[mlir][Linalg] Retire C++ MatmulOp in favor of a linalg-ods-gen'd op.

[nicolasvasilache]

Summary

This revision replaces MatmulOp, now that DRR rules have been dropped.
This revision also fixes minor parsing bugs and a plugs a few holes to get e2e paths working (e.g. library call emission).

During the replacement the i32 version had to be dropped because only the EDSC operators +, *, etc support type inference.

Deciding on a type-polymorphic behavior, and implementing it, is left for future work.

[nicolasvasilache]

This is a resubmit of 8c6c49f293fc85e14d811d772bdc9a68464d67b4 that was reverted in 9b72b47ed63351ee5ceff4c44ccd9a71dc7dad27.

[nicolasvasilache]

Drop spurious test change.

[nicolasvasilache]

Because apparently I can.

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<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(2, 0, {i}, context)
       };
     }
   }];
 
   let hasFolder = 1;
 }
 
-def MatmulOp : LinalgStructured_Op<"matmul", [NInputs<2>, NOutputs<1>]> {
-
-  let arguments = (ins AnyStridedMemRefOfRank<2>,
-                       AnyStridedMemRefOfRank<2>,
-                       AnyStridedMemRefOfRank<2>);
-
-  let extraClassDeclaration = libraryCallName # [{
-    llvm::Optional<SmallVector<StringRef, 8>> referenceIterators() {
-      return SmallVector<StringRef, 8>{
-        getParallelIteratorTypeName(),
-        getParallelIteratorTypeName(),
-        getReductionIteratorTypeName()};
-    }
-
-    //   A(i, r_k) * B(r_k, j) -> C(i, j)
-    llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps() {
-      MLIRContext *context = getContext();
-      AffineExpr i, j, r_k;
-      bindDims(context, i, j, r_k);
-      return SmallVector<AffineMap, 8>{
-        AffineMap::get(3, 0, {i, r_k}, context),
-        AffineMap::get(3, 0, {r_k, j},context),
-        AffineMap::get(3, 0, {i, j}, 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/include/mlir/Dialect/Linalg/Transforms/Transforms.h

 Optional<LinalgOp> promoteSubViews(OpBuilder &b, LinalgOp op,
                                    LinalgPromotionOptions options,
                                    OperationFolder *folder = nullptr);
 
 /// Emit a suitable vector form for a Linalg op with fully static shape.
 void vectorizeLinalgOp(OpBuilder &builder, Operation *op);
 
 /// Emits a loop nest of `LoopTy` with the proper body for `op`.
-template <typename LoopTy, typename ConcreteOp>
+template <typename LoopTy>
 Optional<LinalgLoops> linalgLowerOpToLoops(OpBuilder &builder, Operation *op);
 
 /// Emits a loop nest of `scf.for` with the proper body for `op`.
-template <typename ConcreteOp>
 LogicalResult linalgOpToLoops(OpBuilder &builder, Operation *op);
 
 /// Emits a loop nest of `scf.parallel` with the proper body for `op`.
-template <typename ConcreteOp>
 LogicalResult linalgOpToParallelLoops(OpBuilder &builder, Operation *op);
 
 /// Emits a loop nest of `affine.for` with the proper body for `op`.
-template <typename ConcreteOp>
 LogicalResult linalgOpToAffineLoops(OpBuilder &builder, Operation *op);
 
 //===----------------------------------------------------------------------===//
 // Preconditions that ensure the corresponding transformation suceeds and can be
 // applied as a rewrite pattern.
 //===----------------------------------------------------------------------===//
 /// Emits a `generic` or `indexed_generic` operation with the `indexing_maps`
 /// and `iterator_types` permutated according to `permutation`.
if (!linalgOp)
       return failure();
     if (failed(marker.checkAndNotify(rewriter, linalgOp)))
       return failure();
 
     if (loweringType == LinalgLoweringType::LibraryCall) {
       // TODO: Move lowering to library calls here.
       return failure();
     } else if (loweringType == LinalgLoweringType::Loops) {
-      if (failed(linalgOpToLoops<OpTy>(rewriter, op)))
+      if (failed(linalgOpToLoops(rewriter, op)))
         return failure();
     } else if (loweringType == LinalgLoweringType::AffineLoops) {
-      if (failed(linalgOpToAffineLoops<OpTy>(rewriter, op)))
+      if (failed(linalgOpToAffineLoops(rewriter, op)))
         return failure();
-    } else if (failed(linalgOpToParallelLoops<OpTy>(rewriter, op))) {
+    } else if (failed(linalgOpToParallelLoops(rewriter, op))) {
       return failure();
     }
     rewriter.eraseOp(op);
     return success();
   }
 
 private:
   /// LinalgTransformMarker handles special attribute manipulations.

mlir/lib/Conversion/LinalgToStandard/LinalgToStandard.cpp

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

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

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

 
 template <typename NamedStructuredOpType>
 static void printNamedStructuredOp(OpAsmPrinter &p, NamedStructuredOpType op) {
   std::array<StringRef, 2> silentAttrNames{getIndexingMapsAttrName(),
                                            getIteratorTypesAttrName()};
   p << op.getOperationName() << ' ';
   p.printOptionalAttrDict(op.getAttrs(), silentAttrNames);
   p << ' ' << op.getOperands();
-  p << ": (" << op.getOperandTypes() << ")";
+  p << " : (" << op.getOperandTypes() << ")";
   auto outputTensorTypes = op.getResultTypes();
   if (!outputTensorTypes.empty())
     p << " -> (" << outputTensorTypes << ")";
 }
 
 template <typename NamedStructuredOpType>
 static ParseResult parseNamedStructuredOp(OpAsmParser &parser,
                                           OperationState &result) {
   SmallVector<OpAsmParser::OperandType, 8> operandsInfo;
 
   // Optional attributes may be added.
-  if (parser.parseOptionalAttrDict(result.attributes) ||
-      parser.parseOperandList(operandsInfo))
+  if (parser.parseOperandList(operandsInfo) ||
+      parser.parseOptionalAttrDict(result.attributes))
     return failure();
 
   SmallVector<Type, 8> operandTypes;
   if (parser.parseColon() || parser.parseLParen() ||
       parser.parseTypeList(operandTypes) || parser.parseRParen())
     return failure();
 
   // Generic ops may specify that a subset of its outputs are tensors. Such

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

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

emitLoopRanges(OpBuilder &b, Location loc, AffineMap map,
   }
   return res;
 }
 
 template <typename IndexedValueType, typename OpType>
 static void inlineRegionAndEmitStore(OpType op, ArrayRef<Value> indexedValues,
                                      ArrayRef<SmallVector<Value, 8>> indexing,
                                      ArrayRef<Value> outputBuffers) {
+  assert(op.getOperation()->getNumRegions() == 1 &&
+         "Expected single region op");
   auto &b = ScopedContext::getBuilderRef();
   auto &block = op.region().front();
   BlockAndValueMapping map;
   map.map(block.getArguments(), indexedValues);
   for (auto &op : block.without_terminator()) {
     assert(op.getNumRegions() == 0 && "expected a non-nested region");
     auto *newOp = b.clone(op, map);
     map.map(op.getResults(), newOp->getResults());

 ///          store %14#0, %arg1[%i, %j, %k] :
 ///            memref<?x?x?Xf32, stride_specification>
 ///          store %14#1, %arg2[%i, %k, %j] :
 ///            memref<?x?x?Xf32, stride_specification>
 ///       }
 ///      }
 ///    }
 /// ```
-template <typename IndexedValueType, typename LinalgOpType>
-class LinalgScopedEmitter {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       LinalgOpType linalgOp) {
-    assert(linalgOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    auto &b = ScopedContext::getBuilderRef();
-    auto loc = ScopedContext::getLocation();
-    unsigned nInputs = linalgOp.getNumInputs();
-    unsigned nOutputs = linalgOp.getNumOutputs();
-    SmallVector<Value, 4> indexedValues;
-    indexedValues.reserve(nInputs + nOutputs);
+// TODO: need a LinalgStructuredOpInterface.
+template <typename IndexedValueType, typename LinalgStructuredOpType>
+void emitScalarImplementation(ArrayRef<Value> allIvs,
+                              LinalgStructuredOpType linalgOp) {
 
-    // TODO(mravishankar): Avoid the loads if the corresponding argument of the
-    // region has no uses.
-    // 1.a. Emit load from input views.
-    for (unsigned i = 0; i < nInputs; ++i) {
-      auto indexing = makeCanonicalAffineApplies(
-          b, loc, linalgOp.getInputIndexingMap(i), allIvs);
-      // Passing through IndexedValueType emits the proper load operation.
-      indexedValues.push_back(IndexedValueType(linalgOp.getInput(i))(indexing));
-    }
-    // 1.b. Emit load from output views.
-    for (unsigned i = 0; i < nOutputs; ++i) {
-      auto indexing = makeCanonicalAffineApplies(
-          b, loc, linalgOp.getOutputIndexingMap(i), allIvs);
-      // Passing through IndexedValueType emits the proper load operation.
-      indexedValues.push_back(
-          IndexedValueType(linalgOp.getOutputBuffer(i))(indexing));
-    }
 
-    // TODO(ntv): When a region inliner exists, use it.
-    // 2. Inline region, currently only works for a single basic block.
-    // 3. Emit store.
-    SmallVector<SmallVector<Value, 8>, 8> indexing;
-    SmallVector<Value, 8> outputBuffers;
-    for (unsigned i = 0; i < nOutputs; ++i) {
-      indexing.push_back(makeCanonicalAffineApplies(
-          b, loc, linalgOp.getOutputIndexingMap(i), allIvs));
-      outputBuffers.push_back(linalgOp.getOutputBuffer(i));
-    }
-    inlineRegionAndEmitStore<IndexedValueType>(linalgOp, indexedValues,
-                                               indexing, outputBuffers);
-  }
-};
+  inlineRegionAndEmitStore<IndexedValueType>(linalgOp, indexedValues, indexing,
+                                             outputBuffers);
 
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, CopyOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs, CopyOp copyOp) {
-    assert(copyOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    auto nPar = copyOp.getNumParallelLoops();
-    assert(nPar == allIvs.size());
-    auto inputIvs =
-        permuteIvs(allIvs.take_front(nPar), copyOp.inputPermutation());
-    auto outputIvs =
-        permuteIvs(allIvs.take_front(nPar), copyOp.outputPermutation());
-    SmallVector<Value, 8> iivs(inputIvs.begin(), inputIvs.end());
-    SmallVector<Value, 8> oivs(outputIvs.begin(), outputIvs.end());
-    IndexedValueType O(copyOp.getOutputBuffer(0)), I(copyOp.getInput(0));
-    // Emit the proper scalar assignment, whether we are dealing with a 0-D or
-    // an n-D loop nest; with or without permutations.
-    // clang-format off
+void emitScalarImplementation(ArrayRef<Value> allIvs, CopyOp copyOp) {
     nPar > 0 ? O(oivs) = I(iivs) :
                O() = I();
-    // clang-format on
-  }
-};
 
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, FillOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs, FillOp fillOp) {
-    assert(fillOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    auto nPar = fillOp.getNumParallelLoops();
-    assert(nPar == allIvs.size());
-    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();
-  }
-};
+void emitScalarImplementation(ArrayRef<Value> allIvs, FillOp fillOp) {
 
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, DotOp> {
-public:
-  static 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);
-  }
-};
-
+void emitScalarImplementation(ArrayRef<Value> allIvs, DotOp dotOp) {
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, MatvecOp> {
-public:
-  static 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);
-  }
-};
+void emitScalarImplementation(ArrayRef<Value> allIvs, MatvecOp matvecOp) {
 
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, MatmulOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       MatmulOp matmulOp) {
-    assert(matmulOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    assert(allIvs.size() == 3);
-    Value i(allIvs[0]), j(allIvs[1]), r_k(allIvs[2]);
-    IndexedValueType A(matmulOp.getInput(0)), B(matmulOp.getInput(1)),
-        C(matmulOp.getOutputBuffer(0));
-    // Emit scalar form.
-    C(i, j) = C(i, j) + A(i, r_k) * B(r_k, j);
-  }
-};
-
-template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, ConvOp> {
-public:
-  /// Returns the input value of convOp. If the indices in `imIdx` is out of
-  /// boundary, returns 0 instead.
-  static 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);
+Value getConvOpInput(ConvOp convOp, StdIndexedValue im,
 
-    auto *context = ScopedContext::getContext();
-    Value zeroIndex = std_constant_index(0);
-    SmallVector<Value, 8> conds;
-    SmallVector<Value, 8> clampedImIdx;
-    for (auto iter : llvm::enumerate(imIdx)) {
-      int idx = iter.index();
-      auto dim = iter.value();
-      // Only need to iterate over the window dimensions.
-      if (idx == 0 || idx == static_cast<int>(imIdx.size()) - 1) {
-        clampedImIdx.push_back(dim);
-        continue;
-      }
 
-      using edsc::op::operator<;
-      using edsc::op::operator>=;
-      using edsc::op::operator||;
-      Value leftOutOfBound = dim < zeroIndex;
-      if (conds.empty())
-        conds.push_back(leftOutOfBound);
-      else
-        conds.push_back(conds.back() || leftOutOfBound);
-      Value rightBound = std_dim(convOp.input(), idx);
-      conds.push_back(conds.back() || (dim >= rightBound));
 
-      // When padding is involved, the indices will only be shifted to negative,
-      // so having a max op is enough.
-      auto maxMap = AffineMap::get(/*dimCount=*/1, 0,
-                                   {getAffineDimExpr(/*position=*/0, context),
-                                    getAffineConstantExpr(0, context)},
-                                   context);
-      clampedImIdx.push_back(
-          affine_max(dim.getType(), maxMap, ValueRange{dim}));
-    }
+    clampedImIdx.push_back(affine_max(dim.getType(), maxMap, ValueRange{dim}));
 
-    auto &b = ScopedContext::getBuilderRef();
-    Type type = convOp.input().getType().cast<MemRefType>().getElementType();
-    Value zero = std_constant(type, b.getZeroAttr(type));
-    Value readInput = im(clampedImIdx);
-    return conds.empty() ? readInput
-                         : (Value)std_select(conds.back(), zero, readInput);
-  }
 
-  /// Returns true is `convOp` has a non-zero padding.
-  static bool hasPadding(ConvOp convOp) {
-    for (unsigned i = 0, e = convOp.getNumSpatialDimensions(); i < e; ++i) {
-      if (convOp.getLowPad(i) > 0 || convOp.getHighPad(i) > 0)
-        return true;
-    }
-    return false;
-  }
 
-  static void emitScalarImplementation(ArrayRef<Value> allIvs, ConvOp convOp) {
-    assert(convOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    auto &b = ScopedContext::getBuilderRef();
-    auto loc = ScopedContext::getLocation();
-    auto mapsRange = convOp.indexing_maps().getAsRange<AffineMapAttr>();
-    auto maps = llvm::to_vector<8>(llvm::map_range(
-        mapsRange, [](AffineMapAttr a) { return a.getValue(); }));
-    SmallVector<Value, 8> fIdx(
-        makeCanonicalAffineApplies(b, loc, maps[0], allIvs));
-    SmallVector<Value, 8> imIdx(
-        makeCanonicalAffineApplies(b, loc, maps[1], allIvs));
-    SmallVector<Value, 8> oIdx(
-        makeCanonicalAffineApplies(b, loc, maps[2], allIvs));
+template <typename IndexedValueType>
+  auto maps = llvm::to_vector<8>(
+      llvm::map_range(mapsRange, [](AffineMapAttr a) { return a.getValue(); }));
 
-    IndexedValueType F(convOp.filter()), O(convOp.output());
 
-    // Emit scalar form. Padded conv involves an affine.max in the memory access
-    // which is not allowed by affine.load. Override to use an StdIndexedValue
-    // when there is non-zero padding.
-    if (hasPadding(convOp)) {
-      StdIndexedValue I(convOp.input());
-      Value paddedInput = getConvOpInput(convOp, I, imIdx);
-      O(oIdx) += F(fIdx) * paddedInput;
-    } else {
-      IndexedValueType I(convOp.input());
-      O(oIdx) += F(fIdx) * I(imIdx);
-    }
-  }
-};
+    Value paddedInput = getConvOpInput<IndexedValueType>(convOp, I, imIdx);
 
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, PoolingMaxOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       PoolingMaxOp op) {
-    auto indices = getInputAndOutputIndices(allIvs, op);
-    // Emit scalar form.
-    Value lhs = std_load(op.output(), indices.outputs);
-    Value rhs = std_load(op.input(), indices.inputs);
-    using edsc::op::operator>;
-    Value maxValue = std_select(lhs > rhs, lhs, rhs);
-    std_store(maxValue, op.output(), indices.outputs);
-  }
-};
-
+void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMaxOp op) {
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, PoolingMinOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       PoolingMinOp op) {
-    auto indices = getInputAndOutputIndices(allIvs, op);
-    // Emit scalar form.
-    Value lhs = std_load(op.output(), indices.outputs);
-    Value rhs = std_load(op.input(), indices.inputs);
-    using edsc::op::operator<;
-    Value minValue = std_select(lhs < rhs, lhs, rhs);
-    std_store(minValue, op.output(), indices.outputs);
-  }
-};
-
+void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMinOp op) {
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, PoolingSumOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       PoolingSumOp op) {
-    auto indices = getInputAndOutputIndices(allIvs, op);
-    IndexedValueType input(op.input()), output(op.output());
+void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingSumOp op) {
 
-    // Emit scalar form.
-    output(indices.outputs) += input(indices.inputs);
-  }
-};
-
 /// Emits the MLIR for the scalar part of the indexed generic op by:
 ///   1. Emitting load ops for each input and output view in order. This is
 ///      achieved by applying the appropriate input or output map to the
 ///      enclosing induction variables.
 ///   2. Emitting a call to `op.fun()` that takes as arguments the induction
 ///      variables and the scalars from point 1. above.
 ///   3. Emitting store ops to store the results of 2. to the output views.
 ///

 ///            memref<?x?x?Xf32, stride_specification>
 ///          store %14#1, %arg2[%i, %k, %j] :
 ///            memref<?x?x?Xf32, stride_specification>
 ///       }
 ///      }
 ///    }
 /// ```
 template <typename IndexedValueType>
-class LinalgScopedEmitter<IndexedValueType, IndexedGenericOp> {
-public:
-  static void emitScalarImplementation(ArrayRef<Value> allIvs,
-                                       IndexedGenericOp indexedGenericOp) {
-    assert(indexedGenericOp.hasBufferSemantics() &&
-           "expected linalg op with buffer semantics");
-    auto &b = ScopedContext::getBuilderRef();
-    auto loc = ScopedContext::getLocation();
-    unsigned nInputs = indexedGenericOp.getNumInputs();
-    unsigned nOutputs = indexedGenericOp.getNumOutputs();
-    unsigned nLoops = allIvs.size();
-    SmallVector<Value, 4> indexedValues;
-    indexedValues.reserve(nLoops + nInputs + nOutputs);
-    for (unsigned i = 0; i < nLoops; ++i)
-      indexedValues.push_back(allIvs[i]);
 
-    // TODO(mravishankar): Avoid the loads if the corresponding argument of the
-    // region has no uses.
-    // 1.a. Emit load from input views.
-    for (unsigned i = 0; i < nInputs; ++i) {
-      auto indexing = makeCanonicalAffineApplies(
-          b, loc, indexedGenericOp.getInputIndexingMap(i), allIvs);
-      // Pass input i through IndexedValueType emits the proper load operation.
-      indexedValues.push_back(
-          IndexedValueType(indexedGenericOp.getInput(i))(indexing));
-    }
-    // 1.b. Emit load from output views.
-    for (unsigned i = 0; i < nOutputs; ++i) {
-      auto indexing = makeCanonicalAffineApplies(
-          b, loc, indexedGenericOp.getOutputIndexingMap(i), allIvs);
-      // Pass output i through IndexedValueType emits the proper load operation.
-      indexedValues.push_back(
-          IndexedValueType(indexedGenericOp.getOutputBuffer(i))(indexing));
-    }
 
-    // TODO(ntv): When a region inliner exists, use it.
-    // 2. Inline region, currently only works for a single basic block.
-    // 3. Emit store.
-    SmallVector<SmallVector<Value, 8>, 8> indexing;
-    SmallVector<Value, 8> outputBuffers;
-    for (unsigned i = 0; i < nOutputs; ++i) {
-      indexing.push_back(makeCanonicalAffineApplies(
-          b, loc, indexedGenericOp.getOutputIndexingMap(i), allIvs));
-      outputBuffers.push_back(indexedGenericOp.getOutputBuffer(i));
-    }
-    inlineRegionAndEmitStore<IndexedValueType>(indexedGenericOp, indexedValues,
-                                               indexing, outputBuffers);
-  }
-};
 
 template <typename LoopTy, typename ConcreteOpTy>
 Optional<LinalgLoops> linalgOpToLoopsImpl(Operation *op, OpBuilder &builder) {
   using IndexedValueTy = typename GenerateLoopNest<LoopTy>::IndexedValueTy;
 
   ScopedContext scope(builder, op->getLoc());
 
   // The flattened loopToOperandRangesMaps is expected to be an invertible
   // permutation map (which is asserted in the inverse calculation).
   auto linalgOp = cast<ConcreteOpTy>(op);
   assert(linalgOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   auto nPar = linalgOp.getNumParallelLoops();
   auto nRed = linalgOp.getNumReductionLoops();
   auto nWin = linalgOp.getNumWindowLoops();
   auto nLoops = nPar + nRed + nWin;
   auto mapsRange =
       linalgOp.indexing_maps().template getAsRange<AffineMapAttr>();
   auto maps = llvm::to_vector<8>(
       llvm::map_range(mapsRange, [](AffineMapAttr a) { return a.getValue(); }));
   AffineMap invertedMap = inversePermutation(concatAffineMaps(maps));
   if (!invertedMap)
     return {};
   if (invertedMap.isEmpty()) {
-    LinalgScopedEmitter<IndexedValueTy, ConcreteOpTy>::emitScalarImplementation(
-        {}, linalgOp);
+    emitScalarImplementation<IndexedValueTy>({}, linalgOp);
     return LinalgLoops();
   }
 
   SmallVector<Value, 4> allIvs(nLoops);
   auto loopRanges =
       emitLoopRanges(scope.getBuilderRef(), scope.getLocation(), invertedMap,
                      getViewSizes(builder, linalgOp));
   assert(loopRanges.size() == allIvs.size());
   GenerateLoopNest<LoopTy>::doit(
       allIvs, loopRanges, linalgOp.iterator_types().getValue(), [&] {
         SmallVector<Value, 4> allIvValues(allIvs.begin(), allIvs.end());
-        LinalgScopedEmitter<IndexedValueTy,
-                            ConcreteOpTy>::emitScalarImplementation(allIvValues,
-                                                                    linalgOp);
+        emitScalarImplementation<IndexedValueTy>(allIvValues, linalgOp);
       });
   // Number of loop ops might be different from the number of ivs since some
   // loops like affine.parallel and scf.parallel have multiple ivs.
   llvm::SetVector<Operation *> loopSet;
   for (Value iv : allIvs) {
     if (!iv)
       return {};
     // The induction variable is a block argument of the entry block of the
LogicalResult matchAndRewrite(Operation *op,
                                 PatternRewriter &rewriter) const override {
     if (!linalgOpToLoopsImpl<LoopType, ConcreteOp>(op, rewriter))
       return failure();
     rewriter.eraseOp(op);
     return success();
   }
 };
 
-/// Helper classes for type list expansion.
-template <typename LoopType, typename... LinalgOps>
-class RewritePatternList;
-
-template <typename LoopType>
-class RewritePatternList<LoopType> {
-public:
-  static void build(OwningRewritePatternList &patterns, MLIRContext *ctx) {}
-};
-
-template <typename LoopType, typename ConcreteOp, typename... LinalgOps>
-class RewritePatternList<LoopType, ConcreteOp, LinalgOps...> {
-public:
-  static void build(OwningRewritePatternList &patterns, MLIRContext *ctx) {
-    patterns.insert<LinalgRewritePattern<LoopType, ConcreteOp>>(ctx);
-    RewritePatternList<LoopType, LinalgOps...>::build(patterns, ctx);
-  }
-};
+template <typename LoopType, typename ConcreteOp>
+void insertOnePattern(OwningRewritePatternList &patterns, MLIRContext *ctx) {
 
-/// Populate the given list with patterns that convert from Linalg to loops.
-template <typename LoopType>
-void FillRewritePatterns(OwningRewritePatternList &patterns, MLIRContext *ctx) {
-  RewritePatternList<LoopType,
-#define GET_OP_LIST
-#include "mlir/Dialect/Linalg/IR/LinalgStructuredOps.cpp.inc"
-                     >::build(patterns, ctx);
+template <typename LoopType, typename... Args>
+void insertPatterns(OwningRewritePatternList &patterns, MLIRContext *ctx) {
+  (void)std::initializer_list<int>{
+      0, (insertOnePattern<LoopType, Args>(patterns, ctx), 0)...};
 }
 
 /// Local folding pattern for AffineApplyOp that we can apply greedily.
 /// This replaces AffineApplyOp by the proper value in cases where the
 /// associated map is trivial.
 /// A trivial map here is defined as a map with a single result and either:
 ///   1. Zero operand + returns a single AffineConstantExpr
 ///   2. One operand + returns a single AffineDimExpr
if (expr.dyn_cast<AffineDimExpr>() || expr.dyn_cast<AffineSymbolExpr>()) {
       return success();
     }
     return failure();
   }
 };
 } // namespace
 
 template <typename LoopType>
-static void lowerLinalgToLoopsImpl(Operation *op, MLIRContext *context) {
+static void lowerLinalgToLoopsImpl(FuncOp funcOp, MLIRContext *context) {
   OwningRewritePatternList patterns;
   // Canonicalization and folding patterns applied greedily allow cleaning up
   // the emitted IR on the fly.
   // TODO(ntv) fold view and subview ops?
-  FillRewritePatterns<LoopType>(patterns, context);
+  insertPatterns<LoopType,
+#define GET_OP_LIST
+#include "mlir/Dialect/Linalg/IR/LinalgStructuredOps.cpp.inc"
+                 >(patterns, context);
+
   DimOp::getCanonicalizationPatterns(patterns, context);
   AffineApplyOp::getCanonicalizationPatterns(patterns, context);
   patterns.insert<FoldAffineOp>(context);
   // Just apply the patterns greedily.
-  applyPatternsAndFoldGreedily(op, patterns);
+  applyPatternsAndFoldGreedily(funcOp, patterns);
 }
 
 namespace {
 struct LowerToAffineLoops
     : public LinalgLowerToAffineLoopsBase<LowerToAffineLoops> {
   void runOnFunction() override {
     lowerLinalgToLoopsImpl<AffineForOp>(getFunction(), &getContext());
   }
mlir::createConvertLinalgToParallelLoopsPass() {
   return std::make_unique<LowerToParallelLoops>();
 }
 
 std::unique_ptr<OperationPass<FuncOp>>
 mlir::createConvertLinalgToAffineLoopsPass() {
   return std::make_unique<LowerToAffineLoops>();
 }
 
+// TODO: gradually remove this layer as more ops become "named".
+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<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<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, typename ConcreteOp>
+template <typename LoopTy>
 Optional<LinalgLoops> mlir::linalg::linalgLowerOpToLoops(OpBuilder &builder,
                                                          Operation *op) {
-  return linalgOpToLoopsImpl<LoopTy, ConcreteOp>(op, builder);
+  return linalgOpToLoopsImplSwitch<LoopTy>(op, builder);
 }
 
-/// Emits a loop nest of `scf.for` with the proper body for `op`.
-template <typename ConcreteOp>
-LogicalResult mlir::linalg::linalgOpToLoops(OpBuilder &builder, Operation *op) {
-  Optional<LinalgLoops> loops =
-      linalgLowerOpToLoops<scf::ForOp, ConcreteOp>(builder, op);
-  return loops ? success() : failure();
-}
+template Optional<LinalgLoops>
+mlir::linalg::linalgLowerOpToLoops<AffineForOp>(OpBuilder &builder,
+                                                Operation *op);
+template Optional<LinalgLoops>
+mlir::linalg::linalgLowerOpToLoops<scf::ForOp>(OpBuilder &builder,
+                                               Operation *op);
+template Optional<LinalgLoops>
+mlir::linalg::linalgLowerOpToLoops<scf::ParallelOp>(OpBuilder &builder,
+                                                    Operation *op);
 
 /// Emits a loop nest of `affine.for` with the proper body for `op`.
-template <typename ConcreteOp>
 LogicalResult mlir::linalg::linalgOpToAffineLoops(OpBuilder &builder,
                                                   Operation *op) {
-  Optional<LinalgLoops> loops =
-      linalgLowerOpToLoops<AffineForOp, ConcreteOp>(builder, op);
+  Optional<LinalgLoops> loops = linalgLowerOpToLoops<AffineForOp>(builder, op);
+  return loops ? success() : failure();
+}
+
+/// Emits a loop nest of `scf.for` with the proper body for `op`.
+LogicalResult mlir::linalg::linalgOpToLoops(OpBuilder &builder, Operation *op) {
+  Optional<LinalgLoops> loops = linalgLowerOpToLoops<scf::ForOp>(builder, op);
   return loops ? success() : failure();
 }
 
 /// Emits a loop nest of `scf.parallel` with the proper body for `op`.
-template <typename ConcreteOp>
 LogicalResult mlir::linalg::linalgOpToParallelLoops(OpBuilder &builder,
                                                     Operation *op) {
   Optional<LinalgLoops> loops =
-      linalgLowerOpToLoops<scf::ParallelOp, ConcreteOp>(builder, op);
+      linalgLowerOpToLoops<scf::ParallelOp>(builder, op);
   return loops ? success() : failure();
 }
-
-// TODO Need to make these instantiations more future-proof to avoid the need to
-// update as soon as we add new ops.
-#define INSTANTIATE_LINALG_OP_TO_LOOPS(OP_TYPE)                                \
-  template LogicalResult mlir::linalg::linalgOpToLoops<OP_TYPE>(               \
-      OpBuilder & builder, Operation * op);                                    \
-  template LogicalResult mlir::linalg::linalgOpToAffineLoops<OP_TYPE>(         \
-      OpBuilder & builder, Operation * op);                                    \
-  template LogicalResult mlir::linalg::linalgOpToParallelLoops<OP_TYPE>(       \
-      OpBuilder & builder, Operation * op);                                    \
-  template Optional<LinalgLoops>                                               \
-      mlir::linalg::linalgLowerOpToLoops<scf::ParallelOp, OP_TYPE>(            \
-          OpBuilder & builder, Operation * op);
-
-INSTANTIATE_LINALG_OP_TO_LOOPS(CopyOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(FillOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(DotOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(MatvecOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(MatmulOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(ConvOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(PoolingMaxOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(PoolingMinOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(PoolingSumOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(GenericOp)
-INSTANTIATE_LINALG_OP_TO_LOOPS(IndexedGenericOp)

mlir/test/Dialect/Linalg/affine.mlir

 // CHECK-DAG: #[[$clampMinMap:.*]] = affine_map<(d0) -> (d0, 0)>
 
 func @matmul(%arg0: memref<?xi8>, %M: index, %N: index, %K: index) {
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %A = view %arg0[%c0][%M, %K] : memref<?xi8> to memref<?x?xf32>
   %B = view %arg0[%c0][%K, %N] : memref<?xi8> to memref<?x?xf32>
   %C = view %arg0[%c0][%M, %N] : memref<?xi8> to memref<?x?xf32>
-  linalg.matmul(%A, %B, %C) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+  linalg.matmul %A, %B, %C : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
   return
 }
 
 // CHECK-LABEL: func @matmul(%{{.*}}: memref<?xi8>,
 // CHECK-SAME: [[M:arg[0-9]+]]: index
 // CHECK-SAME: [[N:arg[0-9]+]]: index
 // CHECK-SAME: [[K:arg[0-9]+]]: index
 //       CHECK: %[[A:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?x?xf32>

mlir/test/Dialect/Linalg/canonicalize.mlir

 // RUN: mlir-opt %s -canonicalize -split-input-file | FileCheck %s
 
 // CHECK-LABEL: func @memref_cast(
 func @memref_cast(%a: index, %b: index) -> memref<?x?xf32> {
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %c8 = constant 8 : index
   %c16 = constant 16 : index
   %1 = alloc (%b) : memref<?xi8>
   %2 = view %1[%c0][] : memref<?xi8> to memref<16x16xf32>
   %3 = memref_cast %2 : memref<16x16xf32> to memref<?x?xf32>
   %r0 = linalg.range %c0:%c8:%c1 : !linalg.range
 
   // CHECK:  linalg.slice {{.*}} : memref<16x16xf32>, !linalg.range, !linalg.range, memref<?x?xf32>
   %4 = linalg.slice %3[%r0, %r0] : memref<?x?xf32>, !linalg.range, !linalg.range, memref<?x?xf32>
 
-  // CHECK:  linalg.matmul{{.*}}: memref<16x16xf32>, memref<16x16xf32>, memref<16x16xf32>
-  linalg.matmul(%3, %3, %3) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+  // CHECK:  linalg.matmul{{.*}}: (memref<16x16xf32>, memref<16x16xf32>, memref<16x16xf32>)
+  linalg.matmul %3, %3, %3 : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
   return %4: memref<?x?xf32>
 }
 
 // -----
 
 func @collapsing_tensor_reshapes(%arg0 : tensor<?x?x?x?x?xf32>) -> tensor<?x?xf32>
 {
   %0 = linalg.tensor_reshape %arg0

mlir/test/Dialect/Linalg/fusion-2-level.mlir

 // RUN: mlir-opt %s -linalg-fusion | FileCheck %s
 
 func @f1(%A: memref<?x?xf32, offset: ?, strides: [?, 1]>, %B: memref<?x?xf32, offset: ?, strides: [?, 1]>, %C: memref<?x?xf32, offset: ?, strides: [?, 1]>, %D: memref<?x?xf32, offset: ?, strides: [?, 1]>, %E: memref<?x?xf32, offset: ?, strides: [?, 1]>) -> memref<?x?xf32, offset: ?, strides: [?, 1]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %c40 = constant 40 : index
   %c30 = constant 30 : index
   %c20 = constant 20 : index
   %0 = dim %C, %c0 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %1 = dim %C, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %2 = dim %D, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
-  linalg.matmul(%A, %B, %C) : memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>
+  linalg.matmul %A, %B, %C : (memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>)
   scf.for %arg5 = %c0 to %0 step %c20 {
     scf.for %arg6 = %c0 to %2 step %c30 {
       scf.for %arg7 = %c0 to %1 step %c40 {
         %5 = std.subview %C[%arg5, %arg7][%c20, %c40][%c1, %c1] : memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %D[%arg7, %arg6][%c40, %c30][%c1, %c1]: memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c20, %c40][%c1, %c1] : memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %9 = dim %5, %c0 : memref<?x?xf32, offset: ?, strides: [?, ?]>
         %10 = dim %5, %c1 : memref<?x?xf32, offset: ?, strides: [?, ?]>
         %11 = dim %7, %c1 : memref<?x?xf32, offset: ?, strides: [?, ?]>
         scf.for %arg8 = %c0 to %9 step %c2 {
           scf.for %arg9 = %c0 to %11 step %c3 {
             scf.for %arg10 = %c0 to %10 step %c4 {
               %14 = std.subview %5[%arg8, %arg10][%c2, %c4][%c1, %c1] : memref<?x?xf32, offset: ?, strides: [?, ?]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
               %16 = std.subview %7[%arg10, %arg9][%c4, %c3][%c1, %c1]: memref<?x?xf32, offset: ?, strides: [?, ?]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
               %17 = std.subview %8[%arg8, %arg9][%c2, %c4][%c1, %c1] : memref<?x?xf32, offset: ?, strides: [?, ?]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
-              linalg.matmul(%14, %16, %17) : memref<?x?xf32, offset: ?, strides: [?, ?]>, memref<?x?xf32, offset: ?, strides: [?, ?]>, memref<?x?xf32, offset: ?, strides: [?, ?]>
+              linalg.matmul %14, %16, %17 : (memref<?x?xf32, offset: ?, strides: [?, ?]>, memref<?x?xf32, offset: ?, strides: [?, ?]>, memref<?x?xf32, offset: ?, strides: [?, ?]>)
             }
           }
         }
       }
     }
   }
   return %E : memref<?x?xf32, offset: ?, strides: [?, 1]>
 }

mlir/test/Dialect/Linalg/fusion.mlir

 // RUN: mlir-opt %s -linalg-fusion -split-input-file | FileCheck %s
 
 func @f1(%A: memref<?x?xf32, offset: 0, strides: [?, 1]>,
          %B: memref<?x?xf32, offset: 0, strides: [?, 1]>,
          %C: memref<?x?xf32, offset: 0, strides: [?, 1]>,
          %D: memref<?x?xf32, offset: 0, strides: [?, 1]>,
          %E: memref<?x?xf32, offset: 0, strides: [?, 1]>
         ) -> memref<?x?xf32, offset: 0, strides: [?, 1]> {
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %c1 = constant 1 : index
   %0 = dim %A, %c0 : memref<?x?xf32, offset: 0, strides: [?, 1]>
   %1 = dim %A, %c1 : memref<?x?xf32, offset: 0, strides: [?, 1]>
   %2 = dim %B, %c1 : memref<?x?xf32, offset: 0, strides: [?, 1]>
-  linalg.matmul(%A, %B, %C) :
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, 1]>,
      memref<?x?xf32, offset: 0, strides: [?, 1]>,
-    memref<?x?xf32, offset: 0, strides: [?, 1]>,
-    memref<?x?xf32, offset: 0, strides: [?, 1]>
+     memref<?x?xf32, offset: 0, strides: [?, 1]>)
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %5 = std.subview %A[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, 1]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %B[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, 1]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %C[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, 1]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, 1]>
 }
 // CHECK-LABEL: func @f1
 // CHECK:   (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK: scf.for
func @f2(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %D: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %E: memref<?x?xf32, offset: 0, strides: [?, ?]>
         ) -> memref<?x?xf32, offset: 0, strides: [?, ?]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
-  linalg.matmul(%A, %B, %C) :
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   %0 = dim %C, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %C, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %5 = std.subview %C[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %D[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f2
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK-DAG:  %[[C_0:.*]] = dim %[[C]], %c0{{[_0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
func @f3(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %D: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %E: memref<?x?xf32, offset: 0, strides: [?, ?]>
         ) -> memref<?x?xf32, offset: 0, strides: [?, ?]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
-  linalg.matmul(%A, %B, %C) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   %0 = dim %D, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %C, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %5 = std.subview %D[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %C[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f3
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK:  %[[D_0:.*]] = dim %[[D]], %c0{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
func @f4(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %D: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %E: memref<?x?xf32, offset: 0, strides: [?, ?]>
         ) -> memref<?x?xf32, offset: 0, strides: [?, ?]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
-  linalg.matmul(%A, %B, %C) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %B, %D) :
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
+  linalg.matmul %A, %B, %D :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   %0 = dim %C, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %C, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %5 = std.subview %C[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %D[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f4
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK:  %[[C_0:.*]] = dim %[[C]], %c0{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
func @f5(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %0 = dim %B, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %D, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %B, %C) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%C, %B, %D) :
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
+  linalg.matmul %C, %B, %D :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   scf.for %arg5 = %c0 to %1 step %c2 {
     scf.for %arg6 = %c0 to %0 step %c3 {
       scf.for %arg7 = %c0 to %2 step %c4 {
         %5 = std.subview %D[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %7 = std.subview %B[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f5
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK-DAG:  %[[B_1:.*]] = dim %[[B]], %c1{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK-DAG:  %[[D_0:.*]] = dim %[[D]], %c0{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK-DAG:  %[[D_1:.*]] = dim %[[D]], %c1{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK:  scf.for %[[I:.*]] = %{{.*}} to %[[D_0]] step %{{.*}} {
 // CHECK:    scf.for %[[J:.*]] = %{{.*}} to %[[B_1]] step %{{.*}} {
 // CHECK:      scf.for %[[K:.*]] = %{{.*}} to %[[D_1]] step %{{.*}} {
 // CHECK-DAG:    %[[D_IK:.*]] = subview %[[D]][%[[I]], %[[K]]]
 // CHECK-DAG:    %[[B_KJ:.*]] = subview %[[B]][%[[K]], %[[J]]]
 // CHECK-DAG:    %[[E_IJ:.*]] = subview %[[E]][%[[I]], %[[J]]]
 // CHECK:        dim
 // CHECK-DAG:    %[[C_I0:.*]] = subview %[[C]][%[[I]], %{{.*}}]
 // CHECK-DAG:    %[[B_0K:.*]] = subview %[[B]][%{{.*}}, %[[K]]]
 // CHECK-DAG:    %[[D_IK_:.*]] = subview %[[D]][%[[I]], %[[K]]]
 // CHECK:        dim
 // CHECK-DAG:    %[[A_I0:.*]] = subview %[[A]][%[[I]], %{{.*}}]
 // CHECK-DAG:    %[[B_00:.*]] = subview %[[B]][%{{.*}}, %{{.*}}]
 // CHECK-DAG:    %[[C_I0_:.*]] = subview %[[C]][%[[I]], %{{.*}}]
-// CHECK:        linalg.matmul(%[[A_I0]], %[[B_00]], %[[C_I0_]])
-// CHECK:        linalg.matmul(%[[C_I0]], %[[B_0K]], %[[D_IK_]])
-// CHECK:        linalg.matmul(%[[D_IK]], %[[B_KJ]], %[[E_IJ]])
+// CHECK:        linalg.matmul %[[A_I0]], %[[B_00]], %[[C_I0_]]
+// CHECK:        linalg.matmul %[[C_I0]], %[[B_0K]], %[[D_IK_]]
+// CHECK:        linalg.matmul %[[D_IK]], %[[B_KJ]], %[[E_IJ]]
 
 // -----
 
 #map0 = affine_map<(d0) -> (d0 + 2)>
 #map1 = affine_map<(d0) -> (d0 + 4)>
 #map2 = affine_map<(d0) -> (d0 + 3)>
 
 func @f6(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %B: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %C: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %D: memref<?x?xf32, offset: 0, strides: [?, ?]>,
          %E: memref<?x?xf32, offset: 0, strides: [?, ?]>
         ) -> memref<?x?xf32, offset: 0, strides: [?, ?]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %0 = dim %C, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %B, %C) :
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
+  linalg.matmul %A, %C, %E :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %C, %E) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   %1 = dim %C, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   scf.for %arg5 = %c0 to %1 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %0 step %c4 {
         %3 = affine.apply #map0(%arg5)
         %4 = affine.apply #map1(%arg7)
         %5 = std.subview %C[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %6 = affine.apply #map2(%arg6)
         %7 = std.subview %D[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f6
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // Fuse the producer of E (WAW) then the producer of C (WAR).
func @f7(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %0 = dim %A, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %A, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %2 = dim %C, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %3 = dim %C, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %4 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %C, %E) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %B, %C) :
+  linalg.matmul %A, %C, %E :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %7 = std.subview %A[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %9 = std.subview %C[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %10 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%7, %9, %10) :
+        linalg.matmul %7, %9, %10 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   scf.for %arg5 = %c0 to %3 step %c2 {
     scf.for %arg6 = %c0 to %4 step %c3 {
       scf.for %arg7 = %c0 to %2 step %c4 {
         %7 = std.subview %C[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %9 = std.subview %D[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %10 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%7, %9, %10) :
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %7, %9, %10 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f7
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
 // CHECK:  %[[A_0:.*]] = dim %[[A]], %c0{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK:  %[[A_1:.*]] = dim %[[A]], %c1{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK:  %[[C_1:.*]] = dim %[[C]], %c1{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK:  %[[C_0:.*]] = dim %[[C]], %c0{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
 // CHECK:  %[[D_1:.*]] = dim %[[D]], %c1{{_[0-9]*}} : memref<?x?xf32, #[[$strided2D]]>
-// CHECK:  linalg.matmul(%[[A]], %[[C]], %[[E]])
+// CHECK:  linalg.matmul %[[A]], %[[C]], %[[E]]
 // CHECK:  scf.for %{{.*}} = %{{.*}} to %[[A_0]] step %{{.*}} {
 // CHECK:    scf.for %{{.*}} = %{{.*}} to %[[C_1]] step %{{.*}} {
 // CHECK:      scf.for %{{.*}} = %{{.*}} to %[[A_1]] step %{{.*}} {
 // CHECK:        linalg.matmul
 // CHECK:        linalg.matmul
 // CHECK:  scf.for %{{.*}} = %{{.*}} to %[[C_0]] step %{{.*}} {
 // CHECK:    scf.for %{{.*}} = %{{.*}} to %[[D_1]] step %{{.*}} {
 // CHECK:      scf.for %{{.*}} = %{{.*}} to %[[C_1]] step %{{.*}} {
func @f8(%A: memref<?x?xf32, offset: 0, strides: [?, ?]>,
         ) -> memref<?x?xf32, offset: 0, strides: [?, ?]> {
   %c1 = constant 1 : index
   %c0 = constant 0 : index
   %c4 = constant 4 : index
   %c3 = constant 3 : index
   %c2 = constant 2 : index
   %0 = dim %A, %c0 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %1 = dim %A, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %C, %D) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
-  linalg.matmul(%A, %B, %C) :
+  linalg.matmul %A, %C, %D :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
   %2 = dim %D, %c1 : memref<?x?xf32, offset: 0, strides: [?, ?]>
   scf.for %arg5 = %c0 to %0 step %c2 {
     scf.for %arg6 = %c0 to %2 step %c3 {
       scf.for %arg7 = %c0 to %1 step %c4 {
         %3 = affine.apply #map0(%arg5)
         %4 = affine.apply #map1(%arg7)
         %5 = std.subview %A[%arg5, %arg7][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %6 = affine.apply #map2(%arg6)
         %7 = std.subview %D[%arg7, %arg6][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %8 = std.subview %E[%arg5, %arg6][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%5, %7, %8) :
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %5, %7, %8 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return %E : memref<?x?xf32, offset: 0, strides: [?, ?]>
 }
 // CHECK-LABEL: func @f8
 // CHECK:  (%[[A:.*]]: memref{{.*}}, %[[B:.*]]: memref{{.*}}, %[[C:.*]]: memref{{.*}}, %[[D:.*]]: memref{{.*}}, %[[E:.*]]: memref{{.*}})
 // CHECK:  linalg.matmul
func @accept_different_alloc_ops(%dim: index, %s0 : index, %s1: index) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c4 = constant 4 : index
 
   %A = alloca(%dim, %dim)[%s0, %s1] : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %B = alloca(%dim, %dim)[%s0, %s1] : memref<?x?xf32, offset: 0, strides: [?, ?]>
   %C = alloc(%dim, %dim)[%s0, %s1]  : memref<?x?xf32, offset: 0, strides: [?, ?]>
 
-  linalg.matmul(%A, %B, %C) :
-    memref<?x?xf32, offset: 0, strides: [?, ?]>,
+  linalg.matmul %A, %B, %C :
+    (memref<?x?xf32, offset: 0, strides: [?, ?]>,
      memref<?x?xf32, offset: 0, strides: [?, ?]>,
-    memref<?x?xf32, offset: 0, strides: [?, ?]>
+     memref<?x?xf32, offset: 0, strides: [?, ?]>)
 
   scf.for %i = %c0 to %dim step %c2 {
     scf.for %j = %c0 to %dim step %c3 {
       scf.for %k = %c0 to %dim step %c4 {
         %0 = std.subview %A[%i, %k][%c2, %c4][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %1 = std.subview %B[%k, %j][%c4, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
         %2 = std.subview %C[%i, %j][%c2, %c3][%c1, %c1] :
           memref<?x?xf32, offset: 0, strides: [?, ?]> to
           memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%0, %1, %2) :
+        linalg.matmul %0, %1, %2 :
+          (memref<?x?xf32, offset: ?, strides: [?, ?]>,
            memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>,
-          memref<?x?xf32, offset: ?, strides: [?, ?]>
+           memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return
 }
 
 // CHECK-LABEL: func @accept_different_alloc_ops
 // CHECK-COUNT-3: scf.for
 // CHECK-COUNT-2:   linalg.matmul

mlir/test/Dialect/Linalg/loops.mlir

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

mlir/test/Dialect/Linalg/promote.mlir

func @matmul_f32(%A: memref<?xi8>, %M: index, %N: index, %K: index) {
   %7 = dim %3, %c1 : memref<?x?xf32>
   %8 = dim %4, %c1 : memref<?x?xf32>
   scf.for %arg4 = %c0 to %6 step %c2 {
     scf.for %arg5 = %c0 to %8 step %c3 {
       scf.for %arg6 = %c0 to %7 step %c4 {
         %11 = std.subview %3[%arg4, %arg6][%c2, %c4][1, 1] : memref<?x?xf32> to memref<?x?xf32, offset: ?, strides: [?, 1]>
         %14 = std.subview %4[%arg6, %arg5][%c4, %c3][1, 1] : memref<?x?xf32> to memref<?x?xf32, offset: ?, strides: [?, 1]>
         %17 = std.subview %5[%arg4, %arg5][%c2, %c3][1, 1] : memref<?x?xf32> to memref<?x?xf32, offset: ?, strides: [?, 1]>
-        linalg.matmul(%11, %14, %17) : memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>
+        linalg.matmul %11, %14, %17 :
+          (memref<?x?xf32, offset: ?, strides: [?, 1]>,
+           memref<?x?xf32, offset: ?, strides: [?, 1]>,
+           memref<?x?xf32, offset: ?, strides: [?, 1]>)
       }
     }
   }
   return
 }
 
 // CHECK-LABEL: func @matmul_f32(%{{.*}}: memref<?xi8>, %{{.*}}: index, %{{.*}}: index, %{{.*}}: index) {
 //       CHECK:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {

 //       CHECK:         %[[fullC:.*]] = std.view %[[tmpC]][{{.*}}][{{.*}}] : memref<24xi8> to memref<?x?xf32>
 //     DYNAMIC:         std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?x?xf32>
 //       CHECK:         %[[partialC:.*]] = subview %[[fullC]]{{.*}} : memref<?x?xf32> to memref<?x?xf32, #[[$strided2D_dynamic]]>
 
 //       CHECK:         linalg.copy(%[[vA]], %[[partialA]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D_dynamic]]>
 //       CHECK:         linalg.copy(%[[vB]], %[[partialB]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D_dynamic]]>
 //       CHECK:         linalg.copy(%[[vC]], %[[partialC]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D_dynamic]]>
 //
-//       CHECK:         linalg.matmul(%[[partialA]], %[[partialB]], %[[partialC]]) : memref<?x?xf32, #[[$strided2D_dynamic]]>, memref<?x?xf32, #[[$strided2D_dynamic]]>, memref<?x?xf32, #[[$strided2D_dynamic]]>
-//
-//       CHECK:         linalg.copy(%[[partialC]], %[[vC]]) : memref<?x?xf32, #[[$strided2D_dynamic]]>, memref<?x?xf32, #[[$strided2D]]>
+//       CHECK:         linalg.matmul %[[partialA]], %[[partialB]], %[[partialC]] :
+//       CHECK:           memref<?x?xf32, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf32, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf32, #[[$strided2D_dynamic]]>
+//
+//       CHECK:         linalg.copy(%[[partialC]], %[[vC]]) :
+//       CHECK:           memref<?x?xf32, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf32, #[[$strided2D]]>
 //
 //       CHECK:         dealloc %[[tmpA]] : memref<32xi8>
 //       CHECK:         dealloc %[[tmpB]] : memref<48xi8>
 //       CHECK:         dealloc %[[tmpC]] : memref<24xi8>
 
 // -----
 
 func @matmul_f64(%A: memref<?xi8>, %M: index, %N: index, %K: index) {
func @matmul_f64(%A: memref<?xi8>, %M: index, %N: index, %K: index) {
   %7 = dim %3, %c1 : memref<?x?xf64>
   %8 = dim %4, %c1 : memref<?x?xf64>
   scf.for %arg4 = %c0 to %6 step %c2 {
     scf.for %arg5 = %c0 to %8 step %c3 {
       scf.for %arg6 = %c0 to %7 step %c4 {
         %11 = std.subview %3[%arg4, %arg6][%c2, %c4][1, 1] : memref<?x?xf64> to memref<?x?xf64, offset: ?, strides: [?, 1]>
         %14 = std.subview %4[%arg6, %arg5][%c4, %c3][1, 1] : memref<?x?xf64> to memref<?x?xf64, offset: ?, strides: [?, 1]>
         %17 = std.subview %5[%arg4, %arg5][%c2, %c3][1, 1] : memref<?x?xf64> to memref<?x?xf64, offset: ?, strides: [?, 1]>
-        linalg.matmul(%11, %14, %17) : memref<?x?xf64, offset: ?, strides: [?, 1]>, memref<?x?xf64, offset: ?, strides: [?, 1]>, memref<?x?xf64, offset: ?, strides: [?, 1]>
+        linalg.matmul %11, %14, %17 :
+          (memref<?x?xf64, offset: ?, strides: [?, 1]>,
+           memref<?x?xf64, offset: ?, strides: [?, 1]>,
+           memref<?x?xf64, offset: ?, strides: [?, 1]>)
       }
     }
   }
   return
 }
 
 // CHECK-LABEL: func @matmul_f64(%{{.*}}: memref<?xi8>, %{{.*}}: index, %{{.*}}: index, %{{.*}}: index) {
 //       CHECK:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {

 //       CHECK:         %[[fullC_f64:.*]] = std.view %[[tmpC_f64]][{{.*}}][{{.*}}] : memref<48xi8> to memref<?x?xf64>
 //     DYNAMIC:         std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?x?xf64>
 //       CHECK:         %[[partialC_f64:.*]] = subview %[[fullC_f64]][%{{.*}}, %{{.*}}] : memref<?x?xf64> to memref<?x?xf64, #[[$strided2D_dynamic]]>
 
 //       CHECK:         linalg.copy(%[[vA_f64]], %[[partialA_f64]]) : memref<?x?xf64, #[[$strided2D]]>, memref<?x?xf64, #[[$strided2D_dynamic]]>
 //       CHECK:         linalg.copy(%[[vB_f64]], %[[partialB_f64]]) : memref<?x?xf64, #[[$strided2D]]>, memref<?x?xf64, #[[$strided2D_dynamic]]>
 //       CHECK:         linalg.copy(%[[vC_f64]], %[[partialC_f64]]) : memref<?x?xf64, #[[$strided2D]]>, memref<?x?xf64, #[[$strided2D_dynamic]]>
 //
-//       CHECK:         linalg.matmul(%[[partialA_f64]], %[[partialB_f64]], %[[partialC_f64]]) : memref<?x?xf64, #[[$strided2D_dynamic]]>, memref<?x?xf64, #[[$strided2D_dynamic]]>, memref<?x?xf64, #[[$strided2D_dynamic]]>
-//
-//       CHECK:         linalg.copy(%[[partialC_f64]], %[[vC_f64]]) : memref<?x?xf64, #[[$strided2D_dynamic]]>, memref<?x?xf64, #[[$strided2D]]>
+//       CHECK:         linalg.matmul %[[partialA_f64]], %[[partialB_f64]], %[[partialC_f64]] :
+//       CHECK:           memref<?x?xf64, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf64, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf64, #[[$strided2D_dynamic]]>
+//
+//       CHECK:         linalg.copy(%[[partialC_f64]], %[[vC_f64]]) :
+//       CHECK:           memref<?x?xf64, #[[$strided2D_dynamic]]>,
+//       CHECK:           memref<?x?xf64, #[[$strided2D]]>
 //
 //       CHECK:         dealloc %[[tmpA_f64]] : memref<64xi8>
 //       CHECK:         dealloc %[[tmpB_f64]] : memref<96xi8>
 //       CHECK:         dealloc %[[tmpC_f64]] : memref<48xi8>
-
-// -----
-
-func @matmul_i32(%A: memref<?xi8>, %M: index, %N: index, %K: index) {
-  %c4 = constant 4 : index
-  %c3 = constant 3 : index
-  %c2 = constant 2 : index
-  %c0 = constant 0 : index
-  %c1 = constant 1 : index
-  %3 = view %A[%c0][%M, %K] : memref<?xi8> to memref<?x?xi32>
-  %4 = view %A[%c0][%K, %N] : memref<?xi8> to memref<?x?xi32>
-  %5 = view %A[%c0][%M, %N] : memref<?xi8> to memref<?x?xi32>
-  %6 = dim %3, %c0 : memref<?x?xi32>
-  %7 = dim %3, %c1 : memref<?x?xi32>
-  %8 = dim %4, %c1 : memref<?x?xi32>
-  scf.for %arg4 = %c0 to %6 step %c2 {
-    scf.for %arg5 = %c0 to %8 step %c3 {
-      scf.for %arg6 = %c0 to %7 step %c4 {
-        %11 = std.subview %3[%arg4, %arg6][%c2, %c4][1, 1] : memref<?x?xi32> to memref<?x?xi32, offset: ?, strides: [?, 1]>
-        %14 = std.subview %4[%arg6, %arg5][%c4, %c3][1, 1] : memref<?x?xi32> to memref<?x?xi32, offset: ?, strides: [?, 1]>
-        %17 = std.subview %5[%arg4, %arg5][%c2, %c3][1, 1] : memref<?x?xi32> to memref<?x?xi32, offset: ?, strides: [?, 1]>
-        linalg.matmul(%11, %14, %17) : memref<?x?xi32, offset: ?, strides: [?, 1]>, memref<?x?xi32, offset: ?, strides: [?, 1]>, memref<?x?xi32, offset: ?, strides: [?, 1]>
-      }
-    }
-  }
-  return
-}
-
-// CHECK-LABEL: func @matmul_i32(%{{.*}}: memref<?xi8>, %{{.*}}: index, %{{.*}}: index, %{{.*}}: index) {
-//       CHECK:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECK:     scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECK:       scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECK:         %[[vA_i32:.*]] = subview {{.*}} : memref<?x?xi32>
-//       CHECK:         %[[vB_i32:.*]] = subview {{.*}} : memref<?x?xi32>
-//       CHECK:         %[[vC_i32:.*]] = subview {{.*}} : memref<?x?xi32>
-///
-//       CHECK:         %[[tmpA_i32:.*]] = alloc() : memref<32xi8>
-//       CHECK:         %[[fullA_i32:.*]] = std.view %[[tmpA_i32]][{{.*}}][{{.*}}] : memref<32xi8> to memref<?x?xi32>
-//     DYNAMIC:         std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?x?xi32>
-//       CHECK:         %[[partialA_i32:.*]] = subview %[[fullA_i32]][%{{.*}}, %{{.*}}] : memref<?x?xi32> to memref<?x?xi32, #[[$strided2D_dynamic]]>
-///
-//       CHECK:         %[[tmpB_i32:.*]] = alloc() : memref<48xi8>
-//       CHECK:         %[[fullB_i32:.*]] = std.view %[[tmpB_i32]][{{.*}}][{{.*}}] : memref<48xi8> to memref<?x?xi32>
-//     DYNAMIC:         std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?x?xi32>
-//       CHECK:         %[[partialB_i32:.*]] = subview %[[fullB_i32]][%{{.*}}, %{{.*}}] : memref<?x?xi32> to memref<?x?xi32, #[[$strided2D_dynamic]]>
-///
-//       CHECK:         %[[tmpC_i32:.*]] = alloc() : memref<24xi8>
-//       CHECK:         %[[fullC_i32:.*]] = std.view %[[tmpC_i32]][{{.*}}][{{.*}}] : memref<24xi8> to memref<?x?xi32>
-//     DYNAMIC:         std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?x?xi32>
-//       CHECK:         %[[partialC_i32:.*]] = subview %[[fullC_i32]][%{{.*}}, %{{.*}}] : memref<?x?xi32> to memref<?x?xi32, #[[$strided2D_dynamic]]>
-
-//       CHECK:         linalg.copy(%[[vA_i32]], %[[partialA_i32]]) : memref<?x?xi32, #[[$strided2D]]>, memref<?x?xi32, #[[$strided2D_dynamic]]>
-//       CHECK:         linalg.copy(%[[vB_i32]], %[[partialB_i32]]) : memref<?x?xi32, #[[$strided2D]]>, memref<?x?xi32, #[[$strided2D_dynamic]]>
-//       CHECK:         linalg.copy(%[[vC_i32]], %[[partialC_i32]]) : memref<?x?xi32, #[[$strided2D]]>, memref<?x?xi32, #[[$strided2D_dynamic]]>
-//
-//       CHECK:         linalg.matmul(%[[partialA_i32]], %[[partialB_i32]], %[[partialC_i32]]) : memref<?x?xi32, #[[$strided2D_dynamic]]>, memref<?x?xi32, #[[$strided2D_dynamic]]>, memref<?x?xi32, #[[$strided2D_dynamic]]>
-//
-//       CHECK:         linalg.copy(%[[partialC_i32]], %[[vC_i32]]) : memref<?x?xi32, #[[$strided2D_dynamic]]>, memref<?x?xi32, #[[$strided2D]]>
-//
-//       CHECK:         dealloc %[[tmpA_i32]] : memref<32xi8>
-//       CHECK:         dealloc %[[tmpB_i32]] : memref<48xi8>
-//       CHECK:         dealloc %[[tmpC_i32]] : memref<24xi8>

mlir/test/Dialect/Linalg/promotion_options.mlir

 // RUN: mlir-opt %s -test-linalg-transform-patterns=test-linalg-promotion-options -split-input-file | FileCheck %s
 
 func @gemm(%a : memref<?x?xf32>, %b : memref<?x?xf32>, %c : memref<?x?xf32>)
 {
-   linalg.matmul(%a, %b, %c) {__internal_linalg_transform__ = "START"}
-     : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+   linalg.matmul %a, %b, %c {__internal_linalg_transform__ = "START"}
+     : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
    return
 }
 
 //      CHECK: func @gemm
 // CHECK-SAME: %[[ARG0:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 // CHECK-SAME: %[[ARG1:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 // CHECK-SAME: %[[ARG2:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 //  CHECK-DAG: %[[C42:.+]] = constant 4.200000e+01 : f32
 //      CHECK: scf.for
 //      CHECK:   scf.for
 //      CHECK:     scf.for
 //      CHECK:       %[[T7:.+]] = subview %[[ARG0]]
 //      CHECK:       %[[T12:.+]] = subview %[[ARG1]]
 //      CHECK:       %[[T17:.+]] = subview %[[ARG2]]
 //      CHECK:       %[[T18:.+]] = alloc(%{{.*}}, %{{.*}}) : memref<?x?xf32, 3>
 //      CHECK:       %[[T19:.+]] = subview %[[T18]]
 //      CHECK:       %[[T20:.+]] = alloc(%{{.*}}, %{{.*}}) : memref<?x?xf32, 3>
 //      CHECK:       %[[T21:.+]] = subview %[[T20]]
 //      CHECK:       linalg.fill(%[[T19]], %[[C42]])
 //      CHECK:       linalg.copy(%[[T7]], %[[T19]])
 //      CHECK:       linalg.fill(%[[T21]], %[[C42]])
 //      CHECK:       linalg.copy(%[[T17]], %[[T21]])
-//      CHECK:       linalg.matmul(%[[T19]], %[[T12]], %[[T21]])
+//      CHECK:       linalg.matmul %[[T19]], %[[T12]], %[[T21]]
 //  CHECK-NOT:       linalg.fill
 //      CHECK:       linalg.copy(%[[T21]], %[[T17]])
 //      CHECK:       dealloc %[[T18]]
 //      CHECK:       dealloc %[[T20]]

mlir/test/Dialect/Linalg/roundtrip.mlir

 
 // CHECK-DAG: #[[$strided1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
 // CHECK-DAG: #[[$strided2D:.*]] = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
 
 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]>,
+  linalg.matmul %arg0, %arg0, %arg0 : (memref<?x?xf32, offset: ?, strides: [?, 1]>,
                                        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]>,
                                     memref<f32>
   return
 }
 // CHECK-LABEL: func @ops(%
-//  CHECK-NEXT:  linalg.matmul(%{{.*}}, %{{.*}}, %{{.*}}) :
-//  CHECK-SAME:     memref<?x?xf32, #[[$strided2D]]>,
+//  CHECK-NEXT:  linalg.matmul %{{.*}}, %{{.*}}, %{{.*}} :
+//  CHECK-SAME:    (memref<?x?xf32, #[[$strided2D]]>,
 //  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>

mlir/test/Dialect/Linalg/tile.mlir

 
 //   TILE-2-DAG: #[[$bound_map:.*]] = affine_map<(d0)[s0] -> (2, -d0 + s0)>
 //  TILE-02-DAG: #[[$bound_map:.*]] = affine_map<(d0)[s0] -> (2, -d0 + s0)>
 // TILE-002-DAG: #[[$bound_map:.*]] = affine_map<(d0)[s0] -> (2, -d0 + s0)>
 // TILE-234-DAG: #[[$bound_map_2:.*]] = affine_map<(d0)[s0] -> (2, -d0 + s0)>
 // TILE-234-DAG: #[[$bound_map_3:.*]] = affine_map<(d0)[s0] -> (3, -d0 + s0)>
 // TILE-234-DAG: #[[$bound_map_4:.*]] = affine_map<(d0)[s0] -> (4, -d0 + s0)>
 
+//   TILE-2-DAG: #[[$bound_map_static:.*]] = affine_map<(d0) -> (2, -d0 + 10)>
+//  TILE-02-DAG: #[[$bound_map_static:.*]] = affine_map<(d0) -> (2, -d0 + 12)>
+// TILE-002-DAG: #[[$bound_map_static:.*]] = affine_map<(d0) -> (2, -d0 + 16)>
+
 //   TILE-2-DAG: #[[$stride_99_1_layout_map:.*]] = affine_map<(d0, d1)[s0] -> (d0 * 99 + s0 + d1)>
 //  TILE-02-DAG: #[[$stride_99_1_layout_map:.*]] = affine_map<(d0, d1)[s0] -> (d0 * 99 + s0 + d1)>
 // TILE-234-DAG: #[[$stride_99_1_layout_map:.*]] = affine_map<(d0, d1)[s0] -> (d0 * 99 + s0 + d1)>
 
-func @matmul(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>, %arg1: memref<?x?xf32, offset: ?, strides: [?, 1]>, %arg2: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
-  linalg.matmul(%arg0, %arg1, %arg2) : memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>, memref<?x?xf32, offset: ?, strides: [?, 1]>
+func @matmul(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
+             %arg1: memref<?x?xf32, offset: ?, strides: [?, 1]>,
+             %arg2: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
+  linalg.matmul %arg0, %arg1, %arg2 :
+    (memref<?x?xf32, offset: ?, strides: [?, 1]>,
+     memref<?x?xf32, offset: ?, strides: [?, 1]>,
+     memref<?x?xf32, offset: ?, strides: [?, 1]>)
   return
 }
 // TILE-2-LABEL: func @matmul(
 //       TILE-2-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-2-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-2: %[[M:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2: scf.for %[[I:.*]] = %{{.*}}{{.*}} to %[[M]] step %{{.*}} {
 //       TILE-2:   %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-2:   %[[szM:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localM]]]
 //       TILE-2:   %[[K:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2:   %[[sAi:.*]] = subview %{{.*}}[%[[I]], 0] [%[[szM]], %[[K]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2:   %[[localK:.*]] = dim %{{.*}}, %c0
 //       TILE-2:   %[[szK:.*]] = affine.min #[[$bound_map]](%[[I]])[%[[localK]]]
 //       TILE-2:   %[[N:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-2:   %[[sCi:.*]] = subview %{{.*}}[%[[I]], 0] [%[[szK]], %[[N]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
-//       TILE-2:   linalg.matmul(%[[sAi]], %{{.*}}, %[[sCi]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>
+//       TILE-2:   linalg.matmul %[[sAi]], %{{.*}}, %[[sCi]] :
+//       TILE-2:     (memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-2:      memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-2:      memref<?x?xf32, #[[$strided2D]]>)
 
 // TILE-02-LABEL: func @matmul(
 //       TILE-02-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-02-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-02: %[[N:.*]] = dim %arg1, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02: scf.for %[[J:.*]] = %{{.*}} to %[[N]] step %{{.*}} {
 //       TILE-02:   %[[K:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02:   %[[localN:.*]] = dim %{{.*}}, %c1
 //       TILE-02:   %[[szN:.*]] = affine.min #[[$bound_map]](%[[J]])[%[[localN]]]
 //       TILE-02:   %[[sBj:.*]] = subview %{{.*}}[0, %[[J]]] [%[[K]], %[[szN]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02:   %[[M:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-02:   %[[localK:.*]] = dim %{{.*}}, %c1
 //       TILE-02:   %[[szK:.*]] = affine.min #[[$bound_map]](%[[J]])[%[[localK]]]
 //       TILE-02:   %[[sCj:.*]] = subview %{{.*}}[0, %[[J]]] [%[[M]], %[[szK]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
-//       TILE-02:   linalg.matmul(%{{.*}}, %[[sBj]], %[[sCj]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>
+//       TILE-02:   linalg.matmul %{{.*}}, %[[sBj]], %[[sCj]] :
+//       TILE-02:     (memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-02:      memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-02:      memref<?x?xf32, #[[$strided2D]]>)
 
 // TILE-002-LABEL: func @matmul(
 //       TILE-002-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-002-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-002: %[[ubK:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-002: scf.for %[[K:.*]] = %{{.*}}{{.*}} to %[[ubK]] step %{{.*}} {
 //       TILE-002:   %[[M:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-002:   %[[localK:.*]] = dim %{{.*}}, %c1
 //       TILE-002:   %[[szK:.*]] = affine.min #[[$bound_map]](%[[K]])[%[[localK]]]
 //       TILE-002:   %[[sAj:.*]] = subview %{{.*}}[0, %[[K]]] [%[[M]], %[[szK]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-002:   %[[localK:.*]] = dim %{{.*}}, %c0
 //       TILE-002:   %[[szK:.*]] = affine.min #[[$bound_map]](%[[K]])[%[[localK]]]
 //       TILE-002:   %[[N:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-002:   %[[sBj:.*]] = subview %{{.*}}[%[[K]], 0] [%[[szK]], %[[N]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
-//       TILE-002:   linalg.matmul(%[[sAj]], %[[sBj]], %{{.*}}) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>
+//       TILE-002:   linalg.matmul %[[sAj]], %[[sBj]], %{{.*}} :
+//       TILE-002:     (memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-002:      memref<?x?xf32, #[[$strided2D]]>,
+//       TILE-002:      memref<?x?xf32, #[[$strided2D]]>)
 
 // TILE-234-LABEL: func @matmul(
 //       TILE-234-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-234-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-234-DAG: %[[C3:.*]] = constant 3 : index
 //       TILE-234-DAG: %[[C4:.*]] = constant 4 : index
 //       TILE-234: %[[ubM:.*]] = dim %{{.*}}, %c0 : memref<?x?xf32, #[[$strided2D]]>
 //       TILE-234: %[[ubK:.*]] = dim %{{.*}}, %c1 : memref<?x?xf32, #[[$strided2D]]>

 //       TILE-234:        %[[szN:.*]] = affine.min #[[$bound_map_3]](%[[J]])[%[[localN]]]
 //       TILE-234:        %[[sBkj:.*]] = subview %{{.*}}[%[[K]], %[[J]]] [%[[szK]], %[[szN]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-234:        %[[localM:.*]] = dim %{{.*}}, %c0
 //       TILE-234:        %[[szM:.*]] = affine.min #[[$bound_map_2]](%[[I]])[%[[localM]]]
 //       TILE-234:        %[[localN:.*]] = dim %{{.*}}, %c1
 //       TILE-234:        %[[szN:.*]] = affine.min #[[$bound_map_3]](%[[J]])[%[[localN]]]
 //       TILE-234:        %[[sCij:.*]] = subview %{{.*}}[%[[I]], %[[J]]] [%[[szM]], %[[szN]]] [1, 1] : memref<?x?xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //
-//       TILE-234:        linalg.matmul(%[[sAik]], %[[sBkj]], %[[sCij]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$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]]>)
 
 // When the buffer shapes are known at compile time, it is possible to avoid
 // the "min" in subview size computation. This test uses buffer sizes divisible
 // by respective tile sizes (M=10 divisble by 2, N=12 divisible by 2 and 3,
 // K=16 divisble by 2 and 4).
-func @matmul_static(%arg0: memref<10x16xf32, offset: ?, strides: [?, 1]>, %arg1: memref<16x12xf32, offset: ?, strides: [?, 1]>, %arg2: memref<10x12xf32, offset: ?, strides: [?, 1]>) {
-  linalg.matmul(%arg0, %arg1, %arg2) : memref<10x16xf32, offset: ?, strides: [?, 1]>, memref<16x12xf32, offset: ?, strides: [?, 1]>, memref<10x12xf32, offset: ?, strides: [?, 1]>
+func @matmul_static(%arg0: memref<10x16xf32, offset: ?, strides: [?, 1]>,
+                    %arg1: memref<16x12xf32, offset: ?, strides: [?, 1]>,
+                    %arg2: memref<10x12xf32, offset: ?, strides: [?, 1]>) {
+  linalg.matmul %arg0, %arg1, %arg2 :
+    (memref<10x16xf32, offset: ?, strides: [?, 1]>,
+     memref<16x12xf32, offset: ?, strides: [?, 1]>,
+     memref<10x12xf32, offset: ?, strides: [?, 1]>)
   return
 }
 // TILE-2-LABEL: func @matmul_static(
 //  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-DAG: %[[M:.*]] = constant 10 : index
 //       TILE-2: scf.for %[[I:.*]] = %{{.*}} to %[[M]] step %{{.*}} {
-//       TILE-2:   %[[MIN2:.*]] = affine.min #map2(%[[I]])
+//       TILE-2:   %[[MIN2:.*]] = affine.min #[[$bound_map_static]](%[[I]])
 //       TILE-2:   %[[sAi:.*]] = subview %{{.*}}[%[[I]], 0] [%[[MIN2]], 16] [1, 1] : memref<10x16xf32, #[[$strided2D]]> to memref<?x16xf32, #[[$strided2D]]>
-//       TILE-2:   %[[MIN22:.*]] = affine.min #map2(%[[I]])
+//       TILE-2:   %[[MIN22:.*]] = affine.min #[[$bound_map_static]](%[[I]])
 //       TILE-2:   %[[sCi:.*]] = subview %{{.*}}[%[[I]], 0] [%[[MIN22]], 12] [1, 1] : memref<10x12xf32, #[[$strided2D]]> to memref<?x12xf32, #[[$strided2D]]>
-//       TILE-2:   linalg.matmul(%[[sAi]], %{{.*}}, %[[sCi]])
+//       TILE-2:   linalg.matmul %[[sAi]], %{{.*}}, %[[sCi]]
 
 // TILE-02-LABEL: func @matmul_static(
 //       TILE-02-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-02-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-02-DAG: %[[N:.*]] = constant 12 : index
 //       TILE-02: scf.for %[[J:.*]] = %{{.*}} to %[[N]] step %{{.*}} {
-//       TILE-02:   %[[MIN2:.*]] = affine.min #map2(%[[J]])
+//       TILE-02:   %[[MIN2:.*]] = affine.min #[[$bound_map_static]](%[[J]])
 //       TILE-02:   %[[sBj:.*]] = subview %{{.*}}[0, %[[J]]] [16, %[[MIN2]]] [1, 1] : memref<16x12xf32, #[[$strided2D]]> to memref<16x?xf32, #[[$strided2D]]>
-//       TILE-02:   %[[MIN22:.*]] = affine.min #map2(%[[J]])
+//       TILE-02:   %[[MIN22:.*]] = affine.min #[[$bound_map_static]](%[[J]])
 //       TILE-02:   %[[sCj:.*]] = subview %{{.*}}[0, %[[J]]] [10, %[[MIN22]]] [1, 1] : memref<10x12xf32, #[[$strided2D]]> to memref<10x?xf32, #[[$strided2D]]>
-//       TILE-02:   linalg.matmul(%{{.*}}, %[[sBj]], %[[sCj]]) : memref<10x16xf32, #[[$strided2D]]>, memref<16x?xf32, #[[$strided2D]]>, memref<10x?xf32, #[[$strided2D]]>
+//       TILE-02:   linalg.matmul %{{.*}}, %[[sBj]], %[[sCj]] :
+//       TILE-02:     (memref<10x16xf32, #[[$strided2D]]>,
+//       TILE-02:      memref<16x?xf32, #[[$strided2D]]>,
+//       TILE-02:      memref<10x?xf32, #[[$strided2D]]>)
 
 // TILE-002-LABEL: func @matmul_static(
 //       TILE-002-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-002-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-002-DAG: %[[C16:.*]] = constant 16 : index
 //       TILE-002: scf.for %[[K:.*]] = %{{.*}}{{.*}} to %[[C16]] step %{{.*}} {
-//       TILE-002:   %[[MIN2:.*]] = affine.min #map2(%[[K]])
+//       TILE-002:   %[[MIN2:.*]] = affine.min #[[$bound_map_static]](%[[K]])
 //       TILE-002:   %[[sAj:.*]] = subview %{{.*}}[0, %[[K]]] [10, %[[MIN2]]] [1, 1] : memref<10x16xf32, #[[$strided2D]]> to memref<10x?xf32, #[[$strided2D]]>
-//       TILE-002:   %[[MIN22:.*]] = affine.min #map2(%[[K]])
+//       TILE-002:   %[[MIN22:.*]] = affine.min #[[$bound_map_static]](%[[K]])
 //       TILE-002:   %[[sBj:.*]] = subview %{{.*}}[%[[K]], 0] [%[[MIN22]], 12] [1, 1] : memref<16x12xf32, #[[$strided2D]]> to memref<?x12xf32, #[[$strided2D]]>
-//       TILE-002:   linalg.matmul(%[[sAj]], %[[sBj]], %{{.*}}) : memref<10x?xf32, #[[$strided2D]]>, memref<?x12xf32, #[[$strided2D]]>, memref<10x12xf32, #[[$strided2D]]>
+//       TILE-002:   linalg.matmul %[[sAj]], %[[sBj]], %{{.*}} :
+//       TILE-002:     (memref<10x?xf32, #[[$strided2D]]>,
+//       TILE-002:      memref<?x12xf32, #[[$strided2D]]>,
+//       TILE-002:      memref<10x12xf32, #[[$strided2D]]>)
 
 // TILE-234-LABEL: func @matmul_static(
 //       TILE-234-DAG: %[[C0:.*]] = constant 0 : index
 //       TILE-234-DAG: %[[C2:.*]] = constant 2 : index
 //       TILE-234-DAG: %[[C3:.*]] = constant 3 : index
 //       TILE-234-DAG: %[[C4:.*]] = constant 4 : index
 //       TILE-234-DAG: %[[C10:.*]] = constant 10 : index
 //       TILE-234-DAG: %[[C16:.*]] = constant 16 : index
 //       TILE-234-DAG: %[[C12:.*]] = constant 12 : index
 //       TILE-234:  scf.for %[[I:.*]] = %{{.*}}{{.*}} to %[[C10]] step %{{.*}} {
 //       TILE-234:    scf.for %[[J:.*]] = %{{.*}}{{.*}} to %[[C12]] step %{{.*}} {
 //       TILE-234:      scf.for %[[K:.*]] = %{{.*}}{{.*}} to %[[C16]] step %{{.*}} {
 //       TILE-234:        %[[sAik:.*]] = subview %{{.*}}[%[[I]], %[[K]]] [%{{.*}}, %{{.*}}] [1, 1] : memref<10x16xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-234:        %[[sBkj:.*]] = subview %{{.*}}[%[[K]], %[[J]]] [%{{.*}}, %{{.*}}] [1, 1] : memref<16x12xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //       TILE-234:        %[[sCij:.*]] = subview %{{.*}}[%[[I]], %[[J]]] [%{{.*}}, %{{.*}}] [1, 1] : memref<10x12xf32, #[[$strided2D]]> to memref<?x?xf32, #[[$strided2D]]>
 //
-//       TILE-234:        linalg.matmul(%[[sAik]], %[[sBkj]], %[[sCij]]) : memref<?x?xf32, #[[$strided2D]]>, memref<?x?xf32, #[[$strided2D]]>, 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]>
   return
 }
 // TILE-2-LABEL: func @matvec(
 //  TILE-2-SAME: %[[ARG0:[0-9a-zA-Z]*]]: memref
 //  TILE-2-SAME: %[[ARG1:[0-9a-zA-Z]*]]: memref

mlir/test/Dialect/Linalg/tile_parallel_reduce.mlir

 // RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,4,8" -split-input-file | FileCheck %s
 // RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2" -split-input-file | FileCheck %s -check-prefix=TILE1
 // RUN: mlir-opt %s -linalg-tile-to-parallel-loops="linalg-tile-sizes=2,4" -split-input-file | FileCheck %s -check-prefix=TILE2
 
 func @gemm(%arg0 : memref<?x?xf32>,
            %arg1 : memref<?x?xf32>,
            %arg2 : memref<?x?xf32>)
 {
-  linalg.matmul(%arg0, %arg1, %arg2)
-    : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+  linalg.matmul %arg0, %arg1, %arg2
+    : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
   return
 }
 // CHECK-LABEL: func @gemm
 //   CHECK-DAG:   %[[C2:.*]] = constant 2 : index
 //   CHECK-DAG:   %[[C4:.*]] = constant 4 : index
 //   CHECK-DAG:   %[[C8:.*]] = constant 8 : index
 //       CHECK:   scf.parallel (%[[ARG3:.*]], %[[ARG4:.*]]) =
 //  CHECK-SAME:     step (%[[C2]], %[[C4]])
 //       CHECK:     scf.for %[[ARG5:.*]] =
 //  CHECK-SAME:       step %[[C8]]
 //       CHECK:       %[[SV1:.*]] = subview %{{.*}}[%[[ARG3]], %[[ARG5]]]
 //       CHECK:       %[[SV2:.*]] = subview %{{.*}}[%[[ARG5]], %[[ARG4]]]
 //       CHECK:       %[[SV3:.*]] = subview %{{.*}}[%[[ARG3]], %[[ARG4]]]
-//       CHECK:       linalg.matmul(%[[SV1]], %[[SV2]], %[[SV3]])
+//       CHECK:       linalg.matmul %[[SV1]], %[[SV2]], %[[SV3]]
 
 // TILE1-LABEL: func @gemm
 //   TILE1-DAG:   %[[C2:.*]] = constant 2 : index
 //       TILE1:   scf.parallel (%[[ARG3:.*]]) =
 //  TILE1-SAME:     step (%[[C2]])
 //       TILE1:     %[[SV1:.*]] = subview %{{.*}}[%[[ARG3]], 0]
 //       TILE1:     %[[SV3:.*]] = subview %{{.*}}[%[[ARG3]], 0]
 //   TILE1-NOT:     subview
-//       TILE1:     linalg.matmul(%[[SV1]], %{{.*}}, %[[SV3]])
+//       TILE1:     linalg.matmul %[[SV1]], %{{.*}}, %[[SV3]]
 
 // TILE2-LABEL: func @gemm
 //   TILE2-DAG:   %[[C2:.*]] = constant 2 : index
 //   TILE2-DAG:   %[[C4:.*]] = constant 4 : index
 //       TILE2:   scf.parallel (%[[ARG3:.*]], %[[ARG4:.*]]) =
 //  TILE2-SAME:     step (%[[C2]], %[[C4]])
 //       TILE2:       %[[SV1:.*]] = subview %{{.*}}[%[[ARG3]], 0]
 //       TILE2:       %[[SV2:.*]] = subview %{{.*}}[0, %[[ARG4]]]
 //       TILE2:       %[[SV3:.*]] = subview %{{.*}}[%[[ARG3]], %[[ARG4]]]
-//       TILE2:       linalg.matmul(%[[SV1]], %[[SV2]], %[[SV3]])
+//       TILE2:       linalg.matmul %[[SV1]], %[[SV2]], %[[SV3]]
 
 // -----
 
 #map0 = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
 #map1 = affine_map<(d0, d1, d2) -> (d0, d2)>
 #map2 = affine_map<(d0, d1, d2) -> (d1)>
 #accesses = [#map0, #map1, #map2]
 #trait = {

mlir/test/Dialect/Linalg/transform-patterns-matmul-to-vector.mlir

 // RUN: mlir-opt %s -test-linalg-transform-patterns=test-matmul-to-vector-patterns-tile-1d | FileCheck %s
 // RUN: mlir-opt %s -test-linalg-transform-patterns=test-matmul-to-vector-patterns-tile-2d | FileCheck %s
 
 func @matmul(%A: memref<1584x1584xf32, offset: 0, strides: [1584, 1]>,
                   %B: memref<1584x1584xf32, offset: 0, strides: [1584, 1]>,
                   %C: memref<1584x1584xf32, offset: 0, strides: [1584, 1]>) {
-  linalg.matmul(%A, %B, %C) {__internal_linalg_transform__ = "START"} :
+  linalg.matmul %A, %B, %C {__internal_linalg_transform__ = "START"} :
+    (memref<1584x1584xf32, offset: 0, strides: [1584, 1]>,
      memref<1584x1584xf32, offset: 0, strides: [1584, 1]>,
-    memref<1584x1584xf32, offset: 0, strides: [1584, 1]>,
-    memref<1584x1584xf32, offset: 0, strides: [1584, 1]>
+     memref<1584x1584xf32, offset: 0, strides: [1584, 1]>)
   return
 }
 
 // CHECK-LABEL:func @matmul
 //      CHECK: vector.broadcast {{.*}} : f32 to vector<8x16xf32>
 //      CHECK: store {{.*}}[] : memref<vector<8x16xf32>>
 //
 //      CHECK: vector.broadcast {{.*}} : f32 to vector<16x12xf32>

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

 // 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]]>
 
 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]>
+  linalg.matmul %A, %B, %C { __internal_linalg_transform__ = "MEM" } :
+    (memref<?x?xf32, offset: ?, strides: [?, 1]>,
+     memref<?x?xf32, offset: ?, strides: [?, 1]>)
   return
 }
 // CHECK-LABEL: func @matmul
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c2:.*]] = constant 2 : index
 // CHECK-DAG:     %[[c3:.*]] = constant 3 : index
 // CHECK-DAG:     %[[c4:.*]] = constant 4 : index
 // CHECK-DAG:     %[[c20:.*]] = constant 20 : index

 // CHECK:                 scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
 // CHECK:                   scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
 // CHECK:                     scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
 // CHECK:                       scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
 // CHECK:                         scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
 // CHECK:                           scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c2]] {
 // CHECK:                             scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c3]] {
 // CHECK:                               scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c4]] {
-// CHECK:                                 linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?x?xf32, #[[$STRIDED_2D]]>
+// CHECK:                                 linalg.matmul {{.*}}, {{.*}}, {{.*}} : (
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>,
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>,
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>)
 
 #matmul_trait = {
   args_in = 2,
   args_out = 1,
   indexing_maps = [
     affine_map<(m, n, k) -> (m, k)>,
     affine_map<(m, n, k) -> (k, n)>,
     affine_map<(m, n, k) -> (m, n)>

 //       CHECK: vector.transfer_read %{{.*}} : memref<8x16xf32>, vector<8x16xf32>
 //       CHECK: vector.transfer_read %{{.*}} : memref<16x32xf32>, vector<16x32xf32>
 //       CHECK: vector.transfer_read %{{.*}} : memref<8x32xf32>, vector<8x32xf32>
 //       CHECK: vector.contract {indexing_maps = [#[[$mk]], #[[$kn]], #[[$mn]]], iterator_types = ["parallel", "parallel", "reduction"]} %{{.*}}, %{{.*}}, %{{.*}} : vector<8x16xf32>, vector<16x32xf32> into vector<8x32xf32>
 //       CHECK: vector.transfer_write %{{.*}}, %{{.*}} : vector<8x32xf32>, memref<8x32xf32>
 
 func @vectorization_test_2(%A: memref<8x16xf32>, %B: memref<16x32xf32>,
                          %C: memref<8x32xf32>) {
-  linalg.matmul(%A, %B, %C) { __internal_linalg_transform__ = "VECTORIZE"} :
-    memref<8x16xf32>, memref<16x32xf32>, memref<8x32xf32>
+  linalg.matmul %A, %B, %C { __internal_linalg_transform__ = "VECTORIZE"} :
+    (memref<8x16xf32>, memref<16x32xf32>, memref<8x32xf32>)
   return
 }
 // CHECK-LABEL: func @vectorization_test_2
 //       CHECK: vector.contract {{.*}} :
 //                vector<8x16xf32>, vector<16x32xf32> into vector<8x32xf32>
 
 func @test_vectorize_fill(%A : memref<8x16xf32>, %arg0 : f32) {
   linalg.fill(%A, %arg0) { __internal_linalg_transform__ = "VECTORIZE"} :  memref<8x16xf32>, f32

 // 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]]>
 
 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]>,
+  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]>
+                memref<?x?xf32, offset: ?, strides: [?, 1]>)
   return
 }
 // CHECK-LABEL: func @matmul_perm
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c20:.*]] = constant 20 : index
 // CHECK-DAG:     %[[c30:.*]] = constant 30 : index
 // CHECK-DAG:     %[[c40:.*]] = constant 40 : index
 // CHECK-DAG:     %[[c200:.*]] = constant 200 : index
 // CHECK-DAG:     %[[c300:.*]] = constant 300 : index
 // CHECK-DAG:     %[[c400:.*]] = constant 400 : index
 // CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index
 // CHECK-DAG:     %[[c3000:.*]] = constant 3000 : index
 // CHECK-DAG:     %[[c4000:.*]] = constant 4000 : index
 // CHECK:         scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c3000]] {
 // CHECK:           scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c4000]] {
 // CHECK:             scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c2000]] {
 // CHECK:               scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c300]] {
 // CHECK:                 scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c200]] {
 // CHECK:                   scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c400]] {
 // CHECK:                     scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c20]] {
 // CHECK:                       scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c30]] {
 // CHECK:                         scf.for {{.*}} = %[[c0]] to {{.*}} step %[[c40]] {
-// CHECK:                                 linalg.matmul({{.*}}, {{.*}}, {{.*}}) : memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?x?xf32, #[[$STRIDED_2D]]>
+// CHECK:                                 linalg.matmul {{.*}}, {{.*}}, {{.*}} : (
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>,
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>,
+// CHECK:                                   memref<?x?xf32, #[[$STRIDED_2D]]>)
 
 func @promote_subview_matmul(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
                              %arg1: memref<?x?xf32, offset: ?, strides: [?, 1]>,
                              %arg2: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
   %c2000 = constant 2000 : index
   %c3000 = constant 3000 : index
   %c4000 = constant 4000 : index
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %0 = dim %arg0, %c0 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %1 = dim %arg0, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %2 = dim %arg1, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   scf.for %arg3 = %c0 to %0 step %c2000 {
     scf.for %arg4 = %c0 to %2 step %c3000 {
       scf.for %arg5 = %c0 to %1 step %c4000 {
         %3 = subview %arg0[%arg3, %arg5][%c2000, %c4000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %4 = subview %arg1[%arg5, %arg4][%c4000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %5 = subview %arg2[%arg3, %arg4][%c2000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%3, %4, %5) {__internal_linalg_transform__ = "_promote_views_"} :
-                      memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %3, %4, %5 {__internal_linalg_transform__ = "_promote_views_"} :
+                      (memref<?x?xf32, offset: ?, strides: [?, ?]>,
                        memref<?x?xf32, offset: ?, strides: [?, ?]>,
-                      memref<?x?xf32, offset: ?, strides: [?, ?]>
+                       memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return
 }
 // CHECK-LABEL: func @promote_subview_matmul
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index

 // CHECK:               %[[v1:.*]] = std.view %[[a1]][{{.*}}][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
 // CHECK:               %[[l1:.*]] = subview %[[v1]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[$STRIDED_2D]]>
 // CHECK:               %[[a2:.*]] = alloc({{%.*}}) : memref<?xi8>
 // CHECK:               %[[v2:.*]] = std.view %[[a2]][{{.*}}][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
 // CHECK:               %[[l2:.*]] = subview %[[v2]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[$STRIDED_2D]]>
 // CHECK:               linalg.copy(%[[s0]], %[[l0]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
 // CHECK:               linalg.copy(%[[s1]], %[[l1]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
 // CHECK:               linalg.copy(%[[s2]], %[[l2]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
-// CHECK:               linalg.matmul(%[[v0]], %[[v1]], %[[v2]]) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+// CHECK:               linalg.matmul %[[v0]], %[[v1]], %[[v2]] :
+// CHECK:                 (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
 
 func @promote_first_subview_matmul(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
                              %arg1: memref<?x?xf32, offset: ?, strides: [?, 1]>,
                              %arg2: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
   %c2000 = constant 2000 : index
   %c3000 = constant 3000 : index
   %c4000 = constant 4000 : index
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %0 = dim %arg0, %c0 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %1 = dim %arg0, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   %2 = dim %arg1, %c1 : memref<?x?xf32, offset: ?, strides: [?, 1]>
   scf.for %arg3 = %c0 to %0 step %c2000 {
     scf.for %arg4 = %c0 to %2 step %c3000 {
       scf.for %arg5 = %c0 to %1 step %c4000 {
         %3 = std.subview %arg0[%arg3, %arg5][%c2000, %c4000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %4 = std.subview %arg1[%arg5, %arg4][%c4000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
         %5 = std.subview %arg2[%arg3, %arg4][%c2000, %c3000][%c1, %c1] :
              memref<?x?xf32, offset: ?, strides: [?, 1]> to memref<?x?xf32, offset: ?, strides: [?, ?]>
-        linalg.matmul(%3, %4, %5) {__internal_linalg_transform__ = "_promote_first_view_"} :
-                      memref<?x?xf32, offset: ?, strides: [?, ?]>,
+        linalg.matmul %3, %4, %5 {__internal_linalg_transform__ = "_promote_first_view_"} :
+                      (memref<?x?xf32, offset: ?, strides: [?, ?]>,
                        memref<?x?xf32, offset: ?, strides: [?, ?]>,
-                      memref<?x?xf32, offset: ?, strides: [?, ?]>
+                       memref<?x?xf32, offset: ?, strides: [?, ?]>)
       }
     }
   }
   return
 }
 // CHECK-LABEL: func @promote_first_subview_matmul
 // CHECK-DAG:     %[[c0:.*]] = constant 0 : index
 // CHECK-DAG:     %[[c2000:.*]] = constant 2000 : index

 // CHECK-NOT:     %[[v1:.*]] = std.view %[[a1]][{{.*}}][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
 // CHECK-NOT:     %[[l0:.*]] = subview %[[v1]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[$STRIDED_2D]]>
 // CHECK-NOT:     %[[a2:.*]] = alloc({{%.*}}) : memref<?xi8>
 // CHECK-NOT:     %[[v2:.*]] = std.view %[[a2]][{{.*}}][{{%.*}}, {{%.*}}] : memref<?xi8> to memref<?x?xf32>
 // CHECK-NOT:     %[[l0:.*]] = subview %[[v2]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[$STRIDED_2D]]>
 // CHECK:         linalg.copy(%[[s0]], %[[l0]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
 // CHECK-NOT:     linalg.copy(%[[s1]], %[[l1]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
 // CHECK-NOT:     linalg.copy(%[[s2]], %[[l2]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>^
-// CHECK:         linalg.matmul(%[[v0]], %[[s1]], %[[s2]]) : memref<?x?xf32>, memref<?x?xf32, #[[$STRIDED_2D]]>, memref<?x?xf32, #[[$STRIDED_2D]]>
+// CHECK:         linalg.matmul %[[v0]], %[[s1]], %[[s2]] :
+// CHECK:           (memref<?x?xf32>,
+// CHECK:            memref<?x?xf32, #[[$STRIDED_2D]]>,
+// CHECK:            memref<?x?xf32, #[[$STRIDED_2D]]>)
 
 func @aligned_promote_fill(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>) {
   %c2000 = constant 2000 : index
   %c4000 = constant 4000 : index
   %c0 = constant 0 : index
   %c1 = constant 1 : index
   %cf = constant 1.0 : f32
   %3 = std.subview %arg0[%c0, %c0][%c2000, %c4000][%c1, %c1] :

 // CHECK:         %[[l0:.*]] = subview %[[v0]][{{%.*}}, {{%.*}}] [{{%.*}}, {{%.*}}] : memref<?x?xf32> to memref<?x?xf32, #[[$STRIDED_2D]]>
 // CHECK:         linalg.fill(%[[v0]], {{%.*}}) : memref<?x?xf32>, f32
 // CHECK:         linalg.copy(%[[s0]], %[[l0]]) : memref<?x?xf32, #map{{.*}}>, memref<?x?xf32, #map{{.*}}>
 // CHECK:         linalg.fill(%[[v0]], %[[cf]]) : memref<?x?xf32>, f32
 
 func @tile_permute_parallel_loop(%arg0: memref<?x?xf32>,
                                  %arg1: memref<?x?xf32>,
                                  %arg2: memref<?x?xf32>) {
-  linalg.matmul(%arg0, %arg1, %arg2) {__internal_linalg_transform__ = "par__with_perm__"}
-    : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+  linalg.matmul %arg0, %arg1, %arg2 {__internal_linalg_transform__ = "par__with_perm__"}
+    : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
   return
 }
 // CHECK-LABEL: func @tile_permute_parallel_loop
 //  CHECK-SAME:   %[[ARG0:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 //  CHECK-SAME:   %[[ARG1:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 //  CHECK-SAME:   %[[ARG2:[a-zA-Z0-9_]+]]: memref<?x?xf32>
 //   CHECK-DAG:   %[[C16:.*]] = constant 16 : index
 //   CHECK-DAG:   %[[C8:.*]] = constant 8 : index
 //   CHECK-DAG:   %[[C4:.*]] = constant 4 : index
 //   CHECK-DAG:   %[[C0:.*]] = constant 0 : index
 //   CHECK-DAG:   %[[D0:.*]] = dim %[[ARG0]], %c0
 //   CHECK-DAG:   %[[D1:.*]] = dim %[[ARG0]], %c1
 //   CHECK-DAG:   %[[D2:.*]] = dim %[[ARG1]], %c1
 //       CHECK:   scf.parallel (%{{.*}}) = (%[[C0]]) to (%[[D2]]) step (%[[C8]])
 //       CHECK:     scf.for %{{.*}} = %[[C0]] to %[[D1]] step %[[C4]]
 //       CHECK:       scf.parallel (%{{.*}}) = (%[[C0]]) to (%[[D0]]) step (%[[C16]])

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

func @matmul() -> f32 {
   %bA = call @alloc_filled_f32(%c32, %f2) : (index, f32) -> (memref<?xi8>)
   %bB = call @alloc_filled_f32(%c32, %f1) : (index, f32) -> (memref<?xi8>)
   %bC = call @alloc_filled_f32(%c4, %f10) : (index, f32) -> (memref<?xi8>)
 
   %A = view %bA[%c0][%c2, %c16] : memref<?xi8> to memref<?x?xf32>
   %B = view %bB[%c0][%c16, %c2] : memref<?xi8> to memref<?x?xf32>
   %C = view %bC[%c0][%c2, %c2] : memref<?xi8> to memref<?x?xf32>
 
-  linalg.matmul(%A, %B, %C) : memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>
+  linalg.matmul %A, %B, %C : (memref<?x?xf32>, memref<?x?xf32>, memref<?x?xf32>)
   %res = load %C[%c0, %c1] : memref<?x?xf32>
 
   dealloc %bC : memref<?xi8>
   dealloc %bB : memref<?xi8>
   dealloc %bA : memref<?xi8>
 
   return %res : f32
 }
 
 // All tests return this value
 // CHECK: 4.2{{0+}}e+01

mlir/tools/mlir-linalg-ods-gen/mlir-linalg-ods-gen.cpp

SingleBlockImplicitTerminator<"YieldOp">]> {
         static SmallVector<StringRef, 8> referenceIterators(
           TypeRange inputTypes, TypeRange outputTypes);
 
         llvm::Optional<SmallVector<AffineMap, 8>> referenceIndexingMaps();
         static SmallVector<AffineMap, 8> referenceIndexingMaps(
           TypeRange inputTypes, TypeRange outputTypes);
 
         static void regionBuilder(Block &block);
+
+        std::string getLibraryCallName() {{
+          return generateLibraryCallName(getOperation());
+        }
       }];
   })FMT";
 
   unsigned nInputs = 0, nOutputs = 0;
   for (auto &t : registeredTensors) {
     if (t.getValue().isOutput)
       nOutputs++;
     else