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

[chelini]

Summary

• replace DotOp, now that DRR rules have been dropped.

• Capture arguments mismatch in the parser. The number of parsed arguments must equal the number of expected arguments.

[aartbik]

mlir/test/mlir-cpu-runner/linalg_integration_test.mlir

2

note that we now have the llvm/llvm-project/mlir/integration_test directory for integration tests that actually run generated code through the cpu runner; please consider moving it there at some point

[ftynse]

mlir/test/Dialect/Linalg/invalid.mlir

409–410

Please drop the check for the words 'custom op', they are emitted by the generic infra that is tested elsewhere. IMO, checking for "expects 3 operands, but found 2" is sufficient here.

[chelini]

Drop check for custom op

[chelini]

mlir/test/mlir-cpu-runner/linalg_integration_test.mlir

2

Thanks. I may follow-up with a new revision for that.

[nicolasvasilache]

@chelini thanks for your contribution!
Can we please land this?

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<DotOp>:
+def dot(A: f32(M), B: f32(M)) -> (C: f32()) {
+  C() = std_addf<m>(std_mulf(A(m), B(m)));
+}
+
 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/LinalgOps.h

 ///   2. drop the `linalg.` prefix, and the `<`, `>`, `?` symbols from the type.
 /// Assumes `op` is a LinalgOp.
 ///
 /// Examples:
 ///
 /// 1. linalg.fill(%A, %f) : memref<f32>, f32
 ///   name mangles into `linalg_fill_viewf32_f32_impl`
 ///
-/// 2. linalg.dot(%A, %B, %C) :
-///      memref<?xf32, stride_specification>,
-///      memref<?xf32, stride_specification>, memref<f32>
+/// 2. linalg.dot %A, %B, %C :
+///      (memref<?xf32, stride_specification>,
+///       memref<?xf32, stride_specification>, memref<f32>)
 ///   name mangles into `linalg_dot_viewxf32_viewxf32_viewf32_impl`
 ///
 /// 3. linalg.matmul(...) :
 ///      memref<?x?xf32, stride_specification>,
 ///      memref<?x?xf32, stride_specification>,
 ///      memref<?x?xf32, stride_specification>
 ///   name mangles into `linalg_matmul_viewxxf32_viewxxf32_viewxxf32_impl`
 std::string generateLibraryCallName(Operation *op);

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

let extraClassDeclaration = libraryCallName # [{
     }
   }];
 
   let verifier = [{ return ::verify(*this); }];
 
   let hasFolder = 1;
 }
 
-def DotOp : LinalgStructured_Op<"dot", [NInputs<2>, NOutputs<1>]> {
-
-  let arguments = (ins AnyStridedMemRefOfRank<1>,
-                       AnyStridedMemRefOfRank<1>,
-                       AnyStridedMemRefOfRank<0>);
-
-  let extraClassDeclaration = libraryCallName # [{
-    llvm::Optional<SmallVector<StringRef, 8>> referenceIterators() {
-      return SmallVector<StringRef, 8>{getReductionIteratorTypeName()};
-    }
-
-    // A(r_i) * B(r_i) -> C()
-    llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps() {
-      MLIRContext *context = getContext();
-      auto r_i = getAffineDimExpr(0, context);
-      return SmallVector<AffineMap, 8>{
-        AffineMap::get(1, 0, {r_i}, context),
-        AffineMap::get(1, 0, {r_i}, context),
-        AffineMap::get(1, 0, {}, 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

void mlir::populateLinalgToStandardConversionPatterns(
   // attribute values such as kernel striding and dilation.
   // clang-format off
   patterns.insert<
       CopyTransposeConversion,
       LinalgOpConversion<ConvOp>,
       LinalgOpConversion<PoolingMaxOp>,
       LinalgOpConversion<PoolingMinOp>,
       LinalgOpConversion<PoolingSumOp>,
-      LinalgOpConversion<CopyOp>,
-      LinalgOpConversion<DotOp>,
+      LinalgOpConversion<CopyOp>, 
       LinalgOpConversion<FillOp>,
       LinalgOpConversion<GenericOp>,
       LinalgOpConversion<IndexedGenericOp>>(ctx);
   // TODO: collect all auto-generated named ops with a tblgen directive.
   patterns.insert<
+      LinalgOpConversion<DotOp>,
       LinalgOpConversion<BatchMatmulOp>,
       LinalgOpConversion<MatvecOp>,
       LinalgOpConversion<MatmulOp>>(ctx);
   // clang-format on
 }
 
 namespace {
 struct ConvertLinalgToStandardPass

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

 LogicalResult PoolingSumOp::fold(ArrayRef<Attribute>,
                                  SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
 LogicalResult CopyOp::fold(ArrayRef<Attribute>,
                            SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
-LogicalResult DotOp::fold(ArrayRef<Attribute>,
-                          SmallVectorImpl<OpFoldResult> &) {
-  return foldMemRefCast(*this);
-}
 LogicalResult FillOp::fold(ArrayRef<Attribute>,
                            SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
 LogicalResult GenericOp::fold(ArrayRef<Attribute>,
                               SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
static ParseResult parseNamedStructuredOp(OpAsmParser &parser,
   // outputs are specified in the result type.
   SmallVector<Type, 8> tensorResultTypes;
   if (parser.parseOptionalArrowTypeList(tensorResultTypes))
     return failure();
 
   if (!tensorResultTypes.empty())
     result.addTypes(tensorResultTypes);
 
+  // The number of parsed arguments must equal
+  // the number of expected arguments for the current operation.
+  auto parsedArgs = operandsInfo.size();
+  auto expectedArgs = NamedStructuredOpType::getNumInputs() +
+                      NamedStructuredOpType::getNumOutputs();
+  if (parsedArgs != expectedArgs)
+    return parser.emitError(parser.getNameLoc(),
+                            "expects " + std::to_string(expectedArgs) +
+                                " operands, but found " +
+                                std::to_string(parsedArgs));
+
   buildNamedStructuredOpRegionAndAttributes<NamedStructuredOpType>(
       parser.getBuilder(), result, operandTypes, tensorResultTypes);
 
   return parser.resolveOperands(operandsInfo, operandTypes,
                                 parser.getCurrentLocation(), result.operands);
 }
 
 template <typename NamedStructuredOpType>
 static LogicalResult verifyNamedStructuredOp(NamedStructuredOpType op) {
   return verifyGenericOp<NamedStructuredOpType>(op);
 }
 
 #include "mlir/Dialect/Linalg/IR/LinalgNamedStructuredOps.cpp.inc"
 
 // TODO: Determine whether we can generate the folders and verifiers.
 LogicalResult BatchMatmulOp::fold(ArrayRef<Attribute>,
                                   SmallVectorImpl<OpFoldResult> &) {
   return foldMemRefCast(*this);
 }
+LogicalResult DotOp::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

void emitScalarImplementation(ArrayRef<Value> allIvs, FillOp fillOp) {
   auto ivs = SmallVector<Value, 4>(allIvs.begin(), allIvs.begin() + nPar);
   IndexedValueType O(fillOp.getOutputBuffer(0));
   // Emit the proper scalar assignment, whether we are dealing with a 0-D or
   // an n-D loop nest; with or without permutations.
   nPar > 0 ? O(ivs) = fillOp.value() : O() = fillOp.value();
 }
 
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, DotOp dotOp) {
-  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>
 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);
 
   auto *context = ScopedContext::getContext();
   Value zeroIndex = std_constant_index(0);

 template <typename LoopTy>
 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<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<DotOp>(op))
+    return linalgOpToLoopsImpl<LoopTy, DotOp>(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/invalid.mlir

^bb(%0: i4) :
       %1 = std.addf %0, %0: i4
   } : memref<?x?xi4>
   return
 }
 
 // -----
 
 func @generic_result_0_element_type(%arg0: memref<?xf32>) {
-  // expected-error @+1 {{'linalg.dot' op expected 3 operands, but found 2}}
-  linalg.dot(%arg0, %arg0): memref<?xf32>, memref<?xf32>
+  // expected-error @+1 {{'linalg.dot' expects 3 operands, but found 2}}
+  linalg.dot %arg0, %arg0 : (memref<?xf32>, memref<?xf32>)
 }
 
 // -----
 
 // expected-error @+1 {{unknown Linalg type}}
 !invalid_type = type !linalg.unknown
 
 // -----

mlir/test/Dialect/Linalg/loops.mlir

 
 
 func @dot(%arg0: memref<?xi8>, %M: index) {
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %1 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
   %2 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
   %3 = view %arg0[%c0][] : memref<?xi8> to memref<f32>
-  linalg.dot(%1, %2, %3) : memref<?xf32>, memref<?xf32>, memref<f32>
+  linalg.dot %1, %2, %3 : (memref<?xf32>, memref<?xf32>, memref<f32>)
   return
 }
 // CHECKLOOP-LABEL: func @dot(%{{.*}}: memref<?xi8>,
 //  CHECKLOOP-SAME: [[K:arg[0-9]+]]: index
 //       CHECKLOOP: %[[A:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
 //       CHECKLOOP: %[[B:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
 //       CHECKLOOP: %[[C:.*]] = std.view %{{.*}}[{{.*}}][] : memref<?xi8> to memref<f32>
 //       CHECKLOOP: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {

 //   CHECKPARALLEL-DAG:   %[[b:.*]] = load %[[B]][%{{.*}}] : memref<?xf32>
 //   CHECKPARALLEL-DAG:   %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
 //   CHECKPARALLEL-DAG:   %[[c:.*]] = load %[[C]][] : memref<f32>
 //   CHECKPARALLEL-DAG:   %[[res:.*]] = addf %[[c]], %[[inc]] : f32
 //       CHECKPARALLEL:   store %[[res]], %[[C]][] : memref<f32>
 
 
 func @dot_view(%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>
+  linalg.dot %arg0, %arg1, %arg2  : (memref<?xf32, offset: ?, strides: [1]>, 
+                                     memref<?xf32, offset: ?, strides: [1]>, 
+                                     memref<f32>)
   return
 }
 // CHECKLOOP-LABEL: func @dot_view(
 //       CHECKLOOP:   %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<f32>) {
 //       CHECKLOOP: %[[K:.*]] = dim %arg0, %c0 : memref<?xf32, #[[$strided1D]]>
 //       CHECKLOOP: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
 //   CHECKLOOP-DAG:   %[[a:.*]] = load %arg0[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
 //   CHECKLOOP-DAG:   %[[b:.*]] = load %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>

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]>,
                                        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]>) 
+  linalg.dot %arg1, %arg2, %arg3  : (memref<?xf32, offset: ?, strides: [1]>,
                                      memref<?xf32, offset: ?, strides: [1]>,
-                                    memref<f32>
+                                     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-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-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)>
 
 func @fill_view(%arg0: memref<?xf32, offset: ?, strides: [1]>, %arg1: f32) {
   linalg.fill(%arg0, %arg1) : memref<?xf32, offset: ?, strides: [1]>, f32
   return

mlir/test/Dialect/Linalg/standard.mlir

 // RUN: mlir-opt %s -convert-linalg-to-std | FileCheck %s
 
 // CHECK-DAG: #[[$map0:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
 // CHECK-DAG: #[[$map1:.*]] = affine_map<(d0, d1, d2)[s0, s1, s2] -> (d0 * s1 + s0 + d1 * s2 + d2)>
 // CHECK-DAG: #[[$map2:.*]] = affine_map<(d0, d1, d2)[s0, s1, s2] -> (d0 * s1 + s0 + d2 * s2 + d1)>
 // CHECK-DAG: #[[$map3:.*]] = affine_map<(d0, d1, d2) -> (d0, d2, d1)>
 // CHECK-DAG: #[[$map4:.*]] = affine_map<(d0, d1, d2)[s0, s1, s2] -> (d2 * s1 + s0 + d1 * s2 + d0)>
 // CHECK-DAG: #[[$map5:.*]] = affine_map<(d0, d1, d2) -> (d2, d1, d0)>
 // CHECK-DAG: #[[$map6:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1 + s0)>
 // CHECK-DAG: #[[$map7:.*]] = affine_map<()[s0] -> (s0)>
 // CHECK-DAG: #[[$map8:.*]] = affine_map<(d0, d1, d2)[s0, s1, s2, s3] -> (d0 * s1 + s0 + d1 * s2 + d2 * s3)>
 
 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]>,
+  linalg.dot %arg0, %arg1, %arg2  : (memref<?xf32, offset: ?, strides: [1]>,
                                      memref<?xf32, offset: ?, strides: [1]>,
-                                    memref<f32>
+                                     memref<f32>)
   return
 }
 // CHECK-LABEL: func @dot(
 //  CHECK-SAME: %[[arg0:[a-zA-z0-9]*]]: memref<?xf32, #[[$map0]]>,
 //  CHECK-SAME: %[[arg1:[a-zA-z0-9]*]]: memref<?xf32, #[[$map0]]>,
 //  CHECK-SAME: %[[arg2:[a-zA-z0-9]*]]: memref<f32>) {
 //       CHECK:   %[[o0:.*]] = memref_cast %[[arg0]] :
 //  CHECK-SAME:     memref<?xf32, #[[$map0]]> to memref<?xf32, #[[$map6]]>

mlir/test/Dialect/Linalg/tile.mlir

 //       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]]>)
 
 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>
+  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
 //       TILE-2: %[[M:.*]] = dim %{{.*}}, %c0 : memref<?xf32, #[[$strided1D]]>
 //       TILE-2: scf.for %[[I:.*]] = %{{.*}}{{.*}} to %[[M]] step %{{.*}} {
 //       TILE-2:   %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-2:   %[[szM:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localM]]]
 //       TILE-2:   %[[sAi:.*]] = subview %{{.*}}[%[[I]]] [%[[szM]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
 //       TILE-2:   %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-2:   %[[szM:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localM]]]
 //       TILE-2:   %[[sBi:.*]] = subview %{{.*}}[%[[I]]] [%[[szM]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
-//       TILE-2:   linalg.dot(%[[sAi]], %[[sBi]], {{.*}}) : memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>, memref<f32>
+//       TILE-2:   linalg.dot %[[sAi]], %[[sBi]], {{.*}} : (memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>, memref<f32>)
 
 // TILE-02-LABEL: func @dot(
 //   TILE-02-NOT: scf.for
 
 // TILE-002-LABEL: func @dot(
 //   TILE-002-NOT: scf.for
 
 // TILE-234-LABEL: func @dot(
 //       TILE-234-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-234-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-234:  %[[ubK:.*]] = dim %{{.*}}, %c0 : memref<?xf32, #[[$strided1D]]>
 //       TILE-234:  scf.for %[[I:.*]] = %{{.*}} to %[[ubK]] step %{{.*}} {
 //       TILE-234:    %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-234:    %[[szM:.*]] = affine.min #[[$bound_map_2]](%[[I]])[%[[localM]]]
 //       TILE-234:    %[[sAi:.*]] = subview %{{.*}}[%[[I]]] [%[[szM]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
 //       TILE-234:    %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-234:    %[[szM:.*]] = affine.min #[[$bound_map_2]](%[[I]])[%[[localM]]]
 //       TILE-234:    %[[sBi:.*]] = subview %{{.*}}[%[[I]]] [%[[szM]]] [1] : memref<?xf32, #[[$strided1D]]> to memref<?xf32, #[[$strided1D]]>
-//       TILE-234:    linalg.dot(%[[sAi]], %[[sBi]], %{{.*}}) : memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>, memref<f32>
+//       TILE-234:    linalg.dot %[[sAi]], %[[sBi]], %{{.*}} : (memref<?xf32, #[[$strided1D]]>, memref<?xf32, #[[$strided1D]]>, memref<f32>)
 
 func @fill_static(%arg0: memref<127x99xf32>, %arg1: f32) {
   linalg.fill(%arg0, %arg1) : memref<127x99xf32>, f32
   return
 }
 // TILE-2-LABEL: func @fill_static
 //       TILE-2:   for
 //   TILE-2-NOT:   for

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

 // RUN: mlir-opt %s -test-linalg-transform-patterns=test-patterns | FileCheck %s
 
 // CHECK-DAG: #[[$STRIDED_1D:.*]] = affine_map<(d0)[s0, s1] -> (d0 * s1  + s0)>
 // Map corresponding to a 2D memory access where the stride along the last dim is known to be 1.
 // CHECK-DAG: #[[$STRIDED_2D_u_1:.*]] = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
 // Map corresponding to a 2D memory access where the stride along all dims are unknown.
 // CHECK-DAG: #[[$STRIDED_2D:.*]] = affine_map<(d0, d1)[s0, s1, s2] -> (d0 * s1 + s0 + d1 * s2)>
 // CHECK-DAG: #[[$mk:.*]] = affine_map<(d0, d1, d2) -> (d0, d2)>
 // CHECK-DAG: #[[$kn:.*]] = affine_map<(d0, d1, d2) -> (d2, d1)>
 // CHECK-DAG: #[[$mn:.*]] = affine_map<(d0, d1, d2) -> (d0, d1)>
 // CHECK-DAG: #[[$nm:.*]] = affine_map<(d0, d1, d2) -> (d1, d0)>
 // CHECK-DAG: #[[$km:.*]] = affine_map<(d0, d1, d2) -> (d2, d0)>
 
 func @dot(%x: memref<?xf32, offset: ?, strides: [1]>,
           %y: memref<?xf32, offset: ?, strides: [1]>,
           %v: memref<f32>) {
-  linalg.dot(%x, %y, %v) { __internal_linalg_transform__ = "MEM" } :
+  linalg.dot %x, %y, %v { __internal_linalg_transform__ = "MEM" } :
+             (memref<?xf32, offset: ?, strides: [1]>,
               memref<?xf32, offset: ?, strides: [1]>,
-             memref<?xf32, offset: ?, strides: [1]>,
-             memref<f32>
+              memref<f32>)
   return
 }
 // CHECK-LABEL: func @dot
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c1:.*]] = constant 1 : index
 // CHECK-DAG:     %[[c8000:.*]] = constant 8000 : index
 // CHECK:         scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c8000]] {
 // CHECK:             scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c1]] {
 // CHECK:               load
 // CHECK:               load
-// CHECK:               mulf
 // CHECK:               load
+// CHECK:               mulf
 // 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]>,

mlir/test/mlir-cpu-runner/linalg_integration_test.mlir

 // RUN: mlir-opt %s -convert-linalg-to-std -convert-linalg-to-llvm \
 // RUN: | mlir-cpu-runner -e dot -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libmlir_test_cblas%shlibext,%linalg_test_lib_dir/libmlir_test_cblas_interface%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-linalg-to-std -convert-linalg-to-llvm \
 // RUN: | mlir-cpu-runner -e dot -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libmlir_test_cblas%shlibext,%linalg_test_lib_dir/libmlir_test_cblas_interface%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -convert-linalg-to-std -convert-linalg-to-llvm \
 // RUN: | mlir-cpu-runner -e matmul -entry-point-result=f32 -shared-libs=%linalg_test_lib_dir/libmlir_test_cblas%shlibext,%linalg_test_lib_dir/libmlir_test_cblas_interface%shlibext \
func @dot() -> f32 {
   %bA = call @alloc_filled_f32(%c16, %f2) : (index, f32) -> (memref<?xi8>)
   %bB = call @alloc_filled_f32(%c16, %f1) : (index, f32) -> (memref<?xi8>)
   %bC = call @alloc_filled_f32(%c1, %f10) : (index, f32) -> (memref<?xi8>)
 
   %A = view %bA[%c0][%c16] : memref<?xi8> to memref<?xf32>
   %B = view %bB[%c0][%c16] : memref<?xi8> to memref<?xf32>
   %C = view %bC[%c0][] : memref<?xi8> to memref<f32>
 
-  linalg.dot(%A, %B, %C) : memref<?xf32>, memref<?xf32>, memref<f32>
+  linalg.dot %A, %B, %C : (memref<?xf32>, memref<?xf32>, memref<f32>)
   %res = load %C[] : memref<f32>
 
   dealloc %bC : memref<?xi8>
   dealloc %bB : memref<?xi8>
   dealloc %bA : memref<?xi8>
 
   return %res : f32
 }