[MLIR][Linalg] Retire C++ MatvecOp in favor of a linalg-ods-gen'd op

[chelini]

Summary

Replace C++ MatvecOp, now that DRR rules have been dropped.

[nicolasvasilache]

Great, thank you @chelini !

[chelini]

In D82007#2098305, @nicolasvasilache wrote:

Great, thank you @chelini !

Could you please land it? I don't have commit access.

[ftynse]

Landing. Please consider using arc to send patches, it preserves commit author info. I took yours from your github account.

mlir/include/mlir/Dialect/Linalg/IR/LinalgNamedStructuredOpsSpec.tc

 ods_def<MatmulOp>:
 def matmul(A: f32(M, K), B: f32(K, N)) -> (C: f32(M, N)) {
   C(m, n) = std_addf<k>(std_mulf(A(m, k), B(k, n)));
 }
 
+ods_def<MatvecOp>:
+def matvec(A: f32(M, N), y: f32(N)) -> (x: f32(M)) {
+  x(m) = std_addf<n>(std_mulf(A(m, n), y(n)));
+}
+
 ods_def<BatchMatmulOp>:
 def batch_matmul(A: f32(Batch, M, K), B: f32(Batch, K, N)) -> (C: f32(Batch, M, N)) {
   C(b, m, n) = std_addf<k>(std_mulf(A(b, m, k), B(b, k, n)));
 }

mlir/include/mlir/Dialect/Linalg/IR/LinalgStructuredOps.td

llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps() {
         AffineMap::get(1, 0, {r_i}, context),
         AffineMap::get(1, 0, {}, context)};
     }
   }];
 
   let hasFolder = 1;
 }
 
-def MatvecOp : LinalgStructured_Op<"matvec", [NInputs<2>, NOutputs<1>]> {
-
-  let arguments = (ins AnyStridedMemRefOfRank<2>,
-                       AnyStridedMemRefOfRank<1>,
-                       AnyStridedMemRefOfRank<1>);
-
-  let extraClassDeclaration = libraryCallName # [{
-    llvm::Optional<SmallVector<StringRef, 8>> referenceIterators() {
-      return SmallVector<StringRef, 8>{
-        getParallelIteratorTypeName(), getReductionIteratorTypeName()};
-    }
-
-    // A(i, r_j) * B(r_j) -> C(i)
-    llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps() {
-      MLIRContext *context = getContext();
-      AffineExpr i, r_j;
-      bindDims(context, i, r_j);
-      return SmallVector<AffineMap, 8>{
-        AffineMap::get(2, 0, {i, r_j}, context),
-        AffineMap::get(2, 0, {r_j}, context),
-        AffineMap::get(2, 0, {i}, context)
-      };
-    }
-  }];
-
-  let hasFolder = 1;
-}
-
 /// A base class for pooling operation such as conv. The arguments must contain
 /// optional arguments `strides`, `dilations` and `padding` with following type:
 ///   OptionalAttr<I64ArrayAttr>:$strides
 ///   OptionalAttr<I64ArrayAttr>:$dilations
 ///   OptionalAttr<I64ElementsAttr>:$padding
 /// `strides` denotes the step of each window along the dimension.
 class PoolingBase_Op<string mnemonic, list<OpTrait> props>
   : LinalgStructured_Op<mnemonic, props> {

mlir/lib/Conversion/LinalgToStandard/LinalgToStandard.cpp

patterns.insert<
       LinalgOpConversion<ConvOp>,
       LinalgOpConversion<PoolingMaxOp>,
       LinalgOpConversion<PoolingMinOp>,
       LinalgOpConversion<PoolingSumOp>,
       LinalgOpConversion<CopyOp>,
       LinalgOpConversion<DotOp>,
       LinalgOpConversion<FillOp>,
       LinalgOpConversion<GenericOp>,
-      LinalgOpConversion<IndexedGenericOp>,
-      LinalgOpConversion<MatvecOp>>(ctx);
+      LinalgOpConversion<IndexedGenericOp>>(ctx);
   // TODO: collect all auto-generated named ops with a tblgen directive.
   patterns.insert<
       LinalgOpConversion<BatchMatmulOp>,
+      LinalgOpConversion<MatvecOp>,
       LinalgOpConversion<MatmulOp>>(ctx);
   // clang-format on
 }
 
 namespace {
 struct ConvertLinalgToStandardPass
     : public ConvertLinalgToStandardBase<ConvertLinalgToStandardPass> {
   void runOnOperation() override;

mlir/lib/Dialect/Linalg/IR/LinalgOps.cpp

 LogicalResult GenericOp::fold(ArrayRef<Attribute>,
                               SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
 LogicalResult IndexedGenericOp::fold(ArrayRef<Attribute>,
                                      SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
-LogicalResult MatvecOp::fold(ArrayRef<Attribute>,
-                             SmallVectorImpl<OpFoldResult> &) {
-  return foldMemRefCast(*this);
-}
 OpFoldResult ReshapeOp::fold(ArrayRef<Attribute>) {
   if (succeeded(foldMemRefCast(*this)))
     return getResult();
   return foldReshapeOp(*this);
 }
 OpFoldResult SliceOp::fold(ArrayRef<Attribute>) {
   if (succeeded(foldMemRefCast(*this)))
     return getResult();

 LogicalResult BatchMatmulOp::fold(ArrayRef<Attribute>,
                                   SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
 LogicalResult MatmulOp::fold(ArrayRef<Attribute>,
                              SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
+LogicalResult MatvecOp::fold(ArrayRef<Attribute>,
+                             SmallVectorImpl<OpFoldResult> &) {
+  return foldMemRefCast(*this);
+}

mlir/lib/Dialect/Linalg/Transforms/Loops.cpp

assert(dotOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   assert(allIvs.size() == 1);
   Value r_i(allIvs[0]);
   IndexedValueType A(dotOp.getInput(0)), B(dotOp.getInput(1)),
       C(dotOp.getOutputBuffer(0));
   // Emit scalar form.
   C() = C() + A(r_i) * B(r_i);
 }
-template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, MatvecOp matvecOp) {
-  assert(matvecOp.hasBufferSemantics() &&
-         "expected linalg op with buffer semantics");
-  assert(allIvs.size() == 2);
-  Value i(allIvs[0]), r_j(allIvs[1]);
-  IndexedValueType A(matvecOp.getInput(0)), B(matvecOp.getInput(1)),
-      C(matvecOp.getOutputBuffer(0));
-  // Emit scalar form.
-  C(i) = C(i) + A(i, r_j) * B(r_j);
-}
 
 template <typename IndexedValueType>
 Value getConvOpInput(ConvOp convOp, StdIndexedValue im,
                      MutableArrayRef<Value> imIdx) {
   // TODO(ntv): add a level of indirection to linalg.generic.
   if (!convOp.padding())
     return im(imIdx);
 
Optional<LinalgLoops> linalgOpToLoopsImplSwitch(Operation *op,
                                                 OpBuilder &builder) {
   assert(isa<LinalgOp>(op) && "LinalgOp expected");
   if (isa<CopyOp>(op))
     return linalgOpToLoopsImpl<LoopTy, CopyOp>(op, builder);
   if (isa<FillOp>(op))
     return linalgOpToLoopsImpl<LoopTy, FillOp>(op, builder);
   if (isa<DotOp>(op))
     return linalgOpToLoopsImpl<LoopTy, DotOp>(op, builder);
-  if (isa<MatvecOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, MatvecOp>(op, builder);
   if (isa<ConvOp>(op))
     return linalgOpToLoopsImpl<LoopTy, ConvOp>(op, builder);
   if (isa<PoolingMaxOp>(op))
     return linalgOpToLoopsImpl<LoopTy, PoolingMaxOp>(op, builder);
   if (isa<PoolingMinOp>(op))
     return linalgOpToLoopsImpl<LoopTy, PoolingMinOp>(op, builder);
   if (isa<PoolingSumOp>(op))
     return linalgOpToLoopsImpl<LoopTy, PoolingSumOp>(op, builder);
   if (isa<IndexedGenericOp>(op))
     return linalgOpToLoopsImpl<LoopTy, IndexedGenericOp>(op, builder);
 
   // TODO: Cases below are generic and need a LinalgStructuredOpInterface.
   if (isa<GenericOp>(op))
     return linalgOpToLoopsImpl<LoopTy, GenericOp>(op, builder);
   if (isa<MatmulOp>(op))
     return linalgOpToLoopsImpl<LoopTy, MatmulOp>(op, builder);
+  if (isa<MatvecOp>(op))
+    return linalgOpToLoopsImpl<LoopTy, MatvecOp>(op, builder);
   if (isa<BatchMatmulOp>(op))
     return linalgOpToLoopsImpl<LoopTy, BatchMatmulOp>(op, builder);
   llvm_unreachable("Unexpected op in linalgOpToLoopsImpl");
 }
 
 /// Emits a loop nest with the proper body for `op`.
 template <typename LoopTy>
 Optional<LinalgLoops> mlir::linalg::linalgLowerOpToLoops(OpBuilder &builder,

mlir/test/Dialect/Linalg/loops.mlir

 
 
 func @matvec(%arg0: memref<?xi8>, %M: index, %N: index) {
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %2 = view %arg0[%c0][%M, %N] : memref<?xi8> to memref<?x?xf32>
   %3 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
   %4 = view %arg0[%c0][%N] : memref<?xi8> to memref<?xf32>
-  linalg.matvec(%2, %3, %4) : memref<?x?xf32>, memref<?xf32>, memref<?xf32>
+  linalg.matvec %2, %3, %4 : (memref<?x?xf32>, memref<?xf32>, memref<?xf32>)
   return
 }
 // CHECKLOOP-LABEL: func @matvec(%{{.*}}: memref<?xi8>,
 //  CHECKLOOP-SAME: [[M:arg[0-9]+]]: index
 //  CHECKLOOP-SAME: [[K:arg[0-9]+]]: index
 //       CHECKLOOP: %[[A:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?x?xf32>
 //       CHECKLOOP: %[[B:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>
 //       CHECKLOOP: %[[C:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>

mlir/test/Dialect/Linalg/roundtrip.mlir

 
 func @ops(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
           %arg1: memref<?xf32, offset: ?, strides: [1]>,
           %arg2: memref<?xf32, offset: ?, strides: [1]>,
           %arg3: memref<f32>) {
   linalg.matmul %arg0, %arg0, %arg0 : (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                                        memref<?x?xf32, offset: ?, strides: [?, 1]>,
                                        memref<?x?xf32, offset: ?, strides: [?, 1]>)
-  linalg.matvec(%arg0, %arg1, %arg2) : memref<?x?xf32, offset: ?, strides: [?, 1]>,
+  linalg.matvec %arg0, %arg1, %arg2 : (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                                        memref<?xf32, offset: ?, strides: [1]>,
-                                       memref<?xf32, offset: ?, strides: [1]>
+                                       memref<?xf32, offset: ?, strides: [1]>)
   linalg.dot(%arg1, %arg2, %arg3) : memref<?xf32, offset: ?, strides: [1]>,
                                     memref<?xf32, offset: ?, strides: [1]>,
                                     memref<f32>
   return
 }
 // CHECK-LABEL: func @ops(%
 //  CHECK-NEXT:  linalg.matmul %{{.*}}, %{{.*}}, %{{.*}} :
 //  CHECK-SAME:    (memref<?x?xf32, #[[$strided2D]]>,
 //  CHECK-SAME:     memref<?x?xf32, #[[$strided2D]]>,
 //  CHECK-SAME:     memref<?x?xf32, #[[$strided2D]]>)
-//  CHECK-NEXT:  linalg.matvec(%{{.*}}, %{{.*}}, %{{.*}}) :
-//  CHECK-SAME:     memref<?x?xf32, #[[$strided2D]]>,
+//  CHECK-NEXT:  linalg.matvec %{{.*}}, %{{.*}}, %{{.*}} :
+//  CHECK-SAME:    (memref<?x?xf32, #[[$strided2D]]>,
 //  CHECK-SAME:     memref<?xf32, #[[$strided1D]]>,
-//  CHECK-SAME:     memref<?xf32, #[[$strided1D]]>
+//  CHECK-SAME:     memref<?xf32, #[[$strided1D]]>)
 //  CHECK-NEXT:  linalg.dot(%{{.*}}, %{{.*}}, %{{.*}}) :
 //  CHECK-SAME:     memref<?xf32, #[[$strided1D]]>,
 //  CHECK-SAME:     memref<?xf32, #[[$strided1D]]>,
 //  CHECK-SAME:     memref<f32>
 
 // -----
 
 // CHECK-DAG: #[[$strided1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>

mlir/test/Dialect/Linalg/tile.mlir

 //       TILE-234:        %[[sCij:.*]] = subview %{{.*}}[%[[I]], %[[J]]] [%{{.*}}, %{{.*}}] [1, 1] : memref<10x12xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //
 //       TILE-234:        linalg.matmul %[[sAik]], %[[sBkj]], %[[sCij]] :
 //       TILE-234:          (memref<?x?xf32, #[[$strided2D]]>,
 //       TILE-234:           memref<?x?xf32, #[[$strided2D]]>,
 //       TILE-234:           memref<?x?xf32, #[[$strided2D]]>)
 
 func @matvec(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>, %arg1: memref<?xf32, offset: ?, strides: [1]>, %arg2: memref<?xf32, offset: ?, strides: [1]>) {
-  linalg.matvec(%arg0, %arg1, %arg2) : memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?xf32, offset: ?, strides: [1]>, memref<?xf32, offset: ?, strides: [1]>
+  linalg.matvec %arg0, %arg1, %arg2 : (
+    memref<?x?xf32, offset: ?, strides: [?, 1]>, 
+    memref<?xf32, offset: ?, strides: [1]>, 
+    memref<?xf32, offset: ?, strides: [1]>)
   return
 }
 // TILE-2-LABEL: func @matvec(
 //  TILE-2-SAME: %[[ARG0:[0-9a-zA-Z]*]]: memref
 //  TILE-2-SAME: %[[ARG1:[0-9a-zA-Z]*]]: memref
 //  TILE-2-SAME: %[[ARG2:[0-9a-zA-Z]*]]: memref
 //       TILE-2-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-2-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-2: %[[M:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2: scf.for %[[I:.*]] = %{{.*}}{{.*}} to %[[M]] step %{{.*}} {
 //       TILE-2:   %[[localM:.*]] = dim %[[ARG0]], %c0
 //       TILE-2:   %[[szM:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localM]]]
 //       TILE-2:   %[[N:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2:   %[[sAi:.*]] = subview %{{.*}}[%[[I]], 0] [%[[szM]], %[[N]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2:   %[[localN:.*]] = dim %{{.*}}, %c0
 //       TILE-2:   %[[szN:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localN]]]
 //       TILE-2:   %[[sCi:.*]] = subview %{{.*}}[%[[I]]] [%[[szN]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
-//       TILE-2:   linalg.matvec(%[[sAi]], %{{.*}}, %[[sCi]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>
+//       TILE-2:   linalg.matvec %[[sAi]], %{{.*}}, %[[sCi]] : (memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>)
 
 // TILE-02-LABEL: func @matvec(
 // TILE-02-SAME: %[[ARG0:[0-9a-zA-Z]*]]: memref
 // TILE-02-SAME: %[[ARG1:[0-9a-zA-Z]*]]: memref
 // TILE-02-SAME: %[[ARG2:[0-9a-zA-Z]*]]: memref
 //       TILE-02-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-02-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-02: %[[K:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02: scf.for %[[J:.*]] = %{{.*}}{{.*}} to %[[K]] step %{{.*}} {
 //       TILE-02:   %[[M:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02:   %[[localN:.*]] = dim %{{.*}}, %c1
 //       TILE-02:   %[[szN:.*]] = affine.min #[[$bound_map]](%[[J]])[%[[localN]]]
 //       TILE-02:   %[[sAj:.*]] = subview %{{.*}}[0, %[[J]]] [%[[M]], %[[szN]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02:   %[[localN:.*]] = dim %{{.*}}, %c0
 //       TILE-02:   %[[szN:.*]] = affine.min #[[$bound_map]](%[[J]])[%[[localN]]]
 //       TILE-02:   %[[sBj:.*]] = subview %{{.*}}[%[[J]]] [%[[szN]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
-//       TILE-02:   linalg.matvec(%[[sAj]], %[[sBj]], %{{.*}}) : memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>
+//       TILE-02:   linalg.matvec %[[sAj]], %[[sBj]], %{{.*}} : (memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>)
 
 // TILE-002-LABEL: func @matvec(
 // TILE-002-SAME: %[[ARG0:[0-9a-zA-Z]*]]: memref
 // TILE-002-SAME: %[[ARG1:[0-9a-zA-Z]*]]: memref
 // TILE-002-SAME: %[[ARG2:[0-9a-zA-Z]*]]: memref
 //   TILE-002-NOT: scf.for
 
 // TILE-234-LABEL: func @matvec(

 //       TILE-234:      %[[sAij:.*]] = subview %{{.*}}[%[[I]], %[[J]]] [%[[szM]], %[[szN]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-234:      %[[localN:.*]] = dim %{{.*}}, %c0
 //       TILE-234:      %[[szN:.*]] = affine.min #[[$bound_map_3]](%[[J]])[%[[localN]]]
 //       TILE-234:      %[[sBj:.*]] = subview %{{.*}}[%[[J]]] [%[[szN]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
 //       TILE-234:      %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-234:      %[[szM:.*]] = affine.min #[[$bound_map_2]](%[[I]])[%[[localM]]]
 //       TILE-234:      %[[sCi:.*]] = subview %{{.*}}[%[[I]]] [%[[szM]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
 //
-//       TILE-234:      linalg.matvec(%[[sAij]], %[[sBj]], %[[sCi]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>
+//       TILE-234:      linalg.matvec %[[sAij]], %[[sBj]], %[[sCi]] : (memref<?x?xf32, #[[$strided2D]]>, memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>)
 
 func @dot(%arg0: memref<?xf32, offset: ?, strides: [1]>, %arg1: memref<?xf32, offset: ?, strides: [1]>, %arg2: memref<f32>) {
   linalg.dot(%arg0, %arg1, %arg2) : memref<?xf32, offset: ?, strides: [1]>, memref<?xf32, offset: ?, strides: [1]>, memref<f32>
   return
 }
 // TILE-2-LABEL: func @dot(
 //       TILE-2-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-2-DAG: %[[C2:.*]] = constant 2 : index

mlir/test/Dialect/Linalg/transform-patterns.mlir

 // CHECK:               mulf
 // CHECK:               load
 // CHECK:               addf
 // CHECK:               store
 
 func @matvec(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %x: memref<?xf32, offset: ?, strides: [1]>,
              %y: memref<?xf32, offset: ?, strides: [1]>) {
-  linalg.matvec(%A, %x, %y) :
-                memref<?x?xf32, offset: ?, strides: [?, 1]>,
+  linalg.matvec %A, %x, %y :
+                (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                  memref<?xf32, offset: ?, strides: [1]>,
-                memref<?xf32, offset: ?, strides: [1]>
+                 memref<?xf32, offset: ?, strides: [1]>)
   return
 }
 // CHECK-LABEL: func @matvec
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c5:.*]] = constant 5 : index
 // CHECK-DAG:     %[[c6:.*]] = constant 6 : index
 // CHECK:         scf.parallel {{.*}} step (%[[c5]])
 // CHECK:           scf.for {{.*}} step %[[c6]]
-// CHECK:             linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?xf32, #[[$STRIDED_1D]]>, memref<?xf32, #[[$STRIDED_1D]]>
+// CHECK:             linalg.matvec {{.*}}, {{.*}}, {{.*}} : (memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?xf32, #[[$STRIDED_1D]]>, memref<?xf32, #[[$STRIDED_1D]]>)
 
 func @matmul(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %B: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %C: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
   linalg.matmul %A, %B, %C { __internal_linalg_transform__ = "MEM" } :
     (memref<?x?xf32, offset: ?, strides: [?, 1]>,
      memref<?x?xf32, offset: ?, strides: [?, 1]>,
      memref<?x?xf32, offset: ?, strides: [?, 1]>)

 // CHECK-SAME:     library_call = "linalg_matmul_indexed"} %{{.*}}, %{{.*}}, %{{.*}}
 // CHECK:            memref<?x?xf32, #[[$STRIDED_2D_u_1]]>,
 // CHECK-SAME:       memref<?x?xf32, #[[$STRIDED_2D_u_1]]>,
 // CHECK-SAME:       memref<?x?xf32, #[[$STRIDED_2D_u_1]]>
 
 func @matvec_perm(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %x: memref<?xf32, offset: ?, strides: [1]>,
              %y: memref<?xf32, offset: ?, strides: [1]>) {
-  linalg.matvec(%A, %x, %y) {__internal_linalg_transform__ = "__with_perm__"} :
-               memref<?x?xf32, offset: ?, strides: [?, 1]>,
+  linalg.matvec %A, %x, %y {__internal_linalg_transform__ = "__with_perm__"} :
+               (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                 memref<?xf32, offset: ?, strides: [1]>,
-               memref<?xf32, offset: ?, strides: [1]>
+                memref<?xf32, offset: ?, strides: [1]>)
   return
 }
 // CHECK-LABEL: func @matvec_perm
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c5:.*]] = constant 5 : index
 // CHECK-DAG:     %[[c6:.*]] = constant 6 : index
 // CHECK:         scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c6]]
 // CHECK:           scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c5]]
-// CHECK:             linalg.matvec({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?xf32, #[[$STRIDED_1D]]>, memref<?xf32, #[[$STRIDED_1D]]>
+// CHECK:             linalg.matvec {{.*}}, {{.*}}, {{.*}} : (memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?xf32, #[[$STRIDED_1D]]>, memref<?xf32, #[[$STRIDED_1D]]>)
 
 func @matmul_perm(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %B: memref<?x?xf32, offset: ?, strides: [?, 1]>,
              %C: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
   linalg.matmul %A, %B, %C {__internal_linalg_transform__ = "__with_perm__"} :
                (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                 memref<?x?xf32, offset: ?, strides: [?, 1]>,
                 memref<?x?xf32, offset: ?, strides: [?, 1]>)