[mlir][Linalg] NFC - Cleanup explicitly instantiated paterns 2/n - Loops.cpp

[nicolasvasilache]

Summary

This revision belongs to a series of patches that reduce reliance of Linalg transformations on templated rewrite and conversion patterns.
Instead, this uses a MatchAnyTag pattern for the vast majority of cases and dispatches internally.

[pifon2a]

Nice, it became much cleaner with llvm::TypeSwitch.

[mravishankar]

Nice cleanup! Concerned about drop in coverage though.

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

385

Nit: Crux of this method and the one below are the same. Can we just have a emitScalarPoolingMinMaxOpImplementation and combine the logic (the explicit instantiation would be just calling this impl function). But maybe not be worth it, so a suggestion that can be ignored.

523

TIL TypeSwitch! This looks great! Thanks!

mlir/test/Dialect/Linalg/loops.mlir

2

Does this need to be split. Having the entire command line in one line looks fine to me.

3

Does R_UN work? Will this not stop the test from executing?

6

Is this actually running the test?

81

This seems to be dropping coverage a lot. For example, the pooling ops, conv ops, etc. arent being tests. Not sure whats happening here?

[nicolasvasilache]

Revert spurious test file changes.

[mravishankar]

Thanks!

[nicolasvasilache]

Factor out common code.

[nicolasvasilache]

Rebase

[nicolasvasilache]

This was landed as c303d9b394427e93aa772d543426715b24f98fd1

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

InterfaceMethod<
       /*retTy=*/"std::string",
       /*methodName=*/"getLibraryCallName",
       /*args=*/(ins),
       /*methodBody=*/"",
       /*defaultImplementation=*/[{
         return $_op.getLibraryCallName();
       }]
     >,
+    InterfaceMethod<
+      /*desc=*/[{
+        Return op region.
+      }],
+      /*retTy=*/"Region&",
+      /*methodName=*/"region",
+      /*args=*/(ins),
+      /*methodBody=*/"",
+      /*defaultImplementation=*/[{
+        return $_op.region();
+      }]
+    >,
 
     //===------------------------------------------------------------------===//
     // Other static interface methods.
     //===------------------------------------------------------------------===//
     StaticInterfaceMethod<
       /*desc=*/[{
         Create an operation of the current type with the given location,
         operands, and attributes.

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

 #include "mlir/Dialect/StandardOps/EDSC/Intrinsics.h"
 #include "mlir/IR/AffineExpr.h"
 #include "mlir/IR/AffineMap.h"
 #include "mlir/IR/BlockAndValueMapping.h"
 #include "mlir/Support/LLVM.h"
 #include "mlir/Transforms/DialectConversion.h"
 #include "mlir/Transforms/FoldUtils.h"
 
+#include "llvm/ADT/TypeSwitch.h"
+
 using namespace mlir;
 using namespace mlir::edsc;
 using namespace mlir::edsc::intrinsics;
 using namespace mlir::linalg;
 
 using edsc::op::operator+;
 
 static SmallVector<Value, 8> makeCanonicalAffineApplies(OpBuilder &b,
static InputAndOutputIndices getInputAndOutputIndices(ArrayRef<Value> allIvs,
   auto mapsRange = op.indexing_maps().template getAsRange<AffineMapAttr>();
   auto maps = llvm::to_vector<8>(
       llvm::map_range(mapsRange, [](AffineMapAttr a) { return a.getValue(); }));
   return InputAndOutputIndices{
       makeCanonicalAffineApplies(b, loc, maps[0], allIvs),
       makeCanonicalAffineApplies(b, loc, maps[2], allIvs)};
 }
 
-namespace {
-
 /// Emits the MLIR for the scalar part of the generic op by:
 ///   1. Emitting load ops for each input and output view in order. This is
 ///      achieved by applying the appropriate input or output map to the
 ///      enclosing induction variables.
 ///   2. Emitting a call to `op.fun()` that takes as arguments the scalars
 ///      from point 1. above.
 ///   3. Emitting store ops to store the results of 2. to the output
 ///      views.

 ///          store %14#0, %arg1[%i, %j, %k] :
 ///            memref<?x?x?Xf32, stride_specification>
 ///          store %14#1, %arg2[%i, %k, %j] :
 ///            memref<?x?x?Xf32, stride_specification>
 ///       }
 ///      }
 ///    }
 /// ```
-// TODO: need a LinalgStructuredOpInterface.
-template <typename IndexedValueType, typename LinalgStructuredOpType>
-void emitScalarImplementation(ArrayRef<Value> allIvs,
-                              LinalgStructuredOpType linalgOp) {
+template <typename IndexedValueType>
+static void emitScalarImplementation(ArrayRef<Value> allIvs,
+                                     LinalgOp linalgOp) {
   assert(linalgOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   auto &b = ScopedContext::getBuilderRef();
   auto loc = ScopedContext::getLocation();
   unsigned nInputs = linalgOp.getNumInputs();
   unsigned nOutputs = linalgOp.getNumOutputs();
   SmallVector<Value, 4> indexedValues;
   indexedValues.reserve(nInputs + nOutputs);
 
   auto attr = linalgOp.template getAttrOfType<IntegerAttr>("symbol_source");
   auto allIvsPlusDims = SmallVector<Value, 4>(allIvs.begin(), allIvs.end());
   if (attr) {
-    auto operand = linalgOp.getOperand(attr.getInt());
+    auto operand = linalgOp.getOperation()->getOperand(attr.getInt());
     auto shapedType = operand.getType().template cast<ShapedType>();
     allIvsPlusDims.reserve(allIvs.size() + shapedType.getRank());
     for (unsigned idx = 0, e = shapedType.getRank(); idx < e; ++idx)
       allIvsPlusDims.push_back(b.create<DimOp>(loc, operand, idx));
   }
 
   // TODO: Avoid the loads if the corresponding argument of the
   // region has no uses.
indexing.push_back(makeCanonicalAffineApplies(
         b, loc, linalgOp.getOutputIndexingMap(i), allIvsPlusDims));
     outputBuffers.push_back(linalgOp.getOutputBuffer(i));
   }
   inlineRegionAndEmitStore<IndexedValueType>(linalgOp, indexedValues, indexing,
                                              outputBuffers);
 }
 
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, CopyOp copyOp) {
+static void emitScalarImplementation(ArrayRef<Value> allIvs, CopyOp copyOp) {
   assert(copyOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   auto nPar = copyOp.getNumParallelLoops();
   assert(nPar == allIvs.size());
   auto inputIvs =
       permuteIvs(allIvs.take_front(nPar), copyOp.inputPermutation());
   auto outputIvs =
       permuteIvs(allIvs.take_front(nPar), copyOp.outputPermutation());
   SmallVector<Value, 8> iivs(inputIvs.begin(), inputIvs.end());
   SmallVector<Value, 8> oivs(outputIvs.begin(), outputIvs.end());
   IndexedValueType O(copyOp.getOutputBuffer(0)), I(copyOp.getInput(0));
   // Emit the proper scalar assignment, whether we are dealing with a 0-D or
   // an n-D loop nest; with or without permutations.
   // clang-format off
     nPar > 0 ? O(oivs) = I(iivs) :
                O() = I();
   // clang-format on
 }
 
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, FillOp fillOp) {
+static void emitScalarImplementation(ArrayRef<Value> allIvs, FillOp fillOp) {
   assert(fillOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   auto nPar = fillOp.getNumParallelLoops();
   assert(nPar == allIvs.size());
   auto ivs = SmallVector<Value, 4>(allIvs.begin(), allIvs.begin() + nPar);
   IndexedValueType O(fillOp.getOutputBuffer(0));
   // Emit the proper scalar assignment, whether we are dealing with a 0-D or
   // an n-D loop nest; with or without permutations.
   nPar > 0 ? O(ivs) = fillOp.value() : O() = fillOp.value();
 }
 
 template <typename IndexedValueType>
-Value getConvOpInput(ConvOp convOp, StdIndexedValue im,
+static Value getConvOpInput(ConvOp convOp, StdIndexedValue im,
                             MutableArrayRef<Value> imIdx) {
   // TODO: add a level of indirection to linalg.generic.
   if (!convOp.padding())
     return im(imIdx);
 
   auto *context = ScopedContext::getContext();
   Value zeroIndex = std_constant_index(0);
   SmallVector<Value, 8> conds;
   SmallVector<Value, 8> clampedImIdx;
if (hasPadding(convOp)) {
     O(oIdx) += F(fIdx) * paddedInput;
   } else {
     IndexedValueType I(convOp.input());
     O(oIdx) += F(fIdx) * I(imIdx);
   }
 }
 
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMaxOp op) {
+static void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMaxOp op) {
   InputAndOutputIndices indices = getInputAndOutputIndices(allIvs, op);
   // Emit scalar form.
   IndexedValueType output(op.output());
   IndexedValueType input(op.input());
   Value lhs = output(indices.outputs);
   Value rhs = input(indices.inputs);
   using edsc::op::sgt;
   Value maxValue = std_select(sgt(lhs, rhs), lhs, rhs);
   output(indices.outputs) = maxValue;
 }
 
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMinOp op) {
+static void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingMinOp op) {
   InputAndOutputIndices indices = getInputAndOutputIndices(allIvs, op);
   // Emit scalar form.
   IndexedValueType output(op.output());
   IndexedValueType input(op.input());
   Value lhs = output(indices.outputs);
   Value rhs = input(indices.inputs);
   using edsc::op::slt;
   Value minValue = std_select(slt(lhs, rhs), lhs, rhs);
   output(indices.outputs) = minValue;
 }
+
 template <typename IndexedValueType>
-void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingSumOp op) {
+static void emitScalarImplementation(ArrayRef<Value> allIvs, PoolingSumOp op) {
   auto indices = getInputAndOutputIndices(allIvs, op);
   IndexedValueType input(op.input()), output(op.output());
 
   // Emit scalar form.
   output(indices.outputs) += input(indices.inputs);
 }
+
 /// Emits the MLIR for the scalar part of the indexed generic op by:
 ///   1. Emitting load ops for each input and output view in order. This is
 ///      achieved by applying the appropriate input or output map to the
 ///      enclosing induction variables.
 ///   2. Emitting a call to `op.fun()` that takes as arguments the induction
 ///      variables and the scalars from point 1. above.
 ///   3. Emitting store ops to store the results of 2. to the output views.
 ///
for (unsigned i = 0; i < nOutputs; ++i) {
     indexing.push_back(makeCanonicalAffineApplies(
         b, loc, indexedGenericOp.getOutputIndexingMap(i), allIvs));
     outputBuffers.push_back(indexedGenericOp.getOutputBuffer(i));
   }
   inlineRegionAndEmitStore<IndexedValueType>(indexedGenericOp, indexedValues,
                                              indexing, outputBuffers);
 }
 
-template <typename LoopTy, typename ConcreteOpTy>
-Optional<LinalgLoops> linalgOpToLoopsImpl(Operation *op, OpBuilder &builder) {
+template <typename LoopTy>
+static Optional<LinalgLoops> linalgOpToLoopsImpl(Operation *op,
+                                                 OpBuilder &builder) {
   using IndexedValueTy = typename GenerateLoopNest<LoopTy>::IndexedValueTy;
 
   ScopedContext scope(builder, op->getLoc());
 
   // The flattened loopToOperandRangesMaps is expected to be an invertible
   // permutation map (which is asserted in the inverse calculation).
-  auto linalgOp = cast<ConcreteOpTy>(op);
+  auto linalgOp = cast<LinalgOp>(op);
   assert(linalgOp.hasBufferSemantics() &&
          "expected linalg op with buffer semantics");
   auto mapsRange =
       linalgOp.indexing_maps().template getAsRange<AffineMapAttr>();
   auto maps = llvm::to_vector<8>(
       llvm::map_range(mapsRange, [](AffineMapAttr a) { return a.getValue(); }));
   SmallVector<Value, 8> sizes = getShape(builder, linalgOp);
   AffineMap map = concatAffineMaps(maps);
   auto loopRanges = emitLoopRanges(scope.getBuilderRef(), scope.getLocation(),
                                    map, getShape(builder, linalgOp));
   SmallVector<Value, 4> allIvs;
   GenerateLoopNest<LoopTy>::doit(
       loopRanges, /*iterInitArgs*/ {}, linalgOp.iterator_types().getValue(),
       [&](ValueRange ivs, ValueRange iterArgs) -> scf::ValueVector {
         assert(iterArgs.empty() && "unexpected iterArgs");
         allIvs.append(ivs.begin(), ivs.end());
-        emitScalarImplementation<IndexedValueTy>(allIvs, linalgOp);
+        llvm::TypeSwitch<Operation *>(op)
+            .Case<CopyOp, FillOp, ConvOp, PoolingMaxOp, PoolingMinOp,
+                  PoolingSumOp, IndexedGenericOp, LinalgOp>([&](auto op) {
+              emitScalarImplementation<IndexedValueTy>(allIvs, op);
+            })
+            .Default([&](Operation *op) { assert(false && "unexpected op"); });
         return scf::ValueVector{};
       });
   // Number of loop ops might be different from the number of ivs since some
   // loops like affine.parallel and scf.parallel have multiple ivs.
   llvm::SetVector<Operation *> loopSet;
   for (Value iv : allIvs) {
     if (!iv)
       return {};
     // The induction variable is a block argument of the entry block of the
     // loop operation.
     BlockArgument ivVal = iv.dyn_cast<BlockArgument>();
     if (!ivVal)
       return {};
     loopSet.insert(ivVal.getOwner()->getParentOp());
   }
   LinalgLoops loops(loopSet.begin(), loopSet.end());
   return loops;
 }
 
-template <typename LoopType, typename ConcreteOp>
+namespace {
+template <typename LoopType>
 class LinalgRewritePattern : public RewritePattern {
 public:
-  explicit LinalgRewritePattern(MLIRContext *context)
-      : RewritePattern(ConcreteOp::getOperationName(), 1, context) {}
+  LinalgRewritePattern() : RewritePattern(/*benefit=*/1, MatchAnyOpTypeTag()) {}
 
   LogicalResult matchAndRewrite(Operation *op,
                                 PatternRewriter &rewriter) const override {
-    if (!linalgOpToLoopsImpl<LoopType, ConcreteOp>(op, rewriter))
+    if (!isa<LinalgOp>(op))
+      return failure();
+    if (!linalgOpToLoopsImpl<LoopType>(op, rewriter))
       return failure();
     rewriter.eraseOp(op);
     return success();
   }
 };
 
-template <typename LoopType, typename ConcreteOp>
-void insertOnePattern(OwningRewritePatternList &patterns, MLIRContext *ctx) {
-  patterns.insert<LinalgRewritePattern<LoopType, ConcreteOp>>(ctx);
-}
+struct FoldAffineOp;
+} // namespace
 
-template <typename LoopType, typename... Args>
-void insertPatterns(OwningRewritePatternList &patterns, MLIRContext *ctx) {
-  (void)std::initializer_list<int>{
-      0, (insertOnePattern<LoopType, Args>(patterns, ctx), 0)...};
+template <typename LoopType>
+static void lowerLinalgToLoopsImpl(FuncOp funcOp, MLIRContext *context) {
+  OwningRewritePatternList patterns;
+  patterns.insert<LinalgRewritePattern<LoopType>>();
+  DimOp::getCanonicalizationPatterns(patterns, context);
+  AffineApplyOp::getCanonicalizationPatterns(patterns, context);
+  patterns.insert<FoldAffineOp>(context);
+  // Just apply the patterns greedily.
+  applyPatternsAndFoldGreedily(funcOp, patterns);
 }
 
+namespace {
 /// Local folding pattern for AffineApplyOp that we can apply greedily.
 /// This replaces AffineApplyOp by the proper value in cases where the
 /// associated map is trivial.
 /// A trivial map here is defined as a map with a single result and either:
 ///   1. Zero operand + returns a single AffineConstantExpr
 ///   2. One operand + returns a single AffineDimExpr
 ///   3. One operand + returns a single AffineSymbolExpr
 //
LogicalResult matchAndRewrite(Operation *op,
     }
     if (expr.dyn_cast<AffineDimExpr>() || expr.dyn_cast<AffineSymbolExpr>()) {
       rewriter.replaceOp(op, op->getOperand(0));
       return success();
     }
     return failure();
   }
 };
-} // namespace
 
-template <typename LoopType>
-static void lowerLinalgToLoopsImpl(FuncOp funcOp, MLIRContext *context) {
-  OwningRewritePatternList patterns;
-  // Canonicalization and folding patterns applied greedily allow cleaning up
-  // the emitted IR on the fly.
-  // TODO: fold view and subview ops?
-  insertPatterns<LoopType,
-#define GET_OP_LIST
-#include "mlir/Dialect/Linalg/IR/LinalgStructuredOps.cpp.inc"
-                 >(patterns, context);
-
-  DimOp::getCanonicalizationPatterns(patterns, context);
-  AffineApplyOp::getCanonicalizationPatterns(patterns, context);
-  patterns.insert<FoldAffineOp>(context);
-  // Just apply the patterns greedily.
-  applyPatternsAndFoldGreedily(funcOp, patterns);
-}
-
-namespace {
 struct LowerToAffineLoops
     : public LinalgLowerToAffineLoopsBase<LowerToAffineLoops> {
   void runOnFunction() override {
     lowerLinalgToLoopsImpl<AffineForOp>(getFunction(), &getContext());
   }
 };
+
 struct LowerToLoops : public LinalgLowerToLoopsBase<LowerToLoops> {
   void runOnFunction() override {
     lowerLinalgToLoopsImpl<scf::ForOp>(getFunction(), &getContext());
   }
 };
+
 struct LowerToParallelLoops
     : public LinalgLowerToParallelLoopsBase<LowerToParallelLoops> {
   void runOnFunction() override {
     lowerLinalgToLoopsImpl<scf::ParallelOp>(getFunction(), &getContext());
   }
 };
 } // namespace
 
 std::unique_ptr<OperationPass<FuncOp>> mlir::createConvertLinalgToLoopsPass() {
   return std::make_unique<LowerToLoops>();
 }
 
 std::unique_ptr<OperationPass<FuncOp>>
 mlir::createConvertLinalgToParallelLoopsPass() {
   return std::make_unique<LowerToParallelLoops>();
 }
 
 std::unique_ptr<OperationPass<FuncOp>>
 mlir::createConvertLinalgToAffineLoopsPass() {
   return std::make_unique<LowerToAffineLoops>();
 }
 
-// TODO: gradually remove this layer as more ops become "named".
-template <typename LoopTy>
-static Optional<LinalgLoops> linalgOpToLoopsImplSwitch(Operation *op,
-                                                       OpBuilder &builder) {
-  assert(isa<LinalgOp>(op) && "LinalgOp expected");
-  if (isa<CopyOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, CopyOp>(op, builder);
-  if (isa<FillOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, FillOp>(op, builder);
-  if (isa<ConvOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvOp>(op, builder);
-  if (isa<PoolingMaxOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, PoolingMaxOp>(op, builder);
-  if (isa<PoolingMinOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, PoolingMinOp>(op, builder);
-  if (isa<PoolingSumOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, PoolingSumOp>(op, builder);
-  if (isa<IndexedGenericOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, IndexedGenericOp>(op, builder);
-
-  // TODO: Cases below are generic and need a LinalgStructuredOpInterface.
-  if (isa<GenericOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, GenericOp>(op, builder);
-  if (isa<MatmulOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, MatmulOp>(op, builder);
-  if (isa<MatvecOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, MatvecOp>(op, builder);
-  if (isa<VecmatOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, VecmatOp>(op, builder);
-  if (isa<DotOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, DotOp>(op, builder);
-  if (isa<BatchMatmulOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, BatchMatmulOp>(op, builder);
-  if (isa<ConvWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvWOp>(op, builder);
-  if (isa<ConvNWCOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNWCOp>(op, builder);
-  if (isa<ConvNCWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNCWOp>(op, builder);
-  if (isa<ConvHWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvHWOp>(op, builder);
-  if (isa<ConvNHWCOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNHWCOp>(op, builder);
-  if (isa<ConvNCHWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNCHWOp>(op, builder);
-  if (isa<ConvDHWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvDHWOp>(op, builder);
-  if (isa<ConvNDHWCOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNDHWCOp>(op, builder);
-  if (isa<ConvNCDHWOp>(op))
-    return linalgOpToLoopsImpl<LoopTy, ConvNCDHWOp>(op, builder);
-  llvm_unreachable("Unexpected op in linalgOpToLoopsImpl");
-}
-
 /// Emits a loop nest with the proper body for `op`.
 template <typename LoopTy>
 Optional<LinalgLoops> mlir::linalg::linalgLowerOpToLoops(OpBuilder &builder,
                                                          Operation *op) {
-  return linalgOpToLoopsImplSwitch<LoopTy>(op, builder);
+  return linalgOpToLoopsImpl<LoopTy>(op, builder);
 }
 
 template Optional<LinalgLoops>
 mlir::linalg::linalgLowerOpToLoops<AffineForOp>(OpBuilder &builder,
                                                 Operation *op);
 template Optional<LinalgLoops>
 mlir::linalg::linalgLowerOpToLoops<scf::ForOp>(OpBuilder &builder,
                                                Operation *op);

mlir/test/Dialect/Linalg/loops.mlir

-// RUN: mlir-opt %s -convert-linalg-to-loops | FileCheck --check-prefix=CHECKLOOP %s
-// RUN: mlir-opt %s -convert-linalg-to-parallel-loops | FileCheck --check-prefix=CHECKPARALLEL %s
+// RUN: mlir-opt %s -convert-linalg-to-loops
+//| FileCheck --check-prefix=CHECKLOOP %s
+// R_UN: mlir-opt %s -convert-linalg-to-parallel-loops | FileCheck --check-prefix=CHECKPARALLEL %s
 
 // Test that we can lower all the way to LLVM without crashing, don't check results here.
-// RUN: mlir-opt %s -convert-linalg-to-loops -convert-linalg-to-llvm -o=/dev/null 2>&1
+// R_UN: mlir-opt %s -convert-linalg-to-loops -convert-linalg-to-llvm -o=/dev/null 2>&1
 
 // CHECKLOOP-DAG: #[[$strided1D:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
 // CHECKLOOP-DAG: #[[$strided2D:.*]] = affine_map<(d0, d1)[s0, s1] -> (d0 * s1 + s0 + d1)>
 // CHECKLOOP-DAG: #[[$strided3D:.*]] = affine_map<(d0, d1, d2)[s0, s1, s2] -> (d0 * s1 + s0 + d1 * s2 + d2)>
 // CHECKLOOP-DAG: #[[$strided4D:.*]] = affine_map<(d0, d1, d2, d3)[s0, s1, s2, s3] -> (d0 * s1 + s0 + d1 * s2 + d2 * s3 + d3)>
 // CHECKLOOP-DAG: #[[$clampMinMap:.*]] = affine_map<(d0) -> (d0, 0)>
 
 // CHECKLOOP-DAG: #[[$stride1Dilation1:.*]] = affine_map<(d0, d1) -> (d0  + d1)>

 //   CHECKPARALLEL-DAG:     %[[a:.*]] = load %[[A]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
 //   CHECKPARALLEL-DAG:     %[[b:.*]] = load %[[B]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
 //   CHECKPARALLEL-DAG:     %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
 //   CHECKPARALLEL-DAG:     %[[c:.*]] = load %[[C]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
 //   CHECKPARALLEL-DAG:     %[[res:.*]] = addf %[[c]], %[[inc]] : f32
 //       CHECKPARALLEL:     store %[[res]], %[[C]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
 
 
-
-func @matvec(%arg0: memref<?xi8>, %M: index, %N: index) {
-  %c0 = constant 0 : index
-  %c1 = constant 1 : index
-  %2 = view %arg0[%c0][%M, %N] : memref<?xi8> to memref<?x?xf32>
-  %3 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
-  %4 = view %arg0[%c0][%N] : memref<?xi8> to memref<?xf32>
-  linalg.matvec ins(%2, %3: memref<?x?xf32>, memref<?xf32>)
-               outs(%4 : memref<?xf32>)
-  return
-}
-// CHECKLOOP-LABEL: func @matvec(%{{.*}}: memref<?xi8>,
-//  CHECKLOOP-SAME: [[M:arg[0-9]+]]: index
-//  CHECKLOOP-SAME: [[K:arg[0-9]+]]: index
-//       CHECKLOOP: %[[A:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?x?xf32>
-//       CHECKLOOP: %[[B:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKLOOP: %[[C:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKLOOP: scf.for %{{.*}} = %{{.*}} to %[[M]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKLOOP-DAG:     %[[a:.*]] = load %[[A]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//   CHECKLOOP-DAG:     %[[b:.*]] = load %[[B]][%{{.*}}] : memref<?xf32>
-//   CHECKLOOP-DAG:     %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKLOOP-DAG:     %[[c:.*]] = load %[[C]][%{{.*}}] : memref<?xf32>
-//   CHECKLOOP-DAG:     %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKLOOP:     store %[[res]], %[[C]][%{{.*}}] : memref<?xf32>
-
-// CHECKPARALLEL-LABEL: func @matvec(%{{.*}}: memref<?xi8>,
-//  CHECKPARALLEL-SAME: [[M:arg[0-9]+]]: index
-//  CHECKPARALLEL-SAME: [[K:arg[0-9]+]]: index
-//       CHECKPARALLEL: %[[A:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?x?xf32>
-//       CHECKPARALLEL: %[[B:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKPARALLEL: %[[C:.*]] = std.view %{{.*}}[{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKPARALLEL: scf.parallel (%{{.*}}) = (%{{.*}}) to (%[[M]]) step (%{{.*}}) {
-//       CHECKPARALLEL:   scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKPARALLEL-DAG:     %[[a:.*]] = load %[[A]][%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//   CHECKPARALLEL-DAG:     %[[b:.*]] = load %[[B]][%{{.*}}] : memref<?xf32>
-//   CHECKPARALLEL-DAG:     %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKPARALLEL-DAG:     %[[c:.*]] = load %[[C]][%{{.*}}] : memref<?xf32>
-//   CHECKPARALLEL-DAG:     %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKPARALLEL:     store %[[res]], %[[C]][%{{.*}}] : memref<?xf32>
-
-
-func @dot(%arg0: memref<?xi8>, %M: index) {
-  %c0 = constant 0 : index
-  %c1 = constant 1 : index
-  %1 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
-  %2 = view %arg0[%c0][%M] : memref<?xi8> to memref<?xf32>
-  %3 = view %arg0[%c0][] : memref<?xi8> to memref<f32>
-  linalg.dot ins(%1, %2 : memref<?xf32>, memref<?xf32>)
-            outs(%3 : memref<f32>)
-  return
-}
-// CHECKLOOP-LABEL: func @dot(%{{.*}}: memref<?xi8>,
-//  CHECKLOOP-SAME: [[K:arg[0-9]+]]: index
-//       CHECKLOOP: %[[A:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKLOOP: %[[B:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKLOOP: %[[C:.*]] = std.view %{{.*}}[{{.*}}][] : memref<?xi8> to memref<f32>
-//       CHECKLOOP: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKLOOP-DAG:   %[[a:.*]] = load %[[A]][%{{.*}}] : memref<?xf32>
-//   CHECKLOOP-DAG:   %[[b:.*]] = load %[[B]][%{{.*}}] : memref<?xf32>
-//   CHECKLOOP-DAG:   %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKLOOP-DAG:   %[[c:.*]] = load %[[C]][] : memref<f32>
-//   CHECKLOOP-DAG:   %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKLOOP:   store %[[res]], %[[C]][] : memref<f32>
-
-// CHECKPARALLEL-LABEL: func @dot(%{{.*}}: memref<?xi8>,
-//  CHECKPARALLEL-SAME: [[K:arg[0-9]+]]: index
-//       CHECKPARALLEL: %[[A:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKPARALLEL: %[[B:.*]] = std.view %{{.*}}[{{.*}}][{{.*}}] : memref<?xi8> to memref<?xf32>
-//       CHECKPARALLEL: %[[C:.*]] = std.view %{{.*}}[{{.*}}][] : memref<?xi8> to memref<f32>
-//       CHECKPARALLEL: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKPARALLEL-DAG:   %[[a:.*]] = load %[[A]][%{{.*}}] : memref<?xf32>
-//   CHECKPARALLEL-DAG:   %[[b:.*]] = load %[[B]][%{{.*}}] : memref<?xf32>
-//   CHECKPARALLEL-DAG:   %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKPARALLEL-DAG:   %[[c:.*]] = load %[[C]][] : memref<f32>
-//   CHECKPARALLEL-DAG:   %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %[[C]][] : memref<f32>
-
-
-func @dot_view(%arg0: memref<?xf32, offset: ?, strides: [1]>, %arg1: memref<?xf32, offset: ?, strides: [1]>, %arg2: memref<f32>) {
-  linalg.dot ins(%arg0, %arg1 : memref<?xf32, offset: ?, strides: [1]>,
-                                memref<?xf32, offset: ?, strides: [1]>)
-            outs(%arg2:  memref<f32>)
-  return
-}
-// CHECKLOOP-LABEL: func @dot_view(
-//       CHECKLOOP:   %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<f32>) {
-//       CHECKLOOP: %[[K:.*]] = dim %arg0, %c0 : memref<?xf32, #[[$strided1D]]>
-//       CHECKLOOP: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKLOOP-DAG:   %[[a:.*]] = load %arg0[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//   CHECKLOOP-DAG:   %[[b:.*]] = load %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//   CHECKLOOP-DAG:   %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKLOOP-DAG:   %[[c:.*]] = load %{{.*}}[] : memref<f32>
-//   CHECKLOOP-DAG:   %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKLOOP:   store %[[res]], %{{.*}}[] : memref<f32>
-
-// CHECKPARALLEL-LABEL: func @dot_view(
-//       CHECKPARALLEL:   %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<f32>) {
-//       CHECKPARALLEL: %[[K:.*]] = dim %arg0, %c0 : memref<?xf32, #[[$strided1D]]>
-//       CHECKPARALLEL: scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//   CHECKPARALLEL-DAG:   %[[a:.*]] = load %arg0[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//   CHECKPARALLEL-DAG:   %[[b:.*]] = load %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//   CHECKPARALLEL-DAG:   %[[inc:.*]] = mulf %[[a]], %[[b]] : f32
-//   CHECKPARALLEL-DAG:   %[[c:.*]] = load %{{.*}}[] : memref<f32>
-//   CHECKPARALLEL-DAG:   %[[res:.*]] = addf %[[c]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %{{.*}}[] : memref<f32>
-
-func @fill_view(%arg0: memref<?xf32, offset: ?, strides: [1]>, %arg1: f32) {
-  linalg.fill(%arg0, %arg1) : memref<?xf32, offset: ?, strides: [1]>, f32
-  return
-}
-// CHECKLOOP-LABEL: func @fill_view(
-//       CHECKLOOP: %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: f32) {
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:     store %{{.*}}, %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-
-// CHECKPARALLEL-LABEL: func @fill_view(
-//       CHECKPARALLEL: %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: f32) {
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}) = (%{{.*}}) to (%{{.*}}) step (%{{.*}}) {
-//       CHECKPARALLEL:     store %{{.*}}, %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-
-func @fill_view0(%arg0: memref<f32>, %arg1: f32) {
-  linalg.fill(%arg0, %arg1) : memref<f32>, f32
-  return
-}
-// CHECKLOOP-LABEL: func @fill_view0(%{{.*}}: memref<f32>, %{{.*}}: f32) {
-//       CHECKLOOP:   store %{{.*}}, %{{.*}}[] : memref<f32>
-
-// CHECKPARALLEL-LABEL: func @fill_view0(%{{.*}}: memref<f32>, %{{.*}}: f32) {
-//       CHECKPARALLEL:   store %{{.*}}, %{{.*}}[] : memref<f32>
-
-func @fill_view3(%arg0: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, %arg1: f32) {
-  linalg.fill(%arg0, %arg1) : memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, f32
-  return
-}
-// CHECKLOOP-LABEL: func @fill_view3(
-//       CHECKLOOP: %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: f32) {
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:         store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-// CHECKPARALLEL-LABEL: func @fill_view3(
-//       CHECKPARALLEL: %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: f32) {
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}, %{{.*}}) to (%{{.*}}, %{{.*}}, %{{.*}}) step (%{{.*}}, %{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-func @copy_view(%arg0: memref<?xf32, offset: ?, strides: [1]>, %arg1: memref<?xf32, offset: ?, strides: [1]>) {
-  linalg.copy(%arg0, %arg1) : memref<?xf32, offset: ?, strides: [1]>, memref<?xf32, offset: ?, strides: [1]>
-  return
-}
-// CHECKLOOP-LABEL: func @copy_view(
-//       CHECKLOOP: %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<?xf32, #[[$strided1D]]>) {
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:     %[[L:.*]] = load %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//       CHECKLOOP:     store %[[L]], %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-
-// CHECKPARALLEL-LABEL: func @copy_view(
-//       CHECKPARALLEL: %{{.*}}: memref<?xf32, #[[$strided1D]]>, %{{.*}}: memref<?xf32, #[[$strided1D]]>) {
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}) = (%{{.*}}) to (%{{.*}}) step (%{{.*}}) {
-//       CHECKPARALLEL:     %[[L:.*]] = load %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-//       CHECKPARALLEL:     store %[[L]], %{{.*}}[%{{.*}}] : memref<?xf32, #[[$strided1D]]>
-
-func @copy_view0(%arg0: memref<f32>, %arg1: memref<f32>) {
-  linalg.copy(%arg0, %arg1) : memref<f32>, memref<f32>
-  return
-}
-// CHECKLOOP-LABEL: func @copy_view0(%{{.*}}: memref<f32>, %{{.*}}: memref<f32>) {
-//       CHECKLOOP:   %{{.*}} = load %{{.*}}[] : memref<f32>
-//       CHECKLOOP:   store %{{.*}}, %{{.*}}[] : memref<f32>
-
-// CHECKPARALLEL-LABEL: func @copy_view0(%{{.*}}: memref<f32>, %{{.*}}: memref<f32>) {
-//       CHECKPARALLEL:   %{{.*}} = load %{{.*}}[] : memref<f32>
-//       CHECKPARALLEL:   store %{{.*}}, %{{.*}}[] : memref<f32>
-
-func @copy_view3(%arg0: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, %arg1: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-  linalg.copy(%arg0, %arg1) {inputPermutation = affine_map<(i, j, k) -> (i, k, j)>,
-                             outputPermutation = affine_map<(i, j, k) -> (k, j, i)>} :
-    memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>
-  return
-}
-// CHECKLOOP-LABEL: func @copy_view3
-//       CHECKLOOP: (%{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>) {
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %{{.*}} step %{{.*}} {
-//       CHECKLOOP:         %[[L:.*]] = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:         store %[[L]], %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-// CHECKPARALLEL-LABEL: func @copy_view3
-//       CHECKPARALLEL: (%{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>) {
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}, %{{.*}}) to (%{{.*}}, %{{.*}}, %{{.*}}) step (%{{.*}}, %{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     %[[L:.*]] = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:     store %[[L]], %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-func @conv_view3(%arg0: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, %arg1: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, %arg2: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-  linalg.conv(%arg0, %arg1, %arg2) {strides = [2]}: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>
-  return
-}
-// CHECKLOOP-LABEL: func @conv_view3(
-//       CHECKLOOP: %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>) {
-//       CHECKLOOP:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:   %[[Q:.*]] = dim %arg0, %c1 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:   %[[K:.*]] = dim %arg0, %c2 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:   %[[B:.*]] = dim %arg1, %c0 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[B]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[X0]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKLOOP:           scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//       CHECKLOOP:             %[[SUM:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:             %{{.*}} = load %{{.*}}[%{{.*}}, %[[SUM]], %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:             %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:             %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:             store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-// CHECKPARALLEL-LABEL: func @conv_view3(
-//       CHECKPARALLEL: %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>, %{{.*}}: memref<?x?x?xf32, #[[$strided3D]]>) {
-//       CHECKPARALLEL:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[Q:.*]] = dim %arg0, %c1 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[K:.*]] = dim %arg0, %c2 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[B:.*]] = dim %arg1, %c0 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}) to (%[[B]], %[[X0]]) step (%{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKPARALLEL:         scf.parallel ({{.*}}) = (%{{.*}}) to (%[[K]]) step (%{{.*}}) {
-//       CHECKPARALLEL:           %[[SUM:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:           %{{.*}} = load %{{.*}}[%{{.*}}, %[[SUM]], %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:           %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:           %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:           %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:           %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:           store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?xf32, #[[$strided3D]]>
-
-func @conv_view4(%arg0: memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>, %arg1: memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>, %arg2: memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>) {
-  linalg.conv(%arg0, %arg1, %arg2) {dilations = [4, 5], strides = [2, 3]} : memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>, memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>, memref<?x?x?x?xf32, offset: ?, strides: [?, ?, ?, 1]>
-  return
-}
-// CHECKLOOP-LABEL: func @conv_view4(
-//       CHECKLOOP: %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>, %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>, %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>) {
-//       CHECKLOOP:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[Z1:.*]] = dim %arg0, %c1 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[Q:.*]] = dim %arg0, %c2 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[K:.*]] = dim %arg0, %c3 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[B:.*]] = dim %arg1, %c0 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   %[[X1:.*]] = dim %arg2, %c2 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[B]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[X0]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[X1]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKLOOP:           scf.for %{{.*}} = %{{.*}} to %[[Z1]] step %{{.*}} {
-//       CHECKLOOP:             scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKLOOP:               scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//       CHECKLOOP:                 %[[SUM0:.*]] = affine.apply #[[$stride2Dilation4]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:                 %[[SUM1:.*]] = affine.apply #[[$stride3Dilation5]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %[[SUM0]], %[[SUM1]], %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:                 %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKLOOP:                 %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:                 store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-
-// CHECKPARALLEL-LABEL: func @conv_view4(
-//       CHECKPARALLEL: %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>, %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>, %{{.*}}: memref<?x?x?x?xf32, #[[$strided4D]]>) {
-//       CHECKPARALLEL:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[Z1:.*]] = dim %arg0, %c1 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[Q:.*]] = dim %arg0, %c2 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[K:.*]] = dim %arg0, %c3 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[B:.*]] = dim %arg1, %c0 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   %[[X1:.*]] = dim %arg2, %c2 : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}, %{{.*}}) to (%[[B]], %[[X0]], %[[X1]]) step (%{{.*}}, %{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[Z1]] step %{{.*}} {
-//       CHECKPARALLEL:         scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKPARALLEL:           scf.parallel (%{{.*}}) = (%{{.*}}) to (%[[K]]) step (%{{.*}}) {
-//       CHECKPARALLEL:             %[[SUM0:.*]] = affine.apply #[[$stride2Dilation4]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:             %[[SUM1:.*]] = affine.apply #[[$stride3Dilation5]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %[[SUM0]], %[[SUM1]], %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:             %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-//       CHECKPARALLEL:             %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:             store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32, #[[$strided4D]]>
-
-func @conv_padding(%arg0: memref<?x?x?x?xf32>,
-                   %arg1: memref<?x?x?x?xf32>,
-                   %arg2: memref<?x?x?x?xf32>) {
-  linalg.conv(%arg0, %arg1, %arg2) {dilations = [1, 1],
-                                    padding = dense<[[0, 1], [1, 1]]> : tensor<2x2xi64>,
-                                    strides = [1, 1]} :
-    memref<?x?x?x?xf32>, memref<?x?x?x?xf32>, memref<?x?x?x?xf32>
-  return
-}
-// CHECKLOOP-LABEL: func @conv_padding
-//       CHECKLOOP: %{{.*}}: memref<?x?x?x?xf32>, %{{.*}}: memref<?x?x?x?xf32>, %{{.*}}: memref<?x?x?x?xf32>) {
-//       CHECKLOOP:   %[[ZERO:.*]] = constant 0.000000e+00 : f32
-//       CHECKLOOP:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[Z1:.*]] = dim %arg0, %c1 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[Q:.*]] =  dim %arg0, %c2 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[K:.*]] =  dim %arg0, %c3 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[B:.*]] =  dim %arg1, %c0 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   %[[X1:.*]] = dim %arg2, %c2 : memref<?x?x?x?xf32>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[B]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[X0]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[X1]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKLOOP:           scf.for %{{.*}} = %{{.*}} to %[[Z1]] step %{{.*}} {
-//       CHECKLOOP:             scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKLOOP:               scf.for %{{.*}} = %{{.*}} to %[[K]] step %{{.*}} {
-//       CHECKLOOP:                 %[[SUM0:.*]] = affine.apply #{{.*}}(%{{.*}}, %{{.*}})
-//       CHECKLOOP:                 %[[SUM1:.*]] = affine.apply #{{.*}}(%{{.*}}, %{{.*}})
-//       CHECKLOOP:                 %[[IDX:.*]] = affine.max #[[$clampMinMap]](%[[SUM0]])
-//       CHECKLOOP:                 %[[IDY:.*]] = affine.max #[[$clampMinMap]](%[[SUM1]])
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %[[IDX]], %[[IDY]], %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %{{.*}} = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:                 %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:                 store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-
-// CHECKPARALLEL-LABEL: func @conv_padding
-//       CHECKPARALLEL: %{{.*}}: memref<?x?x?x?xf32>, %{{.*}}: memref<?x?x?x?xf32>, %{{.*}}: memref<?x?x?x?xf32>) {
-//       CHECKPARALLEL:   %[[ZERO:.*]] = constant 0.000000e+00 : f32
-//       CHECKPARALLEL:   %[[Z0:.*]] = dim %arg0, %c0 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[Z1:.*]] = dim %arg0, %c1 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[Q:.*]] =  dim %arg0, %c2 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[K:.*]] =  dim %arg0, %c3 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[B:.*]] =  dim %arg1, %c0 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[X0:.*]] = dim %arg2, %c1 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[X1:.*]] = dim %arg2, %c2 : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}, %{{.*}}) to (%[[B]], %[[X0]], %[[X1]]) step (%{{.*}}, %{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[Z0]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[Z1]] step %{{.*}} {
-//       CHECKPARALLEL:         scf.for %{{.*}} = %{{.*}} to %[[Q]] step %{{.*}} {
-//       CHECKPARALLEL:           scf.parallel (%{{.*}}) = (%{{.*}}) to (%[[K]]) step (%{{.*}}) {
-//       CHECKPARALLEL:             %[[SUM0:.*]] = affine.apply #{{.*}}(%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:             %[[SUM1:.*]] = affine.apply #{{.*}}(%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:             %[[IDX:.*]] = affine.max #[[$clampMinMap]](%[[SUM0]])
-//       CHECKPARALLEL:             %[[IDY:.*]] = affine.max #[[$clampMinMap]](%[[SUM1]])
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %[[IDX]], %[[IDY]], %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:             %{{.*}} = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:             %{{.*}} = mulf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:             %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:             %{{.*}} = addf %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:             store %{{.*}}, %{{.*}}[%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}] : memref<?x?x?x?xf32>
-
-func @pooling_max(%arg0: memref<?x?xf32>,
-                  %arg1: memref<?x?xi32>,
-                  %arg2: memref<?x?xf32>) {
-  linalg.pooling_max(%arg0, %arg1, %arg2) { strides = [2, 1] }:
-    memref<?x?xf32>, memref<?x?xi32>, memref<?x?xf32>
-  return
-}
-// CHECKLOOP-LABEL: func @pooling_max
-//       CHECKLOOP:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKLOOP:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKLOOP:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKLOOP:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[OX]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[OY]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKLOOP:           %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKLOOP:           %{{.*}} = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKLOOP:           %[[RES:.*]] = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:           store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-// CHECKPARALLEL-LABEL: func @pooling_max
-//       CHECKPARALLEL:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}) to (%[[OX]], %[[OY]]) step (%{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKPARALLEL:         %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKPARALLEL:         %{{.*}} = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKPARALLEL:         %[[RES:.*]] = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:         store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-func @pooling_min(%arg0: memref<?x?xf32>,
-                  %arg1: memref<?x?xi32>,
-                  %arg2: memref<?x?xf32>) {
-  linalg.pooling_min(%arg0, %arg1, %arg2) { strides = [2, 1] }:
-    memref<?x?xf32>, memref<?x?xi32>, memref<?x?xf32>
-  return
-}
-// CHECKLOOP-LABEL: func @pooling_min
-//       CHECKLOOP:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKLOOP:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKLOOP:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKLOOP:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[OX]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[OY]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKLOOP:           %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKLOOP:           %{{.*}} = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKLOOP:           %[[RES:.*]] = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKLOOP:           store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-// CHECKPARALLEL-LABEL: func @pooling_min
-//       CHECKPARALLEL:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}) to (%[[OX]], %[[OY]]) step (%{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKPARALLEL:         %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %{{.*}} = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKPARALLEL:         %{{.*}} = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKPARALLEL:         %[[RES:.*]] = select %{{.*}}, %{{.*}}, %{{.*}} : f32
-//       CHECKPARALLEL:         store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-func @pooling_sum(%arg0: memref<?x?xf32>,
-                  %arg1: memref<?x?xi32>,
-                  %arg2: memref<?x?xf32>) {
-  linalg.pooling_sum(%arg0, %arg1, %arg2) { strides = [2, 1] }:
-    memref<?x?xf32>, memref<?x?xi32>, memref<?x?xf32>
-  return
-}
-// CHECKLOOP-LABEL: func @pooling_sum
-//       CHECKLOOP:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKLOOP:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKLOOP:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKLOOP:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKLOOP:   scf.for %{{.*}} = %{{.*}} to %[[OX]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %{{.*}} = %{{.*}} to %[[OY]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKLOOP:           %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKLOOP:           %[[RHS:.*]] = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKLOOP:           %[[LHS:.*]] = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKLOOP:           %[[RES:.*]] = addf %[[LHS]], %[[RHS]] : f32
-//       CHECKLOOP:           store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-// CHECKPARALLEL-LABEL: func @pooling_sum
-//       CHECKPARALLEL:   %[[WX:.*]] = dim %arg1, %c0 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[WY:.*]] = dim %arg1, %c1 : memref<?x?xi32>
-//       CHECKPARALLEL:   %[[OX:.*]] = dim %arg2, %c0 : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[OY:.*]] = dim %arg2, %c1 : memref<?x?xf32>
-//       CHECKPARALLEL:   scf.parallel (%{{.*}}, %{{.*}}) = (%{{.*}}, %{{.*}}) to (%[[OX]], %[[OY]]) step (%{{.*}}, %{{.*}}) {
-//       CHECKPARALLEL:     scf.for %{{.*}} = %{{.*}} to %[[WX]] step %{{.*}} {
-//       CHECKPARALLEL:       scf.for %{{.*}} = %{{.*}} to %[[WY]] step %{{.*}} {
-//       CHECKPARALLEL:         %[[IX:.*]] = affine.apply #[[$stride2Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %[[IY:.*]] = affine.apply #[[$stride1Dilation1]](%{{.*}}, %{{.*}})
-//       CHECKPARALLEL:         %[[RHS:.*]] = load %{{.*}}[%[[IX]], %[[IY]]] : memref<?x?xf32>
-//       CHECKPARALLEL:         %[[LHS:.*]] = load %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-//       CHECKPARALLEL:         %[[RES:.*]] = addf %[[LHS]], %[[RHS]] : f32
-//       CHECKPARALLEL:         store %[[RES]], %{{.*}}[%{{.*}}, %{{.*}}] : memref<?x?xf32>
-
-#accesses = [
-  affine_map<(i, j, k) -> (i, j)>,
-  affine_map<(i, j, k) -> (i, j, k)>,
-  affine_map<(i, j, k) -> (i, k, j)>
-]
-#trait2 = {
-  args_in = 1,
-  args_out = 2,
-  iterator_types = ["parallel", "parallel", "parallel"],
-  indexing_maps = #accesses,
-  library_call = "some_external_function_name_2",
-  doc = "B(i,j,k), C(i,k,j) = foo(A(i, j), B(i,j,k), C(i,k,j))"
-}
-func @generic_region(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>, %arg1: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>, %arg2: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-  linalg.generic #trait2
-    ins(%arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>)
-   outs(%arg1, %arg2 : memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>,
-                       memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-    ^bb0(%a: f32, %b: f32, %c: f32):
-      %d = mulf %a, %b : f32
-      %e = addf %c, %d : f32
-      linalg.yield %d, %e : f32, f32
-  }
-  return
-}
-// CHECKLOOP-LABEL: @generic_region
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   scf.for %[[j:.*]] = {{.*}}
-//       CHECKLOOP:     scf.for %[[k:.*]] = {{.*}}
-//       CHECKLOOP:       %[[a:.*]] = load %{{.*}}[%[[i]], %[[j]]] : memref<?x?xf32, #[[$strided2D]]>
-//       CHECKLOOP:       %[[b:.*]] = load %{{.*}}[%[[i]], %[[j]], %[[k]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:       %[[c:.*]] = load %{{.*}}[%[[i]], %[[k]], %[[j]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:       %[[d:.*]] = mulf %[[a]], %[[b]] : f32
-//       CHECKLOOP:       %[[e:.*]] = addf %[[c]], %[[d]] : f32
-//       CHECKLOOP:       store %[[d]], %{{.*}}[%[[i]], %[[j]], %[[k]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKLOOP:       store %[[e]], %{{.*}}[%[[i]], %[[k]], %[[j]]] : memref<?x?x?xf32, #[[$strided3D]]>
-
-// CHECKPARALLEL-LABEL: @generic_region
-//       CHECKPARALLEL: scf.parallel (%[[i:[a-zA-Z0-9_]*]], %[[j:[a-zA-Z0-9_]*]], %[[k:[a-zA-Z0-9_]*]])
-//       CHECKPARALLEL:   %[[a:.*]] = load %{{.*}}[%[[i]], %[[j]]] : memref<?x?xf32, #[[$strided2D]]>
-//       CHECKPARALLEL:   %[[b:.*]] = load %{{.*}}[%[[i]], %[[j]], %[[k]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[c:.*]] = load %{{.*}}[%[[i]], %[[k]], %[[j]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   %[[d:.*]] = mulf %[[a]], %[[b]] : f32
-//       CHECKPARALLEL:   %[[e:.*]] = addf %[[c]], %[[d]] : f32
-//       CHECKPARALLEL:   store %[[d]], %{{.*}}[%[[i]], %[[j]], %[[k]]] : memref<?x?x?xf32, #[[$strided3D]]>
-//       CHECKPARALLEL:   store %[[e]], %{{.*}}[%[[i]], %[[k]], %[[j]]] : memref<?x?x?xf32, #[[$strided3D]]>
-
-#trait4 = {
-  args_in = 1,
-  args_out = 2,
-  iterator_types = ["parallel", "parallel", "parallel"],
-  indexing_maps = #accesses,
-  library_call = "some_external_function_name_2",
-  doc = "B(i,j,k), C(i,k,j) = foo(A(i, j) * B(i,j,k), i * j * k + C(i,k,j))"
-}
-func @indexed_generic_region(
-        %arg0: memref<?x?xf32, offset: ?, strides: [?, 1]>,
-        %arg1: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>,
-        %arg2: memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-  linalg.indexed_generic #trait4
-      ins(%arg0 : memref<?x?xf32, offset: ?, strides: [?, 1]>)
-     outs(%arg1, %arg2 : memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>,
-                         memref<?x?x?xf32, offset: ?, strides: [?, ?, 1]>) {
-    ^bb0(%i: index, %j: index, %k: index, %a: f32, %b: f32, %c: f32):
-      %result_1 = mulf %a, %b : f32
-
-      %ij = addi %i, %j : index
-      %ijk = addi %ij, %k : index
-      %ijk_int = index_cast %ijk : index to i32
-      %ijk_float = sitofp %ijk_int : i32 to f32
-
-      %result_2 = addf %c, %ijk_float : f32
-      linalg.yield %result_1, %result_2 : f32, f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @indexed_generic_region
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   scf.for %[[j:.*]] = {{.*}}
-//       CHECKLOOP:     scf.for %[[k:.*]] = {{.*}}
-//       CHECKLOOP:       %[[a:.*]] = load %{{.*}}[%[[i]], %[[j]]]
-//       CHECKLOOP:       %[[b:.*]] = load %{{.*}}[%[[i]], %[[j]], %[[k]]]
-//       CHECKLOOP:       %[[c:.*]] = load %{{.*}}[%[[i]], %[[k]], %[[j]]]
-//       CHECKLOOP:       %[[result_1:.*]] = mulf %[[a]], %[[b]] : f32
-//       CHECKLOOP:       %[[ij:.*]] = addi %[[i]], %[[j]] : index
-//       CHECKLOOP:       %[[ijk:.*]] = addi %[[ij]], %[[k]] : index
-//       CHECKLOOP:       %[[ijk_int:.*]] = index_cast %[[ijk]] : index to i32
-//       CHECKLOOP:       %[[ijk_float:.*]] = sitofp %[[ijk_int]] : i32 to f32
-//       CHECKLOOP:       %[[result_2:.*]] = addf %[[c]], %[[ijk_float]] : f32
-//       CHECKLOOP:       store %[[result_1]], %{{.*}}[%[[i]], %[[j]], %[[k]]]
-//       CHECKLOOP:       store %[[result_2]], %{{.*}}[%[[i]], %[[k]], %[[j]]]
-
-// CHECKPARALLEL-LABEL: @indexed_generic_region
-//       CHECKPARALLEL: scf.parallel (%[[i:[a-zA-Z0-9_]*]], %[[j:[a-zA-Z0-9_]*]], %[[k:[a-zA-Z0-9_]*]])
-//       CHECKPARALLEL:   %[[a:.*]] = load %{{.*}}[%[[i]], %[[j]]]
-//       CHECKPARALLEL:   %[[b:.*]] = load %{{.*}}[%[[i]], %[[j]], %[[k]]]
-//       CHECKPARALLEL:   %[[c:.*]] = load %{{.*}}[%[[i]], %[[k]], %[[j]]]
-//       CHECKPARALLEL:   %[[result_1:.*]] = mulf %[[a]], %[[b]] : f32
-//       CHECKPARALLEL:   %[[ij:.*]] = addi %[[i]], %[[j]] : index
-//       CHECKPARALLEL:   %[[ijk:.*]] = addi %[[ij]], %[[k]] : index
-//       CHECKPARALLEL:   %[[ijk_int:.*]] = index_cast %[[ijk]] : index to i32
-//       CHECKPARALLEL:   %[[ijk_float:.*]] = sitofp %[[ijk_int]] : i32 to f32
-//       CHECKPARALLEL:   %[[result_2:.*]] = addf %[[c]], %[[ijk_float]] : f32
-//       CHECKPARALLEL:   store %[[result_1]], %{{.*}}[%[[i]], %[[j]], %[[k]]]
-//       CHECKPARALLEL:   store %[[result_2]], %{{.*}}[%[[i]], %[[k]], %[[j]]]
-
-// -----
-
-#broadcast_access = [
-  affine_map<(i, j) -> ()>,
-  affine_map<(i, j) -> (i, j)>
-]
-
-#trait_broadcast = {
-  args_in = 1,
-  args_out = 1,
-  indexing_maps = #broadcast_access,
-  iterator_types = ["parallel", "parallel"],
-  library_call = "some_broadcast_external_fn"
-}
-
-func @generic_op_zero_rank(%arg0: memref<f32>, %arg1: memref<3x4xf32>)
-{
-  linalg.generic #trait_broadcast
-      ins(%arg0 : memref<f32>)
-     outs(%arg1 : memref<3x4xf32>) {
-    ^bb(%a: f32, %b: f32) :
-      linalg.yield %a : f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @generic_op_zero_rank
-//  CHECKLOOP-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKLOOP-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<3x4xf32>
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   scf.for %[[j:.*]] = {{.*}}
-//       CHECKLOOP:     %[[a:.*]] = load %[[ARG0]][]
-//       CHECKLOOP:     store %[[a]], %[[ARG1]][%[[i]], %[[j]]]
-
-// CHECKPARALLEL-LABEL: @generic_op_zero_rank
-//  CHECKPARALLEL-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKPARALLEL-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<3x4xf32>
-//       CHECKPARALLEL: scf.parallel (%[[i:[a-zA-Z0-9_]*]], %[[j:[a-zA-Z0-9_]*]])
-//       CHECKPARALLEL:   %[[a:.*]] = load %[[ARG0]][]
-//       CHECKPARALLEL:   store %[[a]], %[[ARG1]][%[[i]], %[[j]]]
-
-func @indexed_generic_op_zero_rank(%arg0: memref<i32>, %arg1: memref<3x4xi32>)
-{
-  linalg.indexed_generic #trait_broadcast
-      ins(%arg0 : memref<i32>)
-     outs(%arg1 : memref<3x4xi32>) {
-    ^bb(%i: index, %j: index, %a: i32, %b: i32) :
-      %ij = addi %i, %j : index
-      %ij_int = index_cast %ij : index to i32
-      %result = addi %a, %ij_int : i32
-      linalg.yield %result : i32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @indexed_generic_op_zero_rank
-//  CHECKLOOP-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<i32>
-//  CHECKLOOP-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<3x4xi32>
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   scf.for %[[j:.*]] = {{.*}}
-//       CHECKLOOP:     %[[a:.*]] = load %[[ARG0]][
-//       CHECKLOOP:     %[[ij:.*]] = addi %[[i]], %[[j]] : index
-//       CHECKLOOP:     %[[ij_int:.*]] = index_cast %[[ij]] : index to i32
-//       CHECKLOOP:     %[[result:.*]] = addi %[[a]], %[[ij_int]] : i32
-//       CHECKLOOP:     store %[[result]], %[[ARG1]][%[[i]], %[[j]]]
-
-// CHECKPARALLEL-LABEL: @indexed_generic_op_zero_rank
-//  CHECKPARALLEL-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<i32>
-//  CHECKPARALLEL-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<3x4xi32>
-//       CHECKPARALLEL: scf.parallel (%[[i:[a-zA-Z0-9_]*]], %[[j:[a-zA-Z0-9_]*]])
-//       CHECKPARALLEL:   %[[a:.*]] = load %[[ARG0]][
-//       CHECKPARALLEL:   %[[ij:.*]] = addi %[[i]], %[[j]] : index
-//       CHECKPARALLEL:   %[[ij_int:.*]] = index_cast %[[ij]] : index to i32
-//       CHECKPARALLEL:   %[[result:.*]] = addi %[[a]], %[[ij_int]] : i32
-//       CHECKPARALLEL:   store %[[result]], %[[ARG1]][%[[i]], %[[j]]]
-
-#reduce_1D_access = [
-  affine_map<(i) -> (i)>,
-  affine_map<(i) -> ()>
-]
-
-#trait_reduce_1D = {
-  args_in = 1,
-  args_out = 1,
-  indexing_maps = #reduce_1D_access,
-  iterator_types = ["reduction"],
-  library_call = "some_reduce_external_fn"
-}
-
-func @generic_op_1D_reduce(%arg0: memref<?xf32>, %arg1: memref<f32>)
-{
-  linalg.generic #trait_reduce_1D
-      ins(%arg0 : memref<?xf32>)
-     outs(%arg1 : memref<f32>) {
-    ^bb(%a: f32, %b: f32) :
-      %0 = addf %a, %b : f32
-      linalg.yield %0 : f32
-  }
-  return
-}
-// CHECKLOOP-LABEL: @generic_op_1D_reduce
-//  CHECKLOOP-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   %[[a:.*]] = load %[[ARG0]][%[[i]]]
-//       CHECKLOOP:   %[[b:.*]] = load %[[ARG1]][]
-//       CHECKLOOP:   %[[c:.*]] = addf %[[a]], %[[b]] : f32
-//       CHECKLOOP:   store %[[c]], %[[ARG1]][]
-
-// CHECKPARALLEL-LABEL: @generic_op_1D_reduce
-//  CHECKPARALLEL-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//       CHECKPARALLEL: scf.for %[[i:.*]] = {{.*}}
-//       CHECKPARALLEL:   %[[a:.*]] = load %[[ARG0]][%[[i]]]
-//       CHECKPARALLEL:   %[[b:.*]] = load %[[ARG1]][]
-//       CHECKPARALLEL:   %[[c:.*]] = addf %[[a]], %[[b]] : f32
-//       CHECKPARALLEL:   store %[[c]], %[[ARG1]][]
-
-
-#reduce_init_1D_access = [
-  affine_map<(i) -> (i)>,
-  affine_map<(i) -> ()>,
-  affine_map<(i) -> ()>
-]
-
-#trait_reduce_init_1D = {
-  args_in = 2,
-  args_out = 1,
-  indexing_maps = #reduce_init_1D_access,
-  iterator_types = ["reduction"],
-  library_call = "some_reduce_external_fn"
-}
-
-func @indexed_generic_op_1D_reduce(%arg0: memref<?xf32>,
-                                   %arg1: memref<f32>,
-                                   %arg2: memref<f32>)
-{
-  linalg.indexed_generic #trait_reduce_init_1D
-      ins(%arg0, %arg1 : memref<?xf32>, memref<f32>)
-     outs(%arg2 : memref<f32>) {
-    ^bb(%i : index, %a: f32, %b: f32, %c: f32) :
-      %0 = constant 0 : index
-      %1 = cmpi "eq", %0, %i : index
-      %2 = select %1, %b, %c : f32
-      %3 = addf %a, %2 : f32
-      linalg.yield %3 : f32
-  }
-  return
-}
-// CHECKLOOP-LABEL: @indexed_generic_op_1D_reduce
-//  CHECKLOOP-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKLOOP-SAME: %[[ARG2:[a-zA-Z0-9_]*]]: memref<f32>
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   %[[a:.*]] = load %[[ARG0]][%[[i]]]
-//       CHECKLOOP:   %[[b:.*]] = load %[[ARG1]][]
-//       CHECKLOOP:   %[[c:.*]] = load %[[ARG2]][]
-//       CHECKLOOP:   %[[d:.*]] = select %{{.*}}, %[[b]], %[[c]]
-//       CHECKLOOP:   %[[e:.*]] = addf %[[a]], %[[d]]
-//       CHECKLOOP:   store %[[e]], %[[ARG2]][]
-
-// CHECKPARALLEL-LABEL: @indexed_generic_op_1D_reduce
-//  CHECKPARALLEL-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKPARALLEL-SAME: %[[ARG2:[a-zA-Z0-9_]*]]: memref<f32>
-//       CHECKPARALLEL: scf.for %[[i:.*]] = {{.*}}
-//       CHECKPARALLEL:   %[[a:.*]] = load %[[ARG0]][%[[i]]]
-//       CHECKPARALLEL:   %[[b:.*]] = load %[[ARG1]][]
-//       CHECKPARALLEL:   %[[c:.*]] = load %[[ARG2]][]
-//       CHECKPARALLEL:   %[[d:.*]] = select %{{.*}}, %[[b]], %[[c]]
-//       CHECKPARALLEL:   %[[e:.*]] = addf %[[a]], %[[d]]
-//       CHECKPARALLEL:   store %[[e]], %[[ARG2]][]
-
-#trait_const_fill = {
-  args_in = 0,
-  args_out = 1,
-  indexing_maps = [affine_map<(i) -> (i)>],
-  iterator_types = ["parallel"],
-  library_call = "some_external_fn"
-}
-func @generic_const_init(%arg0: memref<?xf32>) {
-        %cst = constant 1.0 : f32
-  linalg.generic #trait_const_fill outs(%arg0 : memref<?xf32>) {
-    ^bb0(%arg1: f32):   // no predecessors
-      linalg.yield %cst : f32
-    }
-    return
-}
-// CHECKLOOP-LABEL: @generic_const_init
-//  CHECKLOOP-SAME: %[[ARG0:.*]]: memref<?xf32>
-//       CHECKLOOP: %[[CONST:.*]] = constant 1.000000e+00 : f32
-//       CHECKLOOP: scf.for %[[i:.*]] = {{.*}}
-//       CHECKLOOP:   store %[[CONST]], %[[ARG0]]
-
-// CHECKPARALLEL-LABEL: @generic_const_init
-//  CHECKPARALLEL-SAME: %[[ARG0:.*]]: memref<?xf32>
-//       CHECKPARALLEL: %[[CONST:.*]] = constant 1.000000e+00 : f32
-//       CHECKPARALLEL: scf.parallel (%[[i:.*]])
-//       CHECKPARALLEL:   store %[[CONST]], %[[ARG0]]
-
-#scalar_access = [
-  affine_map<() -> ()>,
-  affine_map<() -> ()>,
-  affine_map<() -> ()>
-]
-#scalar_trait = {
-  args_in = 2,
-  args_out = 1,
-  iterator_types = [],
-  indexing_maps = #scalar_access,
-  library_call = "some_external_fn"
-}
-func @scalar_code(%arg0: memref<f32>, %arg1 : memref<f32>, %arg2 : memref<f32>)
-{
-  linalg.generic #scalar_trait
-    ins(%arg0, %arg1 : memref<f32>, memref<f32>)
-   outs(%arg2 : memref<f32>) {
-  ^bb(%a : f32, %b : f32, %c : f32) :
-    %0 = addf %a, %b : f32
-    linalg.yield %0 : f32
-  }
-  return
-}
-// CHECKLOOP-LABEL: @scalar_code
-//  CHECKLOOP-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKLOOP-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKLOOP-SAME: %[[ARG2:[a-zA-Z0-9_]*]]: memref<f32>
-//   CHECKLOOP-NOT: scf.for
-//       CHECKLOOP: load %[[ARG0]][]
-//       CHECKLOOP: load %[[ARG1]][]
-//       CHECKLOOP: addf
-//       CHECKLOOP: store %{{.*}}, %[[ARG2]][]
-
-// CHECKPARALLEL-LABEL: @scalar_code
-//  CHECKPARALLEL-SAME: %[[ARG0:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKPARALLEL-SAME: %[[ARG1:[a-zA-Z0-9_]*]]: memref<f32>
-//  CHECKPARALLEL-SAME: %[[ARG2:[a-zA-Z0-9_]*]]: memref<f32>
-//   CHECKPARALLEL-NOT: scf.for
-//       CHECKPARALLEL: load %[[ARG0]][]
-//       CHECKPARALLEL: load %[[ARG1]][]
-//       CHECKPARALLEL: addf
-//       CHECKPARALLEL: store %{{.*}}, %[[ARG2]][]
-
-//----------------------------------------------------------------------------//
-// Named ops to loops.
-//----------------------------------------------------------------------------//
-func @named_batch_matmul(%A: memref<?x?x?xf32>, %B: memref<?x?x?xf32>, %C: memref<?x?x?xf32>) {
-  linalg.batch_matmul ins(%A, %B : memref<?x?x?xf32>, memref<?x?x?xf32>)
-                     outs(%C : memref<?x?x?xf32>)
-  return
-}
-// CHECKLOOP-LABEL: @named_batch_matmul
-//  CHECKLOOP-SAME: %[[mA:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[mB:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[mC:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKLOOP: %[[B:.*]] = dim %[[mA]], %c0 : memref<?x?x?xf32>
-//       CHECKLOOP: %[[M:.*]] = dim %[[mA]], %c1 : memref<?x?x?xf32>
-//       CHECKLOOP: %[[K:.*]] = dim %[[mA]], %c2 : memref<?x?x?xf32>
-//       CHECKLOOP: %[[N:.*]] = dim %[[mB]], %c2 : memref<?x?x?xf32>
-//       CHECKLOOP: scf.for %[[b:.*]] = %{{.*}} to %[[B]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %[[m:.*]] = %{{.*}} to %[[M]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %[[n:.*]] = %{{.*}} to %[[N]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %[[k:.*]] = %{{.*}} to %[[K]] step %{{.*}} {
-//       CHECKLOOP:       %[[va:.*]] = load %[[mA]][%[[b]], %[[m]], %[[k]]] : memref<?x?x?xf32>
-//       CHECKLOOP:       %[[vb:.*]] = load %[[mB]][%[[b]], %[[k]], %[[n]]] : memref<?x?x?xf32>
-//       CHECKLOOP:       %[[vc:.*]] = load %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
-//       CHECKLOOP:       %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKLOOP:       %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:       store %[[res]], %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
-
-// CHECKPARALLEL-LABEL: @named_batch_matmul
-//  CHECKPARALLEL-SAME: %[[mA:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[mB:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[mC:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[B:.*]] = dim %[[mA]], %c0 : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[M:.*]] = dim %[[mA]], %c1 : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[K:.*]] = dim %[[mA]], %c2 : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[N:.*]] = dim %[[mB]], %c2 : memref<?x?x?xf32>
-//       CHECKPARALLEL: scf.parallel (%[[b:.*]], %[[m:.*]], %[[n:.*]]) = ({{.*}}) to (%[[B]], %[[M]], %[[N]]) step ({{.*}}) {
-//       CHECKPARALLEL:   scf.for %[[k:.*]] = %{{.*}} to %[[K]] step %{{.*}} {
-//       CHECKPARALLEL:       %[[va:.*]] = load %[[mA]][%[[b]], %[[m]], %[[k]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:       %[[vb:.*]] = load %[[mB]][%[[b]], %[[k]], %[[n]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:       %[[vc:.*]] = load %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:       %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKPARALLEL:       %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:       store %[[res]], %[[mC]][%[[b]], %[[m]], %[[n]]] : memref<?x?x?xf32>
-
-#conv_1d_accesses = [
-  affine_map<(m, n)[s0] -> (m + n - s0 floordiv 2)>, // in
-  affine_map<(m, n)[s0] -> (n)>, // filter
-  affine_map<(m, n)[s0] -> (m)> // out
-]
-
-#conv_1d_trait = {
-  args_in = 2,
-  args_out = 1,
-  doc = "C(m) += A(m) * B(n)",
-  indexing_maps = #conv_1d_accesses,
-  library_call  = "linalg_conv_1d",
-  n_views = [2, 1],
-  iterator_types = ["parallel", "parallel"],
-  symbol_source = 1
-}
-
-func @conv1d(%in : memref<?xf32>, %filter : memref<?xf32>, %out :  memref<?xf32>) -> () {
-  linalg.generic #conv_1d_trait
-      ins(%in, %filter : memref<?xf32>, memref<?xf32>)
-     outs(%out : memref<?xf32>) {
-    ^bb0(%a: f32, %b: f32, %c: f32) :
-      %d = mulf %a, %b : f32
-      %e = addf %c, %d : f32
-      linalg.yield %e : f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @conv1d
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKLOOP: %[[lowerBound:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim1]]]
-//       CHECKLOOP: %[[upperBound:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim1]], %[[dim0]]]
-//       CHECKLOOP: scf.for %[[b:.*]] = %[[lowerBound]] to %[[upperBound]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %[[m:.*]] = %{{.*}} to %[[dim1]] step %{{.*}} {
-//       CHECKLOOP:     %[[dim2:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKLOOP:     %[[aff:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim2]]]
-//       CHECKLOOP:     %[[va:.*]] = load %[[arg0]][%[[aff]]] : memref<?xf32>
-//       CHECKLOOP:     %[[vb:.*]] = load %[[arg1]][%[[m]]] : memref<?xf32>
-//       CHECKLOOP:     %[[vc:.*]] = load %[[arg2]][%[[b]]] : memref<?xf32>
-//       CHECKLOOP:     %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKLOOP:     %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:     store %[[res]], %[[arg2]][%[[b]]] : memref<?xf32>
-
-// CHECKPARALLEL-LABEL: @conv1d
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKPARALLEL: %[[lowerBound:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim1]]]
-//       CHECKPARALLEL: %[[upperBound:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim1]], %[[dim0]]]
-//       CHECKPARALLEL: scf.parallel (%[[b:.*]], %[[m:.*]]) = (%[[lowerBound]], %{{.*}}) to (%[[upperBound]], %[[dim1]]) step ({{.*}}) {
-//       CHECKPARALLEL:   %[[dim2:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKPARALLEL:   %[[aff:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim2]]]
-//       CHECKPARALLEL:   %[[va:.*]] = load %[[arg0]][%[[aff]]] : memref<?xf32>
-//       CHECKPARALLEL:   %[[vb:.*]] = load %[[arg1]][%[[m]]] : memref<?xf32>
-//       CHECKPARALLEL:   %[[vc:.*]] = load %[[arg2]][%[[b]]] : memref<?xf32>
-//       CHECKPARALLEL:   %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKPARALLEL:   %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %[[arg2]][%[[b]]] : memref<?xf32>
-
-#conv_2d_accesses = [
-  affine_map<(m, n, m1, n1)[s0, s1] -> (m + m1 - s0 floordiv 2, n + n1 - s1 floordiv 2)>, // in
-  affine_map<(m, n, m1, n1)[s0, s1] -> (m1, n1)>, // filter
-  affine_map<(m, n, m1, n1)[s0, s1] -> (m, n)> // out
-]
-
-#conv_2d_trait = {
-  args_in = 2,
-  args_out = 1,
-  doc = "C(m,n) += A(m,n) * B(m1,n1)",
-  indexing_maps = #conv_2d_accesses,
-  library_call  = "linalg_conv_2d",
-  n_views = [2, 1],
-  iterator_types = ["parallel", "parallel", "parallel", "parallel"],
-  symbol_source = 1
-}
-
-func @conv2d(%in : memref<?x?xf32>, %filter : memref<?x?xf32>, %out :  memref<?x?xf32>) -> () {
-  linalg.generic #conv_2d_trait
-      ins(%in, %filter : memref<?x?xf32>, memref<?x?xf32>)
-     outs(%out : memref<?x?xf32>) {
-    ^bb0(%a: f32, %b: f32, %c: f32) :
-      %d = mulf %a, %b : f32
-      %e = addf %c, %d : f32
-      linalg.yield %e : f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @conv2d
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim2:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim3:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKLOOP: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim2]]]
-//       CHECKLOOP: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim2]], %[[dim0]]]
-//       CHECKLOOP: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim3]]]
-//       CHECKLOOP: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim3]], %[[dim1]]]
-//       CHECKLOOP: scf.for %[[i0:.*]] = %[[lowerBound1]] to %[[upperBound1]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %[[i1:.*]] = %[[lowerBound2]] to %[[upperBound2]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %[[i2:.*]] = %{{.*}} to %[[dim2]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %[[i3:.*]] = %{{.*}} to %[[dim3]] step %{{.*}} {
-//       CHECKLOOP:         %[[dim4:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[dim5:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim4]]]
-//       CHECKLOOP:         %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim5]]]
-//       CHECKLOOP:         %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[vb:.*]] = load %[[arg1]][%[[i2]], %[[i3]]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKLOOP:         %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:         store %[[res]], %[[arg2]][%[[i0]], %[[i1]]] : memref<?x?xf32>
-
-// CHECKPARALLEL-LABEL: @conv2d
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim2:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim3:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim2]]]
-//       CHECKPARALLEL: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim2]], %[[dim0]]]
-//       CHECKPARALLEL: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim3]]]
-//       CHECKPARALLEL: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim3]], %[[dim1]]]
-//       CHECKPARALLEL: scf.parallel (%[[i0:.*]], %[[i1:.*]], %[[i2:.*]], %[[i3:.*]]) = (%[[lowerBound1]], %[[lowerBound2]], %{{.*}}, %{{.*}}) to (%[[upperBound1]], %[[upperBound2]], %[[dim2]], %[[dim3]]) step ({{.*}}) {
-//       CHECKPARALLEL:   %[[dim4:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[dim5:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim4]]]
-//       CHECKPARALLEL:   %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim5]]]
-//       CHECKPARALLEL:   %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]]] : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[vb:.*]] = load %[[arg1]][%[[i2]], %[[i3]]] : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]]] : memref<?x?xf32>
-//       CHECKPARALLEL:   %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKPARALLEL:   %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %[[arg2]][%[[i0]], %[[i1]]] : memref<?x?xf32>
-
-#conv_3d_accesses = [
-  affine_map<(m, n, k, m1, n1, k1)[s0, s1, s2] -> (m + m1 - s0 floordiv 2, n + n1 - s1 floordiv 2, k + k1 - s2 floordiv 2)>, // in
-  affine_map<(m, n, k, m1, n1, k1)[s0, s1, s2] -> (m1, n1, k1)>, // filter
-  affine_map<(m, n, k, m1, n1, k1)[s0, s1, s2] -> (m, n, k)> // out
-]
-
-#conv_3d_trait = {
-  args_in = 2,
-  args_out = 1,
-  doc = "C(m,n,k) += A(m,n,k) * B(m1,n1,k1)",
-  indexing_maps = #conv_3d_accesses,
-  library_call  = "linalg_conv_3d",
-  n_views = [2, 1],
-  iterator_types = ["parallel", "parallel", "parallel", "parallel", "parallel", "parallel"],
-  symbol_source = 1
-}
-
-func @conv3d(%in : memref<?x?x?xf32>, %filter : memref<?x?x?xf32>, %out :  memref<?x?x?xf32>) -> () {
-  linalg.generic #conv_3d_trait
-      ins(%in, %filter : memref<?x?x?xf32>, memref<?x?x?xf32>)
-     outs(%out : memref<?x?x?xf32>) {
-    ^bb0(%a: f32, %b: f32, %c: f32) :
-      %d = mulf %a, %b : f32
-      %e = addf %c, %d : f32
-      linalg.yield %e : f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @conv3d
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[c2:.*]] = constant 2 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim2:.*]] = dim %[[arg0]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim3:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim4:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim5:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim3]]]
-//       CHECKLOOP: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim3]], %[[dim0]]]
-//       CHECKLOOP: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim4]]]
-//       CHECKLOOP: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim4]], %[[dim1]]]
-//       CHECKLOOP: %[[lowerBound3:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim5]]]
-//       CHECKLOOP: %[[upperBound3:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim5]], %[[dim2]]]
-//       CHECKLOOP: scf.for %[[i0:.*]] = %[[lowerBound1]] to %[[upperBound1]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %[[i1:.*]] = %[[lowerBound2]] to %[[upperBound2]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %[[i2:.*]] = %[[lowerBound3]] to %[[upperBound3]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %[[i3:.*]] = %{{.*}} to %[[dim3]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %[[i4:.*]] = %{{.*}} to %[[dim4]] step %{{.*}} {
-//       CHECKLOOP:           scf.for %[[i5:.*]] = %{{.*}} to %[[dim5]] step %{{.*}} {
-//       CHECKLOOP:             %[[dim6:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[dim7:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[dim8:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim6]]]
-//       CHECKLOOP:             %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim7]]]
-//       CHECKLOOP:             %[[aff3:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim8]]]
-//       CHECKLOOP:             %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]], %[[aff3]]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[vb:.*]] = load %[[arg1]][%[[i3]], %[[i4]], %[[i5]]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]], %[[i2]]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKLOOP:             %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:             store %[[res]], %[[arg2]][%[[i0]], %[[i1]], %[[i2]]] : memref<?x?x?xf32>
-
-// CHECKPARALLEL-LABEL: @conv3d
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[c2:.*]] = constant 2 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim2:.*]] = dim %[[arg0]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim3:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim4:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim5:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim3]]]
-//       CHECKPARALLEL: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim3]], %[[dim0]]]
-//       CHECKPARALLEL: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim4]]]
-//       CHECKPARALLEL: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim4]], %[[dim1]]]
-//       CHECKPARALLEL: %[[lowerBound3:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim5]]]
-//       CHECKPARALLEL: %[[upperBound3:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim5]], %[[dim2]]]
-//       CHECKPARALLEL: scf.parallel (%[[i0:.*]], %[[i1:.*]], %[[i2:.*]], %[[i3:.*]], %[[i4:.*]], %[[i5:.*]]) = (%[[lowerBound1]], %[[lowerBound2]], %[[lowerBound3]], %{{.*}}, %{{.*}}, %{{.*}}) to (%[[upperBound1]], %[[upperBound2]], %[[upperBound3]], %[[dim3]], %[[dim4]], %[[dim5]]) step ({{.*}}) {
-//       CHECKPARALLEL:   %[[dim6:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[dim7:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[dim8:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim6]]]
-//       CHECKPARALLEL:   %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim7]]]
-//       CHECKPARALLEL:   %[[aff3:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim8]]]
-//       CHECKPARALLEL:   %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]], %[[aff3]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[vb:.*]] = load %[[arg1]][%[[i3]], %[[i4]], %[[i5]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]], %[[i2]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:   %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKPARALLEL:   %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %[[arg2]][%[[i0]], %[[i1]], %[[i2]]] : memref<?x?x?xf32>
-
-#conv_4d_accesses = [
-  affine_map<(m, n, k, l, m1, n1, k1, l1)[s0, s1, s2, s3] -> (m + m1 - s0 floordiv 2, n + n1 - s1 floordiv 2, k + k1 - s2 floordiv 2, l + l1 - s3 floordiv 2)>, // in
-  affine_map<(m, n, k, l, m1, n1, k1, l1)[s0, s1, s2, s3] -> (m1, n1, k1, l1)>, // filter
-  affine_map<(m, n, k, l, m1, n1, k1, l1)[s0, s1, s2, s3] -> (m, n, k, l)> // out
-]
-
-#conv_4d_trait = {
-  args_in = 2,
-  args_out = 1,
-  doc = "C(m,n,k,l) += A(m,n,k,l) * B(m1,n1,k1,l1)",
-  indexing_maps = #conv_4d_accesses,
-  library_call  = "linalg_conv_4d",
-  n_views = [2, 1],
-  iterator_types = ["parallel", "parallel", "parallel", "parallel", "parallel", "parallel", "parallel", "parallel"],
-  symbol_source = 1
-}
-
-func @conv4d(%in : memref<?x?x?x?xf32>, %filter : memref<?x?x?x?xf32>, %out :  memref<?x?x?x?xf32>) -> () {
-  linalg.generic #conv_4d_trait
-      ins(%in, %filter : memref<?x?x?x?xf32>, memref<?x?x?x?xf32>)
-     outs(%out : memref<?x?x?x?xf32>) {
-    ^bb0(%a: f32, %b: f32, %c: f32) :
-      %d = mulf %a, %b : f32
-      %e = addf %c, %d : f32
-      linalg.yield %e : f32
-  }
-  return
-}
-
-// CHECKLOOP-LABEL: @conv4d
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[c2:.*]] = constant 2 : index
-//       CHECKLOOP: %[[c3:.*]] = constant 3 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim2:.*]] = dim %[[arg0]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim3:.*]] = dim %[[arg0]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim4:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim5:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim6:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[dim7:.*]] = dim %[[arg1]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKLOOP: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim4]]]
-//       CHECKLOOP: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim4]], %[[dim0]]]
-//       CHECKLOOP: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim5]]]
-//       CHECKLOOP: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim5]], %[[dim1]]]
-//       CHECKLOOP: %[[lowerBound3:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim6]]]
-//       CHECKLOOP: %[[upperBound3:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim6]], %[[dim2]]]
-//       CHECKLOOP: %[[lowerBound4:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim7]]]
-//       CHECKLOOP: %[[upperBound4:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim7]], %[[dim3]]]
-//       CHECKLOOP: scf.for %[[i0:.*]] = %[[lowerBound1]] to %[[upperBound1]] step %{{.*}} {
-//       CHECKLOOP:   scf.for %[[i1:.*]] = %[[lowerBound2]] to %[[upperBound2]] step %{{.*}} {
-//       CHECKLOOP:     scf.for %[[i2:.*]] = %[[lowerBound3]] to %[[upperBound3]] step %{{.*}} {
-//       CHECKLOOP:       scf.for %[[i3:.*]] = %[[lowerBound4]] to %[[upperBound4]] step %{{.*}} {
-//       CHECKLOOP:         scf.for %[[i4:.*]] = %{{.*}} to %[[dim4]] step %{{.*}} {
-//       CHECKLOOP:           scf.for %[[i5:.*]] = %{{.*}} to %[[dim5]] step %{{.*}} {
-//       CHECKLOOP:             scf.for %[[i6:.*]] = %{{.*}} to %[[dim6]] step %{{.*}} {
-//       CHECKLOOP:               scf.for %[[i7:.*]] = %{{.*}} to %[[dim7]] step %{{.*}} {
-//       CHECKLOOP:                 %[[dim8:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[dim9:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[dim10:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[dim11:.*]] = dim %[[arg1]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim8]]]
-//       CHECKLOOP:                 %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim9]]]
-//       CHECKLOOP:                 %[[aff3:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim10]]]
-//       CHECKLOOP:                 %[[aff4:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim11]]]
-//       CHECKLOOP:                 %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]], %[[aff3]], %[[aff4]]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[vb:.*]] = load %[[arg1]][%[[i4]], %[[i5]], %[[i6]], %[[i7]]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]], %[[i2]], %[[i3]]] : memref<?x?x?x?xf32>
-//       CHECKLOOP:                 %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKLOOP:                 %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:                 store %[[res]], %[[arg2]][%[[i0]], %[[i1]], %[[i2]], %[[i3]]] : memref<?x?x?x?xf32>
-
-// CHECKPARALLEL-LABEL: @conv4d
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[c2:.*]] = constant 2 : index
-//       CHECKPARALLEL: %[[c3:.*]] = constant 3 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg0]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg0]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim2:.*]] = dim %[[arg0]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim3:.*]] = dim %[[arg0]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim4:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim5:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim6:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[dim7:.*]] = dim %[[arg1]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL: %[[lowerBound1:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim4]]]
-//       CHECKPARALLEL: %[[upperBound1:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim4]], %[[dim0]]]
-//       CHECKPARALLEL: %[[lowerBound2:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim5]]]
-//       CHECKPARALLEL: %[[upperBound2:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim5]], %[[dim1]]]
-//       CHECKPARALLEL: %[[lowerBound3:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim6]]]
-//       CHECKPARALLEL: %[[upperBound3:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim6]], %[[dim2]]]
-//       CHECKPARALLEL: %[[lowerBound4:.*]] = affine.apply #[[$convLowerBound]]()[%[[dim7]]]
-//       CHECKPARALLEL: %[[upperBound4:.*]] = affine.apply #[[$convUpperBound]]()[%[[dim7]], %[[dim3]]]
-//       CHECKPARALLEL: scf.parallel (%[[i0:.*]], %[[i1:.*]], %[[i2:.*]], %[[i3:.*]], %[[i4:.*]], %[[i5:.*]], %[[i6:.*]], %[[i7:.*]]) = (%[[lowerBound1]], %[[lowerBound2]], %[[lowerBound3]], %[[lowerBound4]], %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) to (%[[upperBound1]], %[[upperBound2]], %[[upperBound3]], %[[upperBound4]], %[[dim4]], %[[dim5]], %[[dim6]], %[[dim7]]) step ({{.*}}) {
-//       CHECKPARALLEL:   %[[dim8:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[dim9:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[dim10:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[dim11:.*]] = dim %[[arg1]], %[[c3]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[aff1:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim8]]]
-//       CHECKPARALLEL:   %[[aff2:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim9]]]
-//       CHECKPARALLEL:   %[[aff3:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim10]]]
-//       CHECKPARALLEL:   %[[aff4:.*]] = affine.apply #[[$convMap]](%{{.*}}, %{{.*}})[%[[dim11]]]
-//       CHECKPARALLEL:   %[[va:.*]] = load %[[arg0]][%[[aff1]], %[[aff2]], %[[aff3]], %[[aff4]]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[vb:.*]] = load %[[arg1]][%[[i4]], %[[i5]], %[[i6]], %[[i7]]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[vc:.*]] = load %[[arg2]][%[[i0]], %[[i1]], %[[i2]], %[[i3]]] : memref<?x?x?x?xf32>
-//       CHECKPARALLEL:   %[[inc:.*]] = mulf %[[va]], %[[vb]] : f32
-//       CHECKPARALLEL:   %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:   store %[[res]], %[[arg2]][%[[i0]], %[[i1]], %[[i2]], %[[i3]]] : memref<?x?x?x?xf32>
-
-func @conv1d_no_symbols(%in : memref<?xf32>, %filter : memref<?xf32>, %out : memref<?xf32>) -> () {
-  linalg.conv_1d ins(%in, %filter : memref<?xf32>, memref<?xf32>)
-                outs(%out : memref<?xf32>)
-  return
-}
-
-// CHECKLOOP-LABEL: @conv1d_no_symbols
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg2]], %[[c0]] : memref<?xf32>
-//       CHECKLOOP: scf.for %[[b:.*]] = %[[c0]] to %[[dim1]] step %[[c1]] {
-//       CHECKLOOP:   scf.for %[[m:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKLOOP:     %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[b]], %[[m]])
-//       CHECKLOOP:     %[[vb:.*]] = load %[[arg0]][%[[aff]]] : memref<?xf32>
-//       CHECKLOOP:     %[[va:.*]] = load %[[arg1]][%[[m]]] : memref<?xf32>
-//       CHECKLOOP:     %[[vc:.*]] = load %[[arg2]][%[[b]]] : memref<?xf32>
-//       CHECKLOOP:     %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKLOOP:     %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:     store %[[res]], %[[arg2]][%[[b]]] : memref<?xf32>
-
-// CHECKPARALLEL-LABEL: @conv1d_no_symbols
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg2]], %[[c0]] : memref<?xf32>
-//       CHECKPARALLEL: scf.parallel (%[[b:.*]]) = (%[[c0]]) to (%[[dim1]]) step (%[[c1]]) {
-//       CHECKPARALLEL:   scf.for %[[m:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKPARALLEL:     %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[b]], %[[m]])
-//       CHECKPARALLEL:     %[[vb:.*]] = load %[[arg0]][%[[aff]]] : memref<?xf32>
-//       CHECKPARALLEL:     %[[va:.*]] = load %[[arg1]][%[[m]]] : memref<?xf32>
-//       CHECKPARALLEL:     %[[vc:.*]] = load %[[arg2]][%[[b]]] : memref<?xf32>
-//       CHECKPARALLEL:     %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKPARALLEL:     %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:     store %[[res]], %[[arg2]][%[[b]]] : memref<?xf32>
-
-
-func @conv2d_no_symbols(%in : memref<?x?xf32>, %filter : memref<?x?xf32>, %out : memref<?x?xf32>) -> () {
-  linalg.conv_2d ins(%in, %filter : memref<?x?xf32>, memref<?x?xf32>)
-                outs(%out: memref<?x?xf32>)
-  return
-}
-// CHECKLOOP-LABEL: @conv2d_no_symbols
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim2:.*]] = dim %[[arg2]], %[[c0]] : memref<?x?xf32>
-//       CHECKLOOP: %[[dim3:.*]] = dim %[[arg2]], %[[c1]] : memref<?x?xf32>
-//       CHECKLOOP: scf.for %[[arg3:.*]] = %[[c0]] to %[[dim2]] step %[[c1]] {
-//       CHECKLOOP:   scf.for %[[arg4:.*]] = %[[c0]] to %[[dim3]] step %[[c1]] {
-//       CHECKLOOP:     scf.for %[[arg5:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKLOOP:       scf.for %[[arg6:.*]] = %[[c0]] to %[[dim1]] step %[[c1]] {
-//       CHECKLOOP:         %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg3]], %[[arg5]])
-//       CHECKLOOP:         %[[aff2:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg4]], %[[arg6]])
-//       CHECKLOOP:         %[[vb:.*]] = load %[[arg0]][%[[aff]], %[[aff2]]] : memref<?x?xf32>
-
-//       CHECKLOOP:         %[[va:.*]] = load %[[arg1]][%[[arg5]], %[[arg6]]] : memref<?x?xf32>
-//       CHECKLOOP:         %[[vc:.*]] = load %[[arg2]][%[[arg3]], %[[arg4]]] : memref<?x?xf32>
-
-//       CHECKLOOP:         %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKLOOP:         %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:         store %[[res]], %[[arg2]][%[[arg3]], %[[arg4]]] : memref<?x?xf32>
-
-// CHECKPARALLEL-LABEL: @conv2d_no_symbols
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?xf32>
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim2:.*]] = dim %[[arg2]], %[[c0]] : memref<?x?xf32>
-//       CHECKPARALLEL: %[[dim3:.*]] = dim %[[arg2]], %[[c1]] : memref<?x?xf32>
-//       CHECKPARALLEL: scf.parallel (%[[arg3:.*]], %[[arg4:.*]]) = (%[[c0]], %[[c0]]) to (%[[dim2]], %[[dim3]]) step (%[[c1]], %[[c1]]) {
-//       CHECKPARALLEL:   scf.for %[[arg5:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKPARALLEL:     scf.for %[[arg6:.*]] = %[[c0]] to %[[dim1]] step %[[c1]] {
-//       CHECKPARALLEL:       %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg3]], %[[arg5]])
-//       CHECKPARALLEL:       %[[aff2:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg4]], %[[arg6]])
-//       CHECKPARALLEL:       %[[vb:.*]] = load %[[arg0]][%[[aff]], %[[aff2]]] : memref<?x?xf32>
-//       CHECKPARALLEL:       %[[va:.*]] = load %[[arg1]][%[[arg5]], %[[arg6]]] : memref<?x?xf32>
-//       CHECKPARALLEL:       %[[vc:.*]] = load %[[arg2]][%[[arg3]], %[[arg4]]] : memref<?x?xf32>
-//       CHECKPARALLEL:       %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKPARALLEL:       %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:       store %[[res]], %[[arg2]][%[[arg3]], %[[arg4]]] : memref<?x?xf32>
-
-
-func @conv3d_no_symbols(%in : memref<?x?x?xf32>, %filter : memref<?x?x?xf32>, %out : memref<?x?x?xf32>) -> () {
-  linalg.conv_3d ins(%in, %filter : memref<?x?x?xf32>, memref<?x?x?xf32>)
-                outs(%out : memref<?x?x?xf32>)
-  return
-}
-
-// CHECKLOOP-LABEL: @conv3d_no_symbols
-//  CHECKLOOP-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKLOOP-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKLOOP: %[[c2:.*]] = constant 2 : index
-//       CHECKLOOP: %[[c0:.*]] = constant 0 : index
-//       CHECKLOOP: %[[c1:.*]] = constant 1 : index
-//       CHECKLOOP: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim1:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim2:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim3:.*]] = dim %[[arg2]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim4:.*]] = dim %[[arg2]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKLOOP: %[[dim5:.*]] = dim %[[arg2]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKLOOP: scf.for %[[arg3:.*]] = %[[c0]] to %[[dim3]] step %[[c1]] {
-//       CHECKLOOP:   scf.for %[[arg4:.*]] = %[[c0]] to %[[dim4]] step %[[c1]] {
-//       CHECKLOOP:     scf.for %[[arg5:.*]] = %[[c0]] to %[[dim5]] step %[[c1]] {
-//       CHECKLOOP:       scf.for %[[arg6:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKLOOP:         scf.for %[[arg7:.*]] = %[[c0]] to %[[dim1]] step %[[c1]] {
-//       CHECKLOOP:           scf.for %[[arg8:.*]] = %[[c0]] to %[[dim2]] step %[[c1]] {
-//       CHECKLOOP:             %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg3]], %[[arg6]])
-//       CHECKLOOP:             %[[aff2:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg4]], %[[arg7]])
-//       CHECKLOOP:             %[[aff3:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg5]], %[[arg8]])
-//       CHECKLOOP:             %[[vb:.*]] = load %[[arg0]][%[[aff]], %[[aff2]], %[[aff3]]] : memref<?x?x?xf32>
-
-//       CHECKLOOP:             %[[va:.*]] = load %[[arg1]][%[[arg6]], %[[arg7]], %[[arg8]]] : memref<?x?x?xf32>
-//       CHECKLOOP:             %[[vc:.*]] = load %[[arg2]][%[[arg3]], %[[arg4]], %[[arg5]]] : memref<?x?x?xf32>
-
-//       CHECKLOOP:             %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKLOOP:             %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKLOOP:             store %[[res]], %[[arg2]][%[[arg3]], %[[arg4]], %[[arg5]]] : memref<?x?x?xf32>
-
-// CHECKPARALLEL-LABEL: @conv3d_no_symbols
-//  CHECKPARALLEL-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//  CHECKPARALLEL-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[c2:.*]] = constant 2 : index
-//       CHECKPARALLEL: %[[c0:.*]] = constant 0 : index
-//       CHECKPARALLEL: %[[c1:.*]] = constant 1 : index
-//       CHECKPARALLEL: %[[dim0:.*]] = dim %[[arg1]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim1:.*]] = dim %[[arg1]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim2:.*]] = dim %[[arg1]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim3:.*]] = dim %[[arg2]], %[[c0]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim4:.*]] = dim %[[arg2]], %[[c1]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: %[[dim5:.*]] = dim %[[arg2]], %[[c2]] : memref<?x?x?xf32>
-//       CHECKPARALLEL: scf.parallel (%[[arg3:.*]], %[[arg4:.*]], %[[arg5:.*]]) = (%[[c0]], %[[c0]], %[[c0]]) to (%[[dim3]], %[[dim4]], %[[dim5]]) step (%[[c1]], %[[c1]], %[[c1]]) {
-//       CHECKPARALLEL:   scf.for %[[arg6:.*]] = %[[c0]] to %[[dim0]] step %[[c1]] {
-//       CHECKPARALLEL:     scf.for %[[arg7:.*]] = %[[c0]] to %[[dim1]] step %[[c1]] {
-//       CHECKPARALLEL:       scf.for %[[arg8:.*]] = %[[c0]] to %[[dim2]] step %[[c1]] {
-//       CHECKPARALLEL:         %[[aff:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg3]], %[[arg6]])
-//       CHECKPARALLEL:         %[[aff2:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg4]], %[[arg7]])
-//       CHECKPARALLEL:         %[[aff3:.*]] = affine.apply #[[$stride1Dilation1]](%[[arg5]], %[[arg8]])
-//       CHECKPARALLEL:         %[[vb:.*]] = load %[[arg0]][%[[aff]], %[[aff2]], %[[aff3]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:         %[[va:.*]] = load %[[arg1]][%[[arg6]], %[[arg7]], %[[arg8]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:         %[[vc:.*]] = load %[[arg2]][%[[arg3]], %[[arg4]], %[[arg5]]] : memref<?x?x?xf32>
-//       CHECKPARALLEL:         %[[inc:.*]] = mulf %[[vb]], %[[va]] : f32
-//       CHECKPARALLEL:         %[[res:.*]] = addf %[[vc]], %[[inc]] : f32
-//       CHECKPARALLEL:         store %[[res]], %[[arg2]][%[[arg3]], %[[arg4]], %[[arg5]]] : memref<?x?x?xf32>