8]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_14]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_15:.*]] = tensor_load %[[VAL_9]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_15]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_dd
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga: tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_dd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
 // CHECK:           %[[VAL_7:.*]] = alloca() : memref<32x16xf32>
 // CHECK:           %[[VAL_8:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_2]] step %[[VAL_5]] {
-// CHECK:             scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_13:.*]] = mulf %[[VAL_11]], %[[VAL_12]] : f32
-// CHECK:               store %[[VAL_13]], %[[VAL_8]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
+// CHECK:             scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_14:.*]] = mulf %[[VAL_12]], %[[VAL_13]] : f32
+// CHECK:               store %[[VAL_14]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_14:.*]] = tensor_load %[[VAL_8]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_14]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_15:.*]] = tensor_load %[[VAL_9]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_15]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_dd
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -96,100 +98,102 @@ func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16
 }
 
 // CHECK-LABEL:   func @add_ds(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 1 : index
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 1 : index
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_7]] {
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<?xindex>
-// CHECK:             %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_7]] : index
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_14]], %[[VAL_19:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
-// CHECK:               %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index
-// CHECK:               scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_8]] {
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_8]] : index
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:             %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
+// CHECK:               %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
+// CHECK:               scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
 // CHECK:             } do {
-// CHECK:             ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index):
-// CHECK:               %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:               scf.if %[[VAL_24]] {
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xf32>
-// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
-// CHECK:                 %[[VAL_27:.*]] = addf %[[VAL_25]], %[[VAL_26]] : f32
-// CHECK:                 store %[[VAL_27]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
+// CHECK:             ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
+// CHECK:               %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:               %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:               scf.if %[[VAL_25]] {
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_22]]] : memref<?xf32>
+// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
+// CHECK:                 %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32
+// CHECK:                 store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
 // CHECK:               } else {
-// CHECK:                 scf.if %[[VAL_6]] {
-// CHECK:                   %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
-// CHECK:                   store %[[VAL_28]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
+// CHECK:                 scf.if %[[VAL_7]] {
+// CHECK:                   %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
+// CHECK:                   store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
-// CHECK:               %[[VAL_29:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:               %[[VAL_30:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
-// CHECK:               %[[VAL_31:.*]] = select %[[VAL_29]], %[[VAL_30]], %[[VAL_21]] : index
-// CHECK:               %[[VAL_32:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
-// CHECK:               scf.yield %[[VAL_31]], %[[VAL_32]] : index, index
+// CHECK:               %[[VAL_30:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:               %[[VAL_31:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
+// CHECK:               %[[VAL_32:.*]] = select %[[VAL_30]], %[[VAL_31]], %[[VAL_22]] : index
+// CHECK:               %[[VAL_33:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index
+// CHECK:               scf.yield %[[VAL_32]], %[[VAL_33]] : index, index
 // CHECK:             }
-// CHECK:             scf.for %[[VAL_33:.*]] = %[[VAL_34:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:               %[[VAL_35:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_33]]] : memref<32x16xf32>
-// CHECK:               store %[[VAL_35]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_33]]] : memref<32x16xf32>
+// CHECK:             scf.for %[[VAL_34:.*]] = %[[VAL_35:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:               %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32>
+// CHECK:               store %[[VAL_36]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_36:.*]] = tensor_load %[[VAL_12]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_36]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_37:.*]] = tensor_load %[[VAL_13]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_37]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ds
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_ds(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           scf.for %[[VAL_11:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref<?xindex>
-// CHECK:             %[[VAL_13:.*]] = addi %[[VAL_11]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_13]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_15:.*]] = %[[VAL_12]] to %[[VAL_14]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:               %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xf32>
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_19:.*]] = mulf %[[VAL_17]], %[[VAL_18]] : f32
-// CHECK:               store %[[VAL_19]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<32x16xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xindex>
+// CHECK:             %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:               %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref<?xf32>
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32
+// CHECK:               store %[[VAL_20]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_20:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_20]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_21:.*]] = tensor_load %[[VAL_11]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_21]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ds
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -211,106 +215,108 @@ func @mul_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16
 }
 
 // CHECK-LABEL:   func @add_sd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant true
-// CHECK:           %[[VAL_6:.*]] = constant 0 : index
-// CHECK:           %[[VAL_7:.*]] = constant 1 : index
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant true
+// CHECK:           %[[VAL_7:.*]] = constant 0 : index
+// CHECK:           %[[VAL_8:.*]] = constant 1 : index
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index
-// CHECK:             scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_14]], %[[VAL_18:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_15]] : index
+// CHECK:             scf.condition(%[[VAL_19]]) %[[VAL_17]], %[[VAL_18]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index):
-// CHECK:             %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:             %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
-// CHECK:             scf.if %[[VAL_22]] {
-// CHECK:               scf.for %[[VAL_23:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:                 %[[VAL_24:.*]] = muli %[[VAL_19]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]], %[[VAL_23]]] : memref<32x16xf32>
-// CHECK:                 %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32
-// CHECK:                 store %[[VAL_28]], %[[VAL_12]]{{\[}}%[[VAL_20]], %[[VAL_23]]] : memref<32x16xf32>
+// CHECK:           ^bb0(%[[VAL_20:.*]]: index, %[[VAL_21:.*]]: index):
+// CHECK:             %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:             %[[VAL_23:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
+// CHECK:             scf.if %[[VAL_23]] {
+// CHECK:               scf.for %[[VAL_24:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:                 %[[VAL_25:.*]] = muli %[[VAL_20]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_26:.*]] = addi %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32>
+// CHECK:                 %[[VAL_29:.*]] = addf %[[VAL_27]], %[[VAL_28]] : f32
+// CHECK:                 store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32>
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_5]] {
-// CHECK:                 scf.for %[[VAL_29:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]], %[[VAL_29]]] : memref<32x16xf32>
-// CHECK:                   store %[[VAL_30]], %[[VAL_12]]{{\[}}%[[VAL_20]], %[[VAL_29]]] : memref<32x16xf32>
+// CHECK:               scf.if %[[VAL_6]] {
+// CHECK:                 scf.for %[[VAL_30:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32>
+// CHECK:                   store %[[VAL_31]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32>
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_31:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
-// CHECK:             %[[VAL_32:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index
-// CHECK:             %[[VAL_33:.*]] = select %[[VAL_31]], %[[VAL_32]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_34:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index
-// CHECK:             scf.yield %[[VAL_33]], %[[VAL_34]] : index, index
+// CHECK:             %[[VAL_32:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
+// CHECK:             %[[VAL_33:.*]] = addi %[[VAL_20]], %[[VAL_8]] : index
+// CHECK:             %[[VAL_34:.*]] = select %[[VAL_32]], %[[VAL_33]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_35:.*]] = addi %[[VAL_21]], %[[VAL_8]] : index
+// CHECK:             scf.yield %[[VAL_34]], %[[VAL_35]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_35:.*]] = %[[VAL_36:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
-// CHECK:             scf.for %[[VAL_37:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:               %[[VAL_38:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_35]], %[[VAL_37]]] : memref<32x16xf32>
-// CHECK:               store %[[VAL_38]], %[[VAL_12]]{{\[}}%[[VAL_35]], %[[VAL_37]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_36:.*]] = %[[VAL_37:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
+// CHECK:             scf.for %[[VAL_38:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:               %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32>
+// CHECK:               store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_39:.*]] = tensor_load %[[VAL_12]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_39]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_40:.*]] = tensor_load %[[VAL_13]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_40]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_sd
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_sd(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_15:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_16:.*]] = muli %[[VAL_13]], %[[VAL_3]] : index
-// CHECK:               %[[VAL_17:.*]] = addi %[[VAL_16]], %[[VAL_15]] : index
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref<?xf32>
-// CHECK:               %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]], %[[VAL_15]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32
-// CHECK:               store %[[VAL_20]], %[[VAL_10]]{{\[}}%[[VAL_14]], %[[VAL_15]]] : memref<32x16xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_17:.*]] = muli %[[VAL_14]], %[[VAL_4]] : index
+// CHECK:               %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xf32>
+// CHECK:               %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_21:.*]] = mulf %[[VAL_19]], %[[VAL_20]] : f32
+// CHECK:               store %[[VAL_21]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_21:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_21]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_22:.*]] = tensor_load %[[VAL_11]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_22]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_sd
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -332,135 +338,137 @@ func @mul_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16
 }
 
 // CHECK-LABEL:   func @add_ss(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant true
-// CHECK:           %[[VAL_6:.*]] = constant 0 : index
-// CHECK:           %[[VAL_7:.*]] = constant 1 : index
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant true
+// CHECK:           %[[VAL_7:.*]] = constant 0 : index
+// CHECK:           %[[VAL_8:.*]] = constant 1 : index
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_15]], %[[VAL_19:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index
-// CHECK:             scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index
+// CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
+// CHECK:             scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index):
-// CHECK:             %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:             %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:             scf.if %[[VAL_24]] {
-// CHECK:               %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               %[[VAL_26:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
-// CHECK:               %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:               %[[VAL_28:.*]]:2 = scf.while (%[[VAL_29:.*]] = %[[VAL_25]], %[[VAL_30:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_31:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_27]] : index
-// CHECK:                 scf.condition(%[[VAL_31]]) %[[VAL_29]], %[[VAL_30]] : index, index
+// CHECK:           ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
+// CHECK:             %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:             %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:             scf.if %[[VAL_25]] {
+// CHECK:               %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:               %[[VAL_27:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
+// CHECK:               %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:               %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_26]], %[[VAL_31:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_32:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_28]] : index
+// CHECK:                 scf.condition(%[[VAL_32]]) %[[VAL_30]], %[[VAL_31]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_32:.*]]: index, %[[VAL_33:.*]]: index):
-// CHECK:                 %[[VAL_34:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_32]]] : memref<?xindex>
-// CHECK:                 %[[VAL_35:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
-// CHECK:                 scf.if %[[VAL_35]] {
-// CHECK:                   %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_32]]] : memref<?xf32>
-// CHECK:                   %[[VAL_37:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
-// CHECK:                   %[[VAL_38:.*]] = addf %[[VAL_36]], %[[VAL_37]] : f32
-// CHECK:                   store %[[VAL_38]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
+// CHECK:               ^bb0(%[[VAL_33:.*]]: index, %[[VAL_34:.*]]: index):
+// CHECK:                 %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref<?xindex>
+// CHECK:                 %[[VAL_36:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
+// CHECK:                 scf.if %[[VAL_36]] {
+// CHECK:                   %[[VAL_37:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_33]]] : memref<?xf32>
+// CHECK:                   %[[VAL_38:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
+// CHECK:                   %[[VAL_39:.*]] = addf %[[VAL_37]], %[[VAL_38]] : f32
+// CHECK:                   store %[[VAL_39]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
 // CHECK:                 } else {
-// CHECK:                   scf.if %[[VAL_5]] {
-// CHECK:                     %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
-// CHECK:                     store %[[VAL_39]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
+// CHECK:                   scf.if %[[VAL_6]] {
+// CHECK:                     %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
+// CHECK:                     store %[[VAL_40]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
 // CHECK:                   } else {
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_40:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
-// CHECK:                 %[[VAL_41:.*]] = addi %[[VAL_32]], %[[VAL_7]] : index
-// CHECK:                 %[[VAL_42:.*]] = select %[[VAL_40]], %[[VAL_41]], %[[VAL_32]] : index
-// CHECK:                 %[[VAL_43:.*]] = addi %[[VAL_33]], %[[VAL_7]] : index
-// CHECK:                 scf.yield %[[VAL_42]], %[[VAL_43]] : index, index
+// CHECK:                 %[[VAL_41:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
+// CHECK:                 %[[VAL_42:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
+// CHECK:                 %[[VAL_43:.*]] = select %[[VAL_41]], %[[VAL_42]], %[[VAL_33]] : index
+// CHECK:                 %[[VAL_44:.*]] = addi %[[VAL_34]], %[[VAL_8]] : index
+// CHECK:                 scf.yield %[[VAL_43]], %[[VAL_44]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_44:.*]] = %[[VAL_45:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:                 %[[VAL_46:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_44]]] : memref<32x16xf32>
-// CHECK:                 store %[[VAL_46]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_44]]] : memref<32x16xf32>
+// CHECK:               scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:                 %[[VAL_47:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32>
+// CHECK:                 store %[[VAL_47]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32>
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_5]] {
-// CHECK:                 scf.for %[[VAL_47:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:                   %[[VAL_48:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_47]]] : memref<32x16xf32>
-// CHECK:                   store %[[VAL_48]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_47]]] : memref<32x16xf32>
+// CHECK:               scf.if %[[VAL_6]] {
+// CHECK:                 scf.for %[[VAL_48:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:                   %[[VAL_49:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32>
+// CHECK:                   store %[[VAL_49]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32>
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_49:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:             %[[VAL_50:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
-// CHECK:             %[[VAL_51:.*]] = select %[[VAL_49]], %[[VAL_50]], %[[VAL_21]] : index
-// CHECK:             %[[VAL_52:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
-// CHECK:             scf.yield %[[VAL_51]], %[[VAL_52]] : index, index
+// CHECK:             %[[VAL_50:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:             %[[VAL_51:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
+// CHECK:             %[[VAL_52:.*]] = select %[[VAL_50]], %[[VAL_51]], %[[VAL_22]] : index
+// CHECK:             %[[VAL_53:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index
+// CHECK:             scf.yield %[[VAL_52]], %[[VAL_53]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_53:.*]] = %[[VAL_54:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
-// CHECK:             scf.for %[[VAL_55:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:               %[[VAL_56:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_53]], %[[VAL_55]]] : memref<32x16xf32>
-// CHECK:               store %[[VAL_56]], %[[VAL_14]]{{\[}}%[[VAL_53]], %[[VAL_55]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
+// CHECK:             scf.for %[[VAL_56:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:               %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32>
+// CHECK:               store %[[VAL_57]], %[[VAL_15]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_57:.*]] = tensor_load %[[VAL_14]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_57]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_58:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_58]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_ss(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
-// CHECK:             %[[VAL_17:.*]] = addi %[[VAL_14]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_19:.*]] = %[[VAL_16]] to %[[VAL_18]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:               %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xf32>
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]], %[[VAL_20]]] : memref<32x16xf32>
-// CHECK:               %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32
-// CHECK:               store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_20]]] : memref<32x16xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xindex>
+// CHECK:             %[[VAL_18:.*]] = addi %[[VAL_15]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:               %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<?xf32>
+// CHECK:               %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32
+// CHECK:               store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_24:.*]] = tensor_load %[[VAL_11]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_24]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_25:.*]] = tensor_load %[[VAL_12]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_25]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -482,258 +490,260 @@ func @mul_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16
 }
 
 // CHECK-LABEL:   func @add_ss_ss(
-// CHECK-SAME:                    %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                    %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
-// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
-// CHECK:             scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK-SAME:                    %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
+// CHECK:             %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
+// CHECK:             scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:             %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
-// CHECK:             scf.if %[[VAL_34]] {
-// CHECK:               %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:               %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
-// CHECK:               %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:               %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
-// CHECK:               %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
-// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
-// CHECK:                 %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
-// CHECK:                 scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
+// CHECK:           ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:             %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
+// CHECK:             scf.if %[[VAL_35]] {
+// CHECK:               %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:               %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref<?xindex>
+// CHECK:               %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:               %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref<?xindex>
+// CHECK:               %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
+// CHECK:                 %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
+// CHECK:                 %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
+// CHECK:                 scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
-// CHECK:                 %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
-// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
-// CHECK:                 %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
-// CHECK:                 scf.if %[[VAL_55]] {
-// CHECK:                   %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                   %[[VAL_58:.*]] = addf %[[VAL_56]], %[[VAL_57]] : f32
-// CHECK:                   store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:               ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
+// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xindex>
+// CHECK:                 %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xindex>
+// CHECK:                 %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
+// CHECK:                 scf.if %[[VAL_56]] {
+// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                   %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                   %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32
+// CHECK:                   store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                 } else {
-// CHECK:                   %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                   scf.if %[[VAL_59]] {
-// CHECK:                     %[[VAL_60:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                     store %[[VAL_60]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:                   %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                   scf.if %[[VAL_60]] {
+// CHECK:                     %[[VAL_61:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                     store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                   } else {
-// CHECK:                     %[[VAL_61:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                     scf.if %[[VAL_61]] {
-// CHECK:                       %[[VAL_62:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                       store %[[VAL_62]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:                     %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                     scf.if %[[VAL_62]] {
+// CHECK:                       %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                       store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                     } else {
 // CHECK:                     }
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_63:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_64:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_47]] : index
-// CHECK:                 %[[VAL_66:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_67:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_48]] : index
-// CHECK:                 scf.yield %[[VAL_65]], %[[VAL_68]] : index, index
+// CHECK:                 %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index
+// CHECK:                 %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index
+// CHECK:                 scf.yield %[[VAL_66]], %[[VAL_69]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_69:.*]] = %[[VAL_70:.*]]#0 to %[[VAL_37]] step %[[VAL_4]] {
-// CHECK:                 %[[VAL_71:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_69]]] : memref<?xindex>
-// CHECK:                 %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_69]]] : memref<?xf32>
-// CHECK:                 store %[[VAL_72]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_71]]] : memref<32x16xf32>
+// CHECK:               scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_5]] {
+// CHECK:                 %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref<?xindex>
+// CHECK:                 %[[VAL_73:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_70]]] : memref<?xf32>
+// CHECK:                 store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32>
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_73:.*]] = %[[VAL_74:.*]]#1 to %[[VAL_40]] step %[[VAL_4]] {
-// CHECK:                 %[[VAL_75:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_73]]] : memref<?xindex>
-// CHECK:                 %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_73]]] : memref<?xf32>
-// CHECK:                 store %[[VAL_76]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_75]]] : memref<32x16xf32>
+// CHECK:               scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_5]] {
+// CHECK:                 %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref<?xindex>
+// CHECK:                 %[[VAL_77:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_74]]] : memref<?xf32>
+// CHECK:                 store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32>
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               %[[VAL_77:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:               scf.if %[[VAL_77]] {
-// CHECK:                 %[[VAL_78:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:                 %[[VAL_79:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_80:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_79]]] : memref<?xindex>
-// CHECK:                 scf.for %[[VAL_81:.*]] = %[[VAL_78]] to %[[VAL_80]] step %[[VAL_4]] {
-// CHECK:                   %[[VAL_82:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_81]]] : memref<?xindex>
-// CHECK:                   %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_81]]] : memref<?xf32>
-// CHECK:                   store %[[VAL_83]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_82]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:               scf.if %[[VAL_78]] {
+// CHECK:                 %[[VAL_79:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:                 %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_81:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_80]]] : memref<?xindex>
+// CHECK:                 scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_5]] {
+// CHECK:                   %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref<?xindex>
+// CHECK:                   %[[VAL_84:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_82]]] : memref<?xf32>
+// CHECK:                   store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32>
 // CHECK:                 }
 // CHECK:               } else {
-// CHECK:                 %[[VAL_84:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:                 scf.if %[[VAL_84]] {
-// CHECK:                   %[[VAL_85:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:                   %[[VAL_86:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:                   %[[VAL_87:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_86]]] : memref<?xindex>
-// CHECK:                   scf.for %[[VAL_88:.*]] = %[[VAL_85]] to %[[VAL_87]] step %[[VAL_4]] {
-// CHECK:                     %[[VAL_89:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_88]]] : memref<?xindex>
-// CHECK:                     %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_88]]] : memref<?xf32>
-// CHECK:                     store %[[VAL_90]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_89]]] : memref<32x16xf32>
+// CHECK:                 %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:                 scf.if %[[VAL_85]] {
+// CHECK:                   %[[VAL_86:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:                   %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:                   %[[VAL_88:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_87]]] : memref<?xindex>
+// CHECK:                   scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_5]] {
+// CHECK:                     %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref<?xindex>
+// CHECK:                     %[[VAL_91:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_89]]] : memref<?xf32>
+// CHECK:                     store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32>
 // CHECK:                   }
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_91:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_92:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_93:.*]] = select %[[VAL_91]], %[[VAL_92]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_94:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_95:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_96:.*]] = select %[[VAL_94]], %[[VAL_95]], %[[VAL_27]] : index
-// CHECK:             scf.yield %[[VAL_93]], %[[VAL_96]] : index, index
+// CHECK:             %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index
+// CHECK:             scf.yield %[[VAL_94]], %[[VAL_97]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_97:.*]] = %[[VAL_98:.*]]#0 to %[[VAL_17]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_99:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_97]]] : memref<?xindex>
-// CHECK:             %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_97]]] : memref<?xindex>
-// CHECK:             %[[VAL_101:.*]] = addi %[[VAL_97]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_102:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_101]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_103:.*]] = %[[VAL_100]] to %[[VAL_102]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_104:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_103]]] : memref<?xindex>
-// CHECK:               %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_103]]] : memref<?xf32>
-// CHECK:               store %[[VAL_105]], %[[VAL_15]]{{\[}}%[[VAL_99]], %[[VAL_104]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref<?xindex>
+// CHECK:             %[[VAL_101:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_98]]] : memref<?xindex>
+// CHECK:             %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_103:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_102]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref<?xindex>
+// CHECK:               %[[VAL_106:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_104]]] : memref<?xf32>
+// CHECK:               store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_106:.*]] = %[[VAL_107:.*]]#1 to %[[VAL_19]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_108:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_106]]] : memref<?xindex>
-// CHECK:             %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_106]]] : memref<?xindex>
-// CHECK:             %[[VAL_110:.*]] = addi %[[VAL_106]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_111:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_110]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_112:.*]] = %[[VAL_109]] to %[[VAL_111]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_112]]] : memref<?xindex>
-// CHECK:               %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_112]]] : memref<?xf32>
-// CHECK:               store %[[VAL_114]], %[[VAL_15]]{{\[}}%[[VAL_108]], %[[VAL_113]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref<?xindex>
+// CHECK:             %[[VAL_110:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_107]]] : memref<?xindex>
+// CHECK:             %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_112:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_111]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref<?xindex>
+// CHECK:               %[[VAL_115:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_113]]] : memref<?xf32>
+// CHECK:               store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_115:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_115]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_116:.*]] = tensor_load %[[VAL_16]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_116]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_ss_ss(
-// CHECK-SAME:                    %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                    %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
-// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
-// CHECK:             scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK-SAME:                    %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
+// CHECK:             %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
+// CHECK:             scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:             %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
-// CHECK:             scf.if %[[VAL_34]] {
-// CHECK:               %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:               %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
-// CHECK:               %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:               %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
-// CHECK:               %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
-// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
-// CHECK:                 %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
-// CHECK:                 scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
+// CHECK:           ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:             %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
+// CHECK:             scf.if %[[VAL_35]] {
+// CHECK:               %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:               %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref<?xindex>
+// CHECK:               %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:               %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref<?xindex>
+// CHECK:               %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
+// CHECK:                 %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
+// CHECK:                 %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
+// CHECK:                 scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
-// CHECK:                 %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
-// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
-// CHECK:                 %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
-// CHECK:                 scf.if %[[VAL_55]] {
-// CHECK:                   %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                   %[[VAL_58:.*]] = mulf %[[VAL_56]], %[[VAL_57]] : f32
-// CHECK:                   store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:               ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
+// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xindex>
+// CHECK:                 %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xindex>
+// CHECK:                 %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
+// CHECK:                 scf.if %[[VAL_56]] {
+// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                   %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                   %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32
+// CHECK:                   store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                 } else {
 // CHECK:                 }
-// CHECK:                 %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_60:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_61:.*]] = select %[[VAL_59]], %[[VAL_60]], %[[VAL_47]] : index
-// CHECK:                 %[[VAL_62:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_63:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_64:.*]] = select %[[VAL_62]], %[[VAL_63]], %[[VAL_48]] : index
-// CHECK:                 scf.yield %[[VAL_61]], %[[VAL_64]] : index, index
+// CHECK:                 %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index
+// CHECK:                 %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index
+// CHECK:                 scf.yield %[[VAL_62]], %[[VAL_65]] : index, index
 // CHECK:               }
 // CHECK:             } else {
 // CHECK:             }
-// CHECK:             %[[VAL_65:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_66:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_67:.*]] = select %[[VAL_65]], %[[VAL_66]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_68:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_69:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_70:.*]] = select %[[VAL_68]], %[[VAL_69]], %[[VAL_27]] : index
-// CHECK:             scf.yield %[[VAL_67]], %[[VAL_70]] : index, index
+// CHECK:             %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index
+// CHECK:             scf.yield %[[VAL_68]], %[[VAL_71]] : index, index
 // CHECK:           }
-// CHECK:           %[[VAL_71:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_71]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_72:.*]] = tensor_load %[[VAL_16]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_72]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -755,258 +765,260 @@ func @mul_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32
 }
 
 // CHECK-LABEL:   func @add_sd_ds(
-// CHECK-SAME:                    %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                    %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
-// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
-// CHECK:             scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK-SAME:                    %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
+// CHECK:             %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
+// CHECK:             scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:             %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
-// CHECK:             scf.if %[[VAL_34]] {
-// CHECK:               %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:               %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
-// CHECK:               %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:               %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
-// CHECK:               %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
-// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
-// CHECK:                 %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
-// CHECK:                 scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
+// CHECK:           ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:             %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
+// CHECK:             scf.if %[[VAL_35]] {
+// CHECK:               %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:               %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref<?xindex>
+// CHECK:               %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:               %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref<?xindex>
+// CHECK:               %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
+// CHECK:                 %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
+// CHECK:                 %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
+// CHECK:                 scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
-// CHECK:                 %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
-// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
-// CHECK:                 %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
-// CHECK:                 scf.if %[[VAL_55]] {
-// CHECK:                   %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                   %[[VAL_58:.*]] = addf %[[VAL_56]], %[[VAL_57]] : f32
-// CHECK:                   store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:               ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
+// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xindex>
+// CHECK:                 %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xindex>
+// CHECK:                 %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
+// CHECK:                 scf.if %[[VAL_56]] {
+// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                   %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                   %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32
+// CHECK:                   store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                 } else {
-// CHECK:                   %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                   scf.if %[[VAL_59]] {
-// CHECK:                     %[[VAL_60:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                     store %[[VAL_60]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:                   %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                   scf.if %[[VAL_60]] {
+// CHECK:                     %[[VAL_61:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                     store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                   } else {
-// CHECK:                     %[[VAL_61:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                     scf.if %[[VAL_61]] {
-// CHECK:                       %[[VAL_62:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                       store %[[VAL_62]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:                     %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                     scf.if %[[VAL_62]] {
+// CHECK:                       %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                       store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                     } else {
 // CHECK:                     }
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_63:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_64:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_47]] : index
-// CHECK:                 %[[VAL_66:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_67:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_48]] : index
-// CHECK:                 scf.yield %[[VAL_65]], %[[VAL_68]] : index, index
+// CHECK:                 %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index
+// CHECK:                 %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index
+// CHECK:                 scf.yield %[[VAL_66]], %[[VAL_69]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_69:.*]] = %[[VAL_70:.*]]#0 to %[[VAL_37]] step %[[VAL_4]] {
-// CHECK:                 %[[VAL_71:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_69]]] : memref<?xindex>
-// CHECK:                 %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_69]]] : memref<?xf32>
-// CHECK:                 store %[[VAL_72]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_71]]] : memref<32x16xf32>
+// CHECK:               scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_5]] {
+// CHECK:                 %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref<?xindex>
+// CHECK:                 %[[VAL_73:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_70]]] : memref<?xf32>
+// CHECK:                 store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32>
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_73:.*]] = %[[VAL_74:.*]]#1 to %[[VAL_40]] step %[[VAL_4]] {
-// CHECK:                 %[[VAL_75:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_73]]] : memref<?xindex>
-// CHECK:                 %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_73]]] : memref<?xf32>
-// CHECK:                 store %[[VAL_76]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_75]]] : memref<32x16xf32>
+// CHECK:               scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_5]] {
+// CHECK:                 %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref<?xindex>
+// CHECK:                 %[[VAL_77:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_74]]] : memref<?xf32>
+// CHECK:                 store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32>
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               %[[VAL_77:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:               scf.if %[[VAL_77]] {
-// CHECK:                 %[[VAL_78:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:                 %[[VAL_79:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_80:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_79]]] : memref<?xindex>
-// CHECK:                 scf.for %[[VAL_81:.*]] = %[[VAL_78]] to %[[VAL_80]] step %[[VAL_4]] {
-// CHECK:                   %[[VAL_82:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_81]]] : memref<?xindex>
-// CHECK:                   %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_81]]] : memref<?xf32>
-// CHECK:                   store %[[VAL_83]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_82]]] : memref<32x16xf32>
+// CHECK:               %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:               scf.if %[[VAL_78]] {
+// CHECK:                 %[[VAL_79:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:                 %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_81:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_80]]] : memref<?xindex>
+// CHECK:                 scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_5]] {
+// CHECK:                   %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref<?xindex>
+// CHECK:                   %[[VAL_84:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_82]]] : memref<?xf32>
+// CHECK:                   store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32>
 // CHECK:                 }
 // CHECK:               } else {
-// CHECK:                 %[[VAL_84:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:                 scf.if %[[VAL_84]] {
-// CHECK:                   %[[VAL_85:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:                   %[[VAL_86:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:                   %[[VAL_87:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_86]]] : memref<?xindex>
-// CHECK:                   scf.for %[[VAL_88:.*]] = %[[VAL_85]] to %[[VAL_87]] step %[[VAL_4]] {
-// CHECK:                     %[[VAL_89:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_88]]] : memref<?xindex>
-// CHECK:                     %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_88]]] : memref<?xf32>
-// CHECK:                     store %[[VAL_90]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_89]]] : memref<32x16xf32>
+// CHECK:                 %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:                 scf.if %[[VAL_85]] {
+// CHECK:                   %[[VAL_86:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:                   %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:                   %[[VAL_88:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_87]]] : memref<?xindex>
+// CHECK:                   scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_5]] {
+// CHECK:                     %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref<?xindex>
+// CHECK:                     %[[VAL_91:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_89]]] : memref<?xf32>
+// CHECK:                     store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32>
 // CHECK:                   }
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_91:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_92:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_93:.*]] = select %[[VAL_91]], %[[VAL_92]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_94:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_95:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_96:.*]] = select %[[VAL_94]], %[[VAL_95]], %[[VAL_27]] : index
-// CHECK:             scf.yield %[[VAL_93]], %[[VAL_96]] : index, index
+// CHECK:             %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index
+// CHECK:             scf.yield %[[VAL_94]], %[[VAL_97]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_97:.*]] = %[[VAL_98:.*]]#0 to %[[VAL_17]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_99:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_97]]] : memref<?xindex>
-// CHECK:             %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_97]]] : memref<?xindex>
-// CHECK:             %[[VAL_101:.*]] = addi %[[VAL_97]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_102:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_101]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_103:.*]] = %[[VAL_100]] to %[[VAL_102]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_104:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_103]]] : memref<?xindex>
-// CHECK:               %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_103]]] : memref<?xf32>
-// CHECK:               store %[[VAL_105]], %[[VAL_15]]{{\[}}%[[VAL_99]], %[[VAL_104]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref<?xindex>
+// CHECK:             %[[VAL_101:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_98]]] : memref<?xindex>
+// CHECK:             %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_103:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_102]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref<?xindex>
+// CHECK:               %[[VAL_106:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_104]]] : memref<?xf32>
+// CHECK:               store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_106:.*]] = %[[VAL_107:.*]]#1 to %[[VAL_19]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_108:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_106]]] : memref<?xindex>
-// CHECK:             %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_106]]] : memref<?xindex>
-// CHECK:             %[[VAL_110:.*]] = addi %[[VAL_106]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_111:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_110]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_112:.*]] = %[[VAL_109]] to %[[VAL_111]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_112]]] : memref<?xindex>
-// CHECK:               %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_112]]] : memref<?xf32>
-// CHECK:               store %[[VAL_114]], %[[VAL_15]]{{\[}}%[[VAL_108]], %[[VAL_113]]] : memref<32x16xf32>
+// CHECK:           scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref<?xindex>
+// CHECK:             %[[VAL_110:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_107]]] : memref<?xindex>
+// CHECK:             %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_112:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_111]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref<?xindex>
+// CHECK:               %[[VAL_115:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_113]]] : memref<?xf32>
+// CHECK:               store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_115:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_115]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_116:.*]] = tensor_load %[[VAL_16]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_116]] : tensor<32x16xf32>
 // CHECK:         }
-func @add_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @add_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
 }
 
 // CHECK-LABEL:   func @mul_sd_ds(
-// CHECK-SAME:                    %[[VAL_0:.*]]: tensor<32x16xf32>,
-// CHECK-SAME:                    %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
-// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
-// CHECK:             %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
-// CHECK:             scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK-SAME:                    %[[VAL_0:.*0]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_1:.*1]]: tensor<32x16xf32>,
+// CHECK-SAME:                    %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_20:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
+// CHECK:             %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
+// CHECK:             %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
+// CHECK:             scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
-// CHECK:             %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:             %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:             %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
-// CHECK:             %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
-// CHECK:             scf.if %[[VAL_34]] {
-// CHECK:               %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:               %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
-// CHECK:               %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:               %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
-// CHECK:               %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
-// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
-// CHECK:                 %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
-// CHECK:                 scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
+// CHECK:           ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
+// CHECK:             %[[VAL_29:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:             %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:             %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
+// CHECK:             %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
+// CHECK:             scf.if %[[VAL_35]] {
+// CHECK:               %[[VAL_36:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:               %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_38:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_37]]] : memref<?xindex>
+// CHECK:               %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:               %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref<?xindex>
+// CHECK:               %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
+// CHECK:                 %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
+// CHECK:                 %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
+// CHECK:                 scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
-// CHECK:                 %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
-// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
-// CHECK:                 %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
-// CHECK:                 %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
-// CHECK:                 scf.if %[[VAL_55]] {
-// CHECK:                   %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
-// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
-// CHECK:                   %[[VAL_58:.*]] = mulf %[[VAL_56]], %[[VAL_57]] : f32
-// CHECK:                   store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
+// CHECK:               ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
+// CHECK:                 %[[VAL_50:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xindex>
+// CHECK:                 %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xindex>
+// CHECK:                 %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
+// CHECK:                 %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
+// CHECK:                 scf.if %[[VAL_56]] {
+// CHECK:                   %[[VAL_57:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_48]]] : memref<?xf32>
+// CHECK:                   %[[VAL_58:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_49]]] : memref<?xf32>
+// CHECK:                   %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32
+// CHECK:                   store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
 // CHECK:                 } else {
 // CHECK:                 }
-// CHECK:                 %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_60:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_61:.*]] = select %[[VAL_59]], %[[VAL_60]], %[[VAL_47]] : index
-// CHECK:                 %[[VAL_62:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
-// CHECK:                 %[[VAL_63:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_64:.*]] = select %[[VAL_62]], %[[VAL_63]], %[[VAL_48]] : index
-// CHECK:                 scf.yield %[[VAL_61]], %[[VAL_64]] : index, index
+// CHECK:                 %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index
+// CHECK:                 %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
+// CHECK:                 %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index
+// CHECK:                 scf.yield %[[VAL_62]], %[[VAL_65]] : index, index
 // CHECK:               }
 // CHECK:             } else {
 // CHECK:             }
-// CHECK:             %[[VAL_65:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_66:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_67:.*]] = select %[[VAL_65]], %[[VAL_66]], %[[VAL_26]] : index
-// CHECK:             %[[VAL_68:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
-// CHECK:             %[[VAL_69:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_70:.*]] = select %[[VAL_68]], %[[VAL_69]], %[[VAL_27]] : index
-// CHECK:             scf.yield %[[VAL_67]], %[[VAL_70]] : index, index
+// CHECK:             %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index
+// CHECK:             %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
+// CHECK:             %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index
+// CHECK:             scf.yield %[[VAL_68]], %[[VAL_71]] : index, index
 // CHECK:           }
-// CHECK:           %[[VAL_71:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
-// CHECK:           return %[[VAL_71]] : tensor<32x16xf32>
+// CHECK:           %[[VAL_72:.*]] = tensor_load %[[VAL_16]] : memref<32x16xf32>
+// CHECK:           return %[[VAL_72]] : tensor<32x16xf32>
 // CHECK:         }
-func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
+func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   %0 = linalg.generic #trait_ss_ss
      ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
-    outs(%arga : tensor<32x16xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -1028,9 +1040,9 @@ func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32
 }
 
 // CHECK-LABEL:   func @matvec(
-// CHECK-SAME:                 %[[VAL_0:.*]]: tensor<16x32xf32>,
-// CHECK-SAME:                 %[[VAL_1:.*]]: tensor<32xf32>,
-// CHECK-SAME:                 %[[VAL_2:.*]]: tensor<16xf32>) -> tensor<16xf32> {
+// CHECK-SAME:                 %[[VAL_0:.*0]]: tensor<16x32xf32>,
+// CHECK-SAME:                 %[[VAL_1:.*1]]: tensor<32xf32>,
+// CHECK-SAME:                 %[[VAL_2:.*2]]: tensor<16xf32>) -> tensor<16xf32> {
 // CHECK:           %[[VAL_3:.*]] = constant 999 : index
 // CHECK:           %[[VAL_4:.*]] = constant 16 : index
 // CHECK:           %[[VAL_5:.*]] = constant 0 : index
@@ -1060,8 +1072,8 @@ func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32
 // CHECK:         }
 func @matvec(%argA: tensor<16x32xf32>, %argb: tensor<32xf32>, %argx: tensor<16xf32>) -> tensor<16xf32> {
   %0 = linalg.generic #trait_matvec
-       ins(%argA, %argb : tensor<16x32xf32>, tensor<32xf32>)
-      outs(%argx : tensor<16xf32>) {
+       ins(%argA, %argb: tensor<16x32xf32>, tensor<32xf32>)
+      outs(%argx: tensor<16xf32>) {
     ^bb(%A: f32, %b: f32, %x: f32):
       %0 = mulf %A, %b : f32
       %1 = addf %0, %x : f32
@@ -1091,30 +1103,30 @@ func @matvec(%argA: tensor<16x32xf32>, %argb: tensor<32xf32>, %argx: tensor<16xf
 // CHECK:           %[[VAL_4:.*]] = constant 0 : index
 // CHECK:           %[[VAL_5:.*]] = constant 1 : index
 // CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca() : memref<f32>
-// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xindex>
-// CHECK:             %[[VAL_12:.*]] = addi %[[VAL_10]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_9]][] : memref<f32>
-// CHECK:             %[[VAL_15:.*]] = scf.for %[[VAL_16:.*]] = %[[VAL_11]] to %[[VAL_13]] step %[[VAL_5]] iter_args(%[[VAL_17:.*]] = %[[VAL_14]]) -> (f32) {
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xf32>
-// CHECK:               %[[VAL_19:.*]] = addf %[[VAL_17]], %[[VAL_18]] : f32
-// CHECK:               scf.yield %[[VAL_19]] : f32
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
+// CHECK:           %[[VAL_8:.*]] = alloca() : memref<f32>
+// CHECK:           scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_10:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]]] : memref<?xindex>
+// CHECK:             %[[VAL_11:.*]] = addi %[[VAL_9]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref<?xindex>
+// CHECK:             %[[VAL_13:.*]] = load %[[VAL_8]][] : memref<f32>
+// CHECK:             %[[VAL_14:.*]] = scf.for %[[VAL_15:.*]] = %[[VAL_10]] to %[[VAL_12]] step %[[VAL_5]] iter_args(%[[VAL_16:.*]] = %[[VAL_13]]) -> (f32) {
+// CHECK:               %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xf32>
+// CHECK:               %[[VAL_18:.*]] = addf %[[VAL_16]], %[[VAL_17]] : f32
+// CHECK:               scf.yield %[[VAL_18]] : f32
 // CHECK:             }
-// CHECK:             store %[[VAL_20:.*]], %[[VAL_9]][] : memref<f32>
+// CHECK:             store %[[VAL_19:.*]], %[[VAL_8]][] : memref<f32>
 // CHECK:           }
-// CHECK:           %[[VAL_21:.*]] = tensor_load %[[VAL_9]] : memref<f32>
-// CHECK:           return %[[VAL_21]] : tensor<f32>
+// CHECK:           %[[VAL_20:.*]] = tensor_load %[[VAL_8]] : memref<f32>
+// CHECK:           return %[[VAL_20]] : tensor<f32>
 // CHECK:         }
 func @sum_reduction(%arga: tensor<10x20xf32>, %argx: tensor<f32>) -> tensor<f32> {
   %0 = linalg.generic #trait_sum_reduction
-     ins(%arga : tensor<10x20xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %x : f32):
-        %0 = addf %x, %a  : f32
-        linalg.yield %0: f32
+     ins(%arga: tensor<10x20xf32>)
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %x, %a : f32
+        linalg.yield %0 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }
@@ -1133,38 +1145,39 @@ func @sum_reduction(%arga: tensor<10x20xf32>, %argx: tensor<f32>) -> tensor<f32>
 }
 
 // CHECK-LABEL:   func @scale(
-// CHECK-SAME:                %[[VAL_0:.*]]: tensor<?x?xf64>) -> tensor<?x?xf64> {
-// CHECK:           %[[VAL_1:.*]] = constant 2.000000e+00 : f64
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf64>
-// CHECK:           %[[VAL_8:.*]] = dim %[[VAL_0]], %[[VAL_3]] : tensor<?x?xf64>
-// CHECK:           %[[VAL_9:.*]] = dim %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf64>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_8]], %[[VAL_9]]) : memref<?x?xf64>
-// CHECK:           scf.for %[[VAL_11:.*]] = %[[VAL_3]] to %[[VAL_8]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xindex>
-// CHECK:             %[[VAL_13:.*]] = addi %[[VAL_11]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_13]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_15:.*]] = %[[VAL_12]] to %[[VAL_14]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:               %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xf64>
-// CHECK:               %[[VAL_18:.*]] = mulf %[[VAL_17]], %[[VAL_1]] : f64
-// CHECK:               store %[[VAL_18]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<?x?xf64>
+// CHECK-SAME:                %[[VAL_0:.*]]: tensor<?x?xf64>,
+// CHECK-SAME:                %[[VAL_1:.*]]: tensor<?x?xf64>) -> tensor<?x?xf64> {
+// CHECK:           %[[VAL_2:.*]] = constant 2.000000e+00 : f64
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xf64>
+// CHECK:           %[[VAL_9:.*]] = dim %[[VAL_1]], %[[VAL_4]] : tensor<?x?xf64>
+// CHECK:           %[[VAL_10:.*]] = dim %[[VAL_1]], %[[VAL_5]] : tensor<?x?xf64>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_9]], %[[VAL_10]]) : memref<?x?xf64>
+// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_9]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
+// CHECK:             %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:               %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xf64>
+// CHECK:               %[[VAL_19:.*]] = mulf %[[VAL_18]], %[[VAL_2]] : f64
+// CHECK:               store %[[VAL_19]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<?x?xf64>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_19:.*]] = tensor_load %[[VAL_10]] : memref<?x?xf64>
-// CHECK:           return %[[VAL_19]] : tensor<?x?xf64>
+// CHECK:           %[[VAL_20:.*]] = tensor_load %[[VAL_11]] : memref<?x?xf64>
+// CHECK:           return %[[VAL_20]] : tensor<?x?xf64>
 // CHECK:         }
-func @scale(%arga: tensor<?x?xf64>) -> tensor<?x?xf64> {
+func @scale(%arga: tensor<?x?xf64>, %argx: tensor<?x?xf64>) -> tensor<?x?xf64> {
   %0 = constant 2.0 : f64
   %1 = linalg.generic #trait_scale
      ins(%arga: tensor<?x?xf64>)
-    outs(%arga: tensor<?x?xf64>) {
-      ^bb(%a: f64, %s: f64):
-        %2 = mulf %a, %0  : f64
+    outs(%argx: tensor<?x?xf64>) {
+      ^bb(%a: f64, %x: f64):
+        %2 = mulf %a, %0 : f64
         linalg.yield %2 : f64
   } -> tensor<?x?xf64>
   return %1 : tensor<?x?xf64>
@@ -1238,13 +1251,13 @@ func @sampled_dense_dense(%args: tensor<?x?xf32>,
                           %argb: tensor<?x?xf32>,
                           %argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
   %0 = linalg.generic #trait_sampled_dense_dense
-     ins(%args, %arga, %argb : tensor<?x?xf32>, tensor<?x?xf32>, tensor<?x?xf32>)
-    outs(%argx : tensor<?x?xf32>) {
-      ^bb(%s : f32, %a : f32, %b : f32, %x : f32):
-        %0 = mulf %a, %b  : f32
-        %1 = mulf %s, %0  : f32
-        %2 = addf %x, %1  : f32
-        linalg.yield %2: f32
+     ins(%args, %arga, %argb: tensor<?x?xf32>, tensor<?x?xf32>, tensor<?x?xf32>)
+    outs(%argx: tensor<?x?xf32>) {
+      ^bb(%s: f32, %a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
+        %1 = mulf %s, %0 : f32
+        %2 = addf %x, %1 : f32
+        linalg.yield %2 : f32
   } -> tensor<?x?xf32>
   return %0 : tensor<?x?xf32>
 }
@@ -1469,14 +1482,14 @@ func @sum_kernel_with_inv(%arga: tensor<?x?xf32>,
                                             tensor<?x?xf32>,
                                             tensor<?xf32>,
                                             tensor<f32>)
-    outs(%argx : tensor<?xf32>) {
-      ^bb(%a : f32, %b : f32, %c : f32, %d : f32, %e : f32, %x : f32):
-        %0 = mulf %a, %b  : f32
-        %1 = mulf %0, %d  : f32
-        %2 = mulf %1, %e  : f32
-        %3 = addf %2, %c  : f32
-        %4 = addf %x, %3  : f32
-        linalg.yield %4: f32
+    outs(%argx: tensor<?xf32>) {
+      ^bb(%a: f32, %b: f32, %c: f32, %d: f32, %e: f32, %x: f32):
+        %0 = mulf %a, %b : f32
+        %1 = mulf %0, %d : f32
+        %2 = mulf %1, %e : f32
+        %3 = addf %2, %c : f32
+        %4 = addf %x, %3 : f32
+        linalg.yield %4 : f32
   } -> tensor<?xf32>
   return %0 : tensor<?xf32>
 }

diff  --git a/mlir/test/Dialect/Linalg/sparse_3d.mlir b/mlir/test/Dialect/Linalg/sparse_3d.mlir
index 02ee2a8b1740..6526fa872128 100644
--- a/mlir/test/Dialect/Linalg/sparse_3d.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_3d.mlir
@@ -17,70 +17,72 @@
 }
 
 // CHECK-LABEL:   func @add_ddd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 8 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 8 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
 // CHECK:           %[[VAL_8:.*]] = alloca() : memref<32x16x8xf32>
 // CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_2]] step %[[VAL_6]] {
-// CHECK:             scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:               scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
-// CHECK:                 %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32
-// CHECK:                 store %[[VAL_15]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_11:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] {
+// CHECK:             scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:               scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
+// CHECK:                 %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_16:.*]] = addf %[[VAL_14]], %[[VAL_15]] : f32
+// CHECK:                 store %[[VAL_16]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_16:.*]] = tensor_load %[[VAL_9]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_16]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_17:.*]] = tensor_load %[[VAL_10]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_17]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_ddd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s: f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_ddd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 32 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 8 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 32 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 8 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
 // CHECK:           %[[VAL_8:.*]] = alloca() : memref<32x16x8xf32>
 // CHECK:           %[[VAL_9:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_10:.*]] = %[[VAL_5]] to %[[VAL_2]] step %[[VAL_6]] {
-// CHECK:             scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:               scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
-// CHECK:                 %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_15:.*]] = mulf %[[VAL_13]], %[[VAL_14]] : f32
-// CHECK:                 store %[[VAL_15]], %[[VAL_9]]{{\[}}%[[VAL_10]], %[[VAL_11]], %[[VAL_12]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_11:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] {
+// CHECK:             scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:               scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
+// CHECK:                 %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_16:.*]] = mulf %[[VAL_14]], %[[VAL_15]] : f32
+// CHECK:                 store %[[VAL_16]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]], %[[VAL_13]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_16:.*]] = tensor_load %[[VAL_9]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_16]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_17:.*]] = tensor_load %[[VAL_10]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_17]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_ddd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -102,110 +104,112 @@ func @mul_ddd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_dds(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant 0 : index
-// CHECK:           %[[VAL_7:.*]] = constant true
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant 0 : index
+// CHECK:           %[[VAL_8:.*]] = constant true
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             scf.for %[[VAL_15:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               %[[VAL_16:.*]] = muli %[[VAL_14]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_17:.*]] = addi %[[VAL_16]], %[[VAL_15]] : index
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:               %[[VAL_19:.*]] = addi %[[VAL_17]], %[[VAL_8]] : index
-// CHECK:               %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:               %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_18]], %[[VAL_23:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_20]] : index
-// CHECK:                 scf.condition(%[[VAL_24]]) %[[VAL_22]], %[[VAL_23]] : index, index
+// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               %[[VAL_17:.*]] = muli %[[VAL_15]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:               %[[VAL_20:.*]] = addi %[[VAL_18]], %[[VAL_9]] : index
+// CHECK:               %[[VAL_21:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:               %[[VAL_22:.*]]:2 = scf.while (%[[VAL_23:.*]] = %[[VAL_19]], %[[VAL_24:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_21]] : index
+// CHECK:                 scf.condition(%[[VAL_25]]) %[[VAL_23]], %[[VAL_24]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index):
-// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xindex>
-// CHECK:                 %[[VAL_28:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:                 scf.if %[[VAL_28]] {
-// CHECK:                   %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_26]]] : memref<32x16x8xf32>
-// CHECK:                   %[[VAL_31:.*]] = addf %[[VAL_29]], %[[VAL_30]] : f32
-// CHECK:                   store %[[VAL_31]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_26]]] : memref<32x16x8xf32>
+// CHECK:               ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
+// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref<?xindex>
+// CHECK:                 %[[VAL_29:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:                 scf.if %[[VAL_29]] {
+// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xf32>
+// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32>
+// CHECK:                   %[[VAL_32:.*]] = addf %[[VAL_30]], %[[VAL_31]] : f32
+// CHECK:                   store %[[VAL_32]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32>
 // CHECK:                 } else {
-// CHECK:                   scf.if %[[VAL_7]] {
-// CHECK:                     %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_26]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_32]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_26]]] : memref<32x16x8xf32>
+// CHECK:                   scf.if %[[VAL_8]] {
+// CHECK:                     %[[VAL_33:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_33]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_27]]] : memref<32x16x8xf32>
 // CHECK:                   } else {
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_33:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:                 %[[VAL_34:.*]] = addi %[[VAL_25]], %[[VAL_8]] : index
-// CHECK:                 %[[VAL_35:.*]] = select %[[VAL_33]], %[[VAL_34]], %[[VAL_25]] : index
-// CHECK:                 %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_8]] : index
-// CHECK:                 scf.yield %[[VAL_35]], %[[VAL_36]] : index, index
+// CHECK:                 %[[VAL_34:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:                 %[[VAL_35:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index
+// CHECK:                 %[[VAL_36:.*]] = select %[[VAL_34]], %[[VAL_35]], %[[VAL_26]] : index
+// CHECK:                 %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_9]] : index
+// CHECK:                 scf.yield %[[VAL_36]], %[[VAL_37]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_37:.*]] = %[[VAL_38:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_39:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_37]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_15]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:               scf.for %[[VAL_38:.*]] = %[[VAL_39:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_38]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_40]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_38]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_40:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_40]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_41:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_41]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dds
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_dds(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:             scf.for %[[VAL_13:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
-// CHECK:               %[[VAL_14:.*]] = muli %[[VAL_12]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_15:.*]] = addi %[[VAL_14]], %[[VAL_13]] : index
-// CHECK:               %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:               %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_6]] : index
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_19:.*]] = %[[VAL_16]] to %[[VAL_18]] step %[[VAL_6]] {
-// CHECK:                 %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:                 %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xf32>
-// CHECK:                 %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_20]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32
-// CHECK:                 store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_13]], %[[VAL_20]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:             scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
+// CHECK:               %[[VAL_15:.*]] = muli %[[VAL_13]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_16:.*]] = addi %[[VAL_15]], %[[VAL_14]] : index
+// CHECK:               %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:               %[[VAL_18:.*]] = addi %[[VAL_16]], %[[VAL_7]] : index
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_7]] {
+// CHECK:                 %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:                 %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<?xf32>
+// CHECK:                 %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_14]], %[[VAL_21]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32
+// CHECK:                 store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_14]], %[[VAL_21]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_24:.*]] = tensor_load %[[VAL_11]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_24]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_25:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_25]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dds
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -227,114 +231,116 @@ func @mul_dds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_dsd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_7]] to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<?xindex>
-// CHECK:             %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref<?xindex>
-// CHECK:             %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:               %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
-// CHECK:               scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
+// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_8]] to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]]] : memref<?xindex>
+// CHECK:             %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_17]]] : memref<?xindex>
+// CHECK:             %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_16]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:               %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index
+// CHECK:               scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index
 // CHECK:             } do {
-// CHECK:             ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
-// CHECK:               %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:               %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:               scf.if %[[VAL_25]] {
-// CHECK:                 scf.for %[[VAL_26:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_27:.*]] = muli %[[VAL_22]], %[[VAL_5]] : index
-// CHECK:                   %[[VAL_28:.*]] = addi %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:                   %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xf32>
-// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]], %[[VAL_26]]] : memref<32x16x8xf32>
-// CHECK:                   %[[VAL_31:.*]] = addf %[[VAL_29]], %[[VAL_30]] : f32
-// CHECK:                   store %[[VAL_31]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]], %[[VAL_26]]] : memref<32x16x8xf32>
+// CHECK:             ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index):
+// CHECK:               %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:               %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:               scf.if %[[VAL_26]] {
+// CHECK:                 scf.for %[[VAL_27:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_28:.*]] = muli %[[VAL_23]], %[[VAL_6]] : index
+// CHECK:                   %[[VAL_29:.*]] = addi %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_29]]] : memref<?xf32>
+// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32>
+// CHECK:                   %[[VAL_32:.*]] = addf %[[VAL_30]], %[[VAL_31]] : f32
+// CHECK:                   store %[[VAL_32]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               } else {
-// CHECK:                 scf.if %[[VAL_6]] {
-// CHECK:                   scf.for %[[VAL_32:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_33:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_23]], %[[VAL_32]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_33]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]], %[[VAL_32]]] : memref<32x16x8xf32>
+// CHECK:                 scf.if %[[VAL_7]] {
+// CHECK:                   scf.for %[[VAL_33:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_34:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_33]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_34]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_24]], %[[VAL_33]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
-// CHECK:               %[[VAL_34:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:               %[[VAL_35:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
-// CHECK:               %[[VAL_36:.*]] = select %[[VAL_34]], %[[VAL_35]], %[[VAL_22]] : index
-// CHECK:               %[[VAL_37:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index
-// CHECK:               scf.yield %[[VAL_36]], %[[VAL_37]] : index, index
+// CHECK:               %[[VAL_35:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:               %[[VAL_36:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index
+// CHECK:               %[[VAL_37:.*]] = select %[[VAL_35]], %[[VAL_36]], %[[VAL_23]] : index
+// CHECK:               %[[VAL_38:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index
+// CHECK:               scf.yield %[[VAL_37]], %[[VAL_38]] : index, index
 // CHECK:             }
-// CHECK:             scf.for %[[VAL_38:.*]] = %[[VAL_39:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_40:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_41:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_38]], %[[VAL_40]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_41]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_38]], %[[VAL_40]]] : memref<32x16x8xf32>
+// CHECK:             scf.for %[[VAL_39:.*]] = %[[VAL_40:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_41:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_42:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_15]], %[[VAL_39]], %[[VAL_41]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_42]], %[[VAL_14]]{{\[}}%[[VAL_15]], %[[VAL_39]], %[[VAL_41]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_42:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_42]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_43:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_43]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_dsd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_dsd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dsd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_dsd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 8 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 8 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xindex>
-// CHECK:             %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_6]] : index
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_6]] {
-// CHECK:               %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_18:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
-// CHECK:                 %[[VAL_19:.*]] = muli %[[VAL_16]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_20:.*]] = addi %[[VAL_19]], %[[VAL_18]] : index
-// CHECK:                 %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xf32>
-// CHECK:                 %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_12]], %[[VAL_17]], %[[VAL_18]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32
-// CHECK:                 store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]], %[[VAL_18]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<?xindex>
+// CHECK:             %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_7]] : index
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_17:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_7]] {
+// CHECK:               %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_19:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
+// CHECK:                 %[[VAL_20:.*]] = muli %[[VAL_17]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_21:.*]] = addi %[[VAL_20]], %[[VAL_19]] : index
+// CHECK:                 %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xf32>
+// CHECK:                 %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_19]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32
+// CHECK:                 store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_19]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_24:.*]] = tensor_load %[[VAL_11]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_24]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_25:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_25]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_dsd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_dsd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dsd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -356,143 +362,145 @@ func @mul_dsd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_dss(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_16:.*]] = %[[VAL_7]] to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref<?xindex>
-// CHECK:             %[[VAL_18:.*]] = addi %[[VAL_16]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex>
-// CHECK:             %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_17]], %[[VAL_22:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:               %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_19]] : index
-// CHECK:               scf.condition(%[[VAL_23]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_17:.*]] = %[[VAL_8]] to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_17]]] : memref<?xindex>
+// CHECK:             %[[VAL_19:.*]] = addi %[[VAL_17]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_19]]] : memref<?xindex>
+// CHECK:             %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_18]], %[[VAL_23:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:               %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_20]] : index
+// CHECK:               scf.condition(%[[VAL_24]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:             } do {
-// CHECK:             ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index):
-// CHECK:               %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:               %[[VAL_27:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index
-// CHECK:               scf.if %[[VAL_27]] {
-// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:                 %[[VAL_29:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index
-// CHECK:                 %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_29]]] : memref<?xindex>
-// CHECK:                 %[[VAL_31:.*]]:2 = scf.while (%[[VAL_32:.*]] = %[[VAL_28]], %[[VAL_33:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:                   %[[VAL_34:.*]] = cmpi ult, %[[VAL_32]], %[[VAL_30]] : index
-// CHECK:                   scf.condition(%[[VAL_34]]) %[[VAL_32]], %[[VAL_33]] : index, index
+// CHECK:             ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index):
+// CHECK:               %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:               %[[VAL_28:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
+// CHECK:               scf.if %[[VAL_28]] {
+// CHECK:                 %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:                 %[[VAL_30:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index
+// CHECK:                 %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref<?xindex>
+// CHECK:                 %[[VAL_32:.*]]:2 = scf.while (%[[VAL_33:.*]] = %[[VAL_29]], %[[VAL_34:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:                   %[[VAL_35:.*]] = cmpi ult, %[[VAL_33]], %[[VAL_31]] : index
+// CHECK:                   scf.condition(%[[VAL_35]]) %[[VAL_33]], %[[VAL_34]] : index, index
 // CHECK:                 } do {
-// CHECK:                 ^bb0(%[[VAL_35:.*]]: index, %[[VAL_36:.*]]: index):
-// CHECK:                   %[[VAL_37:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_35]]] : memref<?xindex>
-// CHECK:                   %[[VAL_38:.*]] = cmpi eq, %[[VAL_37]], %[[VAL_36]] : index
-// CHECK:                   scf.if %[[VAL_38]] {
-// CHECK:                     %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_35]]] : memref<?xf32>
-// CHECK:                     %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_36]]] : memref<32x16x8xf32>
-// CHECK:                     %[[VAL_41:.*]] = addf %[[VAL_39]], %[[VAL_40]] : f32
-// CHECK:                     store %[[VAL_41]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_36]]] : memref<32x16x8xf32>
+// CHECK:                 ^bb0(%[[VAL_36:.*]]: index, %[[VAL_37:.*]]: index):
+// CHECK:                   %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_36]]] : memref<?xindex>
+// CHECK:                   %[[VAL_39:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
+// CHECK:                   scf.if %[[VAL_39]] {
+// CHECK:                     %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_36]]] : memref<?xf32>
+// CHECK:                     %[[VAL_41:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:                     %[[VAL_42:.*]] = addf %[[VAL_40]], %[[VAL_41]] : f32
+// CHECK:                     store %[[VAL_42]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
 // CHECK:                   } else {
-// CHECK:                     scf.if %[[VAL_6]] {
-// CHECK:                       %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_36]]] : memref<32x16x8xf32>
-// CHECK:                       store %[[VAL_42]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_36]]] : memref<32x16x8xf32>
+// CHECK:                     scf.if %[[VAL_7]] {
+// CHECK:                       %[[VAL_43:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:                       store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
 // CHECK:                     } else {
 // CHECK:                     }
 // CHECK:                   }
-// CHECK:                   %[[VAL_43:.*]] = cmpi eq, %[[VAL_37]], %[[VAL_36]] : index
-// CHECK:                   %[[VAL_44:.*]] = addi %[[VAL_35]], %[[VAL_8]] : index
-// CHECK:                   %[[VAL_45:.*]] = select %[[VAL_43]], %[[VAL_44]], %[[VAL_35]] : index
-// CHECK:                   %[[VAL_46:.*]] = addi %[[VAL_36]], %[[VAL_8]] : index
-// CHECK:                   scf.yield %[[VAL_45]], %[[VAL_46]] : index, index
+// CHECK:                   %[[VAL_44:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
+// CHECK:                   %[[VAL_45:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index
+// CHECK:                   %[[VAL_46:.*]] = select %[[VAL_44]], %[[VAL_45]], %[[VAL_36]] : index
+// CHECK:                   %[[VAL_47:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index
+// CHECK:                   scf.yield %[[VAL_46]], %[[VAL_47]] : index, index
 // CHECK:                 }
-// CHECK:                 scf.for %[[VAL_47:.*]] = %[[VAL_48:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_49:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_47]]] : memref<32x16x8xf32>
-// CHECK:                   store %[[VAL_49]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_47]]] : memref<32x16x8xf32>
+// CHECK:                 scf.for %[[VAL_48:.*]] = %[[VAL_49:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_50:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32>
+// CHECK:                   store %[[VAL_50]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               } else {
-// CHECK:                 scf.if %[[VAL_6]] {
-// CHECK:                   scf.for %[[VAL_50:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_51:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_50]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_51]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_25]], %[[VAL_50]]] : memref<32x16x8xf32>
+// CHECK:                 scf.if %[[VAL_7]] {
+// CHECK:                   scf.for %[[VAL_51:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_52:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_51]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_52]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_26]], %[[VAL_51]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 } else {
 // CHECK:                 }
 // CHECK:               }
-// CHECK:               %[[VAL_52:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index
-// CHECK:               %[[VAL_53:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index
-// CHECK:               %[[VAL_54:.*]] = select %[[VAL_52]], %[[VAL_53]], %[[VAL_24]] : index
-// CHECK:               %[[VAL_55:.*]] = addi %[[VAL_25]], %[[VAL_8]] : index
-// CHECK:               scf.yield %[[VAL_54]], %[[VAL_55]] : index, index
+// CHECK:               %[[VAL_53:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
+// CHECK:               %[[VAL_54:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index
+// CHECK:               %[[VAL_55:.*]] = select %[[VAL_53]], %[[VAL_54]], %[[VAL_25]] : index
+// CHECK:               %[[VAL_56:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index
+// CHECK:               scf.yield %[[VAL_55]], %[[VAL_56]] : index, index
 // CHECK:             }
-// CHECK:             scf.for %[[VAL_56:.*]] = %[[VAL_57:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_58:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_59:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_16]], %[[VAL_56]], %[[VAL_58]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_59]], %[[VAL_15]]{{\[}}%[[VAL_16]], %[[VAL_56]], %[[VAL_58]]] : memref<32x16x8xf32>
+// CHECK:             scf.for %[[VAL_57:.*]] = %[[VAL_58:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_59:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_60:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_17]], %[[VAL_57]], %[[VAL_59]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_60]], %[[VAL_16]]{{\[}}%[[VAL_17]], %[[VAL_57]], %[[VAL_59]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_60:.*]] = tensor_load %[[VAL_15]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_60]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_61:.*]] = tensor_load %[[VAL_16]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_61]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dss
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_dss(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_13]]] : memref<?xindex>
-// CHECK:             %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_17:.*]] = %[[VAL_14]] to %[[VAL_16]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:               %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:               %[[VAL_20:.*]] = addi %[[VAL_17]], %[[VAL_5]] : index
-// CHECK:               %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_22:.*]] = %[[VAL_19]] to %[[VAL_21]] step %[[VAL_5]] {
-// CHECK:                 %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:                 %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xf32>
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_23]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_26:.*]] = mulf %[[VAL_24]], %[[VAL_25]] : f32
-// CHECK:                 store %[[VAL_26]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_18]], %[[VAL_23]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_18:.*]] = %[[VAL_15]] to %[[VAL_17]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:               %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:               %[[VAL_21:.*]] = addi %[[VAL_18]], %[[VAL_6]] : index
+// CHECK:               %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_23:.*]] = %[[VAL_20]] to %[[VAL_22]] step %[[VAL_6]] {
+// CHECK:                 %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref<?xf32>
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_14]], %[[VAL_19]], %[[VAL_24]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_27:.*]] = mulf %[[VAL_25]], %[[VAL_26]] : f32
+// CHECK:                 store %[[VAL_27]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_19]], %[[VAL_24]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_27:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_27]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_28:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_28]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_dss
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -514,120 +522,122 @@ func @mul_dss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_sdd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_14]], %[[VAL_18:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_15]] : index
-// CHECK:             scf.condition(%[[VAL_19]]) %[[VAL_17]], %[[VAL_18]] : index, index
+// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_15]], %[[VAL_19:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index
+// CHECK:             scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_20:.*]]: index, %[[VAL_21:.*]]: index):
-// CHECK:             %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_20]]] : memref<?xindex>
-// CHECK:             %[[VAL_23:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
-// CHECK:             scf.if %[[VAL_23]] {
-// CHECK:               scf.for %[[VAL_24:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_25:.*]] = muli %[[VAL_20]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_26:.*]] = addi %[[VAL_25]], %[[VAL_24]] : index
-// CHECK:                 scf.for %[[VAL_27:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_28:.*]] = muli %[[VAL_26]], %[[VAL_5]] : index
-// CHECK:                   %[[VAL_29:.*]] = addi %[[VAL_28]], %[[VAL_27]] : index
-// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_29]]] : memref<?xf32>
-// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32>
-// CHECK:                   %[[VAL_32:.*]] = addf %[[VAL_30]], %[[VAL_31]] : f32
-// CHECK:                   store %[[VAL_32]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_24]], %[[VAL_27]]] : memref<32x16x8xf32>
+// CHECK:           ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index):
+// CHECK:             %[[VAL_23:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_21]]] : memref<?xindex>
+// CHECK:             %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
+// CHECK:             scf.if %[[VAL_24]] {
+// CHECK:               scf.for %[[VAL_25:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_26:.*]] = muli %[[VAL_21]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_27:.*]] = addi %[[VAL_26]], %[[VAL_25]] : index
+// CHECK:                 scf.for %[[VAL_28:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_29:.*]] = muli %[[VAL_27]], %[[VAL_6]] : index
+// CHECK:                   %[[VAL_30:.*]] = addi %[[VAL_29]], %[[VAL_28]] : index
+// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref<?xf32>
+// CHECK:                   %[[VAL_32:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_25]], %[[VAL_28]]] : memref<32x16x8xf32>
+// CHECK:                   %[[VAL_33:.*]] = addf %[[VAL_31]], %[[VAL_32]] : f32
+// CHECK:                   store %[[VAL_33]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_25]], %[[VAL_28]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_6]] {
-// CHECK:                 scf.for %[[VAL_33:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                   scf.for %[[VAL_34:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_21]], %[[VAL_33]], %[[VAL_34]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_35]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_33]], %[[VAL_34]]] : memref<32x16x8xf32>
+// CHECK:               scf.if %[[VAL_7]] {
+// CHECK:                 scf.for %[[VAL_34:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                   scf.for %[[VAL_35:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_36:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_34]], %[[VAL_35]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_36]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_34]], %[[VAL_35]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_36:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
-// CHECK:             %[[VAL_37:.*]] = addi %[[VAL_20]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_38:.*]] = select %[[VAL_36]], %[[VAL_37]], %[[VAL_20]] : index
-// CHECK:             %[[VAL_39:.*]] = addi %[[VAL_21]], %[[VAL_8]] : index
-// CHECK:             scf.yield %[[VAL_38]], %[[VAL_39]] : index, index
+// CHECK:             %[[VAL_37:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
+// CHECK:             %[[VAL_38:.*]] = addi %[[VAL_21]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_39:.*]] = select %[[VAL_37]], %[[VAL_38]], %[[VAL_21]] : index
+// CHECK:             %[[VAL_40:.*]] = addi %[[VAL_22]], %[[VAL_9]] : index
+// CHECK:             scf.yield %[[VAL_39]], %[[VAL_40]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_40:.*]] = %[[VAL_41:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             scf.for %[[VAL_42:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_43:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_44:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_40]], %[[VAL_42]], %[[VAL_43]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_44]], %[[VAL_13]]{{\[}}%[[VAL_40]], %[[VAL_42]], %[[VAL_43]]] : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_41:.*]] = %[[VAL_42:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             scf.for %[[VAL_43:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_44:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_45:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_41]], %[[VAL_43]], %[[VAL_44]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_45]], %[[VAL_14]]{{\[}}%[[VAL_41]], %[[VAL_43]], %[[VAL_44]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_45:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_45]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_46:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_46]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_sdd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_sdd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sdd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_sdd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 8 : index
-// CHECK:           %[[VAL_5:.*]] = constant 0 : index
-// CHECK:           %[[VAL_6:.*]] = constant 1 : index
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 8 : index
+// CHECK:           %[[VAL_6:.*]] = constant 0 : index
+// CHECK:           %[[VAL_7:.*]] = constant 1 : index
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_6]] {
-// CHECK:             %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
-// CHECK:               %[[VAL_17:.*]] = muli %[[VAL_14]], %[[VAL_3]] : index
-// CHECK:               %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index
-// CHECK:               scf.for %[[VAL_19:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
-// CHECK:                 %[[VAL_20:.*]] = muli %[[VAL_18]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_21:.*]] = addi %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:                 %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xf32>
-// CHECK:                 %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_19]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32
-// CHECK:                 store %[[VAL_24]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_16]], %[[VAL_19]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_7]] {
+// CHECK:             %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_15]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_17:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
+// CHECK:               %[[VAL_18:.*]] = muli %[[VAL_15]], %[[VAL_4]] : index
+// CHECK:               %[[VAL_19:.*]] = addi %[[VAL_18]], %[[VAL_17]] : index
+// CHECK:               scf.for %[[VAL_20:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
+// CHECK:                 %[[VAL_21:.*]] = muli %[[VAL_19]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_22:.*]] = addi %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:                 %[[VAL_23:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xf32>
+// CHECK:                 %[[VAL_24:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_20]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_25:.*]] = mulf %[[VAL_23]], %[[VAL_24]] : f32
+// CHECK:                 store %[[VAL_25]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_20]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_25:.*]] = tensor_load %[[VAL_11]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_25]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_26:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_26]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_sdd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_sdd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sdd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -649,149 +659,151 @@ func @mul_sdd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_sds(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
-// CHECK:             scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_17]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index
+// CHECK:             scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
-// CHECK:             %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:             %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:             scf.if %[[VAL_25]] {
-// CHECK:               scf.for %[[VAL_26:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_27:.*]] = muli %[[VAL_22]], %[[VAL_4]] : index
-// CHECK:                 %[[VAL_28:.*]] = addi %[[VAL_27]], %[[VAL_26]] : index
-// CHECK:                 %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xindex>
-// CHECK:                 %[[VAL_30:.*]] = addi %[[VAL_28]], %[[VAL_8]] : index
-// CHECK:                 %[[VAL_31:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref<?xindex>
-// CHECK:                 %[[VAL_32:.*]]:2 = scf.while (%[[VAL_33:.*]] = %[[VAL_29]], %[[VAL_34:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:                   %[[VAL_35:.*]] = cmpi ult, %[[VAL_33]], %[[VAL_31]] : index
-// CHECK:                   scf.condition(%[[VAL_35]]) %[[VAL_33]], %[[VAL_34]] : index, index
+// CHECK:           ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index):
+// CHECK:             %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:             %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:             scf.if %[[VAL_26]] {
+// CHECK:               scf.for %[[VAL_27:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_28:.*]] = muli %[[VAL_23]], %[[VAL_5]] : index
+// CHECK:                 %[[VAL_29:.*]] = addi %[[VAL_28]], %[[VAL_27]] : index
+// CHECK:                 %[[VAL_30:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_29]]] : memref<?xindex>
+// CHECK:                 %[[VAL_31:.*]] = addi %[[VAL_29]], %[[VAL_9]] : index
+// CHECK:                 %[[VAL_32:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_31]]] : memref<?xindex>
+// CHECK:                 %[[VAL_33:.*]]:2 = scf.while (%[[VAL_34:.*]] = %[[VAL_30]], %[[VAL_35:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:                   %[[VAL_36:.*]] = cmpi ult, %[[VAL_34]], %[[VAL_32]] : index
+// CHECK:                   scf.condition(%[[VAL_36]]) %[[VAL_34]], %[[VAL_35]] : index, index
 // CHECK:                 } do {
-// CHECK:                 ^bb0(%[[VAL_36:.*]]: index, %[[VAL_37:.*]]: index):
-// CHECK:                   %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_36]]] : memref<?xindex>
-// CHECK:                   %[[VAL_39:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
-// CHECK:                   scf.if %[[VAL_39]] {
-// CHECK:                     %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_36]]] : memref<?xf32>
-// CHECK:                     %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
-// CHECK:                     %[[VAL_42:.*]] = addf %[[VAL_40]], %[[VAL_41]] : f32
-// CHECK:                     store %[[VAL_42]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:                 ^bb0(%[[VAL_37:.*]]: index, %[[VAL_38:.*]]: index):
+// CHECK:                   %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_37]]] : memref<?xindex>
+// CHECK:                   %[[VAL_40:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index
+// CHECK:                   scf.if %[[VAL_40]] {
+// CHECK:                     %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_37]]] : memref<?xf32>
+// CHECK:                     %[[VAL_42:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32>
+// CHECK:                     %[[VAL_43:.*]] = addf %[[VAL_41]], %[[VAL_42]] : f32
+// CHECK:                     store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32>
 // CHECK:                   } else {
-// CHECK:                     scf.if %[[VAL_6]] {
-// CHECK:                       %[[VAL_43:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
-// CHECK:                       store %[[VAL_43]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:                     scf.if %[[VAL_7]] {
+// CHECK:                       %[[VAL_44:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32>
+// CHECK:                       store %[[VAL_44]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_38]]] : memref<32x16x8xf32>
 // CHECK:                     } else {
 // CHECK:                     }
 // CHECK:                   }
-// CHECK:                   %[[VAL_44:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
-// CHECK:                   %[[VAL_45:.*]] = addi %[[VAL_36]], %[[VAL_8]] : index
-// CHECK:                   %[[VAL_46:.*]] = select %[[VAL_44]], %[[VAL_45]], %[[VAL_36]] : index
-// CHECK:                   %[[VAL_47:.*]] = addi %[[VAL_37]], %[[VAL_8]] : index
-// CHECK:                   scf.yield %[[VAL_46]], %[[VAL_47]] : index, index
+// CHECK:                   %[[VAL_45:.*]] = cmpi eq, %[[VAL_39]], %[[VAL_38]] : index
+// CHECK:                   %[[VAL_46:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index
+// CHECK:                   %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_37]] : index
+// CHECK:                   %[[VAL_48:.*]] = addi %[[VAL_38]], %[[VAL_9]] : index
+// CHECK:                   scf.yield %[[VAL_47]], %[[VAL_48]] : index, index
 // CHECK:                 }
-// CHECK:                 scf.for %[[VAL_48:.*]] = %[[VAL_49:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_50:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32>
-// CHECK:                   store %[[VAL_50]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_26]], %[[VAL_48]]] : memref<32x16x8xf32>
+// CHECK:                 scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_51:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32>
+// CHECK:                   store %[[VAL_51]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_27]], %[[VAL_49]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_6]] {
-// CHECK:                 scf.for %[[VAL_51:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                   scf.for %[[VAL_52:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_53:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_51]], %[[VAL_52]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_53]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_51]], %[[VAL_52]]] : memref<32x16x8xf32>
+// CHECK:               scf.if %[[VAL_7]] {
+// CHECK:                 scf.for %[[VAL_52:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                   scf.for %[[VAL_53:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_54:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_52]], %[[VAL_53]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_54]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_52]], %[[VAL_53]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_54:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:             %[[VAL_55:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_56:.*]] = select %[[VAL_54]], %[[VAL_55]], %[[VAL_22]] : index
-// CHECK:             %[[VAL_57:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index
-// CHECK:             scf.yield %[[VAL_56]], %[[VAL_57]] : index, index
+// CHECK:             %[[VAL_55:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:             %[[VAL_56:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_57:.*]] = select %[[VAL_55]], %[[VAL_56]], %[[VAL_23]] : index
+// CHECK:             %[[VAL_58:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index
+// CHECK:             scf.yield %[[VAL_57]], %[[VAL_58]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_58:.*]] = %[[VAL_59:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             scf.for %[[VAL_60:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_61:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_62:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_58]], %[[VAL_60]], %[[VAL_61]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_62]], %[[VAL_15]]{{\[}}%[[VAL_58]], %[[VAL_60]], %[[VAL_61]]] : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             scf.for %[[VAL_61:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_62:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_63:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_59]], %[[VAL_61]], %[[VAL_62]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_59]], %[[VAL_61]], %[[VAL_62]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_63:.*]] = tensor_load %[[VAL_15]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_63]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_64:.*]] = tensor_load %[[VAL_16]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_64]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sds
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_sds(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 16 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 16 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_17:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_18:.*]] = muli %[[VAL_15]], %[[VAL_3]] : index
-// CHECK:               %[[VAL_19:.*]] = addi %[[VAL_18]], %[[VAL_17]] : index
-// CHECK:               %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:               %[[VAL_21:.*]] = addi %[[VAL_19]], %[[VAL_5]] : index
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_23:.*]] = %[[VAL_20]] to %[[VAL_22]] step %[[VAL_5]] {
-// CHECK:                 %[[VAL_24:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref<?xindex>
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_23]]] : memref<?xf32>
-// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_24]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_27:.*]] = mulf %[[VAL_25]], %[[VAL_26]] : f32
-// CHECK:                 store %[[VAL_27]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_17]], %[[VAL_24]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_18:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_19:.*]] = muli %[[VAL_16]], %[[VAL_4]] : index
+// CHECK:               %[[VAL_20:.*]] = addi %[[VAL_19]], %[[VAL_18]] : index
+// CHECK:               %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:               %[[VAL_22:.*]] = addi %[[VAL_20]], %[[VAL_6]] : index
+// CHECK:               %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_24:.*]] = %[[VAL_21]] to %[[VAL_23]] step %[[VAL_6]] {
+// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xindex>
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xf32>
+// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_17]], %[[VAL_18]], %[[VAL_25]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_28:.*]] = mulf %[[VAL_26]], %[[VAL_27]] : f32
+// CHECK:                 store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_17]], %[[VAL_18]], %[[VAL_25]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_28:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_28]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_29:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_29]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sds
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -813,153 +825,155 @@ func @mul_sds(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_ssd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_15:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_16:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_17:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
-// CHECK:           %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
-// CHECK:             scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
+// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_17:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref<?xindex>
+// CHECK:           %[[VAL_19:.*]]:2 = scf.while (%[[VAL_20:.*]] = %[[VAL_17]], %[[VAL_21:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_22:.*]] = cmpi ult, %[[VAL_20]], %[[VAL_18]] : index
+// CHECK:             scf.condition(%[[VAL_22]]) %[[VAL_20]], %[[VAL_21]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
-// CHECK:             %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:             %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:             scf.if %[[VAL_25]] {
-// CHECK:               %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_22]]] : memref<?xindex>
-// CHECK:               %[[VAL_27:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
-// CHECK:               %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
-// CHECK:               %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_26]], %[[VAL_31:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_32:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_28]] : index
-// CHECK:                 scf.condition(%[[VAL_32]]) %[[VAL_30]], %[[VAL_31]] : index, index
+// CHECK:           ^bb0(%[[VAL_23:.*]]: index, %[[VAL_24:.*]]: index):
+// CHECK:             %[[VAL_25:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:             %[[VAL_26:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:             scf.if %[[VAL_26]] {
+// CHECK:               %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_23]]] : memref<?xindex>
+// CHECK:               %[[VAL_28:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index
+// CHECK:               %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
+// CHECK:               %[[VAL_30:.*]]:2 = scf.while (%[[VAL_31:.*]] = %[[VAL_27]], %[[VAL_32:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_33:.*]] = cmpi ult, %[[VAL_31]], %[[VAL_29]] : index
+// CHECK:                 scf.condition(%[[VAL_33]]) %[[VAL_31]], %[[VAL_32]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_33:.*]]: index, %[[VAL_34:.*]]: index):
-// CHECK:                 %[[VAL_35:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref<?xindex>
-// CHECK:                 %[[VAL_36:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
-// CHECK:                 scf.if %[[VAL_36]] {
-// CHECK:                   scf.for %[[VAL_37:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_38:.*]] = muli %[[VAL_33]], %[[VAL_5]] : index
-// CHECK:                     %[[VAL_39:.*]] = addi %[[VAL_38]], %[[VAL_37]] : index
-// CHECK:                     %[[VAL_40:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_39]]] : memref<?xf32>
-// CHECK:                     %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]], %[[VAL_37]]] : memref<32x16x8xf32>
-// CHECK:                     %[[VAL_42:.*]] = addf %[[VAL_40]], %[[VAL_41]] : f32
-// CHECK:                     store %[[VAL_42]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]], %[[VAL_37]]] : memref<32x16x8xf32>
+// CHECK:               ^bb0(%[[VAL_34:.*]]: index, %[[VAL_35:.*]]: index):
+// CHECK:                 %[[VAL_36:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_34]]] : memref<?xindex>
+// CHECK:                 %[[VAL_37:.*]] = cmpi eq, %[[VAL_36]], %[[VAL_35]] : index
+// CHECK:                 scf.if %[[VAL_37]] {
+// CHECK:                   scf.for %[[VAL_38:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_39:.*]] = muli %[[VAL_34]], %[[VAL_6]] : index
+// CHECK:                     %[[VAL_40:.*]] = addi %[[VAL_39]], %[[VAL_38]] : index
+// CHECK:                     %[[VAL_41:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_40]]] : memref<?xf32>
+// CHECK:                     %[[VAL_42:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_38]]] : memref<32x16x8xf32>
+// CHECK:                     %[[VAL_43:.*]] = addf %[[VAL_41]], %[[VAL_42]] : f32
+// CHECK:                     store %[[VAL_43]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_38]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 } else {
-// CHECK:                   scf.if %[[VAL_6]] {
-// CHECK:                     scf.for %[[VAL_43:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                       %[[VAL_44:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_34]], %[[VAL_43]]] : memref<32x16x8xf32>
-// CHECK:                       store %[[VAL_44]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]], %[[VAL_43]]] : memref<32x16x8xf32>
+// CHECK:                   scf.if %[[VAL_7]] {
+// CHECK:                     scf.for %[[VAL_44:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                       %[[VAL_45:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_44]]] : memref<32x16x8xf32>
+// CHECK:                       store %[[VAL_45]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_35]], %[[VAL_44]]] : memref<32x16x8xf32>
 // CHECK:                     }
 // CHECK:                   } else {
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_45:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
-// CHECK:                 %[[VAL_46:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
-// CHECK:                 %[[VAL_47:.*]] = select %[[VAL_45]], %[[VAL_46]], %[[VAL_33]] : index
-// CHECK:                 %[[VAL_48:.*]] = addi %[[VAL_34]], %[[VAL_8]] : index
-// CHECK:                 scf.yield %[[VAL_47]], %[[VAL_48]] : index, index
+// CHECK:                 %[[VAL_46:.*]] = cmpi eq, %[[VAL_36]], %[[VAL_35]] : index
+// CHECK:                 %[[VAL_47:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index
+// CHECK:                 %[[VAL_48:.*]] = select %[[VAL_46]], %[[VAL_47]], %[[VAL_34]] : index
+// CHECK:                 %[[VAL_49:.*]] = addi %[[VAL_35]], %[[VAL_9]] : index
+// CHECK:                 scf.yield %[[VAL_48]], %[[VAL_49]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_49:.*]] = %[[VAL_50:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                 scf.for %[[VAL_51:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_52:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_49]], %[[VAL_51]]] : memref<32x16x8xf32>
-// CHECK:                   store %[[VAL_52]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_49]], %[[VAL_51]]] : memref<32x16x8xf32>
+// CHECK:               scf.for %[[VAL_50:.*]] = %[[VAL_51:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                 scf.for %[[VAL_52:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_53:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_50]], %[[VAL_52]]] : memref<32x16x8xf32>
+// CHECK:                   store %[[VAL_53]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_50]], %[[VAL_52]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_6]] {
-// CHECK:                 scf.for %[[VAL_53:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                   scf.for %[[VAL_54:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_55:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_23]], %[[VAL_53]], %[[VAL_54]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_55]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_53]], %[[VAL_54]]] : memref<32x16x8xf32>
+// CHECK:               scf.if %[[VAL_7]] {
+// CHECK:                 scf.for %[[VAL_54:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                   scf.for %[[VAL_55:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_56:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_24]], %[[VAL_54]], %[[VAL_55]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_56]], %[[VAL_16]]{{\[}}%[[VAL_24]], %[[VAL_54]], %[[VAL_55]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_56:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
-// CHECK:             %[[VAL_57:.*]] = addi %[[VAL_22]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_58:.*]] = select %[[VAL_56]], %[[VAL_57]], %[[VAL_22]] : index
-// CHECK:             %[[VAL_59:.*]] = addi %[[VAL_23]], %[[VAL_8]] : index
-// CHECK:             scf.yield %[[VAL_58]], %[[VAL_59]] : index, index
+// CHECK:             %[[VAL_57:.*]] = cmpi eq, %[[VAL_25]], %[[VAL_24]] : index
+// CHECK:             %[[VAL_58:.*]] = addi %[[VAL_23]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_59:.*]] = select %[[VAL_57]], %[[VAL_58]], %[[VAL_23]] : index
+// CHECK:             %[[VAL_60:.*]] = addi %[[VAL_24]], %[[VAL_9]] : index
+// CHECK:             scf.yield %[[VAL_59]], %[[VAL_60]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_60:.*]] = %[[VAL_61:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             scf.for %[[VAL_62:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_63:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_64:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_60]], %[[VAL_62]], %[[VAL_63]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_64]], %[[VAL_15]]{{\[}}%[[VAL_60]], %[[VAL_62]], %[[VAL_63]]] : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_61:.*]] = %[[VAL_62:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             scf.for %[[VAL_63:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_64:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_65:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_61]], %[[VAL_63]], %[[VAL_64]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_65]], %[[VAL_16]]{{\[}}%[[VAL_61]], %[[VAL_63]], %[[VAL_64]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_65:.*]] = tensor_load %[[VAL_15]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_65]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_66:.*]] = tensor_load %[[VAL_16]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_66]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_ssd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_ssd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_ssd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_ssd(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 8 : index
-// CHECK:           %[[VAL_4:.*]] = constant 0 : index
-// CHECK:           %[[VAL_5:.*]] = constant 1 : index
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 8 : index
+// CHECK:           %[[VAL_5:.*]] = constant 0 : index
+// CHECK:           %[[VAL_6:.*]] = constant 1 : index
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_5]] {
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             %[[VAL_18:.*]] = addi %[[VAL_15]], %[[VAL_5]] : index
-// CHECK:             %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_5]] {
-// CHECK:               %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_22:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
-// CHECK:                 %[[VAL_23:.*]] = muli %[[VAL_20]], %[[VAL_3]] : index
-// CHECK:                 %[[VAL_24:.*]] = addi %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xf32>
-// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_16]], %[[VAL_21]], %[[VAL_22]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_27:.*]] = mulf %[[VAL_25]], %[[VAL_26]] : f32
-// CHECK:                 store %[[VAL_27]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_21]], %[[VAL_22]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_6]] {
+// CHECK:             %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:             %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:             %[[VAL_19:.*]] = addi %[[VAL_16]], %[[VAL_6]] : index
+// CHECK:             %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_21:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_6]] {
+// CHECK:               %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_23:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
+// CHECK:                 %[[VAL_24:.*]] = muli %[[VAL_21]], %[[VAL_4]] : index
+// CHECK:                 %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
+// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_23]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_28:.*]] = mulf %[[VAL_26]], %[[VAL_27]] : f32
+// CHECK:                 store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_23]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_28:.*]] = tensor_load %[[VAL_12]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_28]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_29:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_29]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_ssd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_ssd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_ssd
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -981,182 +995,184 @@ func @mul_ssd(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<
 }
 
 // CHECK-LABEL:   func @add_sss(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 32 : index
-// CHECK:           %[[VAL_4:.*]] = constant 16 : index
-// CHECK:           %[[VAL_5:.*]] = constant 8 : index
-// CHECK:           %[[VAL_6:.*]] = constant true
-// CHECK:           %[[VAL_7:.*]] = constant 0 : index
-// CHECK:           %[[VAL_8:.*]] = constant 1 : index
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_16:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 32 : index
+// CHECK:           %[[VAL_5:.*]] = constant 16 : index
+// CHECK:           %[[VAL_6:.*]] = constant 8 : index
+// CHECK:           %[[VAL_7:.*]] = constant true
+// CHECK:           %[[VAL_8:.*]] = constant 0 : index
+// CHECK:           %[[VAL_9:.*]] = constant 1 : index
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_17:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_7]]] : memref<?xindex>
-// CHECK:           %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
-// CHECK:           %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_18]], %[[VAL_22:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:             %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_19]] : index
-// CHECK:             scf.condition(%[[VAL_23]]) %[[VAL_21]], %[[VAL_22]] : index, index
+// CHECK:           %[[VAL_18:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_8]]] : memref<?xindex>
+// CHECK:           %[[VAL_20:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref<?xindex>
+// CHECK:           %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_19]], %[[VAL_23:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:             %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_20]] : index
+// CHECK:             scf.condition(%[[VAL_24]]) %[[VAL_22]], %[[VAL_23]] : index, index
 // CHECK:           } do {
-// CHECK:           ^bb0(%[[VAL_24:.*]]: index, %[[VAL_25:.*]]: index):
-// CHECK:             %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:             %[[VAL_27:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index
-// CHECK:             scf.if %[[VAL_27]] {
-// CHECK:               %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:               %[[VAL_29:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index
-// CHECK:               %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_29]]] : memref<?xindex>
-// CHECK:               %[[VAL_31:.*]]:2 = scf.while (%[[VAL_32:.*]] = %[[VAL_28]], %[[VAL_33:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:                 %[[VAL_34:.*]] = cmpi ult, %[[VAL_32]], %[[VAL_30]] : index
-// CHECK:                 scf.condition(%[[VAL_34]]) %[[VAL_32]], %[[VAL_33]] : index, index
+// CHECK:           ^bb0(%[[VAL_25:.*]]: index, %[[VAL_26:.*]]: index):
+// CHECK:             %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:             %[[VAL_28:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
+// CHECK:             scf.if %[[VAL_28]] {
+// CHECK:               %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:               %[[VAL_30:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index
+// CHECK:               %[[VAL_31:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_30]]] : memref<?xindex>
+// CHECK:               %[[VAL_32:.*]]:2 = scf.while (%[[VAL_33:.*]] = %[[VAL_29]], %[[VAL_34:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:                 %[[VAL_35:.*]] = cmpi ult, %[[VAL_33]], %[[VAL_31]] : index
+// CHECK:                 scf.condition(%[[VAL_35]]) %[[VAL_33]], %[[VAL_34]] : index, index
 // CHECK:               } do {
-// CHECK:               ^bb0(%[[VAL_35:.*]]: index, %[[VAL_36:.*]]: index):
-// CHECK:                 %[[VAL_37:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_35]]] : memref<?xindex>
-// CHECK:                 %[[VAL_38:.*]] = cmpi eq, %[[VAL_37]], %[[VAL_36]] : index
-// CHECK:                 scf.if %[[VAL_38]] {
-// CHECK:                   %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_35]]] : memref<?xindex>
-// CHECK:                   %[[VAL_40:.*]] = addi %[[VAL_35]], %[[VAL_8]] : index
-// CHECK:                   %[[VAL_41:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_40]]] : memref<?xindex>
-// CHECK:                   %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_39]], %[[VAL_44:.*]] = %[[VAL_7]]) : (index, index) -> (index, index) {
-// CHECK:                     %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_41]] : index
-// CHECK:                     scf.condition(%[[VAL_45]]) %[[VAL_43]], %[[VAL_44]] : index, index
+// CHECK:               ^bb0(%[[VAL_36:.*]]: index, %[[VAL_37:.*]]: index):
+// CHECK:                 %[[VAL_38:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_36]]] : memref<?xindex>
+// CHECK:                 %[[VAL_39:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
+// CHECK:                 scf.if %[[VAL_39]] {
+// CHECK:                   %[[VAL_40:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_36]]] : memref<?xindex>
+// CHECK:                   %[[VAL_41:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index
+// CHECK:                   %[[VAL_42:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_41]]] : memref<?xindex>
+// CHECK:                   %[[VAL_43:.*]]:2 = scf.while (%[[VAL_44:.*]] = %[[VAL_40]], %[[VAL_45:.*]] = %[[VAL_8]]) : (index, index) -> (index, index) {
+// CHECK:                     %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_42]] : index
+// CHECK:                     scf.condition(%[[VAL_46]]) %[[VAL_44]], %[[VAL_45]] : index, index
 // CHECK:                   } do {
-// CHECK:                   ^bb0(%[[VAL_46:.*]]: index, %[[VAL_47:.*]]: index):
-// CHECK:                     %[[VAL_48:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_46]]] : memref<?xindex>
-// CHECK:                     %[[VAL_49:.*]] = cmpi eq, %[[VAL_48]], %[[VAL_47]] : index
-// CHECK:                     scf.if %[[VAL_49]] {
-// CHECK:                       %[[VAL_50:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_46]]] : memref<?xf32>
-// CHECK:                       %[[VAL_51:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_47]]] : memref<32x16x8xf32>
-// CHECK:                       %[[VAL_52:.*]] = addf %[[VAL_50]], %[[VAL_51]] : f32
-// CHECK:                       store %[[VAL_52]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_47]]] : memref<32x16x8xf32>
+// CHECK:                   ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
+// CHECK:                     %[[VAL_49:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_47]]] : memref<?xindex>
+// CHECK:                     %[[VAL_50:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_48]] : index
+// CHECK:                     scf.if %[[VAL_50]] {
+// CHECK:                       %[[VAL_51:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_47]]] : memref<?xf32>
+// CHECK:                       %[[VAL_52:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32>
+// CHECK:                       %[[VAL_53:.*]] = addf %[[VAL_51]], %[[VAL_52]] : f32
+// CHECK:                       store %[[VAL_53]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32>
 // CHECK:                     } else {
-// CHECK:                       scf.if %[[VAL_6]] {
-// CHECK:                         %[[VAL_53:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_47]]] : memref<32x16x8xf32>
-// CHECK:                         store %[[VAL_53]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_47]]] : memref<32x16x8xf32>
+// CHECK:                       scf.if %[[VAL_7]] {
+// CHECK:                         %[[VAL_54:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32>
+// CHECK:                         store %[[VAL_54]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_48]]] : memref<32x16x8xf32>
 // CHECK:                       } else {
 // CHECK:                       }
 // CHECK:                     }
-// CHECK:                     %[[VAL_54:.*]] = cmpi eq, %[[VAL_48]], %[[VAL_47]] : index
-// CHECK:                     %[[VAL_55:.*]] = addi %[[VAL_46]], %[[VAL_8]] : index
-// CHECK:                     %[[VAL_56:.*]] = select %[[VAL_54]], %[[VAL_55]], %[[VAL_46]] : index
-// CHECK:                     %[[VAL_57:.*]] = addi %[[VAL_47]], %[[VAL_8]] : index
-// CHECK:                     scf.yield %[[VAL_56]], %[[VAL_57]] : index, index
+// CHECK:                     %[[VAL_55:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_48]] : index
+// CHECK:                     %[[VAL_56:.*]] = addi %[[VAL_47]], %[[VAL_9]] : index
+// CHECK:                     %[[VAL_57:.*]] = select %[[VAL_55]], %[[VAL_56]], %[[VAL_47]] : index
+// CHECK:                     %[[VAL_58:.*]] = addi %[[VAL_48]], %[[VAL_9]] : index
+// CHECK:                     scf.yield %[[VAL_57]], %[[VAL_58]] : index, index
 // CHECK:                   }
-// CHECK:                   scf.for %[[VAL_58:.*]] = %[[VAL_59:.*]]#1 to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_60:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_58]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_60]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_58]]] : memref<32x16x8xf32>
+// CHECK:                   scf.for %[[VAL_59:.*]] = %[[VAL_60:.*]]#1 to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_61:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_59]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_61]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_59]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 } else {
-// CHECK:                   scf.if %[[VAL_6]] {
-// CHECK:                     scf.for %[[VAL_61:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                       %[[VAL_62:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_61]]] : memref<32x16x8xf32>
-// CHECK:                       store %[[VAL_62]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_36]], %[[VAL_61]]] : memref<32x16x8xf32>
+// CHECK:                   scf.if %[[VAL_7]] {
+// CHECK:                     scf.for %[[VAL_62:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                       %[[VAL_63:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_62]]] : memref<32x16x8xf32>
+// CHECK:                       store %[[VAL_63]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_37]], %[[VAL_62]]] : memref<32x16x8xf32>
 // CHECK:                     }
 // CHECK:                   } else {
 // CHECK:                   }
 // CHECK:                 }
-// CHECK:                 %[[VAL_63:.*]] = cmpi eq, %[[VAL_37]], %[[VAL_36]] : index
-// CHECK:                 %[[VAL_64:.*]] = addi %[[VAL_35]], %[[VAL_8]] : index
-// CHECK:                 %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_35]] : index
-// CHECK:                 %[[VAL_66:.*]] = addi %[[VAL_36]], %[[VAL_8]] : index
-// CHECK:                 scf.yield %[[VAL_65]], %[[VAL_66]] : index, index
+// CHECK:                 %[[VAL_64:.*]] = cmpi eq, %[[VAL_38]], %[[VAL_37]] : index
+// CHECK:                 %[[VAL_65:.*]] = addi %[[VAL_36]], %[[VAL_9]] : index
+// CHECK:                 %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_36]] : index
+// CHECK:                 %[[VAL_67:.*]] = addi %[[VAL_37]], %[[VAL_9]] : index
+// CHECK:                 scf.yield %[[VAL_66]], %[[VAL_67]] : index, index
 // CHECK:               }
-// CHECK:               scf.for %[[VAL_67:.*]] = %[[VAL_68:.*]]#1 to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                 scf.for %[[VAL_69:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                   %[[VAL_70:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_67]], %[[VAL_69]]] : memref<32x16x8xf32>
-// CHECK:                   store %[[VAL_70]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_67]], %[[VAL_69]]] : memref<32x16x8xf32>
+// CHECK:               scf.for %[[VAL_68:.*]] = %[[VAL_69:.*]]#1 to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                 scf.for %[[VAL_70:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                   %[[VAL_71:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_68]], %[[VAL_70]]] : memref<32x16x8xf32>
+// CHECK:                   store %[[VAL_71]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_68]], %[[VAL_70]]] : memref<32x16x8xf32>
 // CHECK:                 }
 // CHECK:               }
 // CHECK:             } else {
-// CHECK:               scf.if %[[VAL_6]] {
-// CHECK:                 scf.for %[[VAL_71:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:                   scf.for %[[VAL_72:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                     %[[VAL_73:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_25]], %[[VAL_71]], %[[VAL_72]]] : memref<32x16x8xf32>
-// CHECK:                     store %[[VAL_73]], %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_71]], %[[VAL_72]]] : memref<32x16x8xf32>
+// CHECK:               scf.if %[[VAL_7]] {
+// CHECK:                 scf.for %[[VAL_72:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:                   scf.for %[[VAL_73:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                     %[[VAL_74:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_26]], %[[VAL_72]], %[[VAL_73]]] : memref<32x16x8xf32>
+// CHECK:                     store %[[VAL_74]], %[[VAL_18]]{{\[}}%[[VAL_26]], %[[VAL_72]], %[[VAL_73]]] : memref<32x16x8xf32>
 // CHECK:                   }
 // CHECK:                 }
 // CHECK:               } else {
 // CHECK:               }
 // CHECK:             }
-// CHECK:             %[[VAL_74:.*]] = cmpi eq, %[[VAL_26]], %[[VAL_25]] : index
-// CHECK:             %[[VAL_75:.*]] = addi %[[VAL_24]], %[[VAL_8]] : index
-// CHECK:             %[[VAL_76:.*]] = select %[[VAL_74]], %[[VAL_75]], %[[VAL_24]] : index
-// CHECK:             %[[VAL_77:.*]] = addi %[[VAL_25]], %[[VAL_8]] : index
-// CHECK:             scf.yield %[[VAL_76]], %[[VAL_77]] : index, index
+// CHECK:             %[[VAL_75:.*]] = cmpi eq, %[[VAL_27]], %[[VAL_26]] : index
+// CHECK:             %[[VAL_76:.*]] = addi %[[VAL_25]], %[[VAL_9]] : index
+// CHECK:             %[[VAL_77:.*]] = select %[[VAL_75]], %[[VAL_76]], %[[VAL_25]] : index
+// CHECK:             %[[VAL_78:.*]] = addi %[[VAL_26]], %[[VAL_9]] : index
+// CHECK:             scf.yield %[[VAL_77]], %[[VAL_78]] : index, index
 // CHECK:           }
-// CHECK:           scf.for %[[VAL_78:.*]] = %[[VAL_79:.*]]#1 to %[[VAL_3]] step %[[VAL_8]] {
-// CHECK:             scf.for %[[VAL_80:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
-// CHECK:               scf.for %[[VAL_81:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
-// CHECK:                 %[[VAL_82:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_78]], %[[VAL_80]], %[[VAL_81]]] : memref<32x16x8xf32>
-// CHECK:                 store %[[VAL_82]], %[[VAL_17]]{{\[}}%[[VAL_78]], %[[VAL_80]], %[[VAL_81]]] : memref<32x16x8xf32>
+// CHECK:           scf.for %[[VAL_79:.*]] = %[[VAL_80:.*]]#1 to %[[VAL_4]] step %[[VAL_9]] {
+// CHECK:             scf.for %[[VAL_81:.*]] = %[[VAL_8]] to %[[VAL_5]] step %[[VAL_9]] {
+// CHECK:               scf.for %[[VAL_82:.*]] = %[[VAL_8]] to %[[VAL_6]] step %[[VAL_9]] {
+// CHECK:                 %[[VAL_83:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_79]], %[[VAL_81]], %[[VAL_82]]] : memref<32x16x8xf32>
+// CHECK:                 store %[[VAL_83]], %[[VAL_18]]{{\[}}%[[VAL_79]], %[[VAL_81]], %[[VAL_82]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_83:.*]] = tensor_load %[[VAL_17]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_83]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_84:.*]] = tensor_load %[[VAL_18]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_84]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @add_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @add_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sss
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = addf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = addf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
 }
 
 // CHECK-LABEL:   func @mul_sss(
-// CHECK-SAME:                  %[[VAL_0:.*]]: tensor<32x16x8xf32>,
-// CHECK-SAME:                  %[[VAL_1:.*]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 0 : index
-// CHECK:           %[[VAL_4:.*]] = constant 1 : index
-// CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK-SAME:                  %[[VAL_0:.*0]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_1:.*1]]: tensor<32x16x8xf32>,
+// CHECK-SAME:                  %[[VAL_2:.*2]]: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 0 : index
+// CHECK:           %[[VAL_5:.*]] = constant 1 : index
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_10:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
 // CHECK:           %[[VAL_13:.*]] = alloca() : memref<32x16x8xf32>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_16:.*]] = %[[VAL_14]] to %[[VAL_15]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_17:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_16]]] : memref<?xindex>
-// CHECK:             %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xindex>
-// CHECK:             %[[VAL_19:.*]] = addi %[[VAL_16]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_20:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_21:.*]] = %[[VAL_18]] to %[[VAL_20]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               %[[VAL_24:.*]] = addi %[[VAL_21]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_25:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:               scf.for %[[VAL_26:.*]] = %[[VAL_23]] to %[[VAL_25]] step %[[VAL_4]] {
-// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_26]]] : memref<?xf32>
-// CHECK:                 %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_27]]] : memref<32x16x8xf32>
-// CHECK:                 %[[VAL_30:.*]] = mulf %[[VAL_28]], %[[VAL_29]] : f32
-// CHECK:                 store %[[VAL_30]], %[[VAL_13]]{{\[}}%[[VAL_17]], %[[VAL_22]], %[[VAL_27]]] : memref<32x16x8xf32>
+// CHECK:           %[[VAL_14:.*]] = alloca() : memref<32x16x8xf32>
+// CHECK:           %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_17:.*]] = %[[VAL_15]] to %[[VAL_16]] step %[[VAL_5]] {
+// CHECK:             %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
+// CHECK:             %[[VAL_19:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref<?xindex>
+// CHECK:             %[[VAL_20:.*]] = addi %[[VAL_17]], %[[VAL_5]] : index
+// CHECK:             %[[VAL_21:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_22:.*]] = %[[VAL_19]] to %[[VAL_21]] step %[[VAL_5]] {
+// CHECK:               %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:               %[[VAL_24:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
+// CHECK:               %[[VAL_25:.*]] = addi %[[VAL_22]], %[[VAL_5]] : index
+// CHECK:               %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:               scf.for %[[VAL_27:.*]] = %[[VAL_24]] to %[[VAL_26]] step %[[VAL_5]] {
+// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:                 %[[VAL_29:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xf32>
+// CHECK:                 %[[VAL_30:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_18]], %[[VAL_23]], %[[VAL_28]]] : memref<32x16x8xf32>
+// CHECK:                 %[[VAL_31:.*]] = mulf %[[VAL_29]], %[[VAL_30]] : f32
+// CHECK:                 store %[[VAL_31]], %[[VAL_14]]{{\[}}%[[VAL_18]], %[[VAL_23]], %[[VAL_28]]] : memref<32x16x8xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_31:.*]] = tensor_load %[[VAL_13]] : memref<32x16x8xf32>
-// CHECK:           return %[[VAL_31]] : tensor<32x16x8xf32>
+// CHECK:           %[[VAL_32:.*]] = tensor_load %[[VAL_14]] : memref<32x16x8xf32>
+// CHECK:           return %[[VAL_32]] : tensor<32x16x8xf32>
 // CHECK:         }
-func @mul_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
+func @mul_sss(%arga: tensor<32x16x8xf32>, %argb: tensor<32x16x8xf32>, %argx: tensor<32x16x8xf32>) -> tensor<32x16x8xf32> {
   %0 = linalg.generic #trait_sss
      ins(%arga, %argb: tensor<32x16x8xf32>, tensor<32x16x8xf32>)
-    outs(%arga : tensor<32x16x8xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
-        %0 = mulf %a, %b  : f32
+    outs(%argx: tensor<32x16x8xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<32x16x8xf32>
   return %0 : tensor<32x16x8xf32>
@@ -1229,9 +1245,9 @@ func @kernel_3d(%arga: tensor<?x?xf32>,
                 %argc: tensor<?x?xf32>,
 	        %argd: tensor<?x?xf32>) -> tensor<?x?xf32> {
   %0 = linalg.generic #trait_kernel_3d
-       ins(%argb, %argc, %argd : tensor<?x?x?xf32>, tensor<?x?xf32>, tensor<?x?xf32>)
-      outs(%arga : tensor<?x?xf32>) {
-    ^bb(%b: f32, %c: f32, %d : f32, %a : f32):
+       ins(%argb, %argc, %argd: tensor<?x?x?xf32>, tensor<?x?xf32>, tensor<?x?xf32>)
+      outs(%arga: tensor<?x?xf32>) {
+    ^bb(%b: f32, %c: f32, %d: f32, %a: f32):
       %0 = mulf %b, %c : f32
       %1 = mulf %0, %d : f32
       %2 = addf %1, %a : f32
@@ -1260,39 +1276,39 @@ func @kernel_3d(%arga: tensor<?x?xf32>,
 // CHECK:           %[[VAL_3:.*]] = constant 0 : index
 // CHECK:           %[[VAL_4:.*]] = constant 1 : index
 // CHECK:           %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
+// CHECK:           %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
 // CHECK:           %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca() : memref<f32>
-// CHECK:           %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
-// CHECK:           scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_4]] {
-// CHECK:             %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
-// CHECK:             %[[VAL_17:.*]] = addi %[[VAL_15]], %[[VAL_4]] : index
-// CHECK:             %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
-// CHECK:             scf.for %[[VAL_19:.*]] = %[[VAL_16]] to %[[VAL_18]] step %[[VAL_4]] {
-// CHECK:               %[[VAL_20:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
-// CHECK:               %[[VAL_21:.*]] = addi %[[VAL_19]], %[[VAL_4]] : index
-// CHECK:               %[[VAL_22:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
-// CHECK:               %[[VAL_23:.*]] = load %[[VAL_12]][] : memref<f32>
-// CHECK:               %[[VAL_24:.*]] = scf.for %[[VAL_25:.*]] = %[[VAL_20]] to %[[VAL_22]] step %[[VAL_4]] iter_args(%[[VAL_26:.*]] = %[[VAL_23]]) -> (f32) {
-// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_25]]] : memref<?xf32>
-// CHECK:                 %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32
-// CHECK:                 scf.yield %[[VAL_28]] : f32
+// CHECK:           %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
+// CHECK:           %[[VAL_9:.*]] = alloca() : memref<f32>
+// CHECK:           %[[VAL_10:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
+// CHECK:           %[[VAL_11:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
+// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_10]] to %[[VAL_11]] step %[[VAL_4]] {
+// CHECK:             %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
+// CHECK:             %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_4]] : index
+// CHECK:             %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
+// CHECK:             scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_4]] {
+// CHECK:               %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xindex>
+// CHECK:               %[[VAL_18:.*]] = addi %[[VAL_16]], %[[VAL_4]] : index
+// CHECK:               %[[VAL_19:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref<?xindex>
+// CHECK:               %[[VAL_20:.*]] = load %[[VAL_9]][] : memref<f32>
+// CHECK:               %[[VAL_21:.*]] = scf.for %[[VAL_22:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_4]] iter_args(%[[VAL_23:.*]] = %[[VAL_20]]) -> (f32) {
+// CHECK:                 %[[VAL_24:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_22]]] : memref<?xf32>
+// CHECK:                 %[[VAL_25:.*]] = addf %[[VAL_23]], %[[VAL_24]] : f32
+// CHECK:                 scf.yield %[[VAL_25]] : f32
 // CHECK:               }
-// CHECK:               store %[[VAL_29:.*]], %[[VAL_12]][] : memref<f32>
+// CHECK:               store %[[VAL_26:.*]], %[[VAL_9]][] : memref<f32>
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_30:.*]] = tensor_load %[[VAL_12]] : memref<f32>
-// CHECK:           return %[[VAL_30]] : tensor<f32>
+// CHECK:           %[[VAL_27:.*]] = tensor_load %[[VAL_9]] : memref<f32>
+// CHECK:           return %[[VAL_27]] : tensor<f32>
 // CHECK:         }
 func @sum_reduction(%arga: tensor<10x20x30xf32>, %argx: tensor<f32>) -> tensor<f32> {
   %0 = linalg.generic #trait_sum_reduction
-     ins(%arga : tensor<10x20x30xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %x : f32):
-        %0 = addf %x, %a  : f32
-        linalg.yield %0: f32
+     ins(%arga: tensor<10x20x30xf32>)
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %x, %a : f32
+        linalg.yield %0 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }
@@ -1346,12 +1362,12 @@ func @sum_reduction_inv(%arga: tensor<?x?x?xf32>,
                         %argb: tensor<?xf32>,
 		        %argx: tensor<f32>) -> tensor<f32> {
   %0 = linalg.generic #trait_sum_reduction_inv
-    ins(%arga, %argb : tensor<?x?x?xf32>, tensor<?xf32>)
-    outs(%argx : tensor<f32>) {
-      ^bb(%a : f32, %b : f32, %x : f32):
-        %0 = mulf %a, %b  : f32
-        %1 = addf %x, %0  : f32
-        linalg.yield %1: f32
+    ins(%arga, %argb: tensor<?x?x?xf32>, tensor<?xf32>)
+    outs(%argx: tensor<f32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
+        %0 = mulf %a, %b : f32
+        %1 = addf %x, %0 : f32
+        linalg.yield %1 : f32
   } -> tensor<f32>
   return %0 : tensor<f32>
 }
@@ -1377,42 +1393,42 @@ func @sum_reduction_inv(%arga: tensor<?x?x?xf32>,
 // CHECK-SAME:                     %[[VAL_0:.*]]: tensor<10xf32>,
 // CHECK-SAME:                     %[[VAL_1:.*]]: tensor<20xf32>,
 // CHECK-SAME:                     %[[VAL_2:.*]]: tensor<30xf32>,
-// CHECK-SAME:                     %[[SHAPE:.*]]: tensor<10x20x30xf32>) -> tensor<10x20x30xf32> {
-// CHECK:           %[[VAL_3:.*]] = constant 10 : index
-// CHECK:           %[[VAL_4:.*]] = constant 20 : index
-// CHECK:           %[[VAL_5:.*]] = constant 30 : index
-// CHECK:           %[[VAL_6:.*]] = constant 0 : index
-// CHECK:           %[[VAL_7:.*]] = constant 1 : index
-// CHECK:           %[[VAL_8:.*]] = alloca() : memref<10xf32>
-// CHECK:           %[[VAL_9:.*]] = alloca() : memref<20xf32>
-// CHECK:           %[[VAL_10:.*]] = alloca() : memref<30xf32>
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<10x20x30xf32>
-// CHECK:           scf.for %[[VAL_12:.*]] = %[[VAL_6]] to %[[VAL_3]] step %[[VAL_7]] {
-// CHECK:             %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_12]]] : memref<10xf32>
-// CHECK:             scf.for %[[VAL_14:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
-// CHECK:               %[[VAL_15:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]]] : memref<20xf32>
-// CHECK:               scf.for %[[VAL_16:.*]] = %[[VAL_6]] to %[[VAL_5]] step %[[VAL_7]] {
-// CHECK:                 %[[VAL_17:.*]] = mulf %[[VAL_13]], %[[VAL_15]] : f32
-// CHECK:                 %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_16]]] : memref<30xf32>
-// CHECK:                 %[[VAL_19:.*]] = mulf %[[VAL_17]], %[[VAL_18]] : f32
-// CHECK:                 store %[[VAL_19]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_14]], %[[VAL_16]]] : memref<10x20x30xf32>
+// CHECK-SAME:                     %[[VAL_3:.*]]: tensor<10x20x30xf32>) -> tensor<10x20x30xf32> {
+// CHECK:           %[[VAL_4:.*]] = constant 10 : index
+// CHECK:           %[[VAL_5:.*]] = constant 20 : index
+// CHECK:           %[[VAL_6:.*]] = constant 30 : index
+// CHECK:           %[[VAL_7:.*]] = constant 0 : index
+// CHECK:           %[[VAL_8:.*]] = constant 1 : index
+// CHECK:           %[[VAL_9:.*]] = alloca() : memref<10xf32>
+// CHECK:           %[[VAL_10:.*]] = alloca() : memref<20xf32>
+// CHECK:           %[[VAL_11:.*]] = alloca() : memref<30xf32>
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<10x20x30xf32>
+// CHECK:           scf.for %[[VAL_13:.*]] = %[[VAL_7]] to %[[VAL_4]] step %[[VAL_8]] {
+// CHECK:             %[[VAL_14:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_13]]] : memref<10xf32>
+// CHECK:             scf.for %[[VAL_15:.*]] = %[[VAL_7]] to %[[VAL_5]] step %[[VAL_8]] {
+// CHECK:               %[[VAL_16:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]]] : memref<20xf32>
+// CHECK:               scf.for %[[VAL_17:.*]] = %[[VAL_7]] to %[[VAL_6]] step %[[VAL_8]] {
+// CHECK:                 %[[VAL_18:.*]] = mulf %[[VAL_14]], %[[VAL_16]] : f32
+// CHECK:                 %[[VAL_19:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_17]]] : memref<30xf32>
+// CHECK:                 %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32
+// CHECK:                 store %[[VAL_20]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_15]], %[[VAL_17]]] : memref<10x20x30xf32>
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_20:.*]] = tensor_load %[[VAL_11]] : memref<10x20x30xf32>
-// CHECK:           return %[[VAL_20]] : tensor<10x20x30xf32>
+// CHECK:           %[[VAL_21:.*]] = tensor_load %[[VAL_12]] : memref<10x20x30xf32>
+// CHECK:           return %[[VAL_21]] : tensor<10x20x30xf32>
 // CHECK:         }
 func @invariants(%arga: tensor<10xf32>,
                  %argb: tensor<20xf32>,
                  %argc: tensor<30xf32>,
-                 %shape : tensor<10x20x30xf32>) -> tensor<10x20x30xf32> {
+                 %argx: tensor<10x20x30xf32>) -> tensor<10x20x30xf32> {
   %0 = linalg.generic #trait_invariants
      ins(%arga, %argb, %argc : tensor<10xf32>, tensor<20xf32>, tensor<30xf32>)
-    outs(%shape : tensor<10x20x30xf32>) {
-      ^bb(%a : f32, %b : f32, %c : f32, %s : f32):
-        %0 = mulf %a, %b  : f32
-        %1 = mulf %0, %c  : f32
-        linalg.yield %1: f32
+    outs(%argx: tensor<10x20x30xf32>) {
+      ^bb(%a: f32, %b: f32, %c: f32, %x: f32):
+        %0 = mulf %a, %b : f32
+        %1 = mulf %0, %c : f32
+        linalg.yield %1 : f32
   } -> tensor<10x20x30xf32>
   return %0 : tensor<10x20x30xf32>
 }

diff  --git a/mlir/test/Dialect/Linalg/sparse_invalid.mlir b/mlir/test/Dialect/Linalg/sparse_invalid.mlir
index bb64e80785fa..4029964737d8 100644
--- a/mlir/test/Dialect/Linalg/sparse_invalid.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_invalid.mlir
@@ -9,18 +9,17 @@
     [ "S" ],  // a
     [ "D" ]   // x
   ],
-  iterator_types = ["parallel"]
+  iterator_types = ["parallel"],
+  doc = "x(i) = a(i) + b"
 }
 
-func @invalid_memref(%arga: memref<32xf32>, %argb: f32, %shape: tensor<32xf32>)
-  -> tensor<32xf32>
-{
+func @invalid_memref(%arga: memref<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   // expected-error at +1 {{'linalg.generic' op expected sparse annotations on tensors only}}
   %0 = linalg.generic #trait_memref
      ins(%arga: memref<32xf32>)
-    outs(%shape: tensor<32xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -38,16 +37,17 @@ func @invalid_memref(%arga: memref<32xf32>, %argb: f32, %shape: tensor<32xf32>)
     [ "S" ],  // b
     [ "D" ]   // x
   ],
-  iterator_types = ["parallel"]
+  iterator_types = ["parallel"],
+  doc = "x(i) = a(i) + b"
 }
 
-func @invalid_too_many(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @invalid_too_many(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   // expected-error at +1 {{'linalg.generic' op expected one sparse annotation for each tensor}}
   %0 = linalg.generic #trait_too_many
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -61,16 +61,17 @@ func @invalid_too_many(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
     affine_map<(i) -> (i)>   // x (out)
   ],
   sparse = [ 1, 2 ],
-  iterator_types = ["parallel"]
+  iterator_types = ["parallel"],
+  doc = "x(i) = a(i) + b"
 }
 
-func @invalid_no_array(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @invalid_no_array(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   // expected-error at +1 {{'linalg.generic' op expected sparse annotation array for tensor 0}}
   %0 = linalg.generic #trait_no_array
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -87,16 +88,17 @@ func @invalid_no_array(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
     [ "S" ],
     [ "D", "D" ]
   ],
-  iterator_types = ["parallel"]
+  iterator_types = ["parallel"],
+  doc = "x(i) = a(i) + b"
 }
 
-func @invalid_wrong_rank(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
+func @invalid_wrong_rank(%arga: tensor<32xf32>, %argb: f32, %argx: tensor<32xf32>) -> tensor<32xf32> {
   // expected-error at +1 {{'linalg.generic' op expected sparse annotation with rank 1 for tensor 1}}
   %0 = linalg.generic #trait_wrong_rank
      ins(%arga: tensor<32xf32>)
-    outs(%arga: tensor<32xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32xf32>
   return %0 : tensor<32xf32>
@@ -113,16 +115,17 @@ func @invalid_wrong_rank(%arga: tensor<32xf32>, %argb: f32) -> tensor<32xf32> {
     [ "S", 1 ],
     [ "D", "D" ]
   ],
-  iterator_types = ["parallel","parallel"]
+  iterator_types = ["parallel","parallel"],
+  doc = "x(i,j) = a(i,j) + b"
 }
 
-func @invalid_no_string(%arga: tensor<32x16xf32>, %argb: f32) -> tensor<32x16xf32> {
+func @invalid_no_string(%arga: tensor<32x16xf32>, %argb: f32, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   // expected-error at +1 {{'linalg.generic' op expected sparse annotation at position 1 for tensor 0}}
   %0 = linalg.generic #trait_no_string
      ins(%arga: tensor<32x16xf32>)
-    outs(%arga: tensor<32x16xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -139,16 +142,17 @@ func @invalid_no_string(%arga: tensor<32x16xf32>, %argb: f32) -> tensor<32x16xf3
     [ "S", "S" ],
     [ "D", "X" ]
   ],
-  iterator_types = ["parallel","parallel"]
+  iterator_types = ["parallel","parallel"],
+  doc = "x(i,j) = a(i,j) + b"
 }
 
-func @invalid_wrong_symbol(%arga: tensor<32x16xf32>, %argb: f32) -> tensor<32x16xf32> {
+func @invalid_wrong_symbol(%arga: tensor<32x16xf32>, %argb: f32, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   // expected-error at +1 {{'linalg.generic' op expected sparse annotation at position 1 for tensor 1}}
   %0 = linalg.generic #trait_wrong_symbol
      ins(%arga: tensor<32x16xf32>)
-    outs(%arga: tensor<32x16xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>
@@ -165,16 +169,17 @@ func @invalid_wrong_symbol(%arga: tensor<32x16xf32>, %argb: f32) -> tensor<32x16
     [ "S", "S" ],
     [ "D", "S" ]
   ],
-  iterator_types = ["parallel","parallel"]
+  iterator_types = ["parallel","parallel"],
+  doc = "x(i,j) = a(i,j) + b"
 }
 
-func @invalid_no_sparse_output(%arga: tensor<32x16xf32>, %argb: f32) -> tensor<32x16xf32> {
+func @invalid_no_sparse_output(%arga: tensor<32x16xf32>, %argb: f32, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
   // expected-error at +1 {{'linalg.generic' op sparse output tensors not supported (yet)}}
   %0 = linalg.generic #trait_no_sparse_output
      ins(%arga: tensor<32x16xf32>)
-    outs(%arga: tensor<32x16xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = addf %a, %argb  : f32
+    outs(%argx: tensor<32x16xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = addf %a, %argb : f32
         linalg.yield %0 : f32
   } -> tensor<32x16xf32>
   return %0 : tensor<32x16xf32>

diff  --git a/mlir/test/Dialect/Linalg/sparse_nd.mlir b/mlir/test/Dialect/Linalg/sparse_nd.mlir
index 2b0762b1bf37..c209a64b9e79 100644
--- a/mlir/test/Dialect/Linalg/sparse_nd.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_nd.mlir
@@ -20,54 +20,55 @@
 }
 
 // CHECK-LABEL:   func @mul(
-// CHECK-SAME:              %[[VAL_0:.*]]: tensor<100x200x300x400x500x600x700x800xf32>,
-// CHECK-SAME:              %[[VAL_1:.*]]: tensor<100x200x300x400x500x600x700x800xf32>) -> tensor<100x200x300x400x500x600x700x800xf32> {
-// CHECK:           %[[VAL_2:.*]] = constant 999 : index
-// CHECK:           %[[VAL_3:.*]] = constant 100 : index
-// CHECK:           %[[VAL_4:.*]] = constant 200 : index
-// CHECK:           %[[VAL_5:.*]] = constant 300 : index
-// CHECK:           %[[VAL_6:.*]] = constant 600 : index
-// CHECK:           %[[VAL_7:.*]] = constant 700 : index
-// CHECK:           %[[VAL_8:.*]] = constant 800 : index
-// CHECK:           %[[VAL_9:.*]] = constant 0 : index
-// CHECK:           %[[VAL_10:.*]] = constant 1 : index
-// CHECK:           %[[VAL_11:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32>
-// CHECK:           %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
-// CHECK:           %[[VAL_16:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
-// CHECK:           %[[VAL_17:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32>
-// CHECK:           scf.for %[[VAL_18:.*]] = %[[VAL_9]] to %[[VAL_8]] step %[[VAL_10]] {
-// CHECK:             scf.for %[[VAL_19:.*]] = %[[VAL_9]] to %[[VAL_7]] step %[[VAL_10]] {
-// CHECK:               %[[VAL_20:.*]] = muli %[[VAL_18]], %[[VAL_7]] : index
-// CHECK:               %[[VAL_21:.*]] = addi %[[VAL_20]], %[[VAL_19]] : index
-// CHECK:               scf.for %[[VAL_22:.*]] = %[[VAL_9]] to %[[VAL_6]] step %[[VAL_10]] {
-// CHECK:                 %[[VAL_23:.*]] = muli %[[VAL_21]], %[[VAL_6]] : index
-// CHECK:                 %[[VAL_24:.*]] = addi %[[VAL_23]], %[[VAL_22]] : index
-// CHECK:                 %[[VAL_25:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_24]]] : memref<?xindex>
-// CHECK:                 %[[VAL_26:.*]] = addi %[[VAL_24]], %[[VAL_10]] : index
-// CHECK:                 %[[VAL_27:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_26]]] : memref<?xindex>
-// CHECK:                 scf.for %[[VAL_28:.*]] = %[[VAL_25]] to %[[VAL_27]] step %[[VAL_10]] {
-// CHECK:                   %[[VAL_29:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_28]]] : memref<?xindex>
-// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_28]]] : memref<?xindex>
-// CHECK:                   %[[VAL_31:.*]] = addi %[[VAL_28]], %[[VAL_10]] : index
-// CHECK:                   %[[VAL_32:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_31]]] : memref<?xindex>
-// CHECK:                   scf.for %[[VAL_33:.*]] = %[[VAL_30]] to %[[VAL_32]] step %[[VAL_10]] {
-// CHECK:                     %[[VAL_34:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_33]]] : memref<?xindex>
-// CHECK:                     scf.for %[[VAL_35:.*]] = %[[VAL_9]] to %[[VAL_5]] step %[[VAL_10]] {
-// CHECK:                       %[[VAL_36:.*]] = muli %[[VAL_33]], %[[VAL_5]] : index
-// CHECK:                       %[[VAL_37:.*]] = addi %[[VAL_36]], %[[VAL_35]] : index
-// CHECK:                       scf.for %[[VAL_38:.*]] = %[[VAL_9]] to %[[VAL_4]] step %[[VAL_10]] {
-// CHECK:                         %[[VAL_39:.*]] = muli %[[VAL_37]], %[[VAL_4]] : index
-// CHECK:                         %[[VAL_40:.*]] = addi %[[VAL_39]], %[[VAL_38]] : index
-// CHECK:                         scf.for %[[VAL_41:.*]] = %[[VAL_9]] to %[[VAL_3]] step %[[VAL_10]] {
-// CHECK:                           %[[VAL_42:.*]] = muli %[[VAL_40]], %[[VAL_3]] : index
-// CHECK:                           %[[VAL_43:.*]] = addi %[[VAL_42]], %[[VAL_41]] : index
-// CHECK:                           %[[VAL_44:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_41]], %[[VAL_38]], %[[VAL_35]], %[[VAL_34]], %[[VAL_29]], %[[VAL_22]], %[[VAL_19]], %[[VAL_18]]] : memref<100x200x300x400x500x600x700x800xf32>
-// CHECK:                           %[[VAL_45:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_43]]] : memref<?xf32>
-// CHECK:                           %[[VAL_46:.*]] = mulf %[[VAL_44]], %[[VAL_45]] : f32
-// CHECK:                           store %[[VAL_46]], %[[VAL_17]]{{\[}}%[[VAL_41]], %[[VAL_38]], %[[VAL_35]], %[[VAL_34]], %[[VAL_29]], %[[VAL_22]], %[[VAL_19]], %[[VAL_18]]] : memref<100x200x300x400x500x600x700x800xf32>
+// CHECK-SAME:              %[[VAL_0:.*0]]: tensor<100x200x300x400x500x600x700x800xf32>,
+// CHECK-SAME:              %[[VAL_1:.*1]]: tensor<100x200x300x400x500x600x700x800xf32>,
+// CHECK-SAME:              %[[VAL_2:.*2]]: tensor<100x200x300x400x500x600x700x800xf32>) -> tensor<100x200x300x400x500x600x700x800xf32> {
+// CHECK:           %[[VAL_3:.*]] = constant 999 : index
+// CHECK:           %[[VAL_4:.*]] = constant 100 : index
+// CHECK:           %[[VAL_5:.*]] = constant 200 : index
+// CHECK:           %[[VAL_6:.*]] = constant 300 : index
+// CHECK:           %[[VAL_7:.*]] = constant 600 : index
+// CHECK:           %[[VAL_8:.*]] = constant 700 : index
+// CHECK:           %[[VAL_9:.*]] = constant 800 : index
+// CHECK:           %[[VAL_10:.*]] = constant 0 : index
+// CHECK:           %[[VAL_11:.*]] = constant 1 : index
+// CHECK:           %[[VAL_12:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32>
+// CHECK:           %[[VAL_13:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_14:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_15:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_16:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
+// CHECK:           %[[VAL_17:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
+// CHECK:           %[[VAL_18:.*]] = alloca() : memref<100x200x300x400x500x600x700x800xf32>
+// CHECK:           scf.for %[[VAL_19:.*]] = %[[VAL_10]] to %[[VAL_9]] step %[[VAL_11]] {
+// CHECK:             scf.for %[[VAL_20:.*]] = %[[VAL_10]] to %[[VAL_8]] step %[[VAL_11]] {
+// CHECK:               %[[VAL_21:.*]] = muli %[[VAL_19]], %[[VAL_8]] : index
+// CHECK:               %[[VAL_22:.*]] = addi %[[VAL_21]], %[[VAL_20]] : index
+// CHECK:               scf.for %[[VAL_23:.*]] = %[[VAL_10]] to %[[VAL_7]] step %[[VAL_11]] {
+// CHECK:                 %[[VAL_24:.*]] = muli %[[VAL_22]], %[[VAL_7]] : index
+// CHECK:                 %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index
+// CHECK:                 %[[VAL_26:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_25]]] : memref<?xindex>
+// CHECK:                 %[[VAL_27:.*]] = addi %[[VAL_25]], %[[VAL_11]] : index
+// CHECK:                 %[[VAL_28:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_27]]] : memref<?xindex>
+// CHECK:                 scf.for %[[VAL_29:.*]] = %[[VAL_26]] to %[[VAL_28]] step %[[VAL_11]] {
+// CHECK:                   %[[VAL_30:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_29]]] : memref<?xindex>
+// CHECK:                   %[[VAL_31:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_29]]] : memref<?xindex>
+// CHECK:                   %[[VAL_32:.*]] = addi %[[VAL_29]], %[[VAL_11]] : index
+// CHECK:                   %[[VAL_33:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_32]]] : memref<?xindex>
+// CHECK:                   scf.for %[[VAL_34:.*]] = %[[VAL_31]] to %[[VAL_33]] step %[[VAL_11]] {
+// CHECK:                     %[[VAL_35:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_34]]] : memref<?xindex>
+// CHECK:                     scf.for %[[VAL_36:.*]] = %[[VAL_10]] to %[[VAL_6]] step %[[VAL_11]] {
+// CHECK:                       %[[VAL_37:.*]] = muli %[[VAL_34]], %[[VAL_6]] : index
+// CHECK:                       %[[VAL_38:.*]] = addi %[[VAL_37]], %[[VAL_36]] : index
+// CHECK:                       scf.for %[[VAL_39:.*]] = %[[VAL_10]] to %[[VAL_5]] step %[[VAL_11]] {
+// CHECK:                         %[[VAL_40:.*]] = muli %[[VAL_38]], %[[VAL_5]] : index
+// CHECK:                         %[[VAL_41:.*]] = addi %[[VAL_40]], %[[VAL_39]] : index
+// CHECK:                         scf.for %[[VAL_42:.*]] = %[[VAL_10]] to %[[VAL_4]] step %[[VAL_11]] {
+// CHECK:                           %[[VAL_43:.*]] = muli %[[VAL_41]], %[[VAL_4]] : index
+// CHECK:                           %[[VAL_44:.*]] = addi %[[VAL_43]], %[[VAL_42]] : index
+// CHECK:                           %[[VAL_45:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_42]], %[[VAL_39]], %[[VAL_36]], %[[VAL_35]], %[[VAL_30]], %[[VAL_23]], %[[VAL_20]], %[[VAL_19]]] : memref<100x200x300x400x500x600x700x800xf32>
+// CHECK:                           %[[VAL_46:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_44]]] : memref<?xf32>
+// CHECK:                           %[[VAL_47:.*]] = mulf %[[VAL_45]], %[[VAL_46]] : f32
+// CHECK:                           store %[[VAL_47]], %[[VAL_18]]{{\[}}%[[VAL_42]], %[[VAL_39]], %[[VAL_36]], %[[VAL_35]], %[[VAL_30]], %[[VAL_23]], %[[VAL_20]], %[[VAL_19]]] : memref<100x200x300x400x500x600x700x800xf32>
 // CHECK:                         }
 // CHECK:                       }
 // CHECK:                     }
@@ -76,17 +77,18 @@
 // CHECK:               }
 // CHECK:             }
 // CHECK:           }
-// CHECK:           %[[VAL_47:.*]] = tensor_load %[[VAL_17]] : memref<100x200x300x400x500x600x700x800xf32>
-// CHECK:           return %[[VAL_47]] : tensor<100x200x300x400x500x600x700x800xf32>
+// CHECK:           %[[VAL_48:.*]] = tensor_load %[[VAL_18]] : memref<100x200x300x400x500x600x700x800xf32>
+// CHECK:           return %[[VAL_48]] : tensor<100x200x300x400x500x600x700x800xf32>
 // CHECK:         }
 func @mul(%arga: tensor<100x200x300x400x500x600x700x800xf32>,
-          %argb: tensor<100x200x300x400x500x600x700x800xf32>)
+          %argb: tensor<100x200x300x400x500x600x700x800xf32>,
+          %argx: tensor<100x200x300x400x500x600x700x800xf32>)
 	      -> tensor<100x200x300x400x500x600x700x800xf32> {
   %0 = linalg.generic #trait_mul
     ins(%arga, %argb: tensor<100x200x300x400x500x600x700x800xf32>,
                       tensor<100x200x300x400x500x600x700x800xf32>)
-    outs(%arga: tensor<100x200x300x400x500x600x700x800xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
+    outs(%argx: tensor<100x200x300x400x500x600x700x800xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
     }      -> tensor<100x200x300x400x500x600x700x800xf32>

diff  --git a/mlir/test/Dialect/Linalg/sparse_parallel.mlir b/mlir/test/Dialect/Linalg/sparse_parallel.mlir
index 3d3d51ae0327..f8e9d4e922c5 100644
--- a/mlir/test/Dialect/Linalg/sparse_parallel.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_parallel.mlir
@@ -48,12 +48,12 @@
 // CHECK-PAR4:           scf.parallel
 // CHECK-PAR4:         return
 //
-func @scale_dd(%scale: f32, %arga: tensor<?x?xf32>) -> tensor<?x?xf32> {
+func @scale_dd(%scale: f32, %arga: tensor<?x?xf32>, %argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
   %0 = linalg.generic #trait_dd
      ins(%arga: tensor<?x?xf32>)
-    outs(%arga: tensor<?x?xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = mulf %a, %scale  : f32
+    outs(%argx: tensor<?x?xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = mulf %a, %scale : f32
         linalg.yield %0 : f32
   } -> tensor<?x?xf32>
   return %0 : tensor<?x?xf32>
@@ -98,12 +98,12 @@ func @scale_dd(%scale: f32, %arga: tensor<?x?xf32>) -> tensor<?x?xf32> {
 // CHECK-PAR4:           scf.parallel
 // CHECK-PAR4:         return
 //
-func @scale_ss(%scale: f32, %arga: tensor<?x?xf32>) -> tensor<?x?xf32> {
+func @scale_ss(%scale: f32, %arga: tensor<?x?xf32>, %argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
   %0 = linalg.generic #trait_ss
      ins(%arga: tensor<?x?xf32>)
-    outs(%arga: tensor<?x?xf32>) {
-      ^bb(%a: f32, %s: f32):
-        %0 = mulf %a, %scale  : f32
+    outs(%argx: tensor<?x?xf32>) {
+      ^bb(%a: f32, %x: f32):
+        %0 = mulf %a, %scale : f32
         linalg.yield %0 : f32
   } -> tensor<?x?xf32>
   return %0 : tensor<?x?xf32>
@@ -153,7 +153,7 @@ func @scale_ss(%scale: f32, %arga: tensor<?x?xf32>) -> tensor<?x?xf32> {
 func @matvec(%argA: tensor<16x32xf32>, %argb: tensor<32xf32>, %argx: tensor<16xf32>) -> tensor<16xf32> {
   %0 = linalg.generic #trait_matvec
       ins(%argA, %argb : tensor<16x32xf32>, tensor<32xf32>)
-     outs(%argx : tensor<16xf32>) {
+     outs(%argx: tensor<16xf32>) {
     ^bb(%A: f32, %b: f32, %x: f32):
       %0 = mulf %A, %b : f32
       %1 = addf %0, %x : f32

diff  --git a/mlir/test/Dialect/Linalg/sparse_storage.mlir b/mlir/test/Dialect/Linalg/sparse_storage.mlir
index ef5dc0d766e3..cc1207ec2204 100644
--- a/mlir/test/Dialect/Linalg/sparse_storage.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_storage.mlir
@@ -122,14 +122,13 @@
 // CHECK-TYPE5:   store %[[MUL]], %{{.*}}[%[[INDC]]] : memref<32xf64>
 // CHECK-TYPE5: }
 
-func @mul_dd(%arga: tensor<32xf64>, %argb: tensor<32xf64>) -> tensor<32xf64> {
+func @mul_dd(%arga: tensor<32xf64>, %argb: tensor<32xf64>, %argx: tensor<32xf64>) -> tensor<32xf64> {
   %0 = linalg.generic #trait_mul_1d
      ins(%arga, %argb: tensor<32xf64>, tensor<32xf64>)
-    outs(%arga : tensor<32xf64>) {
-      ^bb(%a: f64, %b: f64, %s: f64):
-        %0 = mulf %a, %b  : f64
+    outs(%argx: tensor<32xf64>) {
+      ^bb(%a: f64, %b: f64, %x: f64):
+        %0 = mulf %a, %b : f64
         linalg.yield %0 : f64
   } -> tensor<32xf64>
   return %0 : tensor<32xf64>
 }
-

diff  --git a/mlir/test/Dialect/Linalg/sparse_vector.mlir b/mlir/test/Dialect/Linalg/sparse_vector.mlir
index 789b43b26acc..2d79a5cf67d2 100644
--- a/mlir/test/Dialect/Linalg/sparse_vector.mlir
+++ b/mlir/test/Dialect/Linalg/sparse_vector.mlir
@@ -54,11 +54,11 @@
 // CHECK-VEC2:       }
 // CHECK-VEC2:       return
 //
-func @scale_d(%arga: tensor<1024xf32>, %scale: f32) -> tensor<1024xf32> {
+func @scale_d(%arga: tensor<1024xf32>, %scale: f32, %argx: tensor<1024xf32>) -> tensor<1024xf32> {
   %0 = linalg.generic #trait_scale_d
     ins(%arga: tensor<1024xf32>)
-    outs(%arga: tensor<1024xf32>) {
-      ^bb(%a: f32, %s : f32):
+    outs(%argx: tensor<1024xf32>) {
+      ^bb(%a: f32, %x: f32):
         %0 = mulf %a, %scale : f32
         linalg.yield %0 : f32
   } -> tensor<1024xf32>
@@ -134,11 +134,11 @@ func @scale_d(%arga: tensor<1024xf32>, %scale: f32) -> tensor<1024xf32> {
 // CHECK-VEC2:       }
 // CHECK-VEC2:       return
 //
-func @mul_s(%arga: tensor<1024xf32>, %argb: tensor<1024xf32>) -> tensor<1024xf32> {
+func @mul_s(%arga: tensor<1024xf32>, %argb: tensor<1024xf32>, %argx: tensor<1024xf32>) -> tensor<1024xf32> {
   %0 = linalg.generic #trait_mul_s
     ins(%arga, %argb: tensor<1024xf32>, tensor<1024xf32>)
-    outs(%arga: tensor<1024xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
+    outs(%argx: tensor<1024xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<1024xf32>
@@ -208,7 +208,7 @@ func @reduction_d(%arga: tensor<1024xf32>, %argb: tensor<1024xf32>, %argx: tenso
   %0 = linalg.generic #trait_reduction_d
     ins(%arga, %argb: tensor<1024xf32>, tensor<1024xf32>)
     outs(%argx: tensor<f32>) {
-      ^bb(%a: f32, %b : f32, %x : f32):
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = mulf %a, %b : f32
         %1 = addf %x, %0 : f32
         linalg.yield %1 : f32
@@ -288,8 +288,8 @@ func @reduction_d(%arga: tensor<1024xf32>, %argb: tensor<1024xf32>, %argx: tenso
 // CHECK-VEC2:         scf.for %[[j:.*]] = %[[q]] to %[[s]] step %[[c16]] {
 // CHECK-VEC2:           %[[sub:.*]] = subi %[[s]], %[[j]] : index
 // CHECK-VEC2:           %[[mask:.*]] = vector.create_mask %[[sub]] : vector<16xi1>
-// CHECK-VEC2:           %[[lj:.*]] = vector.maskedload %{{.*}}[%arg3], %[[mask]], %{{.*}} : memref<?xi32>, vector<16xi1>, vector<16xi32> into vector<16xi32>
-// CHECK-VEC2:           %[[la:.*]] = vector.maskedload %{{.*}}[%arg3], %[[mask]], %{{.*}} : memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
+// CHECK-VEC2:           %[[lj:.*]] = vector.maskedload %{{.*}}[%[[j]]], %[[mask]], %{{.*}} : memref<?xi32>, vector<16xi1>, vector<16xi32> into vector<16xi32>
+// CHECK-VEC2:           %[[la:.*]] = vector.maskedload %{{.*}}[%[[j]]], %[[mask]], %{{.*}} : memref<?xf32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
 // CHECK-VEC2:           %[[lb:.*]] = vector.gather %{{.*}}[%[[lj]]], %[[mask]], %{{.*}} : memref<512x1024xf32>, vector<16xi32>, vector<16xi1>, vector<16xf32> into vector<16xf32>
 // CHECK-VEC2:           %[[m:.*]] = mulf %[[la]], %[[lb]] : vector<16xf32>
 // CHECK-VEC2:           vector.scatter %{{.*}}[%[[lj]]], %[[mask]], %[[m]] : memref<512x1024xf32>, vector<16xi32>, vector<16xi1>, vector<16xf32>
@@ -297,11 +297,11 @@ func @reduction_d(%arga: tensor<1024xf32>, %argb: tensor<1024xf32>, %argx: tenso
 // CHECK-VEC2:       }
 // CHECK-VEC2:       return
 //
-func @mul_ds(%arga: tensor<512x1024xf32>, %argb: tensor<512x1024xf32>) -> tensor<512x1024xf32> {
+func @mul_ds(%arga: tensor<512x1024xf32>, %argb: tensor<512x1024xf32>, %argx: tensor<512x1024xf32>) -> tensor<512x1024xf32> {
   %0 = linalg.generic #trait_mul_ds
     ins(%arga, %argb: tensor<512x1024xf32>, tensor<512x1024xf32>)
-    outs(%arga: tensor<512x1024xf32>) {
-      ^bb(%a: f32, %b: f32, %s : f32):
+    outs(%argx: tensor<512x1024xf32>) {
+      ^bb(%a: f32, %b: f32, %x: f32):
         %0 = mulf %a, %b : f32
         linalg.yield %0 : f32
   } -> tensor<512x1024xf32>


        


More information about the Mlir-commits mailing list