[mlir][Linalg] Drop deprecated convolution vectorization patterns

[nicolasvasilache]

This was folded and merged into c8f5735301993c363c16ce5ddda6f1f6cb968090 during a rebase.

[nicolasvasilache]

Rebase post revert.

[nicolasvasilache]

Drop old tests.

[nicolasvasilache]

https://buildkite.com/llvm-project/premerge-checks/builds/74313#bc3eefd3-52f4-4d4b-beed-0c2a170d22f5 now shows 1 unrelated failure:

Failed Tests (1):
  MLIR :: Examples/standalone/test.toy
Re-landing.

mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h

 //===----------------------------------------------------------------------===//
 // Transformations exposed as function calls.
 //===----------------------------------------------------------------------===//
 using LinalgLoops = SmallVector<Operation *, 4>;
 
 void populatePadTensorTilingPatterns(RewritePatternSet &patterns,
                                      const LinalgTilingOptions &options);
 
-/// [DEPRECATED] Populate patterns for vectorization of all ConvN-D ops.
-void populateConvVectorizationPatterns(
-    MLIRContext *context, SmallVectorImpl<RewritePatternSet> &patterns,
-    ArrayRef<int64_t> tileSizes);
-
 /// Populate patterns for vectorizing low-D convolution ops. This is a step in
 /// progressive lowering for convolution ops, it assume high-D convolution ops
 /// were decomposed previously.
 void populateConvolutionVectorizationPatterns(RewritePatternSet &patterns,
                                               PatternBenefit benefit = 1);
 
 /// Populate patterns that convert `ElementwiseMappable` ops to linalg
 /// parallel loops.

 struct LinalgCopyVTWForwardingPattern
     : public OpRewritePattern<vector::TransferWriteOp> {
   using OpRewritePattern<vector::TransferWriteOp>::OpRewritePattern;
 
   LogicalResult matchAndRewrite(vector::TransferWriteOp xferOp,
                                 PatternRewriter &rewriter) const override;
 };
 
-/// Converts Convolution op into vector contraction.
-///
-/// Conversion expects ConvOp to have dimensions marked in the *mask* as
-/// false of size 1. This ensures that the ConvOp can be lowered to vector
-/// contraction of dimensions marked in the *mask* as true.
-///
-/// A good example for vectorization is ConvNHWCOp which is 2D Conv op
-/// with channels as the last dimension. Let's vectorize last 3 dimensions.
-/// The initial op definition looks like this:
-/// ```
-/// linalg.conv_2d_nhwc  %arg0, %arg1, %arg2 :
-///   (memref<1x3x3x3xf32>, memref<1x3x3x3xf32>, memref<?x?x?x?xf32>)
-/// ```
-/// This op can be expressed as a dot product between %arg0 (input) and
-/// %arg1 (kernel) which is written into first entry of %arg2 (output). This is
-/// the ConvOp this pass expects and converts into:
-/// ```
-/// #map0 = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
-/// #map1 = affine_map<(d0, d1, d2) -> ()>
-/// .....
-/// %0 = vector.transfer_read %arg0[%c0, %c0, %c0, %c0], %c0_f32
-///   : memref<1x3x3x3xf32>, vector<3x3x3xf32>
-/// %1 = vector.transfer_read %arg1[%c0, %c0, %c0, %c0], %c0_f32
-///   : memref<1x3x3x3xf32>, vector<3x3x3xf32>
-/// %2 = vector.contract {indexing_maps = [#map0, #map0, #map1],
-///   iterator_types = ["reduction", "reduction", "reduction"]} %0, %1,
-///   %c0_f32 : vector<3x3x3xf32>, vector<3x3x3xf32> into f32
-/// store %2, %arg2[%c0, %c0, %c0, %c0] : memref<?x?x?x?xf32>
-/// ```
-/// where first 2 operations read input and kernel memory buffers into vectors.
-/// Subsequently, they are contracted together and the result is written to
-/// the first entry of the output buffer.
-template <typename ConvOp, int N>
-class ConvOpVectorization : public OpRewritePattern<ConvOp> {
-  using OpRewritePattern<ConvOp>::OpRewritePattern;
-  SmallVector<bool, 4> mask;
-
-public:
-  ConvOpVectorization(MLIRContext *context, const SmallVector<bool, 4> &msk)
-      : OpRewritePattern<ConvOp>(context) {
-    assert(msk.size() == N && "Mask size does not match rank");
-    this->mask = msk;
-  }
-
-  LogicalResult matchAndRewrite(ConvOp minOp,
-                                PatternRewriter &rewriter) const override;
-};
-
 /// Rewrite a TiledLoopOp with bounds/step that potentially do not divide evenly
 /// into a TiledLoopOp where the step divides the iteration space evenly,
 /// followed by another TiledLoopOp for the last (partial) iteration (if any).
 /// This transformation is called "loop peeling".
 ///
 /// This function peels the `idx`-th loop of the TiledLoopOp. To tile all loops
 /// in the loop nest, this function must be called multiple times.
 ///

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

patterns.add<GenericPadTensorOpVectorizationPattern>(patterns.getContext(),
                                                        baseBenefit);
   // Try these specialized patterns first before resorting to the generic one.
   patterns.add<PadTensorOpVectorizationWithTransferReadPattern,
                PadTensorOpVectorizationWithTransferWritePattern,
                PadTensorOpVectorizationWithInsertSlicePattern>(
       patterns.getContext(), baseBenefit.getBenefit() + 1);
 }
 
-// TODO: cleanup all the convolution vectorization patterns.
-template <class ConvOp, int N>
-LogicalResult ConvOpVectorization<ConvOp, N>::matchAndRewrite(
-    ConvOp op, PatternRewriter &rewriter) const {
-  Location loc = op.getLoc();
-  MLIRContext *context = op.getContext();
-
-  OpOperand *input = op.getInputOperand(0);
-  OpOperand *kernel = op.getInputOperand(1);
-  OpOperand *output = op.getOutputOperand(0);
-  ArrayRef<int64_t> inShape = op.getShape(input);
-  ArrayRef<int64_t> kShape = op.getShape(kernel);
-
-  if (llvm::any_of(inShape, ShapedType::isDynamic) ||
-      llvm::any_of(kShape, ShapedType::isDynamic))
-    return failure();
-
-  SmallVector<AffineExpr, 4> mapping;
-  SmallVector<int64_t, 4> vectorDims;
-  // Fail to apply when the size of not vectorized dimension is not 1.
-  for (unsigned i = 0; i < N; i++) {
-    if (!mask[i] && (inShape[i] != 1 || kShape[i] != 1))
-      return failure();
-
-    if (mask[i] && inShape[i] != kShape[i])
-      return failure();
-
-    if (mask[i]) {
-      mapping.push_back(getAffineDimExpr(i, context));
-      vectorDims.push_back(inShape[i]);
-    }
-  }
-
-  int64_t rank = op.getRank(input);
-  int64_t numDims = mapping.size();
-  Type elemType = getElementTypeOrSelf(input->get());
-
-  auto map = AffineMap::get(rank, 0, mapping, context);
-  SmallVector<Value, 4> zeros(rank,
-                              rewriter.create<arith::ConstantIndexOp>(loc, 0));
-  auto vecType = VectorType::get(vectorDims, elemType);
-
-  auto inputVec = rewriter.create<vector::TransferReadOp>(
-      loc, vecType, input->get(), zeros, map);
-  auto kernelVec = rewriter.create<vector::TransferReadOp>(
-      loc, vecType, kernel->get(), zeros, map);
-
-  auto acc = rewriter.create<arith::ConstantOp>(loc, elemType,
-                                                rewriter.getZeroAttr(elemType));
-
-  std::array<AffineMap, 3> indexingMaps{
-      AffineMap::getMultiDimIdentityMap(numDims, context),
-      AffineMap::getMultiDimIdentityMap(numDims, context),
-      AffineMap::get(numDims, 0, {}, context)};
-
-  std::vector<StringRef> iteratorTypes(numDims, "reduction");
-
-  auto result = rewriter.create<vector::ContractionOp>(
-      loc, inputVec, kernelVec, acc,
-      rewriter.getAffineMapArrayAttr(indexingMaps),
-      rewriter.getStrArrayAttr(iteratorTypes));
-
-  rewriter.create<memref::StoreOp>(loc, result, output->get(),
-                                   ValueRange(zeros));
-  rewriter.eraseOp(op);
-  return success();
-}
-
-/// Inserts tiling, promotion and vectorization pattern for ConvOp
-/// conversion into corresponding pattern lists.
-template <typename ConvOp, unsigned N>
-static void populateVectorizationPatterns(
-    RewritePatternSet &tilingPatterns, RewritePatternSet &promotionPatterns,
-    RewritePatternSet &vectorizationPatterns, ArrayRef<int64_t> tileSizes) {
-  auto *context = tilingPatterns.getContext();
-  if (tileSizes.size() < N)
-    return;
-
-  constexpr static StringRef kTiledMarker = "TILED";
-  constexpr static StringRef kPromotedMarker = "PROMOTED";
-  tilingPatterns.add<LinalgTilingPattern>(
-      ConvOp::getOperationName(), context,
-      LinalgTilingOptions().setTileSizes(tileSizes),
-      LinalgTransformationFilter(ArrayRef<StringAttr>{},
-                                 StringAttr::get(context, kTiledMarker)));
-
-  promotionPatterns.add<LinalgPromotionPattern<ConvOp>>(
-      context, LinalgPromotionOptions().setUseFullTileBuffersByDefault(true),
-      LinalgTransformationFilter(StringAttr::get(context, kTiledMarker),
-                                 StringAttr::get(context, kPromotedMarker)));
-
-  SmallVector<bool, 4> mask(N);
-  int offset = tileSizes.size() - N;
-  std::transform(tileSizes.begin() + offset, tileSizes.end(), mask.begin(),
-                 [](int64_t i) -> bool { return i > 1; });
-
-  vectorizationPatterns.add<ConvOpVectorization<ConvOp, N>>(context, mask);
-}
-
-void mlir::linalg::populateConvVectorizationPatterns(
-    MLIRContext *context, SmallVectorImpl<RewritePatternSet> &patterns,
-    ArrayRef<int64_t> tileSizes) {
-  RewritePatternSet tiling(context);
-  RewritePatternSet promotion(context);
-  RewritePatternSet vectorization(context);
-  populateVectorizationPatterns<Conv1DOp, 1>(tiling, promotion, vectorization,
-                                             tileSizes);
-
-  populateVectorizationPatterns<Conv2DOp, 2>(tiling, promotion, vectorization,
-                                             tileSizes);
-
-  populateVectorizationPatterns<Conv3DOp, 3>(tiling, promotion, vectorization,
-                                             tileSizes);
-
-  populateVectorizationPatterns<Conv1DNwcWcfOp, 3>(tiling, promotion,
-                                                   vectorization, tileSizes);
-
-  populateVectorizationPatterns<Conv2DNhwcHwcfOp, 4>(tiling, promotion,
-                                                     vectorization, tileSizes);
-
-  populateVectorizationPatterns<Conv3DNdhwcDhwcfOp, 5>(
-      tiling, promotion, vectorization, tileSizes);
-
-  patterns.push_back(std::move(tiling));
-  patterns.push_back(std::move(promotion));
-  patterns.push_back(std::move(vectorization));
-}
-
 //----------------------------------------------------------------------------//
 // Forwarding patterns
 //----------------------------------------------------------------------------//
 
 /// Check whether there is any interleaved use of any `values` between
 /// `firstOp` and `secondOp`. Conservatively return `true` if any op or value
 /// is in a different block.
 static bool mayExistInterleavedUses(Operation *firstOp, Operation *secondOp,

mlir/test/Conversion/LinalgToVector/linalg-to-vector.mlir

-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,3" --cse -split-input-file
-// | FileCheck %s
-
-// CHECK-DAG:  #[[$map0:.*]] = affine_map<(d0)[s0] -> (1, -d0 + s0)>
-// CHECK-DAG:  #[[$map1:.*]] = affine_map<(d0)[s0] -> (d0 + s0)>
-// CHECK-DAG:  #[[$map2:.*]] = affine_map<(d0, d1) -> (d0 + d1)>
-// CHECK-DAG:  #[[$map3:.*]] = affine_map<(d0, d1)[s0] -> (3, -d0 - d1 + s0)>
-// CHECK-DAG:  #[[$map4:.*]] = affine_map<(d0)[s0] -> (3, -d0 + s0)>
-
-// CHECK-LABEL: @conv_1d
-//  CHECK-SAME: %[[arg0:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECK-SAME: %[[arg1:[a-zA-Z0-9]+]]: memref<?xf32>
-//  CHECK-SAME: %[[arg2:[a-zA-Z0-9]+]]: memref<?xf32
-func @conv_1d(%arg0: memref<?xf32>, %arg1: memref<?xf32>, %arg2: memref<?xf32>) {
-//   CHECK-DAG:   %[[c12:.*]] = arith.constant 12 : index
-//   CHECK-DAG:   %[[c4:.*]] = arith.constant 4 : index
-//   CHECK-DAG:   %[[cst:.*]] = arith.constant 0.000000e+00 : f32
-//   CHECK-DAG:   %[[c3:.*]] = arith.constant 3 : index
-//   CHECK-DAG:   %[[c0:.*]] = arith.constant 0 : index
-//   CHECK-DAG:   %[[c1:.*]] = arith.constant 1 : index
-//       CHECK:   %[[v0:.*]] = memref.dim %[[arg1]], %[[c0]] : memref<?xf32>
-//       CHECK:   %[[v1:.*]] = memref.dim %[[arg2]], %[[c0]] : memref<?xf32>
-//       CHECK:   %[[v2:.*]] = memref.dim %[[arg0]], %[[c0]] : memref<?xf32>
-//       CHECK:   %[[v3:.*]] = memref.alloc(%[[c12]]) : memref<?xi8>
-//       CHECK:   %[[v4:.*]] = memref.alloc(%[[c12]]) : memref<?xi8>
-//       CHECK:   %[[v5:.*]] = memref.alloc(%[[c4]]) : memref<?xi8>
-//       CHECK:   %[[v6:.*]] = memref.view %[[v3]][%[[c0]]][] : memref<?xi8> to memref<3xf32>
-//       CHECK:   %[[v7:.*]] = memref.view %[[v4]][%[[c0]]][] : memref<?xi8> to memref<3xf32>
-//       CHECK:   %[[v8:.*]] = memref.view %[[v5]][%[[c0]]][] : memref<?xi8> to memref<1xf32>
-//       CHECK:   scf.for %[[arg3:.*]] = %[[c0]] to %[[v1]] step %[[c1]] {
-//       CHECK:     %[[v9:.*]] = affine.min #[[$map0]](%[[arg3]])[%[[v1]]]
-//       CHECK:     %[[v10:.*]] = subview %[[arg2]][%[[arg3]]] [%[[v9]]] [1]  : memref<?xf32> to memref<?xf32, #[[$map1]]>
-//       CHECK:     %[[v11:.*]] = subview %[[v8]][0] [%[[v9]]] [1]  : memref<1xf32> to memref<?xf32>
-//       CHECK:     scf.for %[[arg4:.*]] = %[[c0]] to %[[v0]] step %[[c3]] {
-//       CHECK:       %[[v12:.*]] = affine.apply #[[$map2]](%[[arg3]], %[[arg4]])
-//       CHECK:       %[[v13:.*]] = affine.min #[[$map3]](%[[arg3]], %[[arg4]])[%[[v2]]]
-//       CHECK:       %[[v14:.*]] = subview %arg0[%12] [%13] [1]  : memref<?xf32> to memref<?xf32, #[[$map1]]>
-//       CHECK:       %[[v15:.*]] = affine.min #[[$map4]](%arg4)[%0]
-//       CHECK:       %[[v16:.*]] = subview %[[arg1]][%[[arg4]]] [%[[v15]]] [1]  : memref<?xf32> to memref<?xf32, #[[$map1]]>
-//       CHECK:       %[[v17:.*]] = subview %[[v6]][0] [%[[v13]]] [1]  : memref<3xf32> to memref<?xf32>
-//       CHECK:       %[[v19:.*]] = vector.transfer_read %[[v6]][%[[c0]]], %[[cst]] {in_bounds = [true]} : memref<3xf32>, vector<3xf32>
-//       CHECK:       %[[v20:.*]] = vector.transfer_read %[[v7]][%[[c0]]], %[[cst]] {in_bounds = [true]} : memref<3xf32>, vector<3xf32>
-//       CHECK:       %[[v21:.*]] = arith.mulf %[[v19]], %[[v20]] : vector<3xf32>
-//       CHECK:       %[[v22:.*]] = vector.reduction "add", %[[v21]], %[[cst]] : vector<3xf32> into f32
-//       CHECK:       store %[[v22]], %[[v8]][%[[c0]]] : memref<1xf32>
-//       CHECK:       scf.for %[[arg5:.*]] = %[[c0]] to %[[v9]] step %[[c1]] {
-//       CHECK:         %[[v23:.*]] = load %[[v11]][%[[arg5]]] : memref<?xf32>
-//       CHECK:         store %[[v23]], %[[v10]][%[[arg5]]] : memref<?xf32, #[[$map1]]>
-  linalg.conv_1d ins(%arg0, %arg1 : memref<?xf32>, memref<?xf32>)
-                outs(%arg2 : memref<?xf32>)
-  return
-}
-

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=4" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=4" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns a 1-D buffer of size %s1 filled with the value %f
 func @alloc_1d_filled_f32(%s1 : index, %f : f32) -> memref<?xf32> {
   %buf = memref.alloc(%s1) : memref<?xf32>
   linalg.fill(%f, %buf) : f32, memref<?xf32>
   return %buf : memref<?xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-1d-nwc-wcf-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,1,1,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,4" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,1,1,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f
 func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> {
   %buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32>
   linalg.fill(%f, %buf) : f32, memref<?x?x?xf32>
   return %buf : memref<?x?x?xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,1,3,3"  -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,1,3,3"  -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns a 2-D buffer of size (%s1, %s2) filled with the value %f
 func @alloc_2d_filled_f32(%s1 : index, %s2 : index, %f : f32) -> memref<?x?xf32> {
   %buf = memref.alloc(%s1, %s2) : memref<?x?xf32>
   linalg.fill(%f, %buf) : f32, memref<?x?xf32>
   return %buf : memref<?x?xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-2d-nhwc-hwcf-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,3,3,2" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns 4-D buffer of size (%s1, %s2, %s3, %s4) filled with the value %f
 func @alloc_4d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %f : f32) -> memref<?x?x?x?xf32> {
   %buf = memref.alloc(%s1, %s2, %s3, %s4) : memref<?x?x?x?xf32>
   linalg.fill(%f, %buf) : f32, memref<?x?x?x?xf32>
   return %buf : memref<?x?x?x?xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=2,2,2" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,1,1,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns 3-D buffer of size (%s1, %s2, %s3) filled with the value %f
 func @alloc_3d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %f : f32) -> memref<?x?x?xf32> {
   %buf = memref.alloc(%s1, %s2, %s3) : memref<?x?x?xf32>
   linalg.fill(%f, %buf) : f32, memref<?x?x?xf32>
   return %buf : memref<?x?x?xf32>
 }

mlir/test/Integration/Dialect/Linalg/CPU/test-conv-3d-ndhwc-dhwcf-call.mlir

 // RUN: mlir-opt %s -convert-linalg-to-loops -convert-scf-to-std -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
 // RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" -convert-linalg-to-loops -convert-scf-to-std \
 // RUN:   -convert-linalg-to-llvm -lower-affine -convert-scf-to-std --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
 // RUN: mlir-cpu-runner -e main -entry-point-result=void \
 // RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
 // RUN: | FileCheck %s
 
-// RUN: mlir-opt %s -test-conv-vectorization="tile-sizes=1,1,1,1,1,3,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
-// RUN: mlir-opt %s -linalg-tile="tile-sizes=0,5,5,5" \
-// RUN:   -test-conv-vectorization="tile-sizes=1,1,1,1,1,3,3,3,3" -convert-linalg-to-llvm -lower-affine -convert-scf-to-std -convert-vector-to-llvm --convert-memref-to-llvm -convert-std-to-llvm -reconcile-unrealized-casts | \
-// RUN: mlir-cpu-runner -e main -entry-point-result=void \
-// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext \
-// RUN: | FileCheck %s
-
 func private @print_memref_f32(memref<*xf32>)
 
 // Creates and returns 5-D buffer of size (%s1, %s2, %s3, %s4, %s5) filled with the value %f
 func @alloc_5d_filled_f32(%s1 : index, %s2 : index, %s3 : index, %s4 : index, %s5 : index, %f : f32) -> memref<?x?x?x?x?xf32> {
   %buf = memref.alloc(%s1, %s2, %s3, %s4, %s5) : memref<?x?x?x?x?xf32>
   linalg.fill(%f, %buf) : f32, memref<?x?x?x?x?xf32>
   return %buf : memref<?x?x?x?x?xf32>
 }

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

 # Exclude tests from libMLIR.so
 add_mlir_library(MLIRLinalgTestPasses
   TestComprehensiveBufferize.cpp
-  TestConvVectorization.cpp
   TestLinalgCodegenStrategy.cpp
   TestLinalgDistribution.cpp
   TestLinalgElementwiseFusion.cpp
   TestLinalgFusionTransforms.cpp
   TestLinalgHoisting.cpp
   TestLinalgTransforms.cpp
   TestPadFusion.cpp
 

mlir/test/lib/Dialect/Linalg/TestConvVectorization.cpp

-//===- TestConvVectorization.cpp - Vectorization of Conv ops --------------===//
-//
-// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-// See https://llvm.org/LICENSE.txt for license information.
-// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-//
-//===----------------------------------------------------------------------===//
-
-#include "mlir/Conversion/VectorToSCF/VectorToSCF.h"
-#include "mlir/Dialect/Linalg/Passes.h"
-#include "mlir/Dialect/Linalg/Transforms/Hoisting.h"
-#include "mlir/Dialect/Linalg/Transforms/Transforms.h"
-#include "mlir/Dialect/SCF/Transforms.h"
-#include "mlir/Dialect/Vector/VectorTransforms.h"
-#include "mlir/Pass/Pass.h"
-#include "mlir/Pass/PassManager.h"
-#include "mlir/Transforms/DialectConversion.h"
-#include "mlir/Transforms/GreedyPatternRewriteDriver.h"
-#include "mlir/Transforms/LoopUtils.h"
-#include "mlir/Transforms/Passes.h"
-
-using namespace mlir;
-using namespace vector;
-
-namespace {
-/// A pass converting MLIR Linalg ops into Vector ops.
-class TestConvVectorization
-    : public PassWrapper<TestConvVectorization, OperationPass<ModuleOp>> {
-public:
-  StringRef getArgument() const final { return "test-conv-vectorization"; }
-  StringRef getDescription() const final {
-    return "Test vectorization of convolutions";
-  }
-  TestConvVectorization() = default;
-  TestConvVectorization(const TestConvVectorization &) {}
-  explicit TestConvVectorization(ArrayRef<int64_t> tileSizesParam) {
-    tileSizes = tileSizesParam;
-  }
-
-  void runOnOperation() override;
-
-  void getDependentDialects(DialectRegistry &registry) const override {
-    registry.insert<VectorDialect>();
-    registry.insert<linalg::LinalgDialect>();
-    registry.insert<memref::MemRefDialect>();
-    registry.insert<scf::SCFDialect>();
-    registry.insert<AffineDialect>();
-    registry.insert<StandardOpsDialect>();
-  }
-
-  ListOption<int64_t> tileSizes{
-      *this, "tile-sizes", llvm::cl::desc("Vectorization sizes."),
-      llvm::cl::ZeroOrMore, llvm::cl::MiscFlags::CommaSeparated};
-};
-} // namespace
-
-void TestConvVectorization::runOnOperation() {
-  MLIRContext *context = &getContext();
-  ModuleOp module = getOperation();
-
-  ConversionTarget target(*context);
-  target.addLegalDialect<AffineDialect, scf::SCFDialect, StandardOpsDialect,
-                         VectorDialect>();
-  target.addLegalOp<ModuleOp, FuncOp, ReturnOp>();
-  target.addLegalOp<linalg::FillOp, linalg::YieldOp>();
-
-  SmallVector<RewritePatternSet, 4> stage1Patterns;
-  linalg::populateConvVectorizationPatterns(context, stage1Patterns, tileSizes);
-  SmallVector<FrozenRewritePatternSet, 4> frozenStage1Patterns;
-  llvm::move(stage1Patterns, std::back_inserter(frozenStage1Patterns));
-
-  RewritePatternSet stage2Patterns =
-      linalg::getLinalgTilingCanonicalizationPatterns(context);
-  scf::populateSCFForLoopCanonicalizationPatterns(stage2Patterns);
-
-  auto stage3Transforms = [](Operation *op) {
-    PassManager pm(op->getContext());
-    pm.addPass(createLoopInvariantCodeMotionPass());
-    if (failed(pm.run(cast<ModuleOp>(op))))
-      llvm_unreachable("Unexpected failure in cleanup pass pipeline.");
-    op->walk([](FuncOp func) {
-      promoteSingleIterationLoops(func);
-      linalg::hoistRedundantVectorTransfers(func);
-    });
-    return success();
-  };
-
-  (void)linalg::applyStagedPatterns(module, frozenStage1Patterns,
-                                    std::move(stage2Patterns),
-                                    stage3Transforms);
-
-  //===--------------------------------------------------------------------===//
-  // Post staged patterns transforms
-  //===--------------------------------------------------------------------===//
-
-  VectorTransformsOptions vectorTransformOptions{
-      VectorContractLowering::Dot, VectorMultiReductionLowering::InnerParallel,
-      VectorTransposeLowering::EltWise};
-
-  RewritePatternSet vectorTransferPatterns(context);
-  // Pattern is not applied: rank-reducing vector transfer is not yet supported
-  // (see: splitFullAndPartialTransferPrecondition in VectorTransforms.cpp).
-  vectorTransferPatterns.add<VectorTransferFullPartialRewriter>(
-      context, vectorTransformOptions);
-  (void)applyPatternsAndFoldGreedily(module, std::move(vectorTransferPatterns));
-
-  // Programmatic controlled lowering of linalg.copy and linalg.fill.
-  PassManager pm(context);
-  pm.addNestedPass<FuncOp>(createConvertLinalgToLoopsPass());
-  if (failed(pm.run(module)))
-    llvm_unreachable("Unexpected failure in linalg to loops pass.");
-
-  // Programmatic controlled lowering of vector.contract only.
-  RewritePatternSet vectorContractLoweringPatterns(context);
-  populateVectorBroadcastLoweringPatterns(vectorContractLoweringPatterns);
-  populateVectorContractLoweringPatterns(vectorContractLoweringPatterns,
-                                         vectorTransformOptions);
-  populateVectorMaskOpLoweringPatterns(vectorContractLoweringPatterns);
-  populateVectorShapeCastLoweringPatterns(vectorContractLoweringPatterns);
-  populateVectorTransposeLoweringPatterns(vectorContractLoweringPatterns,
-                                          vectorTransformOptions);
-  (void)applyPatternsAndFoldGreedily(module,
-                                     std::move(vectorContractLoweringPatterns));
-
-  // Programmatic controlled lowering of vector.transfer only.
-  RewritePatternSet vectorToLoopsPatterns(context);
-  populateVectorToSCFConversionPatterns(vectorToLoopsPatterns,
-                                        VectorTransferToSCFOptions());
-  (void)applyPatternsAndFoldGreedily(module, std::move(vectorToLoopsPatterns));
-
-  // Ensure we drop the marker in the end.
-  module.walk([](linalg::LinalgOp op) {
-    op->removeAttr(linalg::LinalgTransforms::kLinalgTransformMarker);
-  });
-}
-
-namespace mlir {
-namespace test {
-void registerTestConvVectorization() {
-  PassRegistration<TestConvVectorization>();
-}
-} // namespace test
-} // namespace mlir

mlir/tools/mlir-opt/mlir-opt.cpp

 void registerPatternsTestPass();
 void registerSimpleParametricTilingPass();
 void registerTestAffineLoopParametricTilingPass();
 void registerTestAliasAnalysisPass();
 void registerTestBuiltinAttributeInterfaces();
 void registerTestCallGraphPass();
 void registerTestComprehensiveFunctionBufferize();
 void registerTestConstantFold();
-void registerTestConvVectorization();
 void registerTestGpuSerializeToCubinPass();
 void registerTestGpuSerializeToHsacoPass();
 void registerTestDataLayoutQuery();
 void registerTestDecomposeCallGraphTypes();
 void registerTestDiagnosticsPass();
 void registerTestDominancePass();
 void registerTestDynamicPipelinePass();
 void registerTestExpandTanhPass();
void registerTestPasses() {
   mlir::test::registerTestDiagnosticsPass();
 #if MLIR_CUDA_CONVERSIONS_ENABLED
   mlir::test::registerTestGpuSerializeToCubinPass();
 #endif
 #if MLIR_ROCM_CONVERSIONS_ENABLED
   mlir::test::registerTestGpuSerializeToHsacoPass();
 #endif
   mlir::test::registerTestComprehensiveFunctionBufferize();
-  mlir::test::registerTestConvVectorization();
   mlir::test::registerTestDecomposeCallGraphTypes();
   mlir::test::registerTestDataLayoutQuery();
   mlir::test::registerTestDominancePass();
   mlir::test::registerTestDynamicPipelinePass();
   mlir::test::registerTestExpandTanhPass();
   mlir::test::registerTestComposeSubView();
   mlir::test::registerTestGpuParallelLoopMappingPass();
   mlir::test::registerTestIRVisitorsPass();