NFC - Moved VectorOps to Vector

[rsuderman]

Summary

NFC - Moved VectorOps to Vector to better match the dialect naming convention. As all dialects contain ops, having the Ops suffix is unnecessary.

[rsuderman]

Arc diff broke git repo. Attempting to redo.

mlir/docs/Dialects/Vector.md

 concretely needed, but it seems reasonable to have the same levels of
 abstraction for all targets and perform cost-based lowering decisions in MLIR
 even for `LLVM`.
 Specialized `CPU` dialects that would capture specific features not well
 captured by LLVM peephole optimizations of on different types that core MLIR
 supports (e.g. Scalable Vectors) are welcome future extensions.
 
 ### Virtual Vector Ops
-Some existing Standard and VectorOps Dialect on `n-D` `vector` types comprise:
+Some existing Standard and Vector Dialect on `n-D` `vector` types comprise:
 ```
 %2 = std.addf %0, %1 : vector<3x7x8xf32>  // -> vector<3x7x8xf32>
 %2 = std.mulf %0, %1 : vector<3x7x8xf32>  // -> vector<3x7x8xf32>
 %2 = std.splat %1    : vector<3x7x8xf32>  // -> vector<3x7x8xf32>
 
 %1 = vector.extract %0[1]: vector<3x7x8xf32>                 // -> vector<7x8xf32>
 %1 = vector.extract %0[1, 5]: vector<3x7x8xf32>            // -> vector<8xf32>
 %2 = vector.outerproduct %0, %1: vector<4xf32>, vector<8xf32>     // -> vector<4x8xf32>
 %3 = vector.outerproduct %0, %1, %2: vector<4xf32>, vector<8xf32> // fma when adding %2
 %3 = vector.strided_slice %0 {offsets = [2, 2], sizes = [2, 2], strides = [1, 1]}:
    vector<4x8x16xf32> // Returns a slice of type vector<2x2x16xf32>
 
 %2 = vector.transfer_read %A[%0, %1]
   {permutation_map = (d0, d1) -> (d0)}: memref<7x?xf32>, vector<4xf32>
 
 vector.transfer_write %f1, %A[%i0, %i1, %i2, %i3]
   {permutation_map = (d0, d1, d2, d3) -> (d3, d1, d0)} :
     vector<5x4x3xf32>, memref<?x?x?x?xf32>
 ```
 
-The list of VectorOps is currently undergoing evolutions and is best kept
+The list of Vector is currently undergoing evolutions and is best kept
 track of by following the evolution of the
-[VectorOps.td](https://github.com/llvm/llvm-project/blob/master/mlir/include/mlir/Dialect/VectorOps/VectorOps.td)
+[VectorOps.td](https://github.com/llvm/llvm-project/blob/master/mlir/include/mlir/Dialect/Vector/VectorOps.td)
 ODS file (markdown documentation is automatically generated locally when
 building and populates the [Vector
 doc](https://github.com/llvm/llvm-project/blob/master/mlir/docs/Dialects/Vector.md)). Recent
 extensions are driven by concrete use cases of interest. A notable such use
 case is the `vector.contract` op which applies principles of the StructuredOps
 abstraction to `vector` types.
 
 ### Virtual Vector Rewrite Patterns

mlir/include/mlir/Dialect/CMakeLists.txt

 add_subdirectory(AffineOps)
 add_subdirectory(FxpMathOps)
 add_subdirectory(GPU)
 add_subdirectory(Linalg)
 add_subdirectory(LLVMIR)
 add_subdirectory(LoopOps)
 add_subdirectory(OpenMP)
 add_subdirectory(QuantOps)
 add_subdirectory(Shape)
 add_subdirectory(SPIRV)
 add_subdirectory(StandardOps)
-add_subdirectory(VectorOps)
+add_subdirectory(Vector)

mlir/include/mlir/Dialect/Vector/CMakeLists.txt

 add_mlir_dialect(VectorOps vector VectorOps)
 
 set(LLVM_TARGET_DEFINITIONS VectorTransformPatterns.td)
 mlir_tablegen(VectorTransformPatterns.h.inc -gen-rewriters)
 add_public_tablegen_target(MLIRVectorTransformPatternsIncGen)

mlir/include/mlir/Dialect/Vector/EDSC/Builders.h

 //===- Builders.h - MLIR Declarative Vector Builders ------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // Provides intuitive composable interfaces for building structured MLIR
 // snippets in a declarative fashion.
 //
 //===----------------------------------------------------------------------===//
 #ifndef MLIR_DIALECT_VECTOR_EDSC_BUILDERS_H_
 #define MLIR_DIALECT_VECTOR_EDSC_BUILDERS_H_
 
 #include "mlir/Dialect/Utils/StructuredOpsUtils.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/EDSC/Builders.h"
 #include "mlir/EDSC/Intrinsics.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Builders.h"
 
 namespace mlir {
 namespace edsc {
 namespace ops {

mlir/include/mlir/Dialect/Vector/EDSC/Intrinsics.h

-//===- Intrinsics.h - MLIR EDSC Intrinsics for VectorOps --------*- C++ -*-===//
+//===- Intrinsics.h - MLIR EDSC Intrinsics for Vector -----------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
-#ifndef MLIR_DIALECT_VECTOROPS_EDSC_INTRINSICS_H_
-#define MLIR_DIALECT_VECTOROPS_EDSC_INTRINSICS_H_
+#ifndef MLIR_DIALECT_VECTOR_EDSC_INTRINSICS_H_
+#define MLIR_DIALECT_VECTOR_EDSC_INTRINSICS_H_
 
-#include "mlir/Dialect/VectorOps/EDSC/Builders.h"
+#include "mlir/Dialect/Vector/EDSC/Builders.h"
 
 namespace mlir {
 namespace edsc {
 namespace intrinsics {
 
 using vector_broadcast = ValueBuilder<vector::BroadcastOp>;
 using vector_contract = ValueBuilder<vector::ContractionOp>;
 using vector_print = OperationBuilder<vector::PrintOp>;
 
 } // namespace intrinsics
 } // namespace edsc
 } // namespace mlir
 
-#endif // MLIR_DIALECT_VECTOROPS_EDSC_INTRINSICS_H_
+#endif // MLIR_DIALECT_VECTOR_EDSC_INTRINSICS_H_

mlir/include/mlir/Dialect/Vector/VectorOps.h

 //===- VectorOps.h - MLIR Super Vectorizer Operations -----------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file defines the Vector dialect.
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef MLIR_DIALECT_VECTOROPS_VECTOROPS_H
-#define MLIR_DIALECT_VECTOROPS_VECTOROPS_H
+#ifndef MLIR_DIALECT_VECTOR_VECTOROPS_H
+#define MLIR_DIALECT_VECTOR_VECTOROPS_H
 
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/Dialect.h"
 #include "mlir/IR/OpDefinition.h"
 #include "mlir/IR/StandardTypes.h"
 #include "mlir/Interfaces/SideEffects.h"
 
 namespace mlir {

 /// Returns the integer type required for subscripts in the vector dialect.
 IntegerType getVectorSubscriptType(Builder &builder);
 
 /// Returns an integer array attribute containing the given values using
 /// the integer type required for subscripts in the vector dialect.
 ArrayAttr getVectorSubscriptAttr(Builder &b, ArrayRef<int64_t> values);
 
 #define GET_OP_CLASSES
-#include "mlir/Dialect/VectorOps/VectorOps.h.inc"
+#include "mlir/Dialect/Vector/VectorOps.h.inc"
 
-#include "mlir/Dialect/VectorOps/VectorOpsDialect.h.inc"
+#include "mlir/Dialect/Vector/VectorDialect.h.inc"
 
 } // end namespace vector
 } // end namespace mlir
 
-#endif // MLIR_DIALECT_VECTOROPS_VECTOROPS_H
+#endif // MLIR_DIALECT_VECTOR_VECTOROPS_H

mlir/include/mlir/Dialect/Vector/VectorOps.td

 //===----------------------------------------------------------------------===//
 
 #ifndef VECTOR_OPS
 #define VECTOR_OPS
 
 include "mlir/Dialect/AffineOps/AffineOpsBase.td"
 include "mlir/Interfaces/SideEffects.td"
 
-def VectorOps_Dialect : Dialect {
+def Vector_Dialect : Dialect {
   let name = "vector";
   let cppNamespace = "vector";
   let hasConstantMaterializer = 1;
 }
 
 // Base class for Vector dialect ops.
 class Vector_Op<string mnemonic, list<OpTrait> traits = []> :
-    Op<VectorOps_Dialect, mnemonic, traits> {
+    Op<Vector_Dialect, mnemonic, traits> {
   // For every vector op, there needs to be a:
   //   * void print(OpAsmPrinter &p, ${C++ class of Op} op)
   //   * LogicalResult verify(${C++ class of Op} op)
   //   * ParseResult parse${C++ class of Op}(OpAsmParser &parser,
   //                                         OperationState &result)
   // functions.
   let printer = [{ return ::print(p, *this); }];
   let verifier = [{ return ::verify(*this); }];
def Vector_ExtractSlicesOp :
   }];
   let assemblyFormat = [{
     $vector `,` $sizes `,` $strides attr-dict `:` type($vector) `into`
     type(results)
   }];
 }
 
 def Vector_FMAOp :
-  Op<VectorOps_Dialect, "fma", [NoSideEffect,
+  Op<Vector_Dialect, "fma", [NoSideEffect,
                              AllTypesMatch<["lhs", "rhs", "acc", "result"]>]>,
     Arguments<(ins AnyVector:$lhs, AnyVector:$rhs, AnyVector:$acc)>,
     Results<(outs AnyVector:$result)> {
   let summary = "vector fused multiply-add";
   let description = [{
     Multiply-add expressions operate on n-D vectors and compute a fused
     pointwise multiply-and-accumulate: `$result = `$lhs * $rhs + $acc`.
     All operands and result have the same vector type. The semantics

mlir/include/mlir/Dialect/Vector/VectorTransformPatterns.td

 //===- VectorTransformPatterns.td - Vector-Vector patterns -*- tablegen -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This is the pattern definition file for declarative Vector transformations.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef VECTOR_TRANSFORM_PATTERNS
 #define VECTOR_TRANSFORM_PATTERNS
 
 include "mlir/IR/OpBase.td"
 
 class HasShape<list<int> shape> :
   CPred<"$0.getType().cast<ShapedType>().hasStaticShape({" #
     StrJoinInt<shape>.result # "})">;
 
 class UnrollVectorOp<list<int> factors> : NativeCodeCall<
   "unrollSingleResultOpMatchingType($_builder, $0.getDefiningOp(), " #
     "{" # StrJoinInt<factors>.result # "})">;
 
 #endif // VECTOR_TRANSFORM_PATTERNS

mlir/include/mlir/Dialect/Vector/VectorTransforms.h

 //===- VectorTransforms.h - Vector transformations as patterns --*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef DIALECT_VECTOROPS_VECTORTRANSFORMS_H_
-#define DIALECT_VECTOROPS_VECTORTRANSFORMS_H_
+#ifndef DIALECT_VECTOR_VECTORTRANSFORMS_H_
+#define DIALECT_VECTOR_VECTORTRANSFORMS_H_
 
 #include "mlir/IR/PatternMatch.h"
 
 namespace mlir {
 class MLIRContext;
 class OwningRewritePatternList;
 
 /// Collect a set of patterns to convert from the Vector dialect to itself.

 // simple pointwise ops.
 SmallVector<Value, 1>
 unrollSingleResultOpMatchingType(PatternRewriter &builder, Operation *op,
                                  ArrayRef<int64_t> targetShape);
 
 } // namespace vector
 } // namespace mlir
 
-#endif // DIALECT_VECTOROPS_VECTORTRANSFORMS_H_
+#endif // DIALECT_VECTOR_VECTORTRANSFORMS_H_

mlir/include/mlir/Dialect/Vector/VectorUtils.h

 //===- VectorUtils.h - VectorOps Utilities ------------------*- C++ -*-=======//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
-#ifndef MLIR_DIALECT_VECTOROPS_VECTORUTILS_H_
-#define MLIR_DIALECT_VECTOROPS_VECTORUTILS_H_
+#ifndef MLIR_DIALECT_VECTOR_VECTORUTILS_H_
+#define MLIR_DIALECT_VECTOR_VECTORUTILS_H_
 
 #include "mlir/Support/LLVM.h"
 
 #include "llvm/ADT/DenseMap.h"
 
 namespace mlir {
 
 // Forward declarations.

 /// TODO(ntv): this could all be much simpler if we added a bit that a vector
 /// type to mark that a vector is a strict super-vector but it still does not
 /// warrant adding even 1 extra bit in the IR for now.
 bool operatesOnSuperVectorsOf(Operation &op, VectorType subVectorType);
 
 } // end namespace matcher
 } // end namespace mlir
 
-#endif // MLIR_DIALECT_VECTOROPS_VECTORUTILS_H_
+#endif // MLIR_DIALECT_VECTOR_VECTORUTILS_H_

mlir/include/mlir/InitAllDialects.h

 #include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
 #include "mlir/Dialect/LoopOps/LoopOps.h"
 #include "mlir/Dialect/OpenMP/OpenMPDialect.h"
 #include "mlir/Dialect/QuantOps/QuantOps.h"
 #include "mlir/Dialect/SDBM/SDBMDialect.h"
 #include "mlir/Dialect/SPIRV/SPIRVDialect.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/Dialect.h"
 
 namespace mlir {
 
 // This function should be called before creating any MLIRContext if one expect
 // all the possible dialects to be made available to the context automatically.
 inline void registerAllDialects() {
   static bool init_once = []() {
     registerDialect<AffineOpsDialect>();
     registerDialect<fxpmath::FxpMathOpsDialect>();
     registerDialect<gpu::GPUDialect>();
     registerDialect<LLVM::LLVMDialect>();
     registerDialect<linalg::LinalgDialect>();
     registerDialect<loop::LoopOpsDialect>();
     registerDialect<omp::OpenMPDialect>();
     registerDialect<quant::QuantizationDialect>();
     registerDialect<spirv::SPIRVDialect>();
     registerDialect<StandardOpsDialect>();
-    registerDialect<vector::VectorOpsDialect>();
+    registerDialect<vector::VectorDialect>();
     registerDialect<NVVM::NVVMDialect>();
     registerDialect<ROCDL::ROCDLDialect>();
     registerDialect<SDBMDialect>();
     return true;
   }();
   (void)init_once;
 }
 } // namespace mlir
 
 #endif // MLIR_INITALLDIALECTS_H_

mlir/lib/Conversion/VectorToLLVM/CMakeLists.txt

 add_mlir_conversion_library(MLIRVectorToLLVM
   ConvertVectorToLLVM.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Conversion/VectorToLLVM
 )
 set(LIBS
   MLIRLLVMIR
   MLIRStandardToLLVM
-  MLIRVectorOps
+  MLIRVector
   MLIRTransforms
   LLVMCore
   LLVMSupport
   )
 
 add_dependencies(MLIRVectorToLLVM ${LIBS})
 target_link_libraries(MLIRVectorToLLVM
   PUBLIC
   ${LIBS})

mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp

 //===- VectorToLLVM.cpp - Conversion from Vector to the LLVM dialect ------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "mlir/Conversion/VectorToLLVM/ConvertVectorToLLVM.h"
 
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h"
 #include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/MLIRContext.h"
 #include "mlir/IR/Module.h"
 #include "mlir/IR/Operation.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/IR/StandardTypes.h"
 #include "mlir/IR/Types.h"

mlir/lib/Conversion/VectorToLoops/ConvertVectorToLoops.cpp

 //===----------------------------------------------------------------------===//
 
 #include <type_traits>
 
 #include "mlir/Conversion/VectorToLoops/ConvertVectorToLoops.h"
 #include "mlir/Dialect/AffineOps/EDSC/Intrinsics.h"
 #include "mlir/Dialect/LoopOps/EDSC/Builders.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/Location.h"
 #include "mlir/IR/Matchers.h"
 #include "mlir/IR/OperationSupport.h"
 #include "mlir/IR/PatternMatch.h"

mlir/lib/Dialect/CMakeLists.txt

 add_subdirectory(AffineOps)
 add_subdirectory(FxpMathOps)
 add_subdirectory(GPU)
 add_subdirectory(Linalg)
 add_subdirectory(LLVMIR)
 add_subdirectory(LoopOps)
 add_subdirectory(OpenMP)
 add_subdirectory(QuantOps)
 add_subdirectory(SDBM)
 #add_subdirectory(Shape)
 add_subdirectory(SPIRV)
 add_subdirectory(StandardOps)
-add_subdirectory(VectorOps)
+add_subdirectory(Vector)
 
 set(LLVM_OPTIONAL_SOURCES
   Traits.cpp
 )
 
 add_mlir_library(MLIRDialect
   Traits.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect
   )
 target_link_libraries(MLIRDialect
   PUBLIC
   MLIRIR
   )

mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt

target_link_libraries(MLIRLinalgTransforms
   MLIRLinalgEDSC
   MLIRLinalgOps
   MLIRLinalgUtils
   MLIRLoopOps
   MLIRPass
   MLIRStandardOps
   MLIRStandardToLLVM
   MLIRTransformUtils
-  MLIRVectorOps
+  MLIRVector
   )

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

 //===----------------------------------------------------------------------===//
 
 #include "mlir/Dialect/Linalg/Transforms/LinalgTransforms.h"
 #include "mlir/Dialect/Linalg/Analysis/DependenceAnalysis.h"
 #include "mlir/Dialect/Linalg/IR/LinalgOps.h"
 #include "mlir/Dialect/Linalg/Utils/Utils.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Utils/StructuredOpsUtils.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Matchers.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/Pass/Pass.h"
 #include "mlir/Support/LLVM.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 #include <type_traits>

mlir/lib/Dialect/Vector/CMakeLists.txt

-add_mlir_dialect_library(MLIRVectorOps
+add_mlir_dialect_library(MLIRVector
   VectorOps.cpp
   VectorTransforms.cpp
   VectorUtils.cpp
   EDSC/Builders.cpp
 
   ADDITIONAL_HEADER_DIRS
-  ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/VectorOps
+  ${MLIR_MAIN_INCLUDE_DIR}/mlir/Dialect/Vector
 
   DEPENDS
-  MLIRVectorOpsIncGen
+  MLIRVectorIncGen
   MLIRVectorTransformPatternsIncGen
   )
-target_link_libraries(MLIRVectorOps
+target_link_libraries(MLIRVector
   PUBLIC
   MLIREDSC
   MLIRIR
   MLIRStandardOps
   MLIRAffineOps
   MLIRLoopOps
   MLIRLoopAnalysis
   MLIRSideEffects
   )

mlir/lib/Dialect/Vector/EDSC/Builders.cpp

 //===- Builders.cpp - MLIR Declarative Linalg Builders --------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Dialect/VectorOps/EDSC/Builders.h"
-#include "mlir/Dialect/VectorOps/EDSC/Intrinsics.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/EDSC/Builders.h"
+#include "mlir/Dialect/Vector/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/EDSC/Builders.h"
 #include "mlir/EDSC/Intrinsics.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/Support/Functional.h"
 
 using namespace mlir;
 using namespace mlir::edsc;

mlir/lib/Dialect/Vector/VectorOps.cpp

 //===- VectorOps.cpp - MLIR Super Vectorizer Operations -------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements convenience types for working with super-vectorization
 // operations, in particular super-vector loads and stores.
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/Dialect/Utils/StructuredOpsUtils.h"
-#include "mlir/Dialect/VectorOps/VectorUtils.h"
+#include "mlir/Dialect/Vector/VectorUtils.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/OpImplementation.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/IR/TypeUtilities.h"
 #include "mlir/Support/Functional.h"
 #include "mlir/Support/LLVM.h"
 #include "mlir/Support/MathExtras.h"
 #include "mlir/Support/STLExtras.h"
 #include "llvm/ADT/StringSet.h"
 #include <numeric>
 
 using namespace mlir;
 using namespace mlir::vector;
 
 //===----------------------------------------------------------------------===//
-// VectorOpsDialect
+// VectorDialect
 //===----------------------------------------------------------------------===//
 
-VectorOpsDialect::VectorOpsDialect(MLIRContext *context)
+VectorDialect::VectorDialect(MLIRContext *context)
     : Dialect(getDialectNamespace(), context) {
   addOperations<
 #define GET_OP_LIST
-#include "mlir/Dialect/VectorOps/VectorOps.cpp.inc"
+#include "mlir/Dialect/Vector/VectorOps.cpp.inc"
       >();
 }
 
 /// Materialize a single constant operation from a given attribute value with
 /// the desired resultant type.
-Operation *VectorOpsDialect::materializeConstant(OpBuilder &builder,
+Operation *VectorDialect::materializeConstant(OpBuilder &builder,
                                                  Attribute value, Type type,
                                                  Location loc) {
   return builder.create<ConstantOp>(loc, type, value);
 }
 
 IntegerType vector::getVectorSubscriptType(Builder &builder) {
   return builder.getIntegerType(64);
 }
if (memrefVectorElementType.getElementType() != vectorType.getElementType())
           "requires memref and vector types of the same elemental type");
 
     // Check that memref vector type is a suffix of 'vectorType.
     unsigned memrefVecEltRank = memrefVectorElementType.getRank();
     unsigned resultVecRank = vectorType.getRank();
     if (memrefVecEltRank > resultVecRank)
       return op->emitOpError(
           "requires memref vector element and vector result ranks to match.");
-    // TODO(b/146516564) Move this to isSuffix in VectorOps/Utils.h.
+    // TODO(b/146516564) Move this to isSuffix in Vector/Utils.h.
     unsigned rankOffset = resultVecRank - memrefVecEltRank;
     auto memrefVecEltShape = memrefVectorElementType.getShape();
     auto resultVecShape = vectorType.getShape();
     for (unsigned i = 0; i < memrefVecEltRank; ++i)
       if (memrefVecEltShape[i] != resultVecShape[rankOffset + i])
         return op->emitOpError(
             "requires memref vector element shape to match suffix of "
             "vector result shape.");
void mlir::vector::populateVectorToVectorCanonicalizationPatterns(
     OwningRewritePatternList &patterns, MLIRContext *context) {
   patterns.insert<CreateMaskFolder, StridedSliceConstantMaskFolder>(context);
 }
 
 namespace mlir {
 namespace vector {
 
 #define GET_OP_CLASSES
-#include "mlir/Dialect/VectorOps/VectorOps.cpp.inc"
+#include "mlir/Dialect/Vector/VectorOps.cpp.inc"
 
 } // namespace vector
 } // namespace mlir

mlir/lib/Dialect/Vector/VectorTransforms.cpp

 //
 //===----------------------------------------------------------------------===//
 
 #include <type_traits>
 
 #include "mlir/Dialect/AffineOps/AffineOps.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
 #include "mlir/Dialect/Utils/StructuredOpsUtils.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
-#include "mlir/Dialect/VectorOps/VectorTransforms.h"
-#include "mlir/Dialect/VectorOps/VectorUtils.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorTransforms.h"
+#include "mlir/Dialect/Vector/VectorUtils.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/IR/Attributes.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/Function.h"
 #include "mlir/IR/Location.h"
 #include "mlir/IR/Matchers.h"
 #include "mlir/IR/Module.h"

mlir/lib/Dialect/Vector/VectorUtils.cpp

 //===- VectorUtils.cpp - MLIR Utilities for VectorOps   ------------------===//
 //
 // Part of the MLIR Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
-// This file implements utility methods for working with the VectorOps dialect.
+// This file implements utility methods for working with the Vector dialect.
 //
 //===----------------------------------------------------------------------===//
 
-#include "mlir/Dialect/VectorOps/VectorUtils.h"
+#include "mlir/Dialect/Vector/VectorUtils.h"
 #include "mlir/Analysis/LoopAnalysis.h"
 #include "mlir/Dialect/AffineOps/AffineOps.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/IntegerSet.h"
 #include "mlir/IR/Operation.h"
 #include "mlir/Support/Functional.h"
 #include "mlir/Support/LLVM.h"
 #include "mlir/Support/MathExtras.h"
 #include "mlir/Support/STLExtras.h"
 

mlir/lib/Transforms/CMakeLists.txt

 target_link_libraries(MLIRTransforms
   PUBLIC
   MLIRAffineOps
   MLIRAnalysis
   MLIRLoopLikeInterface
   MLIRLoopOps
   MLIRPass
   MLIRTransformUtils
-  MLIRVectorOps
+  MLIRVector
   )

mlir/lib/Transforms/Vectorize.cpp

 //===----------------------------------------------------------------------===//
 
 #include "mlir/Analysis/LoopAnalysis.h"
 #include "mlir/Analysis/NestedMatcher.h"
 #include "mlir/Analysis/SliceAnalysis.h"
 #include "mlir/Analysis/Utils.h"
 #include "mlir/Dialect/AffineOps/AffineOps.h"
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
-#include "mlir/Dialect/VectorOps/VectorUtils.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorUtils.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/Location.h"
 #include "mlir/IR/Types.h"
 #include "mlir/Pass/Pass.h"
 #include "mlir/Support/Functional.h"
 #include "mlir/Support/LLVM.h"
 #include "mlir/Transforms/FoldUtils.h"

mlir/test/Dialect/Vector/canonicalize.mlir

 // RUN: mlir-opt %s -pass-pipeline='func(canonicalize)' -split-input-file | FileCheck %s
 
 // -----
 
 // CHECK-LABEL: create_vector_mask_to_constant_mask
 func @create_vector_mask_to_constant_mask() -> (vector<4x3xi1>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   // CHECK: vector.constant_mask [3, 2] : vector<4x3xi1>
   %0 = vector.create_mask %c3, %c2 : vector<4x3xi1>
   return %0 : vector<4x3xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x2xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [0, 0], sizes = [2, 2], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x2xi1>
   // CHECK: vector.constant_mask [2, 2] : vector<2x2xi1>
   return %1 : vector<2x2xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x2xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [1, 0], sizes = [2, 2], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x2xi1>
   // CHECK: vector.constant_mask [1, 2] : vector<2x2xi1>
   return %1 : vector<2x2xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x2xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [0, 1], sizes = [2, 2], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x2xi1>
   // CHECK: vector.constant_mask [2, 1] : vector<2x2xi1>
   return %1 : vector<2x2xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x2xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [2, 0], sizes = [2, 2], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x2xi1>
   // CHECK: vector.constant_mask [0, 0] : vector<2x2xi1>
   return %1 : vector<2x2xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x1xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [0, 2], sizes = [2, 1], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x1xi1>
   // CHECK: vector.constant_mask [0, 0] : vector<2x1xi1>
   return %1 : vector<2x1xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x1xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [0, 1], sizes = [2, 1], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x1xi1>
   // CHECK: vector.constant_mask [2, 1] : vector<2x1xi1>
   return %1 : vector<2x1xi1>
 }
 
 // -----
 
 func @strided_slice_of_constant_mask() -> (vector<2x1xi1>) {
   %0 = vector.constant_mask [2, 2] : vector<4x3xi1>
   %1 = vector.strided_slice %0
     {offsets = [1, 1], sizes = [2, 1], strides = [1, 1]}
       : vector<4x3xi1> to vector<2x1xi1>
   // CHECK: vector.constant_mask [1, 1] : vector<2x1xi1>
   return %1 : vector<2x1xi1>
 }

mlir/test/Dialect/Vector/invalid.mlir

 // RUN: mlir-opt %s -split-input-file -verify-diagnostics
 
 // -----
 
 func @broadcast_to_scalar(%arg0: f32) -> f32 {
   // expected-error@+1 {{'vector.broadcast' op result #0 must be vector of any type values, but got 'f32'}}
   %0 = vector.broadcast %arg0 : f32 to f32
 }
 
 // -----
 
 func @broadcast_rank_too_high(%arg0: vector<4x4xf32>) {
   // expected-error@+1 {{'vector.broadcast' op source rank higher than destination rank}}
   %1 = vector.broadcast %arg0 : vector<4x4xf32> to vector<4xf32>
 }
 
 // -----
 
 func @broadcast_dim1_mismatch(%arg0: vector<7xf32>) {
   // expected-error@+1 {{'vector.broadcast' op dimension mismatch (7 vs. 3)}}
   %1 = vector.broadcast %arg0 : vector<7xf32> to vector<3xf32>
 }
 
 // -----
 
 func @broadcast_dim2_mismatch(%arg0: vector<4x8xf32>) {
   // expected-error@+1 {{'vector.broadcast' op dimension mismatch (4 vs. 1)}}
   %1 = vector.broadcast %arg0 : vector<4x8xf32> to vector<1x8xf32>
 }
 
 // -----
 
 func @shuffle_elt_type_mismatch(%arg0: vector<2xf32>, %arg1: vector<2xi32>) {
   // expected-error@+1 {{'vector.shuffle' op failed to verify that second operand v2 and result have same element type}}
   %1 = vector.shuffle %arg0, %arg1 [0, 1] : vector<2xf32>, vector<2xi32>
 }
 
 // -----
 
 func @shuffle_rank_mismatch(%arg0: vector<2xf32>, %arg1: vector<4x2xf32>) {
   // expected-error@+1 {{'vector.shuffle' op rank mismatch}}
   %1 = vector.shuffle %arg0, %arg1 [0, 1] : vector<2xf32>, vector<4x2xf32>
 }
 
 // -----
 
 func @shuffle_trailing_dim_size_mismatch(%arg0: vector<2x2xf32>, %arg1: vector<2x4xf32>) {
   // expected-error@+1 {{'vector.shuffle' op dimension mismatch}}
   %1 = vector.shuffle %arg0, %arg1 [0, 1] : vector<2x2xf32>, vector<2x4xf32>
 }
 
 // -----
 
 func @shuffle_index_out_of_range(%arg0: vector<2xf32>, %arg1: vector<2xf32>) {
   // expected-error@+1 {{'vector.shuffle' op mask index #2 out of range}}
   %1 = vector.shuffle %arg0, %arg1 [0, 4] : vector<2xf32>, vector<2xf32>
 }
 
 // -----
 
 func @shuffle_empty_mask(%arg0: vector<2xf32>, %arg1: vector<2xf32>) {
   // expected-error@+1 {{'vector.shuffle' invalid mask length}}
   %1 = vector.shuffle %arg0, %arg1 [] : vector<2xf32>, vector<2xf32>
 }
 
 // -----
 
 func @extract_element(%arg0: vector<4x4xf32>) {
   %c = constant 3 : i32
   // expected-error@+1 {{'vector.extractelement' op expected 1-D vector}}
   %1 = vector.extractelement %arg0[%c : i32] : vector<4x4xf32>
 }
 
 // -----
 
 func @extract_vector_type(%arg0: index) {
   // expected-error@+1 {{expected vector type}}
   %1 = vector.extract %arg0[] : index
 }
 
 // -----
 
 func @extract_position_empty(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected non-empty position attribute}}
   %1 = vector.extract %arg0[] : vector<4x8x16xf32>
 }
 
 // -----
 
 func @extract_position_rank_overflow(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute of rank smaller than vector}}
   %1 = vector.extract %arg0[0, 0, 0, 0] : vector<4x8x16xf32>
 }
 
 // -----
 
 func @extract_position_rank_overflow_generic(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute of rank smaller than vector}}
   %1 = "vector.extract" (%arg0) { position = [0, 0, 0, 0] } : (vector<4x8x16xf32>) -> (vector<16xf32>)
 }
 
 // -----
 
 func @extract_position_overflow(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute #2 to be a non-negative integer smaller than the corresponding vector dimension}}
   %1 = vector.extract %arg0[0, 43, 0] : vector<4x8x16xf32>
 }
 
 // -----
 
 func @extract_precise_position_overflow(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute #3 to be a non-negative integer smaller than the corresponding vector dimension}}
   %1 = vector.extract %arg0[3, 7, 16] : vector<4x8x16xf32>
 }
 
 // -----
 
 func @extract_position_overflow(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute #3 to be a non-negative integer smaller than the corresponding vector dimension}}
   %1 = vector.extract %arg0[0, 0, -1] : vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_element(%arg0: f32, %arg1: vector<4x4xf32>) {
   %c = constant 3 : i32
   // expected-error@+1 {{'vector.insertelement' op expected 1-D vector}}
   %0 = vector.insertelement %arg0, %arg1[%c : i32] : vector<4x4xf32>
 }
 
 // -----
 
 func @insert_element_wrong_type(%arg0: i32, %arg1: vector<4xf32>) {
   %c = constant 3 : i32
   // expected-error@+1 {{'vector.insertelement' op failed to verify that source operand type matches element type of result}}
   %0 = "vector.insertelement" (%arg0, %arg1, %c) : (i32, vector<4xf32>, i32) -> (vector<4xf32>)
 }
 
 // -----
 
 func @insert_vector_type(%a: f32, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected non-empty position attribute}}
   %1 = vector.insert %a, %b[] : f32 into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_vector_type(%a: f32, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute of rank smaller than dest vector rank}}
   %1 = vector.insert %a, %b[3, 3, 3, 3, 3, 3] : f32 into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_vector_type(%a: vector<4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute rank + source rank to match dest vector rank}}
   %1 = vector.insert %a, %b[3] : vector<4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_vector_type(%a: f32, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute rank to match the dest vector rank}}
   %1 = vector.insert %a, %b[3, 3] : f32 into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_position_overflow(%a: f32, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute #3 to be a non-negative integer smaller than the corresponding dest vector dimension}}
   %1 = vector.insert %a, %b[0, 0, -1] : f32 into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_precise_position_overflow(%a: f32, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected position attribute #1 to be a non-negative integer smaller than the corresponding dest vector dimension}}
   %1 = vector.insert %a, %b[4, 7, 15] : f32 into vector<4x8x16xf32>
 }
 
 // -----
 
 func @outerproduct_num_operands(%arg0: f32) {
   // expected-error@+1 {{expected at least 2 operands}}
   %1 = vector.outerproduct %arg0 : f32, f32
 }
 // -----
 
 func @outerproduct_non_vector_operand(%arg0: f32) {
   // expected-error@+1 {{expected 2 vector types}}
   %1 = vector.outerproduct %arg0, %arg0 : f32, f32
 }
 
 // -----
 
 func @outerproduct_operand_1(%arg0: vector<4xf32>, %arg1: vector<4x8xf32>) {
   // expected-error@+1 {{expected 1-d vector for operand #1}}
   %1 = vector.outerproduct %arg1, %arg1 : vector<4x8xf32>, vector<4x8xf32>
 }
 
 // -----
 
 func @outerproduct_operand_2(%arg0: vector<4xf32>, %arg1: vector<4x8xf32>) {
   // expected-error@+1 {{expected 1-d vector for operand #2}}
   %1 = vector.outerproduct %arg0, %arg1 : vector<4xf32>, vector<4x8xf32>
 }
 
 // -----
 
 func @outerproduct_result_generic(%arg0: vector<4xf32>, %arg1: vector<8xf32>) {
   // expected-error@+1 {{expected 2-d vector result}}
   %1 = "vector.outerproduct" (%arg0, %arg1) : (vector<4xf32>, vector<8xf32>) -> (vector<8xf32>)
 }
 
 // -----
 
 func @outerproduct_operand_1_dim_generic(%arg0: vector<4xf32>, %arg1: vector<8xf32>) {
   // expected-error@+1 {{expected #1 operand dim to match result dim #1}}
   %1 = "vector.outerproduct" (%arg0, %arg1) : (vector<4xf32>, vector<8xf32>) -> (vector<8x16xf32>)
 }
 
 // -----
 
 func @outerproduct_operand_2_dim_generic(%arg0: vector<4xf32>, %arg1: vector<8xf32>) {
   // expected-error@+1 {{expected #2 operand dim to match result dim #2}}
   %1 = "vector.outerproduct" (%arg0, %arg1) : (vector<4xf32>, vector<8xf32>) -> (vector<4x16xf32>)
 }
 
 // -----
 
 func @outerproduct_operand_3_result_type_generic(%arg0: vector<4xf32>, %arg1: vector<8xf32>, %arg2: vector<4x16xf32>) {
   // expected-error@+1 {{expected operand #3 of same type as result type}}
   %1 = "vector.outerproduct" (%arg0, %arg1, %arg2) : (vector<4xf32>, vector<8xf32>, vector<4x16xf32>) -> (vector<4x8xf32>)
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{two types required}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst { permutation_map = affine_map<()->(0)> } : memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires 2 indices}}
   %0 = vector.transfer_read %arg0[%c3, %c3, %c3], %cst { permutation_map = affine_map<()->(0)> } : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires attribute 'permutation_map'}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst {perm = affine_map<(d0)->(d0)>} : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires a permutation_map with input dims of the same rank as the memref type}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0)->(d0)>} : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires a permutation_map with result dims of the same rank as the vector type}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires a projected permutation_map (at most one dim or the zero constant can appear in each result)}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0, d1)->(d0 + d1)>} : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires a projected permutation_map (at most one dim or the zero constant can appear in each result)}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0, d1)->(d0 + 1)>} : memref<?x?xf32>, vector<128xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   // expected-error@+1 {{requires a permutation_map that is a permutation (found one dim used more than once)}}
   %0 = vector.transfer_read %arg0[%c3, %c3, %c3], %cst {permutation_map = affine_map<(d0, d1, d2)->(d0, d0)>} : memref<?x?x?xf32>, vector<3x7xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xvector<4x3xf32>>) {
   %c3 = constant 3 : index
   %f0 = constant 0.0 : f32
   %vf0 = splat %f0 : vector<4x3xf32>
   // expected-error@+1 {{requires memref and vector types of the same elemental type}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %vf0 {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : memref<?x?xvector<4x3xf32>>, vector<1x1x4x3xi32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xvector<4x3xf32>>) {
   %c3 = constant 3 : index
   %f0 = constant 0.0 : f32
   %vf0 = splat %f0 : vector<4x3xf32>
   // expected-error@+1 {{requires memref vector element and vector result ranks to match}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %vf0 {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : memref<?x?xvector<4x3xf32>>, vector<3xf32>
 }
 
 // -----
 
 func @test_vector.transfer_read(%arg0: memref<?x?xvector<4x3xf32>>) {
   %c3 = constant 3 : index
   %f0 = constant 0.0 : f32
   %vf0 = splat %f0 : vector<4x3xf32>
   // expected-error@+1 {{ requires memref vector element shape to match suffix of vector result shape}}
   %0 = vector.transfer_read %arg0[%c3, %c3], %vf0 {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : memref<?x?xvector<4x3xf32>>, vector<1x1x2x3xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{expected 5 operand types but had 4}}
   %0 = "vector.transfer_write"(%cst, %arg0, %c3, %c3, %c3) {permutation_map = affine_map<()->(0)>} : (vector<128xf32>, memref<?x?xf32>, index, index) -> ()
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires 2 indices}}
   vector.transfer_write %cst, %arg0[%c3, %c3, %c3] {permutation_map = affine_map<()->(0)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires attribute 'permutation_map'}}
   vector.transfer_write %cst, %arg0[%c3, %c3] {perm = affine_map<(d0)->(d0)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires a permutation_map with input dims of the same rank as the memref type}}
   vector.transfer_write %cst, %arg0[%c3, %c3] {permutation_map = affine_map<(d0)->(d0)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires a permutation_map with result dims of the same rank as the vector type}}
   vector.transfer_write %cst, %arg0[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires a projected permutation_map (at most one dim or the zero constant can appear in each result)}}
   vector.transfer_write %cst, %arg0[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d0 + d1)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<128 x f32>
   // expected-error@+1 {{requires a projected permutation_map (at most one dim or the zero constant can appear in each result)}}
   vector.transfer_write %cst, %arg0[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d0 + 1)>} : vector<128xf32>, memref<?x?xf32>
 }
 
 // -----
 
 func @test_vector.transfer_write(%arg0: memref<?x?x?xf32>) {
   %c3 = constant 3 : index
   %cst = constant dense<3.0> : vector<3 x 7 x f32>
   // expected-error@+1 {{requires a permutation_map that is a permutation (found one dim used more than once)}}
   vector.transfer_write %cst, %arg0[%c3, %c3, %c3] {permutation_map = affine_map<(d0, d1, d2)->(d0, d0)>} : vector<3x7xf32>, memref<?x?x?xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected offsets of same size as destination vector rank}}
   %1 = vector.insert_strided_slice %a, %b {offsets = [100], strides = [1, 1]} : vector<4x4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected strides of same size as source vector rank}}
   %1 = vector.insert_strided_slice %a, %b {offsets = [2, 2, 2], strides = [1]} : vector<4x4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected source rank to be smaller than destination rank}}
   %1 = vector.insert_strided_slice %b, %a {offsets = [2, 2], strides = [1, 1, 1]} : vector<4x8x16xf32> into vector<4x4xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected offsets dimension 0 to be confined to [0, 4)}}
   %1 = vector.insert_strided_slice %a, %b {offsets = [100,100,100], strides = [1, 1]} : vector<4x4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected strides to be confined to [1, 2)}}
   %1 = vector.insert_strided_slice %a, %b {offsets = [2, 2, 2], strides = [100, 100]} : vector<4x4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected sum(offsets, source vector shape) dimension 1 to be confined to [1, 9)}}
   %1 = vector.insert_strided_slice %a, %b {offsets = [2, 7, 2], strides = [1, 1]} : vector<4x4xf32> into vector<4x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected offsets, sizes and strides attributes of same size}}
   %1 = vector.strided_slice %arg0 {offsets = [100], sizes = [2, 2], strides = [1, 1]} : vector<4x8x16xf32> to vector<2x2x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected offsets attribute of rank smaller than vector rank}}
   %1 = vector.strided_slice %arg0 {offsets = [2, 2, 2, 2], sizes = [2, 2, 2, 2], strides = [1, 1, 1, 1]} : vector<4x8x16xf32> to vector<2x2x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{expected offsets attribute of rank smaller than vector rank}}
   %1 = vector.strided_slice %arg0 {offsets = [2, 2, 2, 2], sizes = [2, 2, 2, 2], strides = [1, 1, 1, 1]} : vector<4x8x16xf32> to vector<2x2x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected offsets dimension 0 to be confined to [0, 4)}}
   %1 = vector.strided_slice %arg0 {offsets = [100], sizes = [100], strides = [100]} : vector<4x8x16xf32> to vector<100x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected sizes dimension 0 to be confined to [1, 5)}}
   %1 = vector.strided_slice %arg0 {offsets = [2], sizes = [100], strides = [100]} : vector<4x8x16xf32> to vector<100x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected strides to be confined to [1, 2)}}
   %1 = vector.strided_slice %arg0 {offsets = [2], sizes = [1], strides = [100]} : vector<4x8x16xf32> to vector<1x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected strides to be confined to [1, 2)}}
   %1 = vector.strided_slice %arg0 {offsets = [2], sizes = [1], strides = [100]} : vector<4x8x16xf32> to vector<1x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected sum(offsets, sizes) dimension 0 to be confined to [1, 5)}}
   %1 = vector.strided_slice %arg0 {offsets = [2], sizes = [3], strides = [1]} : vector<4x8x16xf32> to vector<3x8x16xf32>
 }
 
 // -----
 
 func @strided_slice(%arg0: vector<4x8x16xf32>) {
   // expected-error@+1 {{op expected result type to be 'vector<2x8x16xf32>'}}
   %1 = vector.strided_slice %arg0 {offsets = [2], sizes = [2], strides = [1]} : vector<4x8x16xf32> to vector<3x1xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{expected an indexing map for each vector operand}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, c0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{expected indexing map 0 to be a projected permutation of its inputs}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1)[s0] -> (b0, s0, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{op expected indexing map 1 to have no symbols}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{expected indexing map 2 to have 5 number of inputs}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{expected indexing map 1 to have 4 number of outputs}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, b1, b2) -> (b1, b0, b2, f0)>,
   affine_map<(b0, f0, f1, b1, b2) -> (b0, b2, b1, f1)>,
   affine_map<(b0, f0, f1, b1, b2) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "parallel", "parallel"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{op expected at least one contracting dimension pair}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c1, b0, c0, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{invalid contracting dimension map}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (f1, c1, c0, b0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{invalid batch dimension map}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<88x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // expected-error@+1 {{invalid accumulator/result vector shape}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<88x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait = {
   indexing_maps = #contraction_accesses,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 func @contraction(%arg0: vector<7x8x16x15xf32>, %arg1: vector<8x16x7x5xf32>,
                   %arg2: vector<8x15x5xf32>, %arg3 :  vector<8x15x8x5xf32>,
                   %arg4 : index) {
   %lhs_mask = vector.constant_mask [7, 8, 16, 15] : vector<7x8x16x15xi1>
   %rhs_mask = vector.constant_mask [8, 16, 7, 5] : vector<8x16x7x5xi1>
   // expected-error@+1 {{expected zero or exactly 2 vector mask operands}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2, %lhs_mask
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
 }
 
 // -----
 
 #contraction_accesses = [
         affine_map<(i, j, k) -> (i, k)>,
         affine_map<(i, j, k) -> (k, j)>,
         affine_map<(i, j, k) -> (i, j)>
       ]
 #contraction_trait = {
         indexing_maps = #contraction_accesses,
         iterator_types = ["parallel", "parallel", "reduction"]
       }
 func @contraction(%arg0: vector<4x3xi32>,
                   %arg1: vector<3x7xf32>,
                   %arg2: vector<4x7xf32>) -> vector<4x7xf32> {
   // expected-error@+1 {{'vector.contract' op failed to verify that first operand lhs and result have same element type}}
   %0 = vector.contract #contraction_trait %arg0, %arg1, %arg2
     : vector<4x3xi32>, vector<3x7xf32> into vector<4x7xf32>
 }
 
 // -----
 
 func @create_mask() {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   // expected-error@+1 {{must specify an operand for each result vector dimension}}
   %0 = vector.create_mask %c3, %c2 : vector<4x3x7xi1>
 }
 
 
 // -----
 
 func @constant_mask() {
   // expected-error@+1 {{must specify array attr of size equal vector result rank}}
   %0 = vector.constant_mask [3, 2, 7] : vector<4x3xi1>
 }
 
 // -----
 
 func @constant_mask_out_of_bounds() {
   // expected-error@+1 {{array attr of size out of bounds of vector result dimension size}}
   %0 = vector.constant_mask [-1, 2] : vector<4x3xi1>
 }
 
 // -----
 
 func @constant_mask_out_of_bounds() {
   // expected-error@+1 {{array attr of size out of bounds of vector result dimension size}}
   %0 = vector.constant_mask [3, 4] : vector<4x3xi1>
 }
 
 // -----
 
 func @constant_mask_with_zero_mask_dim_size() {
   // expected-error@+1 {{expected all mask dim sizes to be zeros, as a result of conjunction with zero mask dim}}
   %0 = vector.constant_mask [0, 2] : vector<4x3xi1>
 }
 
 
 // -----
 
 func @extract_slices_non_unit_strides(%arg0 : vector<4x2xf32>) {
   // expected-error@+1 {{requires unit strides}}
   %0 = vector.extract_slices %arg0, [2, 2], [1, 3]
     : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 }
 
 // -----
 
 func @extract_slices_tuple_element_wrong_rank(%arg0 : vector<4x2xf32>) {
   // expected-error@+1 {{requires vector tuple elements of rank 2}}
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1]
     : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2x3xf32>>
 }
 
 // -----
 
 func @extract_slices_sizes_strides_wrong_rank(%arg0 : vector<4x2xf32>) {
   // expected-error@+1 {{requires sizes and strides of rank}}
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1, 1]
     : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 }
 
 // -----
 
 func @extract_slices_invalid_tuple_element_type(%arg0 : vector<4x2xf32>) {
   // expected-error@+1 {{invalid tuple element type}}
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1]
     : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<4x2xf32>>
 }
 
 // -----
 
 func @tuple_of_non_vectors(%arg0 : vector<4x2xf32>) {
   %c0 = constant 0 : index
   // expected-error@+1 {{must be vector of any type values}}
   %0 = vector.tuple %arg0, %c0 : vector<4x2xf32>, index
 }
 
 // -----
 
 func @tuple_get_of_non_vectors(%arg0 : tuple<vector<4x2xf32>, index>) {
   // expected-error@+1 {{vector of any type values}}
   %0 = vector.tuple_get %arg0, 0 : tuple<vector<4x2xf32>, index>
 }
 
 // -----
 
 func @insert_slices_non_unit_strides(%arg0 : tuple<vector<2x2xf32>, vector<2x2xf32>>) {
   // expected-error@+1 {{requires unit strides}}
   %0 = vector.insert_slices %arg0, [2, 2], [1, 3]
     : tuple<vector<2x2xf32>, vector<2x2xf32>> into vector<4x2xf32>
 }
 
 // -----
 
 func @insert_slices_tuple_element_wrong_rank(%arg0 : tuple<vector<2x2xf32>, vector<2x2x3xf32>>) {
   // expected-error@+1 {{requires vector tuple elements of rank 2}}
   %0 = vector.insert_slices %arg0, [2, 2], [1, 1]
     : tuple<vector<2x2xf32>, vector<2x2x3xf32>> into vector<4x2xf32>
 }
 
 // -----
 
 func @insert_slices_sizes_strides_wrong_rank(%arg0 : tuple<vector<2x2xf32>, vector<2x2xf32>>) {
   // expected-error@+1 {{requires sizes and strides of rank}}
   %0 = vector.insert_slices %arg0, [2, 2], [1, 1, 1]
     : tuple<vector<2x2xf32>, vector<2x2xf32>> into vector<4x2xf32>
 }
 
 // -----
 
 func @insert_slices_invalid_tuple_element_type(%arg0 : tuple<vector<2x2xf32>, vector<4x2xf32>>) {
   // expected-error@+1 {{invalid tuple element type}}
   %0 = vector.insert_slices %arg0, [2, 2], [1, 1]
     : tuple<vector<2x2xf32>, vector<4x2xf32>> into vector<4x2xf32>
 }
 
 // -----
 
 func @print_no_result(%arg0 : f32) -> i32 {
   // expected-error@+1 {{cannot name an operation with no results}}
   %0 = vector.print %arg0 : f32
 }
 
 // -----
 
 func @reshape_bad_input_shape(%arg0 : vector<3x2x4xf32>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c6 = constant 6 : index
   %c9 = constant 9 : index
   // expected-error@+1 {{invalid input shape for vector type}}
   %1 = vector.reshape %arg0, [%c3, %c6, %c3], [%c2, %c9], [4]
     : vector<3x2x4xf32> to vector<2x3x4xf32>
 }
 
 // -----
 
 func @reshape_bad_output_shape(%arg0 : vector<3x2x4xf32>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c6 = constant 6 : index
   %c9 = constant 9 : index
   // expected-error@+1 {{invalid output shape for vector type}}
   %1 = vector.reshape %arg0, [%c3, %c6], [%c2, %c9, %c3], [4]
     : vector<3x2x4xf32> to vector<2x3x4xf32>
 }
 
 // -----
 
 func @reshape_bad_input_output_shape_product(%arg0 : vector<3x2x4xf32>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c6 = constant 6 : index
   %c9 = constant 9 : index
   // expected-error@+1 {{product of input and output shape sizes must match}}
   %1 = vector.reshape %arg0, [%c3, %c6], [%c2, %c6], [4]
     : vector<3x2x4xf32> to vector<2x3x4xf32>
 }
 
 // -----
 
 func @reshape_bad_input_fixed_size(%arg0 : vector<3x2x5xf32>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c6 = constant 6 : index
   %c9 = constant 9 : index
   // expected-error@+1 {{fixed vector size must match input vector for dim 0}}
   %1 = vector.reshape %arg0, [%c3, %c6], [%c2, %c9], [4]
     : vector<3x2x5xf32> to vector<2x3x4xf32>
 }
 
 // -----
 
 func @reshape_bad_output_fixed_size(%arg0 : vector<3x2x4xf32>) {
   %c2 = constant 2 : index
   %c3 = constant 3 : index
   %c6 = constant 6 : index
   %c9 = constant 9 : index
   // expected-error@+1 {{fixed vector size must match output vector for dim 0}}
   %1 = vector.reshape %arg0, [%c3, %c6], [%c2, %c9], [4]
     : vector<3x2x4xf32> to vector<2x3x5xf32>
 }
 
 // -----
 
 func @shape_cast_wrong_element_type(%arg0 : vector<5x1x3x2xf32>) {
   // expected-error@+1 {{op source/result vectors must have same element type}}
   %0 = vector.shape_cast %arg0 : vector<5x1x3x2xf32> to vector<15x2xi32>
 }
 
 // -----
 
 func @shape_cast_wrong_element_type_tuple(%arg0 : tuple<vector<5x4x2xf32>,
                                                         vector<3x4x2xf32>>) {
   // expected-error@+1 {{op source/result vectors must have same element type}}
   %0 = vector.shape_cast %arg0 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                                  tuple<vector<20x2xi32>, vector<12x2xi32>>
 }
 
 // -----
 
 func @shape_cast_wrong_num_elements(%arg0 : vector<5x1x3x2xf32>) {
   // expected-error@+1 {{op source/result number of elements must match}}
   %0 = vector.shape_cast %arg0 : vector<5x1x3x2xf32> to vector<10x2xf32>
 }
 
 // -----
 
 func @shape_cast_wrong_num_elements_tuple(%arg0 : tuple<vector<5x4x2xf32>,
                                                         vector<3x4x2xf32>>) {
   // expected-error@+1 {{op source/result number of elements must match}}
   %0 = vector.shape_cast %arg0 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                                  tuple<vector<21x2xf32>, vector<13x2xf32>>
 }
 
 // -----
 
 func @shape_cast_invalid_rank_reduction(%arg0 : vector<5x1x3x2xf32>) {
   // expected-error@+1 {{invalid shape cast}}
   %0 = vector.shape_cast %arg0 : vector<5x1x3x2xf32> to vector<2x15xf32>
 }
 
 // -----
 
 func @shape_cast_invalid_rank_reduction_tuple(%arg0
   : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>) {
   // expected-error@+1 {{invalid shape cast}}
   %0 = vector.shape_cast %arg0: tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                                 tuple<vector<10x4xf32>, vector<6x4xf32>>
 }
 
 // -----
 
 func @shape_cast_invalid_rank_expansion(%arg0 : vector<15x2xf32>) {
   // expected-error@+1 {{invalid shape cast}}
   %0 = vector.shape_cast %arg0 : vector<15x2xf32> to vector<5x2x3x1xf32>
 }
 
 // -----
 
 func @shape_cast_invalid_rank_expansion_tuple(%arg0 : tuple<vector<20x2xf32>,
                                                             vector<12x2xf32>>) {
   // expected-error@+1 {{invalid shape cast}}
   %0 = vector.shape_cast %arg0 : tuple<vector<20x2xf32>, vector<12x2xf32>> to
                                  tuple<vector<5x2x4xf32>, vector<4x3x2xf32>>
 }
 
 // -----
 
 func @shape_cast_source_result_different_types(
   %arg1 : tuple<vector<20x2xf32>, vector<12x2xf32>>) {
   // expected-error@+1 {{source/result must be of same type}}
   %1 = vector.shape_cast %arg1 : tuple<vector<20x2xf32>, vector<12x2xf32>> to
                                  vector<5x2x4xf32>
 }
 
 // -----
 
 func @shape_cast_different_tuple_sizes(
   %arg1 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>) {
   // expected-error@+1 {{op source/result tuples must be the same size}}
   %1 = vector.shape_cast %arg1 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                                  tuple<vector<20x2xf32>>
 }
 
 // -----
 
 func @reduce_unknown_kind(%arg0: vector<16xf32>) -> f32 {
   // expected-error@+1 {{'vector.reduction' op unknown reduction kind: joho}}
   %0 = vector.reduction "joho", %arg0 : vector<16xf32> into f32
 }
 
 // -----
 
 func @reduce_elt_type_mismatch(%arg0: vector<16xf32>) -> i32 {
   // expected-error@+1 {{'vector.reduction' op failed to verify that source operand and result have same element type}}
   %0 = vector.reduction "add", %arg0 : vector<16xf32> into i32
 }
 
 // -----
 
 func @reduce_unsupported_attr(%arg0: vector<16xf32>) -> i32 {
   // expected-error@+1 {{'vector.reduction' op attribute 'kind' failed to satisfy constraint: string attribute}}
   %0 = vector.reduction 1234, %arg0 : vector<16xf32> into i32
 }
 
 // -----
 
 func @reduce_unsupported_third_argument(%arg0: vector<16xf32>, %arg1: f32) -> f32 {
   // expected-error@+1 {{'vector.reduction' unsupported number of operands}}
   %0 = vector.reduction "add", %arg0, %arg1, %arg1 : vector<16xf32> into f32
 }
 
 // -----
 
 func @reduce_unsupported_accumulator_kind(%arg0: vector<16xf32>, %arg1: f32) -> f32 {
   // expected-error@+1 {{'vector.reduction' op no accumulator for reduction kind: min}}
   %0 = vector.reduction "min", %arg0, %arg1 : vector<16xf32> into f32
 }
 
 // -----
 
 func @reduce_unsupported_accumulator_type(%arg0: vector<16xi32>, %arg1: i32) -> i32 {
   // expected-error@+1 {{'vector.reduction' op no accumulator for type: 'i32'}}
   %0 = vector.reduction "add", %arg0, %arg1 : vector<16xi32> into i32
 }
 
 // -----
 
 func @reduce_unsupported_type(%arg0: vector<16xf32>) -> f32 {
   // expected-error@+1 {{'vector.reduction' op unsupported reduction type}}
   %0 = vector.reduction "xor", %arg0 : vector<16xf32> into f32
 }
 
 // -----
 
 func @reduce_unsupported_rank(%arg0: vector<4x16xf32>) -> f32 {
   // expected-error@+1 {{'vector.reduction' op unsupported reduction rank: 2}}
   %0 = vector.reduction "add", %arg0 : vector<4x16xf32> into f32
 }

mlir/test/Dialect/Vector/ops.mlir

 // RUN: mlir-opt %s | mlir-opt | FileCheck %s
 
 // CHECK-DAG: #[[MAP0:map[0-9]+]] = affine_map<(d0, d1) -> (d0, d1)>
 
 // CHECK-LABEL: func @vector_transfer_ops(
 func @vector_transfer_ops(%arg0: memref<?x?xf32>,
                           %arg1 : memref<?x?xvector<4x3xf32>>) {
   // CHECK: %[[C3:.*]] = constant 3 : index
   %c3 = constant 3 : index
   %cst = constant 3.0 : f32
   %f0 = constant 0.0 : f32
   %vf0 = splat %f0 : vector<4x3xf32>
 
   //
   // CHECK: vector.transfer_read
   %0 = vector.transfer_read %arg0[%c3, %c3], %f0 {permutation_map = affine_map<(d0, d1)->(d0)>} : memref<?x?xf32>, vector<128xf32>
   // CHECK: vector.transfer_read
   %1 = vector.transfer_read %arg0[%c3, %c3], %f0 {permutation_map = affine_map<(d0, d1)->(d1, d0)>} : memref<?x?xf32>, vector<3x7xf32>
   // CHECK: vector.transfer_read
   %2 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0, d1)->(d0)>} : memref<?x?xf32>,  vector<128xf32>
   // CHECK: vector.transfer_read
   %3 = vector.transfer_read %arg0[%c3, %c3], %cst {permutation_map = affine_map<(d0, d1)->(d1)>} : memref<?x?xf32>,  vector<128xf32>
   // CHECK: vector.transfer_read %{{.*}}[%[[C3]], %[[C3]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<?x?xvector<4x3xf32>>, vector<1x1x4x3xf32>
   %4 = vector.transfer_read %arg1[%c3, %c3], %vf0 {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : memref<?x?xvector<4x3xf32>>, vector<1x1x4x3xf32>
 
   // CHECK: vector.transfer_write
   vector.transfer_write %0, %arg0[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d0)>} : vector<128xf32>, memref<?x?xf32>
   // CHECK: vector.transfer_write
   vector.transfer_write %1, %arg0[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d1, d0)>} : vector<3x7xf32>, memref<?x?xf32>
   // CHECK: vector.transfer_write %{{.*}}, %{{.*}}[%[[C3]], %[[C3]]] {permutation_map = #[[MAP0]]} : vector<1x1x4x3xf32>, memref<?x?xvector<4x3xf32>>
   vector.transfer_write %4, %arg1[%c3, %c3] {permutation_map = affine_map<(d0, d1)->(d0, d1)>} : vector<1x1x4x3xf32>, memref<?x?xvector<4x3xf32>>
 
   return
 }
 
 // CHECK-LABEL: @vector_broadcast
 func @vector_broadcast(%a: f32, %b: vector<16xf32>, %c: vector<1x16xf32>, %d: vector<8x1xf32>) -> vector<8x16xf32> {
   // CHECK: vector.broadcast %{{.*}} : f32 to vector<16xf32>
   %0 = vector.broadcast %a : f32 to vector<16xf32>
   // CHECK-NEXT: vector.broadcast %{{.*}} : vector<16xf32> to vector<8x16xf32>
   %1 = vector.broadcast %b : vector<16xf32> to vector<8x16xf32>
   // CHECK-NEXT: vector.broadcast %{{.*}} : vector<1x16xf32> to vector<8x16xf32>
   %2 = vector.broadcast %c : vector<1x16xf32> to vector<8x16xf32>
   // CHECK-NEXT: vector.broadcast %{{.*}} : vector<8x1xf32> to vector<8x16xf32>
   %3 = vector.broadcast %d : vector<8x1xf32> to vector<8x16xf32>
   return %3 : vector<8x16xf32>
 }
 
 // CHECK-LABEL: @shuffle1D
 func @shuffle1D(%a: vector<2xf32>, %b: vector<4xf32>) -> vector<2xf32> {
   // CHECK: vector.shuffle %{{.*}}, %{{.*}}[0, 1, 2, 3] : vector<2xf32>, vector<2xf32>
   %1 = vector.shuffle %a, %a[0, 1, 2, 3] : vector<2xf32>, vector<2xf32>
   // CHECK-NEXT: vector.shuffle %{{.*}}, %{{.*}}[0, 1, 2] : vector<4xf32>, vector<4xf32>
   %2 = vector.shuffle %1, %b[0, 1, 2] : vector<4xf32>, vector<4xf32>
   // CHECK-NEXT: vector.shuffle %{{.*}}, %{{.*}}[0, 6] : vector<3xf32>, vector<4xf32>
   %3 = vector.shuffle %2, %b[0, 6] : vector<3xf32>, vector<4xf32>
   return %3 : vector<2xf32>
 }
 
 // CHECK-LABEL: @shuffle2D
 func @shuffle2D(%a: vector<1x4xf32>, %b: vector<2x4xf32>) -> vector<3x4xf32> {
   // CHECK: vector.shuffle %{{.*}}, %{{.*}}[0, 1, 2] : vector<1x4xf32>, vector<2x4xf32>
   %1 = vector.shuffle %a, %b[0, 1, 2] : vector<1x4xf32>, vector<2x4xf32>
   return %1 : vector<3x4xf32>
 }
 
 // CHECK-LABEL: @extract_element
 func @extract_element(%a: vector<16xf32>) -> f32 {
   // CHECK:      %[[C15:.*]] = constant 15 : i32
   %c = constant 15 : i32
   // CHECK-NEXT: vector.extractelement %{{.*}}[%[[C15]] : i32] : vector<16xf32>
   %1 = vector.extractelement %a[%c : i32] : vector<16xf32>
   return %1 : f32
 }
 
 // CHECK-LABEL: @extract
 func @extract(%arg0: vector<4x8x16xf32>) -> (vector<8x16xf32>, vector<16xf32>, f32) {
   // CHECK: vector.extract {{.*}}[3] : vector<4x8x16xf32>
   %1 = vector.extract %arg0[3] : vector<4x8x16xf32>
   // CHECK-NEXT: vector.extract {{.*}}[3, 3] : vector<4x8x16xf32>
   %2 = vector.extract %arg0[3, 3] : vector<4x8x16xf32>
   // CHECK-NEXT: vector.extract {{.*}}[3, 3, 3] : vector<4x8x16xf32>
   %3 = vector.extract %arg0[3, 3, 3] : vector<4x8x16xf32>
   return %1, %2, %3 : vector<8x16xf32>, vector<16xf32>, f32
 }
 
 // CHECK-LABEL: @insert_element
 func @insert_element(%a: f32, %b: vector<16xf32>) -> vector<16xf32> {
   // CHECK:      %[[C15:.*]] = constant 15 : i32
   %c = constant 15 : i32
   // CHECK-NEXT: vector.insertelement %{{.*}}, %{{.*}}[%[[C15]] : i32] : vector<16xf32>
   %1 = vector.insertelement %a, %b[%c : i32] : vector<16xf32>
   return %1 : vector<16xf32>
 }
 
 // CHECK-LABEL: @insert
 func @insert(%a: f32, %b: vector<16xf32>, %c: vector<8x16xf32>, %res: vector<4x8x16xf32>) -> vector<4x8x16xf32> {
   // CHECK: vector.insert %{{.*}}, %{{.*}}[3] : vector<8x16xf32> into vector<4x8x16xf32>
   %1 = vector.insert %c, %res[3] : vector<8x16xf32> into vector<4x8x16xf32>
   // CHECK: vector.insert %{{.*}}, %{{.*}}[3, 3] : vector<16xf32> into vector<4x8x16xf32>
   %2 = vector.insert %b, %res[3, 3] : vector<16xf32> into vector<4x8x16xf32>
   // CHECK: vector.insert %{{.*}}, %{{.*}}[3, 3, 3] : f32 into vector<4x8x16xf32>
   %3 = vector.insert %a, %res[3, 3, 3] : f32 into vector<4x8x16xf32>
   return %3 : vector<4x8x16xf32>
 }
 
 // CHECK-LABEL: @outerproduct
 func @outerproduct(%arg0: vector<4xf32>, %arg1: vector<8xf32>, %arg2: vector<4x8xf32>) -> vector<4x8xf32> {
   // CHECK: vector.outerproduct {{.*}} : vector<4xf32>, vector<8xf32>
   %0 = vector.outerproduct %arg0, %arg1 : vector<4xf32>, vector<8xf32>
   // CHECK: vector.outerproduct {{.*}}, {{.*}}, {{.*}} : vector<4xf32>, vector<8xf32>
   %1 = vector.outerproduct %arg0, %arg1, %arg2 : vector<4xf32>, vector<8xf32>
   return %1 : vector<4x8xf32>
 }
 
 // CHECK-LABEL: @insert_strided_slice
 func @insert_strided_slice(%a: vector<4x4xf32>, %b: vector<4x8x16xf32>) {
   // CHECK: vector.insert_strided_slice %{{.*}}, %{{.*}} {offsets = [2, 2, 2], strides = [1, 1]} : vector<4x4xf32> into vector<4x8x16xf32>
   %1 = vector.insert_strided_slice %a, %b {offsets = [2, 2, 2], strides = [1, 1]} : vector<4x4xf32> into vector<4x8x16xf32>
   return
 }
 
 // CHECK-LABEL: @strided_slice
 func @strided_slice(%arg0: vector<4x8x16xf32>) -> vector<2x2x16xf32> {
   // CHECK: vector.strided_slice %{{.*}} {offsets = [2, 2], sizes = [2, 2], strides = [1, 1]} : vector<4x8x16xf32>
   %1 = vector.strided_slice %arg0 {offsets = [2, 2], sizes = [2, 2], strides = [1, 1]} : vector<4x8x16xf32> to vector<2x2x16xf32>
   return %1: vector<2x2x16xf32>
 }
 
 #contraction_to_scalar_accesses = [
   affine_map<(i) -> (i)>,
   affine_map<(i) -> (i)>,
   affine_map<(i) -> ()>
 ]
 #contraction_to_scalar_trait = {
   indexing_maps = #contraction_to_scalar_accesses,
   iterator_types = ["reduction"]
 }
 // CHECK-LABEL: contraction_to_scalar
 func @contraction_to_scalar(%arg0: vector<10xf32>, %arg1: vector<10xf32>) -> f32 {
   // CHECK:      %[[C0:.*]] = constant 0.000000e+00 : f32
   %f0 = constant 0.0: f32
   // CHECK:      %[[X:.*]] = vector.contract {indexing_maps = [#{{.*}}, #{{.*}}, #{{.*}}], iterator_types = ["reduction"]} %{{.*}}, %{{.*}}, %[[C0]] : vector<10xf32>, vector<10xf32> into f32
   %0 = vector.contract #contraction_to_scalar_trait %arg0, %arg1, %f0
     : vector<10xf32>, vector<10xf32> into f32
   // CHECK:      return %[[X]] : f32
   return %0 : f32
 }
 
 #contraction_accesses0 = [
   affine_map<(b0, f0, f1, c0, c1) -> (c0, b0, c1, f0)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, c1, c0, f1)>,
   affine_map<(b0, f0, f1, c0, c1) -> (b0, f0, f1)>
 ]
 #contraction_trait0 = {
   indexing_maps = #contraction_accesses0,
   iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]
 }
 #contraction_accesses1 = [
   affine_map<(f0, f1, f2, f3, c0, c1) -> (c0, f0, c1, f2)>,
   affine_map<(f0, f1, f2, f3, c0, c1) -> (f1, c1, c0, f3)>,
   affine_map<(f0, f1, f2, f3, c0, c1) -> (f0, f1, f2, f3)>
 ]
 #contraction_trait1 = {
   indexing_maps = #contraction_accesses1,
   iterator_types = ["parallel", "parallel", "parallel", "parallel", "reduction",
                     "reduction"]
 }
 // CHECK-LABEL: contraction
 func @contraction(%arg0 : vector<7x8x16x15xf32>, %arg1 : vector<8x16x7x5xf32>,
                   %arg2 : vector<8x15x5xf32>, %arg3 : vector<8x15x8x5xf32>,
                   %arg4 : index) {
   // Test contraction with batch and contracting dims.
   // CHECK: vector.contract {indexing_maps = [#{{.*}}, #{{.*}}, #{{.*}}], iterator_types = ["parallel", "parallel", "parallel", "reduction", "reduction"]} {{.*}}, {{.*}}, {{.*}} : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
   %0 = vector.contract #contraction_trait0 %arg0, %arg1, %arg2
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x5xf32>
   // Test contraction with only contracting dims. In this case the lhs/rhs
   // dimension of size 8 will be considered a parallel dim for lhs/rhs and will
   // appear twice in the output.
   // CHECK: vector.contract {indexing_maps = [#{{.*}}, #{{.*}}, #{{.*}}], iterator_types = ["parallel", "parallel", "parallel", "parallel", "reduction", "reduction"]} {{.*}}, {{.*}}, {{.*}} : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x8x5xf32>
   %1 = vector.contract #contraction_trait1 %arg0, %arg1, %arg3
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x8x5xf32>
   // Test contraction with optional vector mask arguments.
   %lhs_mask = vector.constant_mask [7, 8, 16, 15] : vector<7x8x16x15xi1>
   %rhs_mask = vector.constant_mask [8, 16, 7, 5] : vector<8x16x7x5xi1>
   // CHECK: vector.contract {indexing_maps = [#{{.*}}, #{{.*}}, #{{.*}}], iterator_types = ["parallel", "parallel", "parallel", "parallel", "reduction", "reduction"]} {{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}} : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x8x5xf32>
   %2 = vector.contract #contraction_trait1 %arg0, %arg1, %arg3, %lhs_mask,
                                            %rhs_mask
       : vector<7x8x16x15xf32>, vector<8x16x7x5xf32> into vector<8x15x8x5xf32>
   return
 }
 
 // CHECK-LABEL: create_vector_mask
 func @create_vector_mask() {
   // CHECK:      %[[C2:.*]] = constant 2 : index
   %c2 = constant 2 : index
   // CHECK-NEXT: %[[C3:.*]] = constant 3 : index
   %c3 = constant 3 : index
   // CHECK-NEXT: vector.create_mask %[[C3]], %[[C2]] : vector<4x3xi1>
   %0 = vector.create_mask %c3, %c2 : vector<4x3xi1>
 
   return
 }
 
 // CHECK-LABEL: constant_vector_mask
 func @constant_vector_mask() {
   // CHECK: vector.constant_mask [3, 2] : vector<4x3xi1>
   %0 = vector.constant_mask [3, 2] : vector<4x3xi1>
   return
 }
 
 // CHECK-LABEL: extract_slices
 func @extract_slices(%arg0 : vector<4x2xf32>)
   -> (tuple<vector<2x2xf32>, vector<2x2xf32>>) {
   // CHECK: vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1]
     : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
   %1 = vector.tuple_get %0, 0 : tuple<vector<2x2xf32>, vector<2x2xf32>>
   %2 = vector.tuple_get %0, 1 : tuple<vector<2x2xf32>, vector<2x2xf32>>
   %3 = vector.tuple %1, %2 : vector<2x2xf32>, vector<2x2xf32>
   return %3 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 }
 
 // CHECK-LABEL: insert_slices
 func @insert_slices(%arg0 : tuple<vector<2x2xf32>, vector<2x2xf32>>)
   -> (vector<4x2xf32>) {
   // CHECK: vector.insert_slices %{{.*}}, [2, 2], [1, 1] : tuple<vector<2x2xf32>, vector<2x2xf32>> into vector<4x2xf32>
   %0 = vector.insert_slices %arg0, [2, 2], [1, 1]
     : tuple<vector<2x2xf32>, vector<2x2xf32>> into vector<4x2xf32>
   return %0 : vector<4x2xf32>
 }
 
 // CHECK-LABEL: @vector_print
 func @vector_print(%arg0: vector<8x4xf32>) {
   // CHECK: vector.print %{{.*}} : vector<8x4xf32>
   vector.print %arg0 : vector<8x4xf32>
   return
 }
 
 // CHECK-LABEL: reshape
 func @reshape(%arg0 : vector<3x2x4xf32>) -> (vector<2x3x4xf32>) {
   // CHECK:      %[[C2:.*]] = constant 2 : index
   %c2 = constant 2 : index
   // CHECK:      %[[C3:.*]] = constant 3 : index
   %c3 = constant 3 : index
   // CHECK:      %[[C6:.*]] = constant 6 : index
   %c6 = constant 6 : index
   // CHECK:      %[[C9:.*]] = constant 9 : index
   %c9 = constant 9 : index
   // CHECK: vector.reshape %{{.*}}, [%[[C3]], %[[C6]]], [%[[C2]], %[[C9]]], [4] : vector<3x2x4xf32> to vector<2x3x4xf32>
   %1 = vector.reshape %arg0, [%c3, %c6], [%c2, %c9], [4]
     : vector<3x2x4xf32> to vector<2x3x4xf32>
 
   return %1 : vector<2x3x4xf32>
 }
 
 // CHECK-LABEL: shape_cast
 func @shape_cast(%arg0 : vector<5x1x3x2xf32>,
                  %arg1 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>)
   -> (vector<15x2xf32>, tuple<vector<20x2xf32>, vector<12x2xf32>>) {
 
   // CHECK: vector.shape_cast %{{.*}} : vector<5x1x3x2xf32> to vector<15x2xf32>
   %0 = vector.shape_cast %arg0 : vector<5x1x3x2xf32> to vector<15x2xf32>
 
   // CHECK-NEXT: vector.shape_cast %{{.*}} : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to tuple<vector<20x2xf32>, vector<12x2xf32>>
   %1 = vector.shape_cast %arg1 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                                  tuple<vector<20x2xf32>, vector<12x2xf32>>
 
   return %0, %1 : vector<15x2xf32>, tuple<vector<20x2xf32>, vector<12x2xf32>>
 }
 
 // CHECK-LABEL: @vector_fma
 func @vector_fma(%a: vector<8xf32>, %b: vector<8x4xf32>) {
   // CHECK: vector.fma %{{.*}} : vector<8xf32>
   vector.fma %a, %a, %a : vector<8xf32>
   // CHECK: vector.fma %{{.*}} : vector<8x4xf32>
   vector.fma %b, %b, %b : vector<8x4xf32>
   return
 }
 
 // CHECK-LABEL: reduce_fp
 func @reduce_fp(%arg0: vector<16xf32>, %arg1: f32) -> f32 {
   // CHECK:    vector.reduction "add", %{{.*}} : vector<16xf32> into f32
   vector.reduction "add", %arg0 : vector<16xf32> into f32
   // CHECK:    vector.reduction "add", %{{.*}}, %{{.*}} : vector<16xf32> into f32
   vector.reduction "add", %arg0, %arg1 : vector<16xf32> into f32
   // CHECK:    vector.reduction "mul", %{{.*}} : vector<16xf32> into f32
   vector.reduction "mul", %arg0 : vector<16xf32> into f32
   // CHECK:    vector.reduction "mul", %{{.*}}, %{{.*}} : vector<16xf32> into f32
   vector.reduction "mul", %arg0, %arg1 : vector<16xf32> into f32
   // CHECK:    vector.reduction "min", %{{.*}} : vector<16xf32> into f32
   vector.reduction "min", %arg0 : vector<16xf32> into f32
   // CHECK:    %[[X:.*]] = vector.reduction "max", %{{.*}} : vector<16xf32> into f32
   %0 = vector.reduction "max", %arg0 : vector<16xf32> into f32
   // CHECK:    return %[[X]] : f32
   return %0 : f32
 }
 
 // CHECK-LABEL: reduce_int
 func @reduce_int(%arg0: vector<16xi32>) -> i32 {
   // CHECK:    vector.reduction "add", %{{.*}} : vector<16xi32> into i32
   vector.reduction "add", %arg0 : vector<16xi32> into i32
   // CHECK:    vector.reduction "mul", %{{.*}} : vector<16xi32> into i32
   vector.reduction "mul", %arg0 : vector<16xi32> into i32
   // CHECK:    vector.reduction "min", %{{.*}} : vector<16xi32> into i32
   vector.reduction "min", %arg0 : vector<16xi32> into i32
   // CHECK:    vector.reduction "max", %{{.*}} : vector<16xi32> into i32
   vector.reduction "max", %arg0 : vector<16xi32> into i32
   // CHECK:    vector.reduction "and", %{{.*}} : vector<16xi32> into i32
   vector.reduction "and", %arg0 : vector<16xi32> into i32
   // CHECK:    vector.reduction "or", %{{.*}} : vector<16xi32> into i32
   vector.reduction "or", %arg0 : vector<16xi32> into i32
   // CHECK:    %[[X:.*]] = vector.reduction "xor", %{{.*}} : vector<16xi32> into i32
   %0 = vector.reduction "xor", %arg0 : vector<16xi32> into i32
   // CHECK:    return %[[X]] : i32
   return %0 : i32
 }

mlir/test/Dialect/Vector/vector-contract-transforms.mlir

 // RUN: mlir-opt %s -test-vector-contraction-conversion | FileCheck %s
 // RUN: mlir-opt %s -test-vector-contraction-conversion -vector-lower-matrix-intrinsics | FileCheck %s --check-prefix=MATRIX
 
 #dotp_accesses = [
   affine_map<(i) -> (i)>,
   affine_map<(i) -> (i)>,
   affine_map<(i) -> ()>
 ]
 #dotp_trait = {
   indexing_maps = #dotp_accesses,
   iterator_types = ["reduction"]
 }
 
 // CHECK-LABEL: func @extract_contract1
 // CHECK-SAME: %[[A:.*0]]: vector<4xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<4xf32>,
 // CHECK-SAME: %[[C:.*2]]: f32
 // CHECK:      %[[Z:.*]] = constant dense<0.000000e+00> : vector<4xf32>
 // CHECK:      %[[F:.*]] = vector.fma %[[A]], %[[B]], %[[Z]] : vector<4xf32>
 // CHECK:      %[[R:.*]] = vector.reduction "add", %[[F]], %[[C]] : vector<4xf32> into f32
 // CHECK:      return %[[R]] : f32
 
 func @extract_contract1(%arg0: vector<4xf32>, %arg1: vector<4xf32>, %arg2: f32) -> f32 {
   %0 = vector.contract #dotp_trait %arg0, %arg1, %arg2
     : vector<4xf32>, vector<4xf32> into f32
   return %0 : f32
 }
 
 #matvec_accesses = [
   affine_map<(i, j) -> (i, j)>,
   affine_map<(i, j) -> (j)>,
   affine_map<(i, j) -> (i)>
 ]
 #matvec_trait = {
   indexing_maps = #matvec_accesses,
   iterator_types = ["parallel", "reduction"]
 }
 
 // CHECK-LABEL: func @extract_contract2
 // CHECK-SAME: %[[A:.*0]]: vector<2x3xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<3xf32>,
 // CHECK-SAME: %[[C:.*2]]: vector<2xf32>
 // CHECK:      %[[R:.*]] = constant dense<0.000000e+00> : vector<2xf32>
 // CHECK:      %[[Z:.*]] = constant dense<0.000000e+00> : vector<3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[A]][0] : vector<2x3xf32>
 // CHECK:      %[[T1:.*]] = vector.extract %[[C]][0] : vector<2xf32>
 // CHECK:      %[[T2:.*]] = vector.fma %[[T0]], %[[B]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T3:.*]] = vector.reduction "add", %[[T2]], %[[T1]] : vector<3xf32> into f32
 // CHECK:      %[[T4:.*]] = vector.insert %[[T3]], %[[R]] [0] : f32 into vector<2xf32>
 // CHECK:      %[[T5:.*]] = vector.extract %[[A]][1] : vector<2x3xf32>
 // CHECK:      %[[T6:.*]] = vector.extract %[[C]][1] : vector<2xf32>
 // CHECK:      %[[T7:.*]] = vector.fma %[[T5]], %[[B]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T8:.*]] = vector.reduction "add", %[[T7]], %[[T6]] : vector<3xf32> into f32
 // CHECK:      %[[T9:.*]] = vector.insert %[[T8]], %[[T4]] [1] : f32 into vector<2xf32>
 // CHECK:      return %[[T9]] : vector<2xf32>
 
 func @extract_contract2(%arg0: vector<2x3xf32>,
                         %arg1: vector<3xf32>,
       %arg2: vector<2xf32>) -> vector<2xf32> {
   %0 = vector.contract #matvec_trait %arg0, %arg1, %arg2
     : vector<2x3xf32>, vector<3xf32> into vector<2xf32>
   return %0 : vector<2xf32>
 }
 
 #vecmat_accesses = [
   affine_map<(i, j) -> (j)>,
   affine_map<(i, j) -> (i, j)>,
   affine_map<(i, j) -> (i)>
 ]
 #vecmat_trait = {
   indexing_maps = #vecmat_accesses,
   iterator_types = ["parallel", "reduction"]
 }
 
 // CHECK-LABEL: func @extract_contract3
 // CHECK-SAME: %[[A:.*0]]: vector<3xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<2x3xf32>,
 // CHECK-SAME: %[[C:.*2]]: vector<2xf32>
 // CHECK:      %[[R:.*]] = constant dense<0.000000e+00> : vector<2xf32>
 // CHECK:      %[[Z:.*]] = constant dense<0.000000e+00> : vector<3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[B]][0] : vector<2x3xf32>
 // CHECK:      %[[T1:.*]] = vector.extract %[[C]][0] : vector<2xf32>
 // CHECK:      %[[T2:.*]] = vector.fma %[[A]], %[[T0]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T3:.*]] = vector.reduction "add", %[[T2]], %[[T1]] : vector<3xf32> into f32
 // CHECK:      %[[T4:.*]] = vector.insert %[[T3]], %[[R]] [0] : f32 into vector<2xf32>
 // CHECK:      %[[T5:.*]] = vector.extract %[[B]][1] : vector<2x3xf32>
 // CHECK:      %[[T6:.*]] = vector.extract %[[C]][1] : vector<2xf32>
 // CHECK:      %[[T7:.*]] = vector.fma %[[A]], %[[T5]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T8:.*]] = vector.reduction "add", %[[T7]], %[[T6]] : vector<3xf32> into f32
 // CHECK:      %[[T9:.*]] = vector.insert %[[T8]], %[[T4]] [1] : f32 into vector<2xf32>
 // CHECK:      return %[[T9]] : vector<2xf32>
 
 func @extract_contract3(%arg0: vector<3xf32>,
                         %arg1: vector<2x3xf32>,
                         %arg2: vector<2xf32>) -> vector<2xf32> {
   %0 = vector.contract #vecmat_trait %arg0, %arg1, %arg2
     : vector<3xf32>, vector<2x3xf32> into vector<2xf32>
   return %0 : vector<2xf32>
 }
 
 #matmat_accesses = [
   affine_map<(i, j, k) -> (i, k)>,
   affine_map<(i, j, k) -> (k, j)>,
   affine_map<(i, j, k) -> (i, j)>
 ]
 #matmat_trait = {
   indexing_maps = #matmat_accesses,
   iterator_types = ["parallel", "parallel", "reduction"]
 }
 
 // CHECK-LABEL: func @extract_contract4
 // CHECK-SAME: %[[A:.*0]]: vector<2x2xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<2x2xf32>,
 // CHECK-SAME: %[[C:.*2]]: vector<2x2xf32>
 // CHECK:    %[[R:.*]] = constant dense<0.000000e+00> : vector<2x2xf32>
 // CHECK:    %[[Z:.*]] = constant dense<0.000000e+00> : vector<2xf32>
 // CHECK:    %[[T0:.*]] = vector.extract %[[A]][0] : vector<2x2xf32>
 // CHECK:    %[[T1:.*]] = vector.extract %[[C]][0] : vector<2x2xf32>
 // CHECK:    %[[T2:.*]] = vector.extract %[[B]][0] : vector<2x2xf32>
 // CHECK:    %[[T3:.*]] = vector.extract %[[T2]][0] : vector<2xf32>
 // CHECK:    %[[T4:.*]] = vector.insert %[[T3]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T5:.*]] = vector.extract %[[B]][1] : vector<2x2xf32>
 // CHECK:    %[[T6:.*]] = vector.extract %[[T5]][0] : vector<2xf32>
 // CHECK:    %[[T7:.*]] = vector.insert %[[T6]], %[[T4]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T8:.*]] = vector.extract %[[T1]][0] : vector<2xf32>
 // CHECK:    %[[T9:.*]] = vector.fma %[[T0]], %[[T7]], %[[Z]] : vector<2xf32>
 // CHECK:    %[[T10:.*]] = vector.reduction "add", %[[T9]], %[[T8]] : vector<2xf32> into f32
 // CHECK:    %[[T11:.*]] = vector.insert %[[T10]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T12:.*]] = vector.extract %[[B]][0] : vector<2x2xf32>
 // CHECK:    %[[T13:.*]] = vector.extract %[[T12]][1] : vector<2xf32>
 // CHECK:    %[[T14:.*]] = vector.insert %[[T13]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T15:.*]] = vector.extract %[[B]][1] : vector<2x2xf32>
 // CHECK:    %[[T16:.*]] = vector.extract %[[T15]][1] : vector<2xf32>
 // CHECK:    %[[T17:.*]] = vector.insert %[[T16]], %[[T14]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T18:.*]] = vector.extract %[[T1]][1] : vector<2xf32>
 // CHECK:    %[[T19:.*]] = vector.fma %[[T0]], %[[T17]], %[[Z]] : vector<2xf32>
 // CHECK:    %[[T20:.*]] = vector.reduction "add", %[[T19]], %[[T18]] : vector<2xf32> into f32
 // CHECK:    %[[T21:.*]] = vector.insert %[[T20]], %[[T11]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T22:.*]] = vector.insert %[[T21]], %[[R]] [0] : vector<2xf32> into vector<2x2xf32>
 // CHECK:    %[[T23:.*]] = vector.extract %[[A]][1] : vector<2x2xf32>
 // CHECK:    %[[T24:.*]] = vector.extract %[[C]][1] : vector<2x2xf32>
 // CHECK:    %[[T25:.*]] = vector.extract %[[B]][0] : vector<2x2xf32>
 // CHECK:    %[[T26:.*]] = vector.extract %[[T25]][0] : vector<2xf32>
 // CHECK:    %[[T27:.*]] = vector.insert %[[T26]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T28:.*]] = vector.extract %[[B]][1] : vector<2x2xf32>
 // CHECK:    %[[T29:.*]] = vector.extract %[[T28]][0] : vector<2xf32>
 // CHECK:    %[[T30:.*]] = vector.insert %[[T29]], %[[T27]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T31:.*]] = vector.extract %[[T24]][0] : vector<2xf32>
 // CHECK:    %[[T32:.*]] = vector.fma %[[T23]], %[[T30]], %[[Z]] : vector<2xf32>
 // CHECK:    %[[T33:.*]] = vector.reduction "add", %[[T32]], %[[T31]] : vector<2xf32> into f32
 // CHECK:    %[[T34:.*]] = vector.insert %[[T33]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T35:.*]] = vector.extract %[[B]][0] : vector<2x2xf32>
 // CHECK:    %[[T36:.*]] = vector.extract %[[T35]][1] : vector<2xf32>
 // CHECK:    %[[T37:.*]] = vector.insert %[[T36]], %[[Z]] [0] : f32 into vector<2xf32>
 // CHECK:    %[[T38:.*]] = vector.extract %[[B]][1] : vector<2x2xf32>
 // CHECK:    %[[T39:.*]] = vector.extract %[[T38]][1] : vector<2xf32>
 // CHECK:    %[[T40:.*]] = vector.insert %[[T39]], %[[T37]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T41:.*]] = vector.extract %[[T24]][1] : vector<2xf32>
 // CHECK:    %[[T42:.*]] = vector.fma %[[T23]], %[[T40]], %[[Z]] : vector<2xf32>
 // CHECK:    %[[T43:.*]] = vector.reduction "add", %[[T42]], %[[T41]] : vector<2xf32> into f32
 // CHECK:    %[[T44:.*]] = vector.insert %[[T43]], %[[T34]] [1] : f32 into vector<2xf32>
 // CHECK:    %[[T45:.*]] = vector.insert %[[T44]], %[[T22]] [1] : vector<2xf32> into vector<2x2xf32>
 // CHECK:    return %[[T45]] : vector<2x2xf32>
 
 func @extract_contract4(%arg0: vector<2x2xf32>,
                         %arg1: vector<2x2xf32>,
                         %arg2: vector<2x2xf32>) -> vector<2x2xf32> {
   %0 = vector.contract #matmat_trait %arg0, %arg1, %arg2
     : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
   return %0 : vector<2x2xf32>
 }
 
 #contraction2d_accesses = [
   affine_map<(i, j) -> (i, j)>,
   affine_map<(i, j) -> (i, j)>,
   affine_map<(i, j) -> ()>
 ]
 #contraction2d_trait = {
   indexing_maps = #contraction2d_accesses,
   iterator_types = ["reduction", "reduction"]
 }
 
 // CHECK-LABEL: func @full_contract1
 // CHECK-SAME: %[[A:.*0]]: vector<2x3xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<2x3xf32>,
 // CHECK-SAME: %[[C:.*2]]: f32
 // CHECK:      %[[Z:.*]] = constant dense<0.000000e+00> : vector<3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[A]][0] : vector<2x3xf32>
 // CHECK:      %[[T1:.*]] = vector.extract %[[B]][0] : vector<2x3xf32>
 // CHECK:      %[[T2:.*]] = vector.fma %[[T0]], %[[T1]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T3:.*]] = vector.reduction "add", %[[T2]], %[[C]] : vector<3xf32> into f32
 // CHECK:      %[[T4:.*]] = vector.extract %[[A]][1] : vector<2x3xf32>
 // CHECK:      %[[T5:.*]] = vector.extract %[[B]][1] : vector<2x3xf32>
 // CHECK:      %[[T6:.*]] = vector.fma %[[T4]], %[[T5]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T7:.*]] = vector.reduction "add", %[[T6]], %[[T3]] : vector<3xf32> into f32
 // CHECK:      return %[[T7]] : f32
 
 func @full_contract1(%arg0: vector<2x3xf32>,
                      %arg1: vector<2x3xf32>,
          %arg2: f32) -> f32 {
   %0 = vector.contract #contraction2d_trait %arg0, %arg1, %arg2
     : vector<2x3xf32>, vector<2x3xf32> into f32
   return %0 : f32
 }
 
 #contraction2d_trans_accesses = [
   affine_map<(i, j) -> (i, j)>,
   affine_map<(i, j) -> (j, i)>,
   affine_map<(i, j) -> ()>
 ]
 #contraction2d_trans_trait = {
   indexing_maps = #contraction2d_trans_accesses,
   iterator_types = ["reduction", "reduction"]
 }
 
 // CHECK-LABEL: func @full_contract2
 // CHECK-SAME: %[[A:.*0]]: vector<2x3xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<3x2xf32>,
 // CHECK-SAME: %[[C:.*2]]: f32
 // CHECK:      %[[Z:.*]] = constant dense<0.000000e+00> : vector<3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[A]][0] : vector<2x3xf32>
 // CHECK:      %[[T1:.*]] = vector.extract %[[B]][0] : vector<3x2xf32>
 // CHECK:      %[[T2:.*]] = vector.extract %[[T1]][0] : vector<2xf32>
 // CHECK:      %[[T3:.*]] = vector.insert %[[T2]], %[[Z]] [0] : f32 into vector<3xf32>
 // CHECK:      %[[T4:.*]] = vector.extract %[[B]][1] : vector<3x2xf32>
 // CHECK:      %[[T5:.*]] = vector.extract %[[T4]][0] : vector<2xf32>
 // CHECK:      %[[T6:.*]] = vector.insert %[[T5]], %[[T3]] [1] : f32 into vector<3xf32>
 // CHECK:      %[[T7:.*]] = vector.extract %[[B]][2] : vector<3x2xf32>
 // CHECK:      %[[T8:.*]] = vector.extract %[[T7]][0] : vector<2xf32>
 // CHECK:      %[[T9:.*]] = vector.insert %[[T8]], %[[T6]] [2] : f32 into vector<3xf32>
 // CHECK:      %[[T10:.*]] = vector.fma %[[T0]], %[[T9]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T11:.*]] = vector.reduction "add", %[[T10]], %[[C]] : vector<3xf32> into f32
 // CHECK:      %[[T12:.*]] = vector.extract %[[A]][1] : vector<2x3xf32>
 // CHECK:      %[[T13:.*]] = vector.extract %[[B]][0] : vector<3x2xf32>
 // CHECK:      %[[T14:.*]] = vector.extract %[[T13]][1] : vector<2xf32>
 // CHECK:      %[[T15:.*]] = vector.insert %[[T14]], %[[Z]] [0] : f32 into vector<3xf32>
 // CHECK:      %[[T16:.*]] = vector.extract %[[B]][1] : vector<3x2xf32>
 // CHECK:      %[[T17:.*]] = vector.extract %[[T16]][1] : vector<2xf32>
 // CHECK:      %[[T18:.*]] = vector.insert %[[T17]], %[[T15]] [1] : f32 into vector<3xf32>
 // CHECK:      %[[T19:.*]] = vector.extract %[[B]][2] : vector<3x2xf32>
 // CHECK:      %[[T20:.*]] = vector.extract %[[T19]][1] : vector<2xf32>
 // CHECK:      %[[T21:.*]] = vector.insert %[[T20]], %[[T18]] [2] : f32 into vector<3xf32>
 // CHECK:      %[[T22:.*]] = vector.fma %[[T12]], %[[T21]], %[[Z]] : vector<3xf32>
 // CHECK:      %[[T23:.*]] = vector.reduction "add", %[[T22]], %[[T11]] : vector<3xf32> into f32
 // CHECK:      return %[[T23]] : f32
 
 func @full_contract2(%arg0: vector<2x3xf32>,
                      %arg1: vector<3x2xf32>,
          %arg2: f32) -> f32 {
   %0 = vector.contract #contraction2d_trans_trait %arg0, %arg1, %arg2
     : vector<2x3xf32>, vector<3x2xf32> into f32
   return %0 : f32
 }
 
 // CHECK-LABEL: func @outerproduct_noacc
 // CHECK-SAME: %[[A:.*0]]: vector<2xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<3xf32>
 // CHECK:      %[[C0:.*]] = constant dense<0.000000e+00> : vector<2x3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xf32>
 // CHECK:      %[[T1:.*]] = vector.broadcast %[[T0]] : f32 to vector<3xf32>
 // CHECK:      %[[T2:.*]] = mulf %[[T1]], %[[B]] : vector<3xf32>
 // CHECK:      %[[T3:.*]] = vector.insert %[[T2]], %[[C0]] [0] : vector<3xf32> into vector<2x3xf32>
 // CHECK:      %[[T4:.*]] = vector.extract %[[A]][1] : vector<2xf32>
 // CHECK:      %[[T5:.*]] = vector.broadcast %[[T4]] : f32 to vector<3xf32>
 // CHECK:      %[[T6:.*]] = mulf %[[T5]], %[[B]] : vector<3xf32>
 // CHECK:      %[[T7:.*]] = vector.insert %[[T6]], %[[T3]] [1] : vector<3xf32> into vector<2x3xf32>
 // CHECK:      return %[[T7]] : vector<2x3xf32>
 
 func @outerproduct_noacc(%arg0: vector<2xf32>,
                          %arg1: vector<3xf32>) -> vector<2x3xf32> {
   %0 = vector.outerproduct %arg0, %arg1 : vector<2xf32>, vector<3xf32>
   return %0: vector<2x3xf32>
 }
 
 // CHECK-LABEL: func @outerproduct_acc
 // CHECK-SAME: %[[A:.*0]]: vector<2xf32>,
 // CHECK-SAME: %[[B:.*1]]: vector<3xf32>,
 // CHECK-SAME: %[[C:.*2]]: vector<2x3xf32>
 // CHECK:      %[[C0:.*]] = constant dense<0.000000e+00> : vector<2x3xf32>
 // CHECK:      %[[T0:.*]] = vector.extract %[[A]][0] : vector<2xf32>
 // CHECK:      %[[T1:.*]] = vector.broadcast %[[T0]] : f32 to vector<3xf32>
 // CHECK:      %[[T2:.*]] = vector.extract %[[C]][0] : vector<2x3xf32>
 // CHECK:      %[[T3:.*]] = vector.fma %[[T1]], %[[B]], %[[T2]] : vector<3xf32>
 // CHECK:      %[[T4:.*]] = vector.insert %[[T3]], %[[C0]] [0] : vector<3xf32> into vector<2x3xf32>
 // CHECK:      %[[T5:.*]] = vector.extract %[[A]][1] : vector<2xf32>
 // CHECK:      %[[T6:.*]] = vector.broadcast %[[T5]] : f32 to vector<3xf32>
 // CHECK:      %[[T7:.*]] = vector.extract %[[C]][1] : vector<2x3xf32>
 // CHECK:      %[[T8:.*]] = vector.fma %[[T6]], %[[B]], %[[T7]] : vector<3xf32>
 // CHECK:      %[[T9:.*]] = vector.insert %[[T8]], %[[T4]] [1] : vector<3xf32> into vector<2x3xf32>
 // CHECK:      return %[[T9]] : vector<2x3xf32>
 
 func @outerproduct_acc(%arg0: vector<2xf32>,
                        %arg1: vector<3xf32>,
                        %arg2: vector<2x3xf32>) -> vector<2x3xf32> {
   %0 = vector.outerproduct %arg0, %arg1, %arg2 : vector<2xf32>, vector<3xf32>
   return %0: vector<2x3xf32>
 }
 
 // Shape up and downcasts for 2-D vectors, for supporting conversion to
 // llvm.matrix operations
 // CHECK-LABEL: func @shape_casts
 func @shape_casts(%a: vector<2x2xf32>) -> (vector<4xf32>, vector<2x2xf32>) {
   // CHECK: %[[cst:.*]] = constant dense<0.000000e+00> : vector<4xf32>
   // CHECK: %[[cst22:.*]] = constant dense<0.000000e+00> : vector<2x2xf32>
   // CHECK: %[[ex0:.*]] = vector.extract %{{.*}}[0] : vector<2x2xf32>
   //
   // CHECK: %[[in0:.*]] = vector.insert_strided_slice %[[ex0]], %[[cst]]
   // CHECK-SAME: {offsets = [0], strides = [1]} : vector<2xf32> into vector<4xf32>
   //
   // CHECK: %[[ex1:.*]] = vector.extract %{{.*}}[1] : vector<2x2xf32>
   //
   // CHECK: %[[in2:.*]] = vector.insert_strided_slice %[[ex1]], %[[in0]]
   // CHECK-SAME: {offsets = [2], strides = [1]} : vector<2xf32> into vector<4xf32>
   //
   %0 = vector.shape_cast %a : vector<2x2xf32> to vector<4xf32>
   // CHECK: %[[add:.*]] = addf %[[in2]], %[[in2]] : vector<4xf32>
   %r0 = addf %0, %0: vector<4xf32>
   //
   // CHECK: %[[ss0:.*]] = vector.strided_slice %[[add]]
   // CHECK-SAME: {offsets = [0], sizes = [2], strides = [1]} :
   // CHECK-SAME: vector<4xf32> to vector<2xf32>
   //
   // CHECK: %[[res0:.*]] = vector.insert %[[ss0]], %[[cst22]] [0] :
   // CHECK-SAME: vector<2xf32> into vector<2x2xf32>
   //
   // CHECK: %[[s2:.*]] = vector.strided_slice %[[add]]
   // CHECK-SAME: {offsets = [2], sizes = [2], strides = [1]} :
   // CHECK-SAME: vector<4xf32> to vector<2xf32>
   //
   // CHECK: %[[res1:.*]] = vector.insert %[[s2]], %[[res0]] [1] :
   // CHECK-SAME: vector<2xf32> into vector<2x2xf32>
   //
   %1 = vector.shape_cast %r0  : vector<4xf32> to vector<2x2xf32>
   // CHECK: return %[[add]], %[[res1]] : vector<4xf32>, vector<2x2xf32>
   return %r0, %1 : vector<4xf32>, vector<2x2xf32>
 }
 
 // MATRIX-LABEL: func @column_major_matmul
 // MATRIX-SAME: %[[A:[a-zA-Z0-9]*]]: vector<4x3xf32>,
 // MATRIX-SAME: %[[B:[a-zA-Z0-9]*]]: vector<2x4xf32>,
 // MATRIX-SAME: %[[C:[a-zA-Z0-9]*]]: vector<3x2xf32>
 //      MATRIX:  %[[vcst:.*]] = constant dense<0.000000e+00> : vector<12xf32>
 //      MATRIX:  %[[vcst_0:.*]] = constant dense<0.000000e+00> : vector<8xf32>
 //      MATRIX:  %[[vcst_1:.*]] = constant dense<0.000000e+00> : vector<3x2xf32>
 //      MATRIX:  %[[a0:.*]] = vector.extract %[[A]][0] : vector<4x3xf32>
 //      MATRIX:  %[[a1:.*]] = vector.insert_strided_slice %[[a0]], %[[vcst]] {offsets = [0], strides = [1]} : vector<3xf32> into vector<12xf32>
 //      MATRIX:  %[[a2:.*]] = vector.extract %[[A]][1] : vector<4x3xf32>
 //      MATRIX:  %[[a3:.*]] = vector.insert_strided_slice %[[a2]], %[[a1]] {offsets = [3], strides = [1]} : vector<3xf32> into vector<12xf32>
 //      MATRIX:  %[[a4:.*]] = vector.extract %[[A]][2] : vector<4x3xf32>
 //      MATRIX:  %[[a5:.*]] = vector.insert_strided_slice %[[a4]], %[[a3]] {offsets = [6], strides = [1]} : vector<3xf32> into vector<12xf32>
 //      MATRIX:  %[[a6:.*]] = vector.extract %[[A]][3] : vector<4x3xf32>
 //      MATRIX:  %[[a7:.*]] = vector.insert_strided_slice %[[a6]], %[[a5]] {offsets = [9], strides = [1]} : vector<3xf32> into vector<12xf32>
 //      MATRIX:  %[[b8:.*]] = vector.extract %[[B]][0] : vector<2x4xf32>
 //      MATRIX:  %[[b9:.*]] = vector.insert_strided_slice %[[b8]], %[[vcst_0]] {offsets = [0], strides = [1]} : vector<4xf32> into vector<8xf32>
 //      MATRIX:  %[[b10:.*]] = vector.extract %[[B]][1] : vector<2x4xf32>
 //      MATRIX:  %[[b11:.*]] = vector.insert_strided_slice %[[b10]], %[[b9]] {offsets = [4], strides = [1]} : vector<4xf32> into vector<8xf32>
 //      MATRIX:  %[[mm12:.*]] = vector.matrix_multiply %[[a7]], %[[b11]] {lhs_columns = 3 : i32, lhs_rows = 4 : i32, rhs_columns = 4 : i32} : (vector<12xf32>, vector<8xf32>) -> vector<12xf32>
 //      MATRIX:  %[[mm13:.*]] = vector.strided_slice %[[mm12]] {offsets = [0], sizes = [2], strides = [1]} : vector<12xf32> to vector<2xf32>
 //      MATRIX:  %[[mm14:.*]] = vector.insert %[[mm13]], %[[vcst_1]] [0] : vector<2xf32> into vector<3x2xf32>
 //      MATRIX:  %[[mm15:.*]] = vector.strided_slice %[[mm12]] {offsets = [2], sizes = [2], strides = [1]} : vector<12xf32> to vector<2xf32>
 //      MATRIX:  %[[mm16:.*]] = vector.insert %[[mm15]], %[[mm14]] [1] : vector<2xf32> into vector<3x2xf32>
 //      MATRIX:  %[[mm17:.*]] = vector.strided_slice %[[mm12]] {offsets = [4], sizes = [2], strides = [1]} : vector<12xf32> to vector<2xf32>
 //      MATRIX:  %[[mm18:.*]] = vector.insert %[[mm17]], %[[mm16]] [2] : vector<2xf32> into vector<3x2xf32>
 //      MATRIX:  %[[mm19:.*]] = addf %[[C]], %[[mm18]] : vector<3x2xf32>
 #column_major_matmat_accesses = [
   affine_map<(i, j, k) -> (k, j)>,
   affine_map<(i, j, k) -> (i, k)>,
   affine_map<(i, j, k) -> (j, i)>
 ]
 #column_major_matmat_trait = {
   indexing_maps = #column_major_matmat_accesses,
   iterator_types = ["parallel", "parallel", "reduction"]
 }
 func @column_major_matmul(%arg0: vector<4x3xf32>,
                           %arg1: vector<2x4xf32>,
                           %arg2: vector<3x2xf32>) -> vector<3x2xf32> {
   %0 = vector.contract #column_major_matmat_trait %arg0, %arg1, %arg2
     : vector<4x3xf32>, vector<2x4xf32> into vector<3x2xf32>
   return %0 : vector<3x2xf32>
 }

mlir/test/Dialect/Vector/vector-slices-transforms.mlir

 // RUN: mlir-opt %s -test-vector-slices-conversion | FileCheck %s
 
 // CHECK-LABEL: func @extract_slices(%arg0: vector<3x3xf32>)
 //       CHECK: %[[SS:.*]] = vector.strided_slice %arg0 {offsets = [0, 0], sizes = [2, 2], strides = [1, 1]}
 //       CHECK: return %[[SS]]
 
 func @extract_slices(%arg0: vector<3x3xf32>) -> vector<2x2xf32> {
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1]
     : vector<3x3xf32> into tuple<vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>>
   %1 = vector.tuple_get %0, 0 : tuple<vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>>
   return %1 : vector<2x2xf32>
 }
 
 // CHECK-LABEL: func @insert_slices(%arg0: vector<2x2xf32>, %arg1: vector<2x1xf32>, %arg2: vector<1x2xf32>, %arg3: vector<1x1xf32>)
 //       CHECK: %[[C0:.*]] = constant dense<0.000000e+00> : vector<3x3xf32>
 //       CHECK: %[[I0:.*]] = vector.insert_strided_slice %arg0, %[[C0]] {offsets = [0, 0], strides = [1, 1]}
 //       CHECK: %[[I1:.*]] = vector.insert_strided_slice %arg1, %[[I0]] {offsets = [0, 2], strides = [1, 1]}
 //       CHECK: %[[I2:.*]] = vector.insert_strided_slice %arg2, %[[I1]] {offsets = [2, 0], strides = [1, 1]}
 //       CHECK: %[[I3:.*]] = vector.insert_strided_slice %arg3, %[[I2]] {offsets = [2, 2], strides = [1, 1]}
 //       CHECK: return %[[I3]]
 
 func @insert_slices(%arg0: vector<2x2xf32>,
                     %arg1: vector<2x1xf32>,
                     %arg2: vector<1x2xf32>,
                     %arg3: vector<1x1xf32>) -> vector<3x3xf32> {
   %0 = vector.tuple %arg0, %arg1, %arg2, %arg3
     : vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>
   %1 = vector.insert_slices %0, [2, 2], [1, 1]
     : tuple<vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>> into vector<3x3xf32>
   return %1 : vector<3x3xf32>
 }
 
 // CHECK-LABEL: func @extract_insert_slices(%arg0: vector<3x3xf32>)
 //       CHECK: %[[C:.*]] = constant dense<0.000000e+00> : vector<3x3xf32>
 //       CHECK: %[[X0:.*]] = vector.strided_slice %arg0 {offsets = [0, 0], sizes = [2, 2], strides = [1, 1]}
 //       CHECK: %[[X1:.*]] = vector.strided_slice %arg0 {offsets = [0, 2], sizes = [2, 1], strides = [1, 1]}
 //       CHECK: %[[X2:.*]] = vector.strided_slice %arg0 {offsets = [2, 0], sizes = [1, 2], strides = [1, 1]}
 //       CHECK: %[[X3:.*]] = vector.strided_slice %arg0 {offsets = [2, 2], sizes = [1, 1], strides = [1, 1]}
 //       CHECK: %[[X4:.*]] = vector.insert_strided_slice %[[X0]], %[[C0]] {offsets = [0, 0], strides = [1, 1]}
 //       CHECK: %[[X5:.*]] = vector.insert_strided_slice %[[X1]], %[[X4]] {offsets = [0, 2], strides = [1, 1]}
 //       CHECK: %[[X6:.*]] = vector.insert_strided_slice %[[X2]], %[[X5]] {offsets = [2, 0], strides = [1, 1]}
 //       CHECK: %[[X7:.*]] = vector.insert_strided_slice %[[X3]], %[[X6]] {offsets = [2, 2], strides = [1, 1]}
 //       CHECK:return %[[X7]]
 
 func @extract_insert_slices(%arg0: vector<3x3xf32>) -> vector<3x3xf32> {
   %0 = vector.extract_slices %arg0, [2, 2], [1, 1]
     : vector<3x3xf32> into tuple<vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>>
   %1 = vector.insert_slices %0, [2, 2], [1, 1]
     : tuple<vector<2x2xf32>, vector<2x1xf32>, vector<1x2xf32>, vector<1x1xf32>> into vector<3x3xf32>
   return %1 : vector<3x3xf32>
 }
 
 // CHECK-LABEL: func @extract_slices_tuple_leaks(%arg0: vector<4xf32>)
 //       CHECK: %[[X0:.*]] = vector.strided_slice %arg0 {offsets = [0], sizes = [2], strides = [1]}
 //       CHECK: %[[X1:.*]] = vector.strided_slice %arg0 {offsets = [2], sizes = [2], strides = [1]}
 //       CHECK: %[[X2:.*]] = vector.tuple %[[X0]], %[[X1]]
 //       CHECK: return %[[X2]]
 
 func @extract_slices_tuple_leaks(%arg0: vector<4xf32>) -> tuple<vector<2xf32>, vector<2xf32>> {
   %0 = vector.extract_slices %arg0, [2], [1] : vector<4xf32> into tuple<vector<2xf32>, vector<2xf32>>
   return %0 : tuple<vector<2xf32>, vector<2xf32>>
 }
 

mlir/test/Dialect/Vector/vector-transforms.mlir

 // RUN: mlir-opt %s -test-vector-to-vector-conversion | FileCheck %s
 
 // CHECK-DAG: #[[MAP0:map[0-9]+]] = affine_map<(d0, d1) -> (d0, d1)>
 // CHECK-DAG: #[[MAP1:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d1, d2)>
 
 // CHECK-LABEL: func @add4x2
 //      CHECK: %[[ES1:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES2:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG1:.*]] = vector.tuple_get %[[ES1]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG2:.*]] = vector.tuple_get %[[ES2]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A1:.*]] = addf %[[TG1]], %[[TG2]] : vector<2x2xf32>
 // CHECK-NEXT: %[[TG3:.*]] = vector.tuple_get %[[ES1]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG4:.*]] = vector.tuple_get %[[ES2]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A2:.*]] = addf %[[TG3]], %[[TG4]] : vector<2x2xf32>
 // CHECK-NEXT: %[[R1:.*]] = vector.tuple %[[A1]], %[[A2]] : vector<2x2xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[R2:.*]] = vector.insert_slices %[[R1]], [2, 2], [1, 1] : tuple<vector<2x2xf32>, vector<2x2xf32>> into vector<4x2xf32>
 // CHECK-NEXT: return %[[R2:.*]] : vector<4x2xf32>
 
 func @add4x2(%0: vector<4x2xf32>) -> vector<4x2xf32> {
   %1 = addf %0, %0: vector<4x2xf32>
   return %1: vector<4x2xf32>
 }
 
 // CHECK-LABEL: func @add4x4
 //      CHECK: %[[ES1:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES2:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 
 // CHECK-NEXT: %[[TG1:.*]] = vector.tuple_get %[[ES1]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG2:.*]] = vector.tuple_get %[[ES2]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A1:.*]] = addf %[[TG1]], %[[TG2]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG3:.*]] = vector.tuple_get %[[ES1]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG4:.*]] = vector.tuple_get %[[ES2]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A2:.*]] = addf %[[TG3]], %[[TG4]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG5:.*]] = vector.tuple_get %[[ES1]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG6:.*]] = vector.tuple_get %[[ES2]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A3:.*]] = addf %[[TG5]], %[[TG6]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG7:.*]] = vector.tuple_get %[[ES1]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG8:.*]] = vector.tuple_get %[[ES2]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A4:.*]] = addf %[[TG7]], %[[TG8]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[ES3:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 
 // CHECK-NEXT: %[[TG9:.*]] = vector.tuple_get %[[ES3]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A5:.*]] = addf %[[TG9]], %[[A1]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG11:.*]] = vector.tuple_get %[[ES3]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A6:.*]] = addf %[[TG11]], %[[A2]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG13:.*]] = vector.tuple_get %[[ES3]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A7:.*]] = addf %[[TG13]], %[[A3]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG15:.*]] = vector.tuple_get %[[ES3]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[A8:.*]] = addf %[[TG15]], %[[A4]] : vector<2x2xf32>
 
 // CHECK-NEXT: %[[R3:.*]] = vector.tuple %[[A5]], %[[A6]], %[[A7]], %[[A8]] : vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[R4:.*]] = vector.insert_slices %[[R3]], [2, 2], [1, 1] : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>> into vector<4x4xf32>
 // CHECK-NEXT: return %[[R4]] : vector<4x4xf32>
 
 func @add4x4(%0: vector<4x4xf32>, %1: vector<4x4xf32>) -> vector<4x4xf32> {
   %2 = addf %0, %1: vector<4x4xf32>
   %3 = addf %1, %2: vector<4x4xf32>
   return %3: vector<4x4xf32>
 }
 
 #contraction_accesses0 = [
   affine_map<(i, j, k) -> (i, k)>,
   affine_map<(i, j, k) -> (k, j)>,
   affine_map<(i, j, k) -> (i, j)>
 ]
 #contraction_trait0 = {
   indexing_maps = #contraction_accesses0,
   iterator_types = ["parallel", "parallel", "reduction"]
 }
 
 // CHECK-LABEL: func @contraction4x4_ijk
 
 //      CHECK: %[[LMASK:.*]] = vector.constant_mask [4, 6] : vector<4x6xi1>
 // CHECK-NEXT: %[[RMASK:.*]] = vector.constant_mask [6, 4] : vector<6x4xi1>
 
 // Reducing output vector [0, 0]
 
 // CHECK-NEXT: %[[ES1:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x6xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES2:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<6x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES3:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES4:.*]] = vector.extract_slices %[[LMASK]], [2, 2], [1, 1] : vector<4x6xi1> into tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[ES5:.*]] = vector.extract_slices %[[RMASK]], [2, 2], [1, 1] : vector<6x4xi1> into tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 
 // CHECK-NEXT: %[[TG1:.*]] = vector.tuple_get %[[ES1]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG2:.*]] = vector.tuple_get %[[ES2]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG3:.*]] = vector.tuple_get %[[ES3]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG4:.*]] = vector.tuple_get %[[ES4]], 0 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[TG5:.*]] = vector.tuple_get %[[ES5]], 0 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R1S00:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG1]], %[[TG2]], %[[TG3]], %[[TG4]], %[[TG5]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG6:.*]] = vector.tuple_get %[[ES1]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG7:.*]] = vector.tuple_get %[[ES2]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG8:.*]] = vector.tuple_get %[[ES4]], 1 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[TG9:.*]] = vector.tuple_get %[[ES5]], 2 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R2S00:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG6]], %[[TG7]], %[[R1S00]], %[[TG8]], %[[TG9]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG10:.*]] = vector.tuple_get %[[ES1]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG11:.*]] = vector.tuple_get %[[ES2]], 4 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG12:.*]] = vector.tuple_get %[[ES4]], 2 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[TG13:.*]] = vector.tuple_get %[[ES5]], 4 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R3S00:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG10]], %[[TG11]], %[[R2S00]], %[[TG12]], %[[TG13]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [0, 2]
 
 // CHECK-NEXT: %[[TG14:.*]] = vector.tuple_get %[[ES2]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG15:.*]] = vector.tuple_get %[[ES3]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG16:.*]] = vector.tuple_get %[[ES5]], 1 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R1S02:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG1]], %[[TG14]], %[[TG15]], %[[TG4]], %[[TG16]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG17:.*]] = vector.tuple_get %[[ES2]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG18:.*]] = vector.tuple_get %[[ES5]], 3 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R2S02:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG6]], %[[TG17]], %[[R1S02]], %[[TG8]], %[[TG18]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG19:.*]] = vector.tuple_get %[[ES2]], 5 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG20:.*]] = vector.tuple_get %[[ES5]], 5 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R3S02:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG10]], %[[TG19]], %[[R2S02]], %[[TG12]], %[[TG20]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [2, 0]
 
 // CHECK-NEXT: %[[TG21:.*]] = vector.tuple_get %[[ES1]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG22:.*]] = vector.tuple_get %[[ES3]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG23:.*]] = vector.tuple_get %[[ES4]], 3 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[R1S20:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG21]], %[[TG2]], %[[TG22]], %[[TG23]], %[[TG5]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG24:.*]] = vector.tuple_get %[[ES1]], 4 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG25:.*]] = vector.tuple_get %[[ES4]], 4 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT:  %[[R2S20:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG24]], %[[TG7]], %[[R1S20]], %[[TG25]], %[[TG9]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[TG26:.*]] = vector.tuple_get %[[ES1]], 5 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG27:.*]] = vector.tuple_get %[[ES4]], 5 : tuple<vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT:  %[[R3S20:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG26]], %[[TG11]], %[[R2S20]], %[[TG27]], %[[TG13]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [2, 2]
 
 // CHECK-NEXT: %[[TG28:.*]] = vector.tuple_get %[[ES3]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[R1S22:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG21]], %[[TG14]], %[[TG28]], %[[TG23]], %[[TG16]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 // CHECK-NEXT: %[[R2S22:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG24]], %[[TG17]], %[[R1S22]], %[[TG25]], %[[TG18]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 // CHECK-NEXT: %[[R3S22:.*]] = vector.contract {indexing_maps = [#map0, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]} %[[TG26]], %[[TG19]], %[[R2S22]], %[[TG27]], %[[TG20]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[RES0:.*]] = vector.tuple %[[R3S00]], %[[R3S02]], %[[R3S20]], %[[R3S22]] : vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[RES1:.*]] = vector.insert_slices %[[RES0]], [2, 2], [1, 1] : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>> into vector<4x4xf32>
 // CHECK-NEXT:  return %[[RES1]] : vector<4x4xf32>
 
 func @contraction4x4_ijk(%arg0 : vector<4x6xf32>, %arg1 : vector<6x4xf32>,
                          %arg2 : vector<4x4xf32>, %arg3 : index)
                          -> (vector<4x4xf32>) {
   %lhsm = vector.constant_mask [4, 6] : vector<4x6xi1>
   %rhsm = vector.constant_mask [6, 4] : vector<6x4xi1>
   %0 = vector.contract #contraction_trait0 %arg0, %arg1, %arg2, %lhsm, %rhsm
       : vector<4x6xf32>, vector<6x4xf32> into vector<4x4xf32>
 
   return %0 : vector<4x4xf32>
 }
 
 #contraction_accesses1 = [
   affine_map<(i, k, j) -> (i, k)>,
   affine_map<(i, k, j) -> (k, j)>,
   affine_map<(i, k, j) -> (i, j)>
 ]
 #contraction_trait1 = {
   indexing_maps = #contraction_accesses1,
   iterator_types = ["parallel", "reduction", "parallel"]
 }
 
 // CHECK-LABEL: func @contraction4x4_ikj
 
 
 //      CHECK: %[[LMASK:.*]] = vector.constant_mask [4, 2] : vector<4x2xi1>
 // CHECK-NEXT: %[[RMASK:.*]] = vector.constant_mask [2, 4] : vector<2x4xi1>
 
 // Reducing output vector [0, 0]
 
 // CHECK-NEXT: %[[ES1:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x2xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES2:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<2x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES3:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x4xf32> into tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[ES4:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<4x2xi1> into tuple<vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[ES5:.*]] = vector.extract_slices %{{.*}}, [2, 2], [1, 1] : vector<2x4xi1> into tuple<vector<2x2xi1>, vector<2x2xi1>>
 
 // CHECK-NEXT: %[[TG1:.*]] = vector.tuple_get %[[ES1]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG2:.*]] = vector.tuple_get %[[ES2]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG3:.*]] = vector.tuple_get %[[ES3]], 0 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG4:.*]] = vector.tuple_get %[[ES4]], 0 : tuple<vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT: %[[TG5:.*]] = vector.tuple_get %[[ES5]], 0 : tuple<vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT:  %[[R1S00:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[TG1]], %[[TG2]], %[[TG3]], %[[TG4]], %[[TG5]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [0, 2]
 
 // CHECK-NEXT: %[[TG6:.*]] = vector.tuple_get %[[ES2]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG7:.*]] = vector.tuple_get %[[ES3]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG8:.*]] = vector.tuple_get %[[ES5]], 1 : tuple<vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT:  %[[R1S02:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[TG1]], %[[TG6]], %[[TG7]], %[[TG4]], %[[TG8]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [2, 0]
 
 // CHECK-NEXT: %[[TG9:.*]] = vector.tuple_get %[[ES1]], 1 : tuple<vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG10:.*]] = vector.tuple_get %[[ES3]], 2 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT: %[[TG11:.*]] = vector.tuple_get %[[ES4]], 1 : tuple<vector<2x2xi1>, vector<2x2xi1>>
 // CHECK-NEXT:  %[[R1S20:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[TG9]], %[[TG2]], %[[TG10]], %[[TG11]], %[[TG5]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // Reducing output vector [2, 2]
 
 // CHECK-NEXT: %[[TG12:.*]] = vector.tuple_get %[[ES3]], 3 : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>>
 // CHECK-NEXT:  %[[R1S22:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[TG9]], %[[TG6]], %[[TG12]], %[[TG11]], %[[TG8]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: %[[RES0:.*]] = vector.tuple %[[R1S00]], %[[R1S02]], %[[R1S20]], %[[R1S22]] : vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[RES1:.*]] = vector.insert_slices %[[RES0]], [2, 2], [1, 1] : tuple<vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>, vector<2x2xf32>> into vector<4x4xf32>
 // CHECK-NEXT:  return %[[RES1]] : vector<4x4xf32>
 
 func @contraction4x4_ikj(%arg0 : vector<4x2xf32>, %arg1 : vector<2x4xf32>,
                          %arg2 : vector<4x4xf32>, %arg3 : index)
                          -> (vector<4x4xf32>) {
   %lhsm = vector.constant_mask [4, 2] : vector<4x2xi1>
   %rhsm = vector.constant_mask [2, 4] : vector<2x4xi1>
   %0 = vector.contract #contraction_trait1 %arg0, %arg1, %arg2, %lhsm, %rhsm
       : vector<4x2xf32>, vector<2x4xf32> into vector<4x4xf32>
 
   return %0 : vector<4x4xf32>
 }
 
 // CHECK-LABEL: func @contraction4x4_ikj_xfer_read
 
 // CHECK:      %[[C0:.*]] = constant 0 : index
 // CHECK:      %[[C2:.*]] = constant 2 : index
 
 // Check LHS vector.transfer read is split for each user.
 
 //      CHECK: %[[VTR0:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x2xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[VTR1:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x2xf32>, vector<2x2xf32>
 
 // CHECK-NEXT: %[[VTR2:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<2x4xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[VTR3:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C2]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<2x4xf32>, vector<2x2xf32>
 
 // CHECK-NEXT: %[[VTR4:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x4xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[VTR5:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C2]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x4xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[VTR6:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x4xf32>, vector<2x2xf32>
 // CHECK-NEXT: %[[VTR7:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C2]]], %{{.*}} {permutation_map = #[[MAP0]]} : memref<4x4xf32>, vector<2x2xf32>
 
 // CHECK-NEXT: %[[R0:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[VTR0]], %[[VTR2]], %[[VTR4]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 // CHECK-NEXT: %[[R1:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[VTR0]], %[[VTR3]], %[[VTR5]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 // CHECK-NEXT: %[[R2:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[VTR1]], %[[VTR2]], %[[VTR6]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 // CHECK-NEXT: %[[R3:.*]] = vector.contract {indexing_maps = [#map2, #map3, #map0], iterator_types = ["parallel", "reduction", "parallel"]} %[[VTR1]], %[[VTR3]], %[[VTR7]] : vector<2x2xf32>, vector<2x2xf32> into vector<2x2xf32>
 
 // CHECK-NEXT: vector.transfer_write %[[R0]], %{{.*}}[%[[C0]], %[[C0]]] {permutation_map = #[[MAP0]]} : vector<2x2xf32>, memref<4x4xf32>
 // CHECK-NEXT: vector.transfer_write %[[R1]], %{{.*}}[%[[C0]], %[[C2]]] {permutation_map = #[[MAP0]]} : vector<2x2xf32>, memref<4x4xf32>
 // CHECK-NEXT: vector.transfer_write %[[R2]], %{{.*}}[%[[C2]], %[[C0]]] {permutation_map = #[[MAP0]]} : vector<2x2xf32>, memref<4x4xf32>
 // CHECK-NEXT: vector.transfer_write %[[R3]], %{{.*}}[%[[C2]], %[[C2]]] {permutation_map = #[[MAP0]]} : vector<2x2xf32>, memref<4x4xf32>
 // CHECK-NEXT: return
 
 func @contraction4x4_ikj_xfer_read(%arg0 : memref<4x2xf32>,
                                    %arg1 : memref<2x4xf32>,
                                    %arg2 : memref<4x4xf32>) {
   %c0 = constant 0 : index
   %cf0 = constant 0.0 : f32
 
   %0 = vector.transfer_read %arg0[%c0, %c0], %cf0
     { permutation_map = affine_map<(d0, d1) -> (d0, d1)> }
       : memref<4x2xf32>, vector<4x2xf32>
 
   %1 = vector.transfer_read %arg1[%c0, %c0], %cf0
     { permutation_map = affine_map<(d0, d1) -> (d0, d1)> }
     : memref<2x4xf32>, vector<2x4xf32>
 
   %2 = vector.transfer_read %arg2[%c0, %c0], %cf0
     { permutation_map = affine_map<(d0, d1) -> (d0, d1)> }
       : memref<4x4xf32>, vector<4x4xf32>
 
   %3 = vector.contract #contraction_trait1 %0, %1, %2
       : vector<4x2xf32>, vector<2x4xf32> into vector<4x4xf32>
 
   vector.transfer_write %3, %arg2[%c0, %c0]
     {permutation_map = affine_map<(d0, d1) -> (d0, d1)>}
       : vector<4x4xf32>, memref<4x4xf32>
   return
 }
 
 // TODO(andydavis) Update test with VTR split transform.
 // CHECK-LABEL: func @vector_transfers
 // CHECK-COUNT-8: vector.transfer_read
 // CHECK-COUNT-4: addf
 // CHECK-COUNT-4: vector.transfer_write
 
 func @vector_transfers(%arg0: index, %arg1: index) {
   %cst = constant 0.000000e+00 : f32
   %0 = alloc(%arg0, %arg1) : memref<?x?xf32>
   %1 = alloc(%arg0, %arg1) : memref<?x?xf32>
   %2 = alloc(%arg0, %arg1) : memref<?x?xf32>
   %cst_0 = constant 1.000000e+00 : f32
   %cst_1 = constant 2.000000e+00 : f32
   affine.for %arg2 = 0 to %arg0 step 4 {
     affine.for %arg3 = 0 to %arg1 step 4 {
       %4 = vector.transfer_read %0[%arg2, %arg3], %cst  {permutation_map = affine_map<(d0, d1) -> (d0, d1)>} : memref<?x?xf32>, vector<4x4xf32>
       %5 = vector.transfer_read %1[%arg2, %arg3], %cst  {permutation_map = affine_map<(d0, d1) -> (d0, d1)>} : memref<?x?xf32>, vector<4x4xf32>
       %6 = addf %4, %5 : vector<4x4xf32>
       vector.transfer_write %6, %2[%arg2, %arg3] {permutation_map = affine_map<(d0, d1) -> (d0, d1)>} : vector<4x4xf32>, memref<?x?xf32>
     }
   }
   return
 }
 
 // CHECK-LABEL: func @tuple_get(%arg0: vector<4xf32>, %arg1: vector<8xf32>)
 //       CHECK: return %arg1
 
 func @tuple_get(%arg0: vector<4xf32>, %arg1: vector<8xf32>) -> vector<8xf32> {
   %0 = vector.tuple %arg0, %arg1 : vector<4xf32>, vector<8xf32>
   %1 = vector.tuple_get %0, 1 : tuple<vector<4xf32>, vector<8xf32>>
   return %1 : vector<8xf32>
 }
 
 // CHECK-LABEL: func @vector_transfers_vector_element_type
 //      CHECK: %[[C0:.*]] = constant 0 : index
 //      CHECK: %[[C1:.*]] = constant 1 : index
 //      CHECK: %[[VTR0:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP1]]} : memref<6x2x1xvector<2x4xf32>>, vector<1x1x2x4xf32>
 // CHECK-NEXT: %[[VTR1:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C1]], %[[C0]]], %{{.*}} {permutation_map = #[[MAP1]]} : memref<6x2x1xvector<2x4xf32>>, vector<1x1x2x4xf32>
 // CHECK-NEXT: vector.transfer_write %[[VTR0]], %{{.*}}[%[[C0]], %[[C0]], %[[C0]]] {permutation_map = #[[MAP1]]} : vector<1x1x2x4xf32>, memref<6x2x1xvector<2x4xf32>>
 // CHECK-NEXT: vector.transfer_write %[[VTR1]], %{{.*}}[%[[C0]], %[[C1]], %[[C0]]] {permutation_map = #[[MAP1]]} : vector<1x1x2x4xf32>, memref<6x2x1xvector<2x4xf32>>
 
 func @vector_transfers_vector_element_type() {
   %c0 = constant 0 : index
   %cf0 = constant 0.000000e+00 : f32
   %vf0 = splat %cf0 : vector<2x4xf32>
 
   %0 = alloc() : memref<6x2x1xvector<2x4xf32>>
 
   %1 = vector.transfer_read %0[%c0, %c0, %c0], %vf0
       {permutation_map = affine_map<(d0, d1, d2) -> (d1, d2)>}
         : memref<6x2x1xvector<2x4xf32>>, vector<2x1x2x4xf32>
 
   %2 = vector.extract_slices %1, [1, 1, 2, 4], [1, 1, 1, 1]
     : vector<2x1x2x4xf32> into tuple<vector<1x1x2x4xf32>, vector<1x1x2x4xf32>>
   %3 = vector.tuple_get %2, 0 : tuple<vector<1x1x2x4xf32>, vector<1x1x2x4xf32>>
   %4 = vector.tuple_get %2, 1 : tuple<vector<1x1x2x4xf32>, vector<1x1x2x4xf32>>
   %5 = vector.tuple %3, %4 : vector<1x1x2x4xf32>, vector<1x1x2x4xf32>
   %6 = vector.insert_slices %5, [1, 1, 2, 4], [1, 1, 1, 1]
     : tuple<vector<1x1x2x4xf32>, vector<1x1x2x4xf32>> into vector<2x1x2x4xf32>
 
   vector.transfer_write %6, %0[%c0, %c0, %c0]
     {permutation_map = affine_map<(d0, d1, d2) -> (d1, d2)>}
       : vector<2x1x2x4xf32>, memref<6x2x1xvector<2x4xf32>>
 
   return
 }
 
 // Test that ShapeCastOp on tuple of vectors, decomposes to multiple
 // ShapeCastOps on vectors.
 // CHECK-LABEL: func @shape_cast_decomposition
 //       CHECK: %[[V0:.*]] = vector.shape_cast %{{.*}} : vector<5x4x2xf32> to vector<20x2xf32>
 //  CHECK-NEXT: %[[V1:.*]] = vector.shape_cast %{{.*}} : vector<3x4x2xf32> to vector<12x2xf32>
 //  CHECK-NEXT: return %[[V0]], %[[V1]] : vector<20x2xf32>, vector<12x2xf32>
 
 func @shape_cast_decomposition(%arg0 : vector<5x4x2xf32>,
                                %arg1 : vector<3x4x2xf32>)
   -> (vector<20x2xf32>, vector<12x2xf32>) {
   %0 = vector.tuple %arg0, %arg1 : vector<5x4x2xf32>, vector<3x4x2xf32>
   %1 = vector.shape_cast %0 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                               tuple<vector<20x2xf32>, vector<12x2xf32>>
   %2 = vector.tuple_get %1, 0 : tuple<vector<20x2xf32>, vector<12x2xf32>>
   %3 = vector.tuple_get %1, 1 : tuple<vector<20x2xf32>, vector<12x2xf32>>
   return %2, %3 : vector<20x2xf32>, vector<12x2xf32>
 }
 
 // Test that cancelling ShapeCastOps are canonicalized away.
 // EX:
 //
 //  The following MLIR with cancelling ShapeCastOps:
 //
 //   %0 = source : vector<5x4x2xf32>
 //   %1 = shape_cast %0 : vector<5x4x2xf32> to vector<20x2xf32>
 //   %2 = shape_cast %1 : vector<20x2xf32> to vector<5x4x2xf32>
 //   %3 = user %2 : vector<5x4x2xf32>
 //
 //  Should canonicalize to the following:
 //
 //
 //   %0 = source : vector<5x4x2xf32>
 //   %1 = user %0 : vector<5x4x2xf32>
 //
 
 // ShapeCastOps on vectors.
 // CHECK-LABEL: func @shape_cast_fold
 //       CHECK: return %{{.*}},  %{{.*}} : vector<5x4x2xf32>, vector<3x4x2xf32>
 
 func @shape_cast_fold(%arg0 : vector<5x4x2xf32>, %arg1 : vector<3x4x2xf32>)
   -> (vector<5x4x2xf32>, vector<3x4x2xf32>) {
   %0 = vector.tuple %arg0, %arg1 : vector<5x4x2xf32>, vector<3x4x2xf32>
 
   %1 = vector.shape_cast %0 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>> to
                               tuple<vector<20x2xf32>, vector<12x2xf32>>
 
   %2 = vector.tuple_get %1, 0 : tuple<vector<20x2xf32>, vector<12x2xf32>>
   %3 = vector.tuple_get %1, 1 : tuple<vector<20x2xf32>, vector<12x2xf32>>
 
   %4 = vector.tuple %2, %3 : vector<20x2xf32>, vector<12x2xf32>
   %5 = vector.shape_cast %4 : tuple<vector<20x2xf32>, vector<12x2xf32>> to
                               tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>
 
   %6 = vector.tuple_get %5, 0 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>
   %7 = vector.tuple_get %5, 1 : tuple<vector<5x4x2xf32>, vector<3x4x2xf32>>
 
   return %6, %7 : vector<5x4x2xf32>, vector<3x4x2xf32>
 }

mlir/test/EDSC/CMakeLists.txt

 add_llvm_executable(mlir-edsc-builder-api-test
   builder-api-test.cpp
 )
 
 llvm_update_compile_flags(mlir-edsc-builder-api-test)
 
 target_link_libraries(mlir-edsc-builder-api-test
   PRIVATE
   MLIRAffineOps
   MLIREDSC
   MLIRIR
   MLIRLinalgEDSC
   MLIRLinalgOps
   MLIRLoopOps
   MLIRStandardOps
   MLIRTransforms
-  MLIRVectorOps
+  MLIRVector
   LLVMCore
   LLVMSupport
 )
 
 target_include_directories(mlir-edsc-builder-api-test PRIVATE ..)
 
 whole_archive_link(mlir-edsc-builder-api-test
   MLIRAffineOps
   MLIRLinalgOps
   MLIRLoopOps
   MLIRStandardOps
-  MLIRVectorOps
+  MLIRVector
   MLIRTransforms
 )

mlir/test/EDSC/builder-api-test.cpp

 //===- builder-api-test.cpp - Tests for Declarative Builder APIs ----------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // RUN: mlir-edsc-builder-api-test | FileCheck %s -dump-input-on-failure
 
 #include "mlir/Dialect/AffineOps/EDSC/Intrinsics.h"
 #include "mlir/Dialect/Linalg/EDSC/Intrinsics.h"
 #include "mlir/Dialect/LoopOps/EDSC/Builders.h"
 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
-#include "mlir/Dialect/VectorOps/EDSC/Intrinsics.h"
+#include "mlir/Dialect/Vector/EDSC/Intrinsics.h"
 #include "mlir/EDSC/Builders.h"
 #include "mlir/EDSC/Intrinsics.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/IntegerSet.h"
 #include "mlir/IR/MLIRContext.h"
 #include "mlir/IR/Module.h"
 #include "mlir/IR/StandardTypes.h"

 using namespace mlir::edsc::intrinsics;
 
 static MLIRContext &globalContext() {
   static bool init_once = []() {
     registerDialect<AffineOpsDialect>();
     registerDialect<linalg::LinalgDialect>();
     registerDialect<loop::LoopOpsDialect>();
     registerDialect<StandardOpsDialect>();
-    registerDialect<vector::VectorOpsDialect>();
+    registerDialect<vector::VectorDialect>();
     return true;
   }();
   (void)init_once;
   static thread_local MLIRContext context;
   return context;
 }
 
 static FuncOp makeFunction(StringRef name, ArrayRef<Type> results = {},

mlir/test/lib/DeclarativeTransforms/TestVectorTransformPatterns.td

 // tests.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef TEST_VECTOR_TRANSFORMS_PATTERNS
 #define TEST_VECTOR_TRANSFORMS_PATTERNS
 
 include "mlir/Dialect/StandardOps/IR/Ops.td"
-include "mlir/Dialect/VectorOps/VectorOps.td"
-include "mlir/Dialect/VectorOps/VectorTransformPatterns.td"
+include "mlir/Dialect/Vector/VectorOps.td"
+include "mlir/Dialect/Vector/VectorTransformPatterns.td"
 
 def : Pat<(AddFOp:$op_results $a, $b),
           (UnrollVectorOp<[2, 2]> $op_results, $a, $b),
           [(Constraint<HasShape<[4, 2]>> $a)]>;
 
 def : Pat<(AddFOp:$op_results $a, $b),
           (UnrollVectorOp<[2, 2]> $op_results, $a, $b),
           [(Constraint<HasShape<[4, 4]>> $a)]>;
 
 // TODO(andydavis) Add Constraints on lhs/rhs shapes.
 def : Pat<(Vector_ContractionOp:$op_results $a, $b, $c, $masks, $attr0, $attr1),
           (UnrollVectorOp<[2, 2, 2]> $op_results, $a, $b, $c),
           [(Constraint<HasShape<[4, 4]>> $c)]>;
 
 #endif // TEST_VECTOR_TRANSFORMS_PATTERNS

mlir/test/lib/Transforms/CMakeLists.txt

target_link_libraries(MLIRTestTransforms
   MLIRLinalgOps
   MLIRLinalgTransforms
   MLIRLoopOps
   MLIRGPU
   MLIRPass
   MLIRTestDialect
   MLIRTransformUtils
   MLIRVectorToLoops
-  MLIRVectorOps
+  MLIRVector
   )

mlir/test/lib/Transforms/TestVectorTransforms.cpp

 //===- TestVectorToVectorConversion.cpp - Test VectorTransfers lowering ---===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include <type_traits>
 
 #include "mlir/Dialect/StandardOps/IR/Ops.h"
-#include "mlir/Dialect/VectorOps/VectorOps.h"
-#include "mlir/Dialect/VectorOps/VectorTransforms.h"
+#include "mlir/Dialect/Vector/VectorOps.h"
+#include "mlir/Dialect/Vector/VectorTransforms.h"
 #include "mlir/IR/PatternMatch.h"
 #include "mlir/Pass/Pass.h"
 
 using namespace mlir;
 using namespace mlir::vector;
 
 namespace {
 

mlir/test/lib/Transforms/TestVectorizationUtils.cpp

 //===- VectorizerTestPass.cpp - VectorizerTestPass Pass Impl --------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements a simple testing pass for vectorization functionality.
 //
 //===----------------------------------------------------------------------===//
 
 #include "mlir/Analysis/AffineAnalysis.h"
 #include "mlir/Analysis/NestedMatcher.h"
 #include "mlir/Analysis/SliceAnalysis.h"
 #include "mlir/Dialect/AffineOps/AffineOps.h"
-#include "mlir/Dialect/VectorOps/VectorUtils.h"
+#include "mlir/Dialect/Vector/VectorUtils.h"
 #include "mlir/IR/Builders.h"
 #include "mlir/IR/Diagnostics.h"
 #include "mlir/IR/StandardTypes.h"
 #include "mlir/Pass/Pass.h"
 #include "mlir/Support/Functional.h"
 #include "mlir/Support/STLExtras.h"
 #include "mlir/Transforms/Passes.h"