[mlir][Vector] Make minor identity permutation map optional in transfer op printing and parsing

[nicolasvasilache]

Summary

This revision makes the use of vector transfer operatons more idiomatic by
allowing to omit and inferring the permutation_map.

[ftynse]

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

866

You don't need a class unless it's parameterized. Try

def Vector_TransferOpUtils {
  code transferDeclaration = [{...}];
}

def Vector_TransferReadOp : ...{
  let extraClassDeclaration = Vector_TransferOpUtils.transferdeclaration # [{...}];
}

without classes or inheritance.

877

Typo: tte

mlir/lib/Dialect/Vector/VectorOps.cpp

1331

Can you just put this into the declaration of the function in .td ?

1337

Should we also check that it is a minor identity of the correct size, i.e. has the expected number of equal dimensions? Or is it impossible for valid ops?

1371

Please add tests for user-visible error messages

1462

parser.emitError(..) is convertible to ParseResult::failure() IIRC

mlir/test/Conversion/AffineToStandard/lower-affine-to-vector.mlir

3

Please drop the capture for the map if it is no longer necessary. Here and below, maybe in other files too.

[nicolasvasilache]

Address review.

[nicolasvasilache]

mlir/lib/Dialect/Vector/VectorOps.cpp

1337

since it's inferred we can just construct and test.

[dcaballe]

I was thinking about doing the same! Thanks for doing this, Nicolas!

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

let extraClassDeclaration = [{
     static StringRef getStridesAttrName() { return "strides"; }
     VectorType getVectorType(){ return vector().getType().cast<VectorType>(); }
     void getOffsets(SmallVectorImpl<int64_t> &results);
   }];
   let hasCanonicalizer = 1;
   let assemblyFormat = "$vector attr-dict `:` type($vector) `to` type(results)";
 }
 
+class Vector_TransferOpBase<int dummy> {
+  code extraTransferDeclaration = [{
+    static StringRef getPermutationMapAttrName() { return "permutation_map"; }
+    MemRefType getMemRefType() {
+      return memref().getType().cast<MemRefType>();
+    }
+    VectorType getVectorType() {
+      return vector().getType().cast<VectorType>();
+    }
+    /// Build the default minor identity map suitable for a vector transfer.
+    /// This also handles the case memref<... x vector<...>> -> vector<...> in
+    /// which the rank of tte identity map must take the vector element type
+    /// into account.
+    static AffineMap getTransferMinorIdentityMap(
+      MemRefType memRefType, VectorType vectorType);
+  }];
+}
+
 def Vector_TransferReadOp :
   Vector_Op<"transfer_read">,
+  Vector_TransferOpBase<0>,
     Arguments<(ins AnyMemRef:$memref, Variadic<Index>:$indices,
                AffineMapAttr:$permutation_map, AnyType:$padding)>,
     Results<(outs AnyVector:$vector)> {
 
   let summary = "Reads a supervector from memory into an SSA vector value.";
 
   let description = [{
     The `vector.transfer_read` op performs a blocking read from a slice within
     a [MemRef](../LangRef.md#memref-type) supplied as its first operand
     into a [vector](../LangRef.md#vector-type) of the same base elemental type.
 
     A memref operand with vector element type, must have its vector element
     type match a suffix (shape and element type) of the vector (e.g.
     memref<3x2x6x4x3xf32>, vector<1x1x4x3xf32>).
 
     The slice is further defined by a full-rank index within the MemRef,
     supplied as the operands `2 .. 1 + rank(memref)`. The permutation_map
     [attribute](../LangRef.md#attributes) is an
     [affine-map](Affine.md#affine-maps) which specifies the transposition on the
-    slice to match the vector shape. The size of the slice is specified by the
-    size of the vector, given as the return type. An `ssa-value` of the same
-    elemental type as the MemRef is provided as the last operand to specify
-    padding in the case of out-of-bounds accesses. This operation is called
-    'read' by opposition to 'load' because the super-vector granularity is
-    generally not representable with a single hardware register.
-    A `vector.transfer_read` is thus a mid-level
-    abstraction that supports super-vectorization with non-effecting padding for
-    full-tile-only code.
+    slice to match the vector shape. The permutation map may be implicit and
+    ommitted from parsing and printing if it is the canonical minor identity map
+    (i.e. if it does not permute or broadcast any dimension).
+
+    The size of the slice is specified by the size of the vector, given as the
+    return type.
+
+    An `ssa-value` of the same elemental type as the MemRef is provided as the
+    last operand to specify padding in the case of out-of-bounds accesses.
+
+    This operation is called 'read' by opposition to 'load' because the
+    super-vector granularity is generally not representable with a single
+    hardware register. A `vector.transfer_read` is thus a mid-level abstraction
+    that supports super-vectorization with non-effecting padding for full-tile
+    only operations.
 
     More precisely, let's dive deeper into the permutation_map for the following
     MLIR:
 
     ```mlir
     vector.transfer_read %A[%expr1, %expr2, %expr3, %expr4]
       { permutation_map : (d0,d1,d2,d3) -> (d2,0,d0) } :
       memref<?x?x?x?xf32>, vector<3x4x5xf32>
let description = [{
     // Read from a memref with vector element type.
     %4 = vector.transfer_read %arg1[%c3, %c3], %vf0
       {permutation_map = (d0, d1)->(d0, d1)}
         : memref<?x?xvector<4x3xf32>>, vector<1x1x4x3xf32>
     ```
   }];
 
   let builders = [
-    // Builder that sets permutation map and padding to 'getMinorIdentityMap'
-    // and zero, respectively, by default.
+    // Builder that sets padding to zero.
+    OpBuilder<"OpBuilder &builder, OperationState &result, VectorType vector, "
+              "Value memref, ValueRange indices, AffineMap permutationMap">,
+    // Builder that sets permutation map (resp. padding) to
+    // 'getMinorIdentityMap' (resp. zero).
     OpBuilder<"OpBuilder &builder, OperationState &result, VectorType vector, "
               "Value memref, ValueRange indices">
   ];
 
-  let extraClassDeclaration = [{
-    MemRefType getMemRefType() {
-      return memref().getType().cast<MemRefType>();
-    }
-    VectorType getVectorType() {
-      return vector().getType().cast<VectorType>();
-    }
+  let extraClassDeclaration = extraTransferDeclaration # [{
   }];
 }
 
 def Vector_TransferWriteOp :
   Vector_Op<"transfer_write">,
+  Vector_TransferOpBase<0>,
     Arguments<(ins AnyVector:$vector, AnyMemRef:$memref,
                Variadic<Index>:$indices,
                AffineMapAttr:$permutation_map)> {
 
   let summary = "The vector.transfer_write op writes a supervector to memory.";
 
   let description = [{
     The `vector.transfer_write` performs a blocking write from a
     [vector](../LangRef.md#vector-type), supplied as its first operand, into a
     slice within a [MemRef](../LangRef.md#memref-type) of the same base
     elemental type, supplied as its second operand.
 
     A vector memref operand must have its vector element type match a suffix
     (shape and element type) of the vector (e.g. memref<3x2x6x4x3xf32>,
     vector<1x1x4x3xf32>).
 
     The slice is further defined by a full-rank index within the MemRef,
     supplied as the operands `3 .. 2 + rank(memref)`.
     The permutation_map [attribute](../LangRef.md#attributes) is an
     [affine-map](Affine.md#affine-maps) which specifies the transposition on the
-    slice to match the vector shape. The size of the slice is specified by the
-    size of the vector. This operation is called 'write' by opposition to
-    'store' because the super-vector granularity is generally not representable
-    with a single hardware register. A `vector.transfer_write` is thus a
+    slice to match the vector shape. The permutation map may be implicit and
+    ommitted from parsing and printing if it is the canonical minor identity map
+    (i.e. if it does not permute or broadcast any dimension).
+
+    The size of the slice is specified by the size of the vector.
+
+    This operation is called 'write' by opposition to 'store' because the
+    super-vector granularity is generally not representable with a single
+    hardware register. A `vector.transfer_write` is thus a
     mid-level abstraction that supports super-vectorization with non-effecting
     padding for full-tile-only code. It is the responsibility of
     `vector.transfer_write`'s implementation to ensure the memory writes are
     valid. Different lowerings may be pertinent depending on the hardware
     support.
 
     Example:
 
let description = [{
     // write to a memref with vector element type.
     vector.transfer_write %4, %arg1[%c3, %c3]
       {permutation_map = (d0, d1)->(d0, d1)}
         : vector<1x1x4x3xf32>, memref<?x?xvector<4x3xf32>>
     ```
   }];
 
   let builders = [
-    // Builder that sets permutation map and padding to 'getMinorIdentityMap'
-    // by default.
+    // Builder that sets permutation map to 'getMinorIdentityMap'.
     OpBuilder<"OpBuilder &builder, OperationState &result, Value vector, "
               "Value memref, ValueRange indices">
   ];
 
-  let extraClassDeclaration = [{
-    VectorType getVectorType() {
-      return vector().getType().cast<VectorType>();
-    }
-    MemRefType getMemRefType() {
-      return memref().getType().cast<MemRefType>();
-    }
-  }];
-  let assemblyFormat = [{
-    $vector `,` $memref `[` $indices `]` attr-dict `:` type($vector) `,`
-    type($memref)
+  let extraClassDeclaration = extraTransferDeclaration # [{
   }];
 }
 
 def Vector_ShapeCastOp :
   Vector_Op<"shape_cast", [NoSideEffect]>,
     Arguments<(ins AnyTypeOf<[AnyVector, TupleOf<[AnyVector]>]>:$source)>,
     Results<(outs AnyTypeOf<[AnyVector, TupleOf<[AnyVector]>]>:$result)> {
   let summary = "shape_cast casts between vector shapes";

mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp

 LogicalResult NDTransferOpHelper<TransferReadOp>::doReplace() {
   Value alloc = std_alloc(memRefMinorVectorType);
 
   emitLoops([&](ValueRange majorIvs, ValueRange leadingOffsets,
                 ValueRange majorOffsets, ValueRange minorOffsets,
                 MemRefBoundsCapture &memrefBounds) {
     // If in-bounds, index into memref and lower to 1-D transfer read.
     auto thenBlockBuilder = [&](ValueRange majorIvsPlusOffsets) {
-      auto map = AffineMap::getMinorIdentityMap(
-          xferOp.getMemRefType().getRank(), minorRank, xferOp.getContext());
-      // Lower to 1-D vector_transfer_read and let recursion handle it.
-      Value memref = xferOp.memref();
       SmallVector<Value, 8> indexing;
       indexing.reserve(leadingRank + majorRank + minorRank);
       indexing.append(leadingOffsets.begin(), leadingOffsets.end());
       indexing.append(majorIvsPlusOffsets.begin(), majorIvsPlusOffsets.end());
       indexing.append(minorOffsets.begin(), minorOffsets.end());
+      // Lower to 1-D vector_transfer_read and let recursion handle it.
+      Value memref = xferOp.memref();
+      auto map = TransferReadOp::getTransferMinorIdentityMap(
+          xferOp.getMemRefType(), minorVectorType);
       auto loaded1D =
           vector_transfer_read(minorVectorType, memref, indexing,
                                AffineMapAttr::get(map), xferOp.padding());
       // Store the 1-D vector.
       std_store(loaded1D, alloc, majorIvs);
     };
     // If out-of-bounds, just store a splatted vector.
     auto elseBlockBuilder = [&](ValueRange majorIvsPlusOffsets) {
LogicalResult NDTransferOpHelper<TransferWriteOp>::doReplace() {
   std_store(xferOp.vector(),
             vector_type_cast(MemRefType::get({}, vectorType), alloc));
 
   emitLoops([&](ValueRange majorIvs, ValueRange leadingOffsets,
                 ValueRange majorOffsets, ValueRange minorOffsets,
                 MemRefBoundsCapture &memrefBounds) {
     auto thenBlockBuilder = [&](ValueRange majorIvsPlusOffsets) {
       // Lower to 1-D vector_transfer_write and let recursion handle it.
-      Value loaded1D = std_load(alloc, majorIvs);
-      auto map = AffineMap::getMinorIdentityMap(
-          xferOp.getMemRefType().getRank(), minorRank, xferOp.getContext());
       SmallVector<Value, 8> indexing;
       indexing.reserve(leadingRank + majorRank + minorRank);
       indexing.append(leadingOffsets.begin(), leadingOffsets.end());
       indexing.append(majorIvsPlusOffsets.begin(), majorIvsPlusOffsets.end());
       indexing.append(minorOffsets.begin(), minorOffsets.end());
+      // Lower to 1-D vector_transfer_write and let recursion handle it.
+      Value loaded1D = std_load(alloc, majorIvs);
+      auto map = TransferWriteOp::getTransferMinorIdentityMap(
+          xferOp.getMemRefType(), minorVectorType);
       vector_transfer_write(loaded1D, xferOp.memref(), indexing,
                             AffineMapAttr::get(map));
     };
     // Don't write anything when out of bounds.
     auto elseBlockBuilder = [&](ValueRange majorIvsPlusOffsets) {};
     emitInBounds(majorIvs, majorOffsets, memrefBounds, thenBlockBuilder,
                  elseBlockBuilder);
   });

mlir/lib/Dialect/Affine/Transforms/SuperVectorize.cpp

if (auto load = dyn_cast<AffineLoadOp>(opInst)) {
     auto permutationMap =
         makePermutationMap(opInst, indices, state->strategy->loopToVectorDim);
     if (!permutationMap)
       return LogicalResult::Failure;
     LLVM_DEBUG(dbgs() << "\n[early-vect]+++++ permutationMap: ");
     LLVM_DEBUG(permutationMap.print(dbgs()));
     auto transfer = b.create<vector::TransferReadOp>(
         opInst->getLoc(), vectorType, memoryOp.getMemRef(), indices,
-        AffineMapAttr::get(permutationMap),
-        // TODO(b/144455320) add a proper padding value, not just 0.0 : f32
-        state->folder->create<ConstantFloatOp>(b, opInst->getLoc(),
-                                               APFloat(0.0f), b.getF32Type()));
+        permutationMap);
     state->registerReplacement(opInst, transfer.getOperation());
   } else {
     state->registerTerminal(opInst);
   }
   return success();
 }
 /// end TODO(ntv): Hoist to a VectorizationMaterialize.cpp when appropriate. ///
 

mlir/lib/Dialect/Vector/VectorOps.cpp

if (permutationMap.getNumResults() != vectorType.getRank())
                              "the same rank as the vector type");
   }
 
   if (permutationMap.getNumSymbols() != 0)
     return op->emitOpError("requires permutation_map without symbols");
   if (permutationMap.getNumInputs() != memrefType.getRank())
     return op->emitOpError("requires a permutation_map with input dims of the "
                            "same rank as the memref type");
+
   return success();
 }
 
+namespace impl {
+/// Build the default minor identity map suitable for a vector transfer. This
+/// also handles the case memref<... x vector<...>> -> vector<...> in which the
+/// rank of the identity map must take the vector element type into account.
+static AffineMap getTransferMinorIdentityMap(MemRefType memRefType,
+                                             VectorType vectorType) {
+  int64_t elementVectorRank = 0;
+  VectorType elementVectorType =
+      memRefType.getElementType().dyn_cast<VectorType>();
+  if (elementVectorType)
+    elementVectorRank += elementVectorType.getRank();
+  return AffineMap::getMinorIdentityMap(
+      memRefType.getRank(), vectorType.getRank() - elementVectorRank,
+      memRefType.getContext());
+}
+} // namespace impl
+
 /// Builder that sets permutation map and padding to 'getMinorIdentityMap' and
 /// zero, respectively, by default.
 void TransferReadOp::build(OpBuilder &builder, OperationState &result,
-                           VectorType vector, Value memref,
-                           ValueRange indices) {
-  auto permMap = AffineMap::getMinorIdentityMap(
-      memref.getType().cast<MemRefType>().getRank(), vector.getRank(),
-      builder.getContext());
+                           VectorType vector, Value memref, ValueRange indices,
+                           AffineMap permutationMap) {
   Type elemType = vector.cast<VectorType>().getElementType();
   Value padding = builder.create<ConstantOp>(result.location, elemType,
                                              builder.getZeroAttr(elemType));
+  build(builder, result, vector, memref, indices, permutationMap, padding);
+}
 
-  build(builder, result, vector, memref, indices, permMap, padding);
+/// Builder that sets permutation map (resp. padding) to 'getMinorIdentityMap'
+/// (resp. zero).
+void TransferReadOp::build(OpBuilder &builder, OperationState &result,
+                           VectorType vectorType, Value memref,
+                           ValueRange indices) {
+  build(builder, result, vectorType, memref, indices,
+        getTransferMinorIdentityMap(memref.getType().cast<MemRefType>(),
+                                    vectorType));
+}
+
+/// Build the default minor identity map suitable for a vector transfer. This
+/// also handles the case memref<... x vector<...>> -> vector<...> in which the
+/// rank of the identity map must take the vector element type into account.
+AffineMap TransferReadOp::getTransferMinorIdentityMap(MemRefType memRefType,
+                                                      VectorType vectorType) {
+  return ::impl::getTransferMinorIdentityMap(memRefType, vectorType);
+}
+
+template <typename TransferOp>
+void printTransferAttrs(OpAsmPrinter &p, TransferOp op) {
+  SmallVector<StringRef, 1> elidedAttrs;
+  if (AffineMap::isMinorIdentity(op.permutation_map()))
+    elidedAttrs.push_back(op.getPermutationMapAttrName());
+  p.printOptionalAttrDict(op.getAttrs(), elidedAttrs);
 }
 
 static void print(OpAsmPrinter &p, TransferReadOp op) {
   p << op.getOperationName() << " " << op.memref() << "[" << op.indices()
-    << "], " << op.padding() << " ";
-  p.printOptionalAttrDict(op.getAttrs());
+    << "], " << op.padding();
+  printTransferAttrs(p, op);
   p << " : " << op.getMemRefType() << ", " << op.getVectorType();
 }
 
 static ParseResult parseTransferReadOp(OpAsmParser &parser,
                                        OperationState &result) {
   llvm::SMLoc typesLoc;
   OpAsmParser::OperandType memrefInfo;
   SmallVector<OpAsmParser::OperandType, 8> indexInfo;
   OpAsmParser::OperandType paddingInfo;
   SmallVector<Type, 2> types;
-  // Parsing with support for optional paddingValue.
+  // Parsing with support for paddingValue.
   if (parser.parseOperand(memrefInfo) ||
       parser.parseOperandList(indexInfo, OpAsmParser::Delimiter::Square) ||
       parser.parseComma() || parser.parseOperand(paddingInfo) ||
       parser.parseOptionalAttrDict(result.attributes) ||
       parser.getCurrentLocation(&typesLoc) || parser.parseColonTypeList(types))
     return failure();
   if (types.size() != 2)
     return parser.emitError(typesLoc, "two types required");
   auto indexType = parser.getBuilder().getIndexType();
   MemRefType memRefType = types[0].dyn_cast<MemRefType>();
   if (!memRefType)
     return parser.emitError(typesLoc, "memref type required"), failure();
-  Type vectorType = types[1];
+  VectorType vectorType = types[1].dyn_cast<VectorType>();
+  if (!vectorType)
+    return parser.emitError(typesLoc, "vector type required"), failure();
+  auto permutationAttrName = TransferReadOp::getPermutationMapAttrName();
+  auto attr = result.attributes.get(permutationAttrName);
+  if (!attr) {
+    auto permMap =
+        TransferReadOp::getTransferMinorIdentityMap(memRefType, vectorType);
+    result.attributes.set(permutationAttrName, AffineMapAttr::get(permMap));
+  }
   return failure(
       parser.resolveOperand(memrefInfo, memRefType, result.operands) ||
       parser.resolveOperands(indexInfo, indexType, result.operands) ||
       parser.resolveOperand(paddingInfo, memRefType.getElementType(),
                             result.operands) ||
       parser.addTypeToList(vectorType, result.types));
 }
 
static LogicalResult verify(TransferReadOp op) {
   return verifyPermutationMap(permutationMap,
                               [&op](Twine t) { return op.emitOpError(t); });
 }
 
 //===----------------------------------------------------------------------===//
 // TransferWriteOp
 //===----------------------------------------------------------------------===//
 
-/// Builder that sets permutation map and padding to 'getMinorIdentityMap' by
-/// default.
+/// Build the default minor identity map suitable for a vector transfer. This
+/// also handles the case memref<... x vector<...>> -> vector<...> in which the
+/// rank of the identity map must take the vector element type into account.
+AffineMap TransferWriteOp::getTransferMinorIdentityMap(MemRefType memRefType,
+                                                       VectorType vectorType) {
+  return ::impl::getTransferMinorIdentityMap(memRefType, vectorType);
+}
+
+/// Builder that sets permutation map to 'getMinorIdentityMap'.
 void TransferWriteOp::build(OpBuilder &builder, OperationState &result,
                             Value vector, Value memref, ValueRange indices) {
   auto vectorType = vector.getType().cast<VectorType>();
-  auto permMap = AffineMap::getMinorIdentityMap(
-      memref.getType().cast<MemRefType>().getRank(), vectorType.getRank(),
-      builder.getContext());
+  auto permMap = getTransferMinorIdentityMap(
+      memref.getType().cast<MemRefType>(), vectorType);
   build(builder, result, vector, memref, indices, permMap);
 }
 
+static ParseResult parseTransferWriteOp(OpAsmParser &parser,
+                                        OperationState &result) {
+  llvm::SMLoc typesLoc;
+  OpAsmParser::OperandType vectorInfo, memrefInfo;
+  SmallVector<OpAsmParser::OperandType, 8> indexInfo;
+  SmallVector<Type, 2> types;
+  if (parser.parseOperand(vectorInfo) || parser.parseComma() ||
+      parser.parseOperand(memrefInfo) ||
+      parser.parseOperandList(indexInfo, OpAsmParser::Delimiter::Square) ||
+      parser.parseOptionalAttrDict(result.attributes) ||
+      parser.getCurrentLocation(&typesLoc) || parser.parseColonTypeList(types))
+    return failure();
+  if (types.size() != 2)
+    return parser.emitError(typesLoc, "two types required");
+  auto indexType = parser.getBuilder().getIndexType();
+  VectorType vectorType = types[0].dyn_cast<VectorType>();
+  if (!vectorType)
+    return parser.emitError(typesLoc, "vector type required"), failure();
+  MemRefType memRefType = types[1].dyn_cast<MemRefType>();
+  if (!memRefType)
+    return parser.emitError(typesLoc, "memref type required"), failure();
+  auto permutationAttrName = TransferWriteOp::getPermutationMapAttrName();
+  auto attr = result.attributes.get(permutationAttrName);
+  if (!attr) {
+    auto permMap =
+        TransferWriteOp::getTransferMinorIdentityMap(memRefType, vectorType);
+    result.attributes.set(permutationAttrName, AffineMapAttr::get(permMap));
+  }
+  return failure(
+      parser.resolveOperand(vectorInfo, vectorType, result.operands) ||
+      parser.resolveOperand(memrefInfo, memRefType, result.operands) ||
+      parser.resolveOperands(indexInfo, indexType, result.operands));
+}
+
+static void print(OpAsmPrinter &p, TransferWriteOp op) {
+  p << op.getOperationName() << " " << op.vector() << ", " << op.memref() << "["
+    << op.indices() << "]";
+  printTransferAttrs(p, op);
+  p << " : " << op.getVectorType() << ", " << op.getMemRefType();
+}
+
 static LogicalResult verify(TransferWriteOp op) {
   // Consistency of elemental types in memref and vector.
   MemRefType memrefType = op.getMemRefType();
   VectorType vectorType = op.getVectorType();
   auto permutationMap = op.permutation_map();
 
   if (llvm::size(op.indices()) != memrefType.getRank())
     return op.emitOpError("requires ") << memrefType.getRank() << " indices";

mlir/test/Conversion/AffineToStandard/lower-affine-to-vector.mlir

 // RUN: mlir-opt -lower-affine --split-input-file %s | FileCheck %s
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0) -> (d0)>
 // CHECK-LABEL: func @affine_vector_load
 func @affine_vector_load(%arg0 : index) {
   %0 = alloc() : memref<100xf32>
   affine.for %i0 = 0 to 16 {
     %1 = affine.vector_load %0[%i0 + symbol(%arg0) + 7] : memref<100xf32>, vector<8xf32>
   }
 // CHECK:       %[[buf:.*]] = alloc
 // CHECK:       %[[a:.*]] = addi %{{.*}}, %{{.*}} : index
 // CHECK-NEXT:  %[[c7:.*]] = constant 7 : index
 // CHECK-NEXT:  %[[b:.*]] = addi %[[a]], %[[c7]] : index
 // CHECK-NEXT:  %[[pad:.*]] = constant 0.0
-// CHECK-NEXT:  vector.transfer_read %[[buf]][%[[b]]], %[[pad]] {permutation_map = #[[perm_map]]} : memref<100xf32>, vector<8xf32>
+// CHECK-NEXT:  vector.transfer_read %[[buf]][%[[b]]], %[[pad]] : memref<100xf32>, vector<8xf32>
   return
 }
 
 // -----
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0) -> (d0)>
 // CHECK-LABEL: func @affine_vector_store
 func @affine_vector_store(%arg0 : index) {
   %0 = alloc() : memref<100xf32>
   %1 = constant dense<11.0> : vector<4xf32>
   affine.for %i0 = 0 to 16 {
     affine.vector_store %1, %0[%i0 - symbol(%arg0) + 7] : memref<100xf32>, vector<4xf32>
 }
 // CHECK:       %[[buf:.*]] = alloc
 // CHECK:       %[[val:.*]] = constant dense
 // CHECK:       %[[c_1:.*]] = constant -1 : index
 // CHECK-NEXT:  %[[a:.*]] = muli %arg0, %[[c_1]] : index
 // CHECK-NEXT:  %[[b:.*]] = addi %{{.*}}, %[[a]] : index
 // CHECK-NEXT:  %[[c7:.*]] = constant 7 : index
 // CHECK-NEXT:  %[[c:.*]] = addi %[[b]], %[[c7]] : index
-// CHECK-NEXT:  vector.transfer_write  %[[val]], %[[buf]][%[[c]]] {permutation_map = #[[perm_map]]} : vector<4xf32>, memref<100xf32>
+// CHECK-NEXT:  vector.transfer_write  %[[val]], %[[buf]][%[[c]]] : vector<4xf32>, memref<100xf32>
   return
 }
 
 // -----
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0) -> (d0)>
 // CHECK-LABEL: func @affine_vector_load
 func @affine_vector_load(%arg0 : index) {
   %0 = alloc() : memref<100xf32>
   affine.for %i0 = 0 to 16 {
     %1 = affine.vector_load %0[%i0 + symbol(%arg0) + 7] : memref<100xf32>, vector<8xf32>
   }
 // CHECK:       %[[buf:.*]] = alloc
 // CHECK:       %[[a:.*]] = addi %{{.*}}, %{{.*}} : index
 // CHECK-NEXT:  %[[c7:.*]] = constant 7 : index
 // CHECK-NEXT:  %[[b:.*]] = addi %[[a]], %[[c7]] : index
 // CHECK-NEXT:  %[[pad:.*]] = constant 0.0
-// CHECK-NEXT:  vector.transfer_read %[[buf]][%[[b]]], %[[pad]] {permutation_map = #[[perm_map]]} : memref<100xf32>, vector<8xf32>
+// CHECK-NEXT:  vector.transfer_read %[[buf]][%[[b]]], %[[pad]] : memref<100xf32>, vector<8xf32>
   return
 }
 
 // -----
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0) -> (d0)>
 // CHECK-LABEL: func @affine_vector_store
 func @affine_vector_store(%arg0 : index) {
   %0 = alloc() : memref<100xf32>
   %1 = constant dense<11.0> : vector<4xf32>
   affine.for %i0 = 0 to 16 {
     affine.vector_store %1, %0[%i0 - symbol(%arg0) + 7] : memref<100xf32>, vector<4xf32>
 }
 // CHECK:       %[[buf:.*]] = alloc
 // CHECK:       %[[val:.*]] = constant dense
 // CHECK:       %[[c_1:.*]] = constant -1 : index
 // CHECK-NEXT:  %[[a:.*]] = muli %arg0, %[[c_1]] : index
 // CHECK-NEXT:  %[[b:.*]] = addi %{{.*}}, %[[a]] : index
 // CHECK-NEXT:  %[[c7:.*]] = constant 7 : index
 // CHECK-NEXT:  %[[c:.*]] = addi %[[b]], %[[c7]] : index
-// CHECK-NEXT:  vector.transfer_write  %[[val]], %[[buf]][%[[c]]] {permutation_map = #[[perm_map]]} : vector<4xf32>, memref<100xf32>
+// CHECK-NEXT:  vector.transfer_write  %[[val]], %[[buf]][%[[c]]] : vector<4xf32>, memref<100xf32>
   return
 }
 
 // -----
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0, d1) -> (d0, d1)>
 // CHECK-LABEL: func @vector_load_2d
 func @vector_load_2d() {
   %0 = alloc() : memref<100x100xf32>
   affine.for %i0 = 0 to 16 step 2{
     affine.for %i1 = 0 to 16 step 8 {
       %1 = affine.vector_load %0[%i0, %i1] : memref<100x100xf32>, vector<2x8xf32>
 // CHECK:      %[[buf:.*]] = alloc
 // CHECK:      scf.for %[[i0:.*]] =
 // CHECK:        scf.for %[[i1:.*]] =
 // CHECK-NEXT:     %[[pad:.*]] = constant 0.0
-// CHECK-NEXT:     vector.transfer_read %[[buf]][%[[i0]], %[[i1]]], %[[pad]] {permutation_map = #[[perm_map]]} : memref<100x100xf32>, vector<2x8xf32>
+// CHECK-NEXT:     vector.transfer_read %[[buf]][%[[i0]], %[[i1]]], %[[pad]] : memref<100x100xf32>, vector<2x8xf32>
     }
   }
   return
 }
 
 // -----
 
 // CHECK: #[[perm_map:.*]] = affine_map<(d0, d1) -> (d0, d1)>
 // CHECK-LABEL: func @vector_store_2d
 func @vector_store_2d() {
   %0 = alloc() : memref<100x100xf32>
   %1 = constant dense<11.0> : vector<2x8xf32>
   affine.for %i0 = 0 to 16 step 2{
     affine.for %i1 = 0 to 16 step 8 {
       affine.vector_store %1, %0[%i0, %i1] : memref<100x100xf32>, vector<2x8xf32>
 // CHECK:      %[[buf:.*]] = alloc
 // CHECK:      %[[val:.*]] = constant dense
 // CHECK:      scf.for %[[i0:.*]] =
 // CHECK:        scf.for %[[i1:.*]] =
-// CHECK-NEXT:     vector.transfer_write  %[[val]], %[[buf]][%[[i0]], %[[i1]]] {permutation_map = #[[perm_map]]} : vector<2x8xf32>, memref<100x100xf32>
+// CHECK-NEXT:     vector.transfer_write  %[[val]], %[[buf]][%[[i0]], %[[i1]]] : vector<2x8xf32>, memref<100x100xf32>
     }
   }
   return
 }
 

mlir/test/Conversion/VectorToLoops/vector-to-loops.mlir

func @transfer_read_progressive(%A : memref<?x?xf32>, %base: index) -> vector<17x15xf32> {
   // CHECK-DAG: %[[splat:.*]] = constant dense<7.000000e+00> : vector<15xf32>
   // CHECK-DAG: %[[alloc:.*]] = alloc() : memref<17xvector<15xf32>>
   // CHECK-DAG: %[[dim:.*]] = dim %[[A]], 0 : memref<?x?xf32>
   // CHECK: affine.for %[[I:.*]] = 0 to 17 {
   // CHECK:   %[[add:.*]] = affine.apply #[[MAP0]](%[[I]])[%[[base]]]
   // CHECK:   %[[cmp:.*]] = cmpi "slt", %[[add]], %[[dim]] : index
   // CHECK:   %[[cond1:.*]] = and %[[cmp]], %[[cond0]] : i1
   // CHECK:   scf.if %[[cond1]] {
-  // CHECK:     %[[vec_1d:.*]] = vector.transfer_read %[[A]][%[[add]], %[[base]]], %[[cst]]  {permutation_map = #[[MAP1]]} : memref<?x?xf32>, vector<15xf32>
+  // CHECK:     %[[vec_1d:.*]] = vector.transfer_read %[[A]][%[[add]], %[[base]]], %[[cst]] : memref<?x?xf32>, vector<15xf32>
   // CHECK:     store %[[vec_1d]], %[[alloc]][%[[I]]] : memref<17xvector<15xf32>>
   // CHECK:   } else {
   // CHECK:     store %[[splat]], %[[alloc]][%[[I]]] : memref<17xvector<15xf32>>
   // CHECK:   }
   // CHECK: %[[vmemref:.*]] = vector.type_cast %[[alloc]] : memref<17xvector<15xf32>> to memref<vector<17x15xf32>>
   // CHECK: %[[cst:.*]] = load %[[vmemref]][] : memref<vector<17x15xf32>>
   %f = vector.transfer_read %A[%base, %base], %f7
       {permutation_map = affine_map<(d0, d1) -> (d0, d1)>} :
func @transfer_write_progressive(%A : memref<?x?xf32>, %base: index, %vec: vector<17x15xf32>) {
   // CHECK: store %[[vec]], %[[vmemref]][] : memref<vector<17x15xf32>>
   // CHECK: %[[dim:.*]] = dim %[[A]], 0 : memref<?x?xf32>
   // CHECK: affine.for %[[I:.*]] = 0 to 17 {
   // CHECK:   %[[add:.*]] = affine.apply #[[MAP0]](%[[I]])[%[[base]]]
   // CHECK:   %[[cmp:.*]] = cmpi "slt", %[[add]], %[[dim]] : index
   // CHECK:   %[[cond1:.*]] = and %[[cmp]], %[[cond0]] : i1
   // CHECK:   scf.if %[[cond1]] {
   // CHECK:     %[[vec_1d:.*]] = load %0[%[[I]]] : memref<17xvector<15xf32>>
-  // CHECK:     vector.transfer_write %[[vec_1d]], %[[A]][%[[add]], %[[base]]] {permutation_map = #[[MAP1]]} : vector<15xf32>, memref<?x?xf32>
+  // CHECK:     vector.transfer_write %[[vec_1d]], %[[A]][%[[add]], %[[base]]] : vector<15xf32>, memref<?x?xf32>
   // CHECK:   }
   vector.transfer_write %vec, %A[%base, %base]
       {permutation_map = affine_map<(d0, d1) -> (d0, d1)>} :
     vector<17x15xf32>, memref<?x?xf32>
   return
 }

mlir/test/Dialect/Affine/SuperVectorize/vectorize_1d.mlir

 // RUN: mlir-opt %s -affine-super-vectorize="virtual-vector-size=128 test-fastest-varying=0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1_0:map[0-9]+]] = affine_map<(d0, d1) -> (0)>
-// CHECK: #[[map_proj_d0d1_d1:map[0-9]+]] = affine_map<(d0, d1) -> (d1)>
 
 #map0 = affine_map<(d0) -> (d0)>
 #mapadd1 = affine_map<(d0) -> (d0 + 1)>
 #mapadd2 = affine_map<(d0) -> (d0 + 2)>
 #mapadd3 = affine_map<(d0) -> (d0 + 3)>
 #set0 = affine_set<(i) : (i >= 0)>
 
 // Maps introduced to vectorize fastest varying memory index.
 // CHECK-LABEL: func @vec1d_1
 func @vec1d_1(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: %[[C0:[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %{{.*}}, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %{{.*}}, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %{{.*}}, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
-//
+
 // CHECK: for {{.*}} step 128
 // CHECK-NEXT: %{{.*}} = affine.apply #map0(%[[C0]])
 // CHECK-NEXT: %{{.*}} = affine.apply #map0(%[[C0]])
+// CHECK-NEXT: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-NEXT: {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_0]]} : memref<?x?xf32>, vector<128xf32>
    affine.for %i0 = 0 to %M { // vectorized due to scalar -> vector
      %a0 = affine.load %A[%cst0, %cst0] : memref<?x?xf32>
    }
    return
 }
 
 // CHECK-LABEL: func @vec1d_2
 func @vec1d_2(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: %[[C0:[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %{{.*}}, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %{{.*}}, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %{{.*}}, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
 //
 // CHECK:for [[IV3:%[a-zA-Z0-9]+]] = 0 to [[ARG_M]] step 128
-// CHECK-NEXT:   {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : memref<?x?xf32>, vector<128xf32>
+// CHECK-NEXT: %[[CST:.*]] = constant 0.0{{.*}}: f32
+// CHECK-NEXT: {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %[[CST]] : memref<?x?xf32>, vector<128xf32>
    affine.for %i3 = 0 to %M { // vectorized
      %a3 = affine.load %A[%cst0, %i3] : memref<?x?xf32>
    }
    return
 }
 
 // CHECK-LABEL: func @vec1d_3
 func @vec1d_3(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: %[[C0:[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %arg0, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %arg0, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %arg1, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
 //
 // CHECK:for [[IV8:%[arg0-9]+]] = 0 to [[ARG_M]] step 128
 // CHECK-NEXT:   for [[IV9:%[arg0-9]*]] = 0 to [[ARG_N]] {
 // CHECK-NEXT:   %[[APP9_0:[0-9]+]] = affine.apply {{.*}}([[IV9]], [[IV8]])
 // CHECK-NEXT:   %[[APP9_1:[0-9]+]] = affine.apply {{.*}}([[IV9]], [[IV8]])
-// CHECK-NEXT:   {{.*}} = vector.transfer_read %{{.*}}[%[[APP9_0]], %[[APP9_1]]], %{{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : memref<?x?xf32>, vector<128xf32>
+// CHECK-NEXT:   %[[CST:.*]] = constant 0.0{{.*}}: f32
+// CHECK-NEXT:   {{.*}} = vector.transfer_read %{{.*}}[%[[APP9_0]], %[[APP9_1]]], %[[CST]] : memref<?x?xf32>, vector<128xf32>
    affine.for %i8 = 0 to %M { // vectorized
      affine.for %i9 = 0 to %N {
        %a9 = affine.load %A[%i9, %i8 + %i9] : memref<?x?xf32>
      }
    }
    return
 }
 
 // CHECK-LABEL: func @vector_add_2d
 func @vector_add_2d(%M : index, %N : index) -> f32 {
   %A = alloc (%M, %N) : memref<?x?xf32, 0>
   %B = alloc (%M, %N) : memref<?x?xf32, 0>
   %C = alloc (%M, %N) : memref<?x?xf32, 0>
   %f1 = constant 1.0 : f32
   %f2 = constant 2.0 : f32
   affine.for %i0 = 0 to %M {
     affine.for %i1 = 0 to %N {
-      // CHECK: [[C1:%.*]] = constant dense<1.000000e+00> : vector<128xf32>
-      // CHECK: vector.transfer_write [[C1]], {{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : vector<128xf32>, memref<?x?xf32>
+      // CHECK: %[[C1:.*]] = constant dense<1.000000e+00> : vector<128xf32>
+      // CHECK: vector.transfer_write %[[C1]], {{.*}} : vector<128xf32>, memref<?x?xf32>
       // non-scoped %f1
       affine.store %f1, %A[%i0, %i1] : memref<?x?xf32, 0>
     }
   }
   affine.for %i2 = 0 to %M {
     affine.for %i3 = 0 to %N {
-      // CHECK: [[C3:%.*]] = constant dense<2.000000e+00> : vector<128xf32>
-      // CHECK: vector.transfer_write [[C3]], {{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : vector<128xf32>, memref<?x?xf32>
+      // CHECK: %[[C3:.*]] = constant dense<2.000000e+00> : vector<128xf32>
+      // CHECK: vector.transfer_write %[[C3]], {{.*}} : vector<128xf32>, memref<?x?xf32>
       // non-scoped %f2
       affine.store %f2, %B[%i2, %i3] : memref<?x?xf32, 0>
     }
   }
   affine.for %i4 = 0 to %M {
     affine.for %i5 = 0 to %N {
-      // CHECK: [[A5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : memref<?x?xf32>, vector<128xf32>
-      // CHECK: [[B5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : memref<?x?xf32>, vector<128xf32>
-      // CHECK: [[S5:%.*]] = addf [[A5]], [[B5]] : vector<128xf32>
-      // CHECK: [[SPLAT1:%.*]] = constant dense<1.000000e+00> : vector<128xf32>
-      // CHECK: [[S6:%.*]] = addf [[S5]], [[SPLAT1]] : vector<128xf32>
-      // CHECK: [[SPLAT2:%.*]] = constant dense<2.000000e+00> : vector<128xf32>
-      // CHECK: [[S7:%.*]] = addf [[S5]], [[SPLAT2]] : vector<128xf32>
-      // CHECK: [[S8:%.*]] = addf [[S7]], [[S6]] : vector<128xf32>
-      // CHECK: vector.transfer_write [[S8]], {{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : vector<128xf32>, memref<?x?xf32>
+      // CHECK: %[[A5:.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{[a-zA-Z0-9_]*}} : memref<?x?xf32>, vector<128xf32>
+      // CHECK: %[[B5:.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{[a-zA-Z0-9_]*}} : memref<?x?xf32>, vector<128xf32>
+      // CHECK: %[[S5:.*]] = addf %[[A5]], %[[B5]] : vector<128xf32>
+      // CHECK: %[[SPLAT1:.*]] = constant dense<1.000000e+00> : vector<128xf32>
+      // CHECK: %[[S6:.*]] = addf %[[S5]], %[[SPLAT1]] : vector<128xf32>
+      // CHECK: %[[SPLAT2:.*]] = constant dense<2.000000e+00> : vector<128xf32>
+      // CHECK: %[[S7:.*]] = addf %[[S5]], %[[SPLAT2]] : vector<128xf32>
+      // CHECK: %[[S8:.*]] = addf %[[S7]], %[[S6]] : vector<128xf32>
+      // CHECK: vector.transfer_write %[[S8]], {{.*}} : vector<128xf32>, memref<?x?xf32>
       %a5 = affine.load %A[%i4, %i5] : memref<?x?xf32, 0>
       %b5 = affine.load %B[%i4, %i5] : memref<?x?xf32, 0>
       %s5 = addf %a5, %b5 : f32
       // non-scoped %f1
       %s6 = addf %s5, %f1 : f32
       // non-scoped %f2
       %s7 = addf %s5, %f2 : f32
       // diamond dependency.
// CHECK:   affine.for %{{.*}}{{[0-9]*}} = 0 to [[ARG_M]] {
    affine.for %i2 = 0 to %M { // not vectorized, would vectorize with --test-fastest-varying=1
      %a2 = affine.load %A[%i2, %cst0] : memref<?x?xf32>
    }
    return
 }
 
 // CHECK-LABEL: func @vec_rejected_3
 func @vec_rejected_3(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: [[C0:%[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %{{.*}}, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %{{.*}}, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %{{.*}}, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
 //
 // CHECK:for [[IV4:%[arg0-9]+]] = 0 to [[ARG_M]] step 128 {
 // CHECK-NEXT:   for [[IV5:%[arg0-9]*]] = 0 to [[ARG_N]] {
-// CHECK-NEXT:   {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_d1]]} : memref<?x?xf32>, vector<128xf32>
+// CHECK-NEXT:     %{{.*}} = constant 0.0{{.*}}: f32
+// CHECK-NEXT:     {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{[a-zA-Z0-9_]*}} : memref<?x?xf32>, vector<128xf32>
    affine.for %i4 = 0 to %M { // vectorized
      affine.for %i5 = 0 to %N { // not vectorized, would vectorize with --test-fastest-varying=1
        %a5 = affine.load %A[%i5, %i4] : memref<?x?xf32>
      }
    }
    return
 }
 
affine.for %i16 = 0 to %M { // not vectorized, can't vectorize a vector load
      %a16 = alloc(%M) : memref<?xvector<2xf32>>
      %l16 = affine.load %a16[%i16] : memref<?xvector<2xf32>>
    }
    return
 }
 
 // CHECK-LABEL: func @vec_rejected_8
 func @vec_rejected_8(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: %[[C0:[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %{{.*}}, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %{{.*}}, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %{{.*}}, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
 //
 // CHECK: affine.for %{{.*}}{{[0-9]*}} = 0 to %{{[0-9]*}} {
 // CHECK:   for [[IV18:%[a-zA-Z0-9]+]] = 0 to [[ARG_M]] step 128
 // CHECK:     %{{.*}} = affine.apply #map0(%{{.*}})
 // CHECK:     %{{.*}} = affine.apply #map0(%{{.*}})
+// CHECK:     %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK:     {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_0]]} : memref<?x?xf32>, vector<128xf32>
    affine.for %i17 = 0 to %M { // not vectorized, the 1-D pattern that matched %{{.*}} in DFS post-order prevents vectorizing %{{.*}}
      affine.for %i18 = 0 to %M { // vectorized due to scalar -> vector
        %a18 = affine.load %A[%cst0, %cst0] : memref<?x?xf32>
      }
    }
    return
 }
 
 // CHECK-LABEL: func @vec_rejected_9
 func @vec_rejected_9(%A : memref<?x?xf32>, %B : memref<?x?x?xf32>) {
-// CHECK-DAG: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-DAG: %[[C0:[a-z0-9_]+]] = constant 0 : index
 // CHECK-DAG: [[ARG_M:%[0-9]+]] = dim %{{.*}}, 0 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_N:%[0-9]+]] = dim %{{.*}}, 1 : memref<?x?xf32>
 // CHECK-DAG: [[ARG_P:%[0-9]+]] = dim %{{.*}}, 2 : memref<?x?x?xf32>
    %M = dim %A, 0 : memref<?x?xf32>
    %N = dim %A, 1 : memref<?x?xf32>
    %P = dim %B, 2 : memref<?x?x?xf32>
    %cst0 = constant 0 : index
 //
 // CHECK: affine.for %{{.*}}{{[0-9]*}} = 0 to %{{[0-9]*}} {
 // CHECK:   for [[IV18:%[a-zA-Z0-9]+]] = 0 to [[ARG_M]] step 128
 // CHECK:      %{{.*}} = affine.apply #map0(%{{.*}})
 // CHECK-NEXT: %{{.*}} = affine.apply #map0(%{{.*}})
+// CHECK-NEXT: %{{.*}} = constant 0.0{{.*}}: f32
 // CHECK-NEXT: {{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1_0]]} : memref<?x?xf32>, vector<128xf32>
    affine.for %i17 = 0 to %M { // not vectorized, the 1-D pattern that matched %i18 in DFS post-order prevents vectorizing %{{.*}}
      affine.for %i18 = 0 to %M { // vectorized due to scalar -> vector
        %a18 = affine.load %A[%cst0, %cst0] : memref<?x?xf32>
      }
    }
    return
 }

mlir/test/Dialect/Affine/SuperVectorize/vectorize_2d.mlir

func @vector_add_2d(%M : index, %N : index) -> f32 {
   %A = alloc (%M, %N) : memref<?x?xf32, 0>
   %B = alloc (%M, %N) : memref<?x?xf32, 0>
   %C = alloc (%M, %N) : memref<?x?xf32, 0>
   %f1 = constant 1.0 : f32
   %f2 = constant 2.0 : f32
   affine.for %i0 = 0 to %M {
     affine.for %i1 = 0 to %N {
       // CHECK: [[C1:%.*]] = constant dense<1.000000e+00> : vector<32x256xf32>
-      // CHECK: vector.transfer_write [[C1]], {{.*}} {permutation_map = #[[map_id2]]} : vector<32x256xf32>, memref<?x?xf32>
+      // CHECK: vector.transfer_write [[C1]], {{.*}} : vector<32x256xf32>, memref<?x?xf32>
       // non-scoped %f1
       affine.store %f1, %A[%i0, %i1] : memref<?x?xf32, 0>
     }
   }
   affine.for %i2 = 0 to %M {
     affine.for %i3 = 0 to %N {
       // CHECK: [[C3:%.*]] = constant dense<2.000000e+00> : vector<32x256xf32>
-      // CHECK: vector.transfer_write [[C3]], {{.*}} {permutation_map = #[[map_id2]]}  : vector<32x256xf32>, memref<?x?xf32>
+      // CHECK: vector.transfer_write [[C3]], {{.*}}  : vector<32x256xf32>, memref<?x?xf32>
       // non-scoped %f2
       affine.store %f2, %B[%i2, %i3] : memref<?x?xf32, 0>
     }
   }
   affine.for %i4 = 0 to %M {
     affine.for %i5 = 0 to %N {
-      // CHECK: [[A5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} {permutation_map = #[[map_id2]]} : memref<?x?xf32>, vector<32x256xf32>
-      // CHECK: [[B5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} {permutation_map = #[[map_id2]]} : memref<?x?xf32>, vector<32x256xf32>
+      // CHECK: [[A5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} : memref<?x?xf32>, vector<32x256xf32>
+      // CHECK: [[B5:%.*]] = vector.transfer_read %{{.*}}[{{.*}}], %{{.*}} : memref<?x?xf32>, vector<32x256xf32>
       // CHECK: [[S5:%.*]] = addf [[A5]], [[B5]] : vector<32x256xf32>
       // CHECK: [[SPLAT1:%.*]] = constant dense<1.000000e+00> : vector<32x256xf32>
       // CHECK: [[S6:%.*]] = addf [[S5]], [[SPLAT1]] : vector<32x256xf32>
       // CHECK: [[SPLAT2:%.*]] = constant dense<2.000000e+00> : vector<32x256xf32>
       // CHECK: [[S7:%.*]] = addf [[S5]], [[SPLAT2]] : vector<32x256xf32>
       // CHECK: [[S8:%.*]] = addf [[S7]], [[S6]] : vector<32x256xf32>
-      // CHECK: vector.transfer_write [[S8]], {{.*}} {permutation_map = #[[map_id2]]} : vector<32x256xf32>, memref<?x?xf32>
+      // CHECK: vector.transfer_write [[S8]], {{.*}} : vector<32x256xf32>, memref<?x?xf32>
       //
       %a5 = affine.load %A[%i4, %i5] : memref<?x?xf32, 0>
       %b5 = affine.load %B[%i4, %i5] : memref<?x?xf32, 0>
       %s5 = addf %a5, %b5 : f32
       // non-scoped %f1
       %s6 = addf %s5, %f1 : f32
       // non-scoped %f2
       %s7 = addf %s5, %f2 : f32
func @vectorize_matmul(%arg0: memref<?x?xf32>, %arg1: memref<?x?xf32>, %arg2: memref<?x?xf32>) {
   %N = dim %arg2, 1 : memref<?x?xf32>
   //      VECT: %[[C0:.*]] = constant 0 : index
   // VECT-NEXT: %[[M:.*]] = dim %{{.*}}, 0 : memref<?x?xf32>
   // VECT-NEXT: %[[K:.*]] = dim %{{.*}}, 1 : memref<?x?xf32>
   // VECT-NEXT: %[[N:.*]] = dim %{{.*}}, 1 : memref<?x?xf32>
   //      VECT: {{.*}} #[[map_id1]](%[[M]]) step 4 {
   // VECT-NEXT:   {{.*}} #[[map_id1]](%[[N]]) step 8 {
   //      VECT:     %[[VC0:.*]] = constant dense<0.000000e+00> : vector<4x8xf32>
-  // VECT-NEXT:     vector.transfer_write %[[VC0]], %{{.*}}[%{{.*}}, %{{.*}}] {permutation_map = #[[map_id2]]} : vector<4x8xf32>, memref<?x?xf32>
+  // VECT-NEXT:     vector.transfer_write %[[VC0]], %{{.*}}[%{{.*}}, %{{.*}}] : vector<4x8xf32>, memref<?x?xf32>
   affine.for %i0 = affine_map<(d0) -> (d0)>(%c0) to affine_map<(d0) -> (d0)>(%M) {
     affine.for %i1 = affine_map<(d0) -> (d0)>(%c0) to affine_map<(d0) -> (d0)>(%N) {
       %cst = constant 0.000000e+00 : f32
       affine.store %cst, %arg2[%i0, %i1] : memref<?x?xf32>
     }
   }
   //      VECT:  affine.for %[[I2:.*]] = #[[map_id1]](%[[C0]]) to #[[map_id1]](%[[M]]) step 4 {
   // VECT-NEXT:    affine.for %[[I3:.*]] = #[[map_id1]](%[[C0]]) to #[[map_id1]](%[[N]]) step 8 {
   // VECT-NEXT:      affine.for %[[I4:.*]] = #map5(%[[C0]]) to #[[map_id1]](%[[K]]) {
-  // VECT-NEXT:        %[[A:.*]] = vector.transfer_read %{{.*}}[%[[I4]], %[[I3]]], %{{.*}} {permutation_map = #[[map_proj_d0d1_zerod1]]} : memref<?x?xf32>, vector<4x8xf32>
-  // VECT-NEXT:        %[[B:.*]] = vector.transfer_read %{{.*}}[%[[I2]], %[[I4]]], %{{.*}} {permutation_map = #[[map_proj_d0d1_d0zero]]} : memref<?x?xf32>, vector<4x8xf32>
+  //      VECT:        %[[A:.*]] = vector.transfer_read %{{.*}}[%[[I4]], %[[I3]]], %{{.*}} {permutation_map = #[[map_proj_d0d1_zerod1]]} : memref<?x?xf32>, vector<4x8xf32>
+  //      VECT:        %[[B:.*]] = vector.transfer_read %{{.*}}[%[[I2]], %[[I4]]], %{{.*}} {permutation_map = #[[map_proj_d0d1_d0zero]]} : memref<?x?xf32>, vector<4x8xf32>
   // VECT-NEXT:        %[[C:.*]] = mulf %[[B]], %[[A]] : vector<4x8xf32>
-  // VECT-NEXT:        %[[D:.*]] = vector.transfer_read %{{.*}}[%[[I2]], %[[I3]]], %{{.*}} {permutation_map = #[[map_id2]]} : memref<?x?xf32>, vector<4x8xf32>
+  //      VECT:        %[[D:.*]] = vector.transfer_read %{{.*}}[%[[I2]], %[[I3]]], %{{.*}} : memref<?x?xf32>, vector<4x8xf32>
   // VECT-NEXT:        %[[E:.*]] = addf %[[D]], %[[C]] : vector<4x8xf32>
-  // VECT-NEXT:        vector.transfer_write %[[E]], %{{.*}}[%[[I2]], %[[I3]]] {permutation_map = #[[map_id2]]} : vector<4x8xf32>, memref<?x?xf32>
+  //      VECT:        vector.transfer_write %[[E]], %{{.*}}[%[[I2]], %[[I3]]] : vector<4x8xf32>, memref<?x?xf32>
   affine.for %i2 = affine_map<(d0) -> (d0)>(%c0) to affine_map<(d0) -> (d0)>(%M) {
     affine.for %i3 = affine_map<(d0) -> (d0)>(%c0) to affine_map<(d0) -> (d0)>(%N) {
       affine.for %i4 = affine_map<(d0) -> (d0)>(%c0) to affine_map<(d0) -> (d0)>(%K) {
         %6 = affine.load %arg1[%i4, %i3] : memref<?x?xf32>
         %7 = affine.load %arg0[%i2, %i4] : memref<?x?xf32>
         %8 = mulf %7, %6 : f32
         %9 = affine.load %arg2[%i2, %i3] : memref<?x?xf32>
         %10 = addf %9, %8 : f32
         affine.store %10, %arg2[%i2, %i3] : memref<?x?xf32>
       }
     }
   }
   return
 }

mlir/test/Dialect/Affine/SuperVectorize/vectorize_3d.mlir

 // RUN: mlir-opt %s -affine-super-vectorize="virtual-vector-size=32,64,256 test-fastest-varying=2,1,0" | FileCheck %s
 
 // Permutation maps used in vectorization.
 // CHECK: #[[map_proj_d0d1d2_d0d1d2:map[0-9]+]] = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
 
 func @vec3d(%A : memref<?x?x?xf32>) {
    %0 = dim %A, 0 : memref<?x?x?xf32>
    %1 = dim %A, 1 : memref<?x?x?xf32>
    %2 = dim %A, 2 : memref<?x?x?xf32>
    // CHECK: affine.for %{{.*}} = 0 to %{{.*}} {
    // CHECK:   affine.for %{{.*}} = 0 to %{{.*}} {
    // CHECK:     affine.for %{{.*}} = 0 to %{{.*}} step 32 {
    // CHECK:       affine.for %{{.*}} = 0 to %{{.*}} step 64 {
    // CHECK:         affine.for %{{.*}} = 0 to %{{.*}} step 256 {
-   // CHECK:           %{{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}], %{{.*}} {permutation_map = #[[map_proj_d0d1d2_d0d1d2]]} : memref<?x?x?xf32>, vector<32x64x256xf32>
+   // CHECK:           %{{.*}} = vector.transfer_read %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}], %{{.*}} : memref<?x?x?xf32>, vector<32x64x256xf32>
    affine.for %t0 = 0 to %0 {
      affine.for %t1 = 0 to %0 {
        affine.for %i0 = 0 to %0 {
          affine.for %i1 = 0 to %1 {
            affine.for %i2 = 0 to %2 {
              %a2 = affine.load %A[%i0, %i1, %i2] : memref<?x?x?xf32>
            }
          }
        }
      }
    }
    return
 }

mlir/test/Dialect/Vector/invalid.mlir

func @test_vector.transfer_read(%arg0: memref<?x?xf32>) {
   %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
func @test_vector.transfer_write(%arg0: memref<?x?xf32>) {
   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

mlir/test/Dialect/Vector/ops.mlir

func @vector_transfer_ops(%arg0: memref<?x?xf32>,
   // 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>
+  // CHECK: vector.transfer_read %{{.*}}[%[[C3]], %[[C3]]], %{{.*}} : 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>>
+  // CHECK: vector.transfer_write %{{.*}}, %{{.*}}[%[[C3]], %[[C3]]] : 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>

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

 
 // 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: %[[VTR0:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} : memref<4x2xf32>, vector<2x2xf32>
+// CHECK-NEXT: %[[VTR1:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C0]]], %{{.*}} : 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: %[[VTR2:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} : memref<2x4xf32>, vector<2x2xf32>
+// CHECK-NEXT: %[[VTR3:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C2]]], %{{.*}} : 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: %[[VTR4:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]]], %{{.*}} : memref<4x4xf32>, vector<2x2xf32>
+// CHECK-NEXT: %[[VTR5:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C2]]], %{{.*}} : memref<4x4xf32>, vector<2x2xf32>
+// CHECK-NEXT: %[[VTR6:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C0]]], %{{.*}} : memref<4x4xf32>, vector<2x2xf32>
+// CHECK-NEXT: %[[VTR7:.*]] = vector.transfer_read %{{.*}}[%[[C2]], %[[C2]]], %{{.*}} : 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: vector.transfer_write %[[R0]], %{{.*}}[%[[C0]], %[[C0]]] : vector<2x2xf32>, memref<4x4xf32>
+// CHECK-NEXT: vector.transfer_write %[[R1]], %{{.*}}[%[[C0]], %[[C2]]] : vector<2x2xf32>, memref<4x4xf32>
+// CHECK-NEXT: vector.transfer_write %[[R2]], %{{.*}}[%[[C2]], %[[C0]]] : vector<2x2xf32>, memref<4x4xf32>
+// CHECK-NEXT: vector.transfer_write %[[R3]], %{{.*}}[%[[C2]], %[[C2]]] : 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
 
func @cancelling_shape_cast_ops(%arg0 : vector<2x4xf32>) -> vector<2x4xf32> {
   %0 = vector.shape_cast %arg0 : vector<2x4xf32> to vector<8xf32>
   %1 = vector.shape_cast %0 : vector<8xf32> to vector<2x4xf32>
   return %1 : vector<2x4xf32>
 }
 
 // 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>>
+//      CHECK: %[[VTR0:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C0]], %[[C0]]], %{{.*}} : memref<6x2x1xvector<2x4xf32>>, vector<1x1x2x4xf32>
+// CHECK-NEXT: %[[VTR1:.*]] = vector.transfer_read %{{.*}}[%[[C0]], %[[C1]], %[[C0]]], %{{.*}} : memref<6x2x1xvector<2x4xf32>>, vector<1x1x2x4xf32>
+// CHECK-NEXT: vector.transfer_write %[[VTR0]], %{{.*}}[%[[C0]], %[[C0]], %[[C0]]] : vector<1x1x2x4xf32>, memref<6x2x1xvector<2x4xf32>>
+// CHECK-NEXT: vector.transfer_write %[[VTR1]], %{{.*}}[%[[C0]], %[[C1]], %[[C0]]] : 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>>