[mlir][linalg] Add support for masked vectorization of tensor.insert_slice (1/N)

For context, note that `tensor.insert_slice` is vectorised using the
`vector.transfer_read` + `vector.transfer_write` pair. An unmasked
example is shown below:

```mlir
// BEFORE VECTORIZATION
%res = tensor.insert_slice
  %source_slice into %init[0, %c2]
  [5, 1] [1, 1] : tensor<5x1xi32> into tensor<5x3xi32>

// AFTER VECTORIZATION
%read = vector.transfer_read %extracted_slice[%c0, %c0], %c0_i32 : tensor<5x1xi32>, vector<8x1xi32>
%res = vector.transfer_write %2, %0[%c0_0, %c2] : vector<8x1xi32>, tensor<5x3xi32>
```

This PR refactors `InsertSliceVectorizePattern` (which is used to
vectorize `tensor.extract_slice`) to enable masked vectorization. ATM,
only `vector.transfer_read` is masked. If `vector.transfer_write` also
requires masking, the vectorizer will bail out. This will be addressed
in a sub-sequent PR.

Summary of changes:
  * Added an argument to specify vector sizes (behavior remains
    unchanged if vector sizes are not specified).
  * Renamed `InsertSliceVectorizePattern` to `vectorizeAsInsertSliceOp`
    and integrated into (alongside other hooks for vectorization) in
    `linalg::vectorize`.
  * Removed `populateInsertSliceVectorizationPatterns`, as
    `InsertSliceVectorizePattern` was its only pattern.
  * Updated `vectorizeAsInsertSliceOp` to support masking for the
    "read" operation.
  * Updated `@pad_and_insert_slice_dest` in
    "vectorization-pad-patterns.mlir" to reflect the removal of
    `populateInsertSliceVectorizationPatterns` from
    `ApplyPadVectorizationPatternsOps`.

Author: banach-space

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

@@ -1723,11 +1723,6 @@ void populateDecomposePadPatterns(RewritePatternSet &patterns);
 /// \see rewriteInIm2Col for more details.
 void populateConvertConv2DToImg2ColPatterns(RewritePatternSet &patterns);
 
-/// Populates `patterns` with vectorisation patterns for tensor.insert_slice.
-/// TODO: Avoid having a dedicated `populate{}` for one pattern. Instead, either
-/// expand or merge with other `populate{}`.
-void populateInsertSliceVectorizationPatterns(RewritePatternSet &patterns);
-
 /// Populates `patterns` with patterns that vectorize tensor.pad.
 /// These patterns are meant to apply in a complementary fashion. Benefits
 /// are used to encode a certain ordering of pattern application. To avoid

mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp

@@ -265,7 +265,6 @@ void transform::ApplyFoldAddIntoDestPatternsOp::populatePatterns(
 void transform::ApplyPadVectorizationPatternsOp::populatePatterns(
     RewritePatternSet &patterns) {
   linalg::populatePadOpVectorizationPatterns(patterns);
-  linalg::populateInsertSliceVectorizationPatterns(patterns);
 }
 
 //===----------------------------------------------------------------------===//
@@ -3504,9 +3503,6 @@ transform::VectorizeChildrenAndApplyPatternsOp::applyToOne(
 
   patterns.add<CopyVectorizationPattern>(ctx);
 
-  // Add misc. vectorization patterns (e.g. for tensor.insert_slice)
-  linalg::populateInsertSliceVectorizationPatterns(patterns);
-
   if (getVectorizePadding()) {
     linalg::populatePadOpVectorizationPatterns(patterns);
     // This creates an alternative path for lowering tensor.pad - by

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

@@ -59,6 +59,30 @@ vectorizeConvolution(RewriterBase &rewriter, LinalgOp convOp,
                      ArrayRef<bool> inputVecScalableFlags = {},
                      bool flatten1DDepthwiseConv = false);
 
+/// Vectorize tensor::InsertSliceOp with:
+///   * vector::TransferReadOp + vector::TransferWriteOp
+/// The vector sizes are either:
+///   * user-provided in `inputVectorSizes`, or
+///   * inferred from the static dims in the input and output tensors.
+/// Bails out if:
+///   * vector sizes are not user-provided, and
+///   * at least one dim is dynamic (in both the input and output tensors),
+///   bails out.
+///
+/// Before:
+///     !t_in_type = tensor<1x2x3xf32>
+///     !t_out_type = tensor<9x8x7x1x2x3xf32>
+///     !v_type = vector<1x2x3xf32>
+///     %inserted_slice = tensor.insert_slice %src into %dest ... : !t_in_type
+///     into !t_out_type
+/// After:
+///     %read = vector.transfer_read %src[...], %pad ... : !t_in_type, !v_type
+///     %write = vector.transfer_write %read, %dest ... : !v_type, !t_out_type
+static LogicalResult
+vectorizeAsInsertSliceOp(RewriterBase &rewriter, tensor::InsertSliceOp sliceOp,
+                         ArrayRef<int64_t> inputVectorSizes,
+                         SmallVectorImpl<Value> &newResults);
+
 /// Return the unique instance of OpType in `block` if it is indeed unique.
 /// Return null if none or more than 1 instances exist.
 template <typename OpType>
@@ -1557,6 +1581,7 @@ static LogicalResult
 vectorizeAsTensorPackOp(RewriterBase &rewriter, tensor::PackOp packOp,
                         ArrayRef<int64_t> inputVectorSizes,
                         SmallVectorImpl<Value> &newResults) {
+  // TODO: Introduce a parent class that will handle the insertion point update.
   OpBuilder::InsertionGuard g(rewriter);
   rewriter.setInsertionPoint(packOp);
 
@@ -1633,6 +1658,7 @@ vectorizeAsTensorUnpackOp(RewriterBase &rewriter, tensor::UnPackOp unpackOp,
                           ArrayRef<int64_t> inputVectorSizes,
                           SmallVectorImpl<Value> &newResults) {
 
+  // TODO: Introduce a parent class that will handle the insertion point update.
   OpBuilder::InsertionGuard g(rewriter);
   rewriter.setInsertionPoint(unpackOp);
 
@@ -1763,7 +1789,7 @@ vectorizeAsTensorPadOp(RewriterBase &rewriter, tensor::PadOp padOp,
   auto padValue = padOp.getConstantPaddingValue();
   Location loc = padOp.getLoc();
 
-  // transfer_write_in_bounds(transfer_read_masked(pad_source, pad_value))
+  // TODO: Introduce a parent class that will handle the insertion point update.
   OpBuilder::InsertionGuard g(rewriter);
   rewriter.setInsertionPoint(padOp);
 
@@ -1874,6 +1900,15 @@ vectorizeUnPackOpPrecondition(tensor::UnPackOp unpackOp,
   return success();
 }
 
+/// Need to check if the inner-tiles are static/constant.
+static LogicalResult
+vectorizeInsertSliceOpPrecondition(tensor::InsertSliceOp sliceOp,
+                                   ArrayRef<int64_t> inputVectorSizes) {
+
+  // TODO: Move pre-conditions from the vectorization logic
+  return success();
+}
+
 static LogicalResult vectorizeLinalgOpPrecondition(
     LinalgOp linalgOp, ArrayRef<int64_t> inputVectorSizes,
     bool vectorizeNDExtract, bool flatten1DDepthwiseConv) {
@@ -2144,6 +2179,9 @@ LogicalResult mlir::linalg::vectorizeOpPrecondition(
       .Case<tensor::UnPackOp>([&](auto unpackOp) {
         return vectorizeUnPackOpPrecondition(unpackOp, inputVectorSizes);
       })
+      .Case<tensor::InsertSliceOp>([&](auto sliceOp) {
+        return vectorizeInsertSliceOpPrecondition(sliceOp, inputVectorSizes);
+      })
       .Default([](auto) { return failure(); });
 }
 
@@ -2163,8 +2201,8 @@ static void convertAffineApply(RewriterBase &rewriter, LinalgOp linalgOp) {
 }
 
 bool mlir::linalg::hasVectorizationImpl(Operation *op) {
-  return isa<linalg::LinalgOp, tensor::PadOp, tensor::PackOp, tensor::UnPackOp>(
-      op);
+  return isa<linalg::LinalgOp, tensor::PadOp, tensor::PackOp, tensor::UnPackOp,
+             tensor::InsertSliceOp>(op);
 }
 
 /// Emit a suitable vector form for an operation. If provided,
@@ -2178,6 +2216,7 @@ LogicalResult mlir::linalg::vectorize(RewriterBase &rewriter, Operation *op,
                                       ArrayRef<bool> inputScalableVecDims,
                                       bool vectorizeNDExtract,
                                       bool flatten1DDepthwiseConv) {
+  rewriter.getInsertionPoint();
   LDBG("Attempting to vectorize:\n" << *op << "\n");
   LDBG("Input vector sizes: ");
   LLVM_DEBUG(llvm::interleaveComma(inputVectorSizes, llvm::dbgs()));
@@ -2244,6 +2283,10 @@ LogicalResult mlir::linalg::vectorize(RewriterBase &rewriter, Operation *op,
             return vectorizeAsTensorPackOp(rewriter, packOp, inputVectorSizes,
                                            results);
           })
+          .Case<tensor::InsertSliceOp>([&](auto sliceOp) {
+            return vectorizeAsInsertSliceOp(rewriter, sliceOp, inputVectorSizes,
+                                            results);
+          })
           .Case<tensor::UnPackOp>([&](auto unpackOp) {
             return vectorizeAsTensorUnpackOp(rewriter, unpackOp,
                                              inputVectorSizes, results);
@@ -2583,113 +2626,139 @@ static Value getStaticPadVal(Operation *op) {
   return {};
 }
 
-/// Rewrite tensor.insert.slice as a vector.transfer_read +
-/// vector.transfer_write pair. The vector size is inferred from the static
-/// dims in the input and output tensors. If a dim is dynamic in both the input
-/// and output tensors, bails out.
-///
-/// Before:
-///     !t_in_type = tensor<1x2x3xf32>
-///     !t_out_type = tensor<9x8x7x1x2x3xf32>
-///     !v_type = vector<1x2x3xf32>
-///     %inserted_slice = tensor.insert_slice %src into %dest ... : !t_in_type
-///     into !t_out_type
-/// After:
-///     %read = vector.transfer_read %src[...], %pad ... : !t_in_type, !v_type
-///     %write = vector.transfer_write %read, %dest ... : !v_type, !t_out_type
-///
-/// TODO: Support masking
-struct InsertSliceVectorizePattern
-    : public OpRewritePattern<tensor::InsertSliceOp> {
-  using OpRewritePattern<tensor::InsertSliceOp>::OpRewritePattern;
+static LogicalResult
+vectorizeAsInsertSliceOp(RewriterBase &rewriter, tensor::InsertSliceOp sliceOp,
+                         ArrayRef<int64_t> inputVectorSizes,
+                         SmallVectorImpl<Value> &newResults) {
+  // TODO: Introduce a parent class that will handle the insertion point update.
+  OpBuilder::InsertionGuard g(rewriter);
+  rewriter.setInsertionPoint(sliceOp);
 
-  LogicalResult matchAndRewrite(tensor::InsertSliceOp sliceOp,
-                                PatternRewriter &rewriter) const final {
-    auto sourceType = sliceOp.getSource().getType();
-    if (!VectorType::isValidElementType(sourceType.getElementType()))
-      return failure();
+  TypedValue<RankedTensorType> source = sliceOp.getSource();
+  auto sourceType = source.getType();
+  if (!VectorType::isValidElementType(sourceType.getElementType()))
+    return failure();
 
-    auto resultType = sliceOp.getResultType();
-
-    // 1. Get the pad value.
-    // TransferReadOp requires a scalar padding value. Note that:
-    //    * for in-bounds access, the value is actually irrelevant.
-    //  There are 2 cases in which xfer.read accesses are known to be in-bounds:
-    //  1. The source shape is static (output vector sizes would be based on
-    //     the source shape and hence all memory accesses would be in-bounds),
-    //  2. Masking is used (output vector sizes would be user-provided, in which
-    //     case it is assumed that all memory accesses are in-bounds). This
-    //     remains a TODO.
-    //
-    // When the value is not known and not needed, use 0. Otherwise, bail out.
-    Value padValue = getStaticPadVal(sliceOp);
-    bool isOutOfBoundsRead = !sourceType.hasStaticShape();
-
-    if (!padValue && isOutOfBoundsRead) {
-      LDBG("Failed to get a pad value for out-of-bounds read access\n");
+  auto resultType = sliceOp.getResultType();
+
+  // 1. Get the pad value.
+  // TransferReadOp requires a scalar padding value. Note that:
+  //    * for in-bounds access, the value is actually irrelevant.
+  // There are 2 cases in which xfer.read accesses are known to be in-bounds:
+  //  1. The source shape is static (output vector sizes would be based on
+  //     the source shape and hence all memory accesses would be in-bounds),
+  //  2. Masking is used (output vector sizes would be user-provided, in which
+  //     case it is assumed that all memory accesses are in-bounds). This
+  //     remains a TODO.
+  //
+  // When the value is not known and not needed, use 0. Otherwise, bail out.
+  Value padValue = getStaticPadVal(sliceOp);
+  bool isOutOfBoundsRead =
+      !sourceType.hasStaticShape() && inputVectorSizes.empty();
+
+  if (!padValue && isOutOfBoundsRead) {
+    LDBG("Failed to get a pad value for out-of-bounds read access\n");
+    return failure();
+  }
+
+  if (!padValue) {
+    auto elemType = sourceType.getElementType();
+    padValue = rewriter.create<arith::ConstantOp>(
+        sliceOp.getLoc(), elemType, rewriter.getZeroAttr(elemType));
+  }
+
+  // 2. Get the vector shape and in-bounds attributes
+  SmallVector<int64_t> vecShape;
+  SmallVector<bool> readInBounds;
+  SmallVector<bool> writeInBounds;
+  size_t rankDiff = resultType.getRank() - sourceType.getRank();
+  for (unsigned i = 0; i < sourceType.getRank(); ++i) {
+    if (!inputVectorSizes.empty()) {
+      vecShape.push_back(inputVectorSizes[i]);
+      readInBounds.push_back(false);
+      writeInBounds.push_back(false);
+    } else if (!sourceType.isDynamicDim(i)) {
+      vecShape.push_back(sourceType.getDimSize(i));
+      // Source shape is statically known: Neither read nor write are
+      // out-of-bounds.
+      readInBounds.push_back(true);
+      writeInBounds.push_back(true);
+    } else if (!resultType.isDynamicDim(i)) {
+      // Source shape is not statically known, but result shape is.
+      // Vectorize with size of result shape. This may be larger than the
+      // source size.
+      // FIXME: Using rankDiff implies that the source tensor is inserted at
+      // the end of the destination tensor. However, that's not required.
+      vecShape.push_back(resultType.getDimSize(rankDiff + i));
+      // Read may be out-of-bounds because the result size could be larger
+      // than the source size.
+      readInBounds.push_back(false);
+      // Write will be in-bounds provided that the corresponding write idx is 0.
+      // To keep this logic simple, conservatively mark as out-of-bounds.
+      writeInBounds.push_back(false);
+    } else {
+      // Neither source nor result dim of padOp is static. Cannot vectorize
+      // the copy.
+      // TODO: Add support for masking
       return failure();
     }
+  }
+  auto vecType = VectorType::get(vecShape, sourceType.getElementType());
 
-    if (!padValue) {
-      auto elemType = sourceType.getElementType();
-      padValue = rewriter.create<arith::ConstantOp>(
-          sliceOp.getLoc(), elemType, rewriter.getZeroAttr(elemType));
-    }
+  // 3. Generate TransferReadOp.
+  SmallVector<Value> readIndices(
+      vecType.getRank(),
+      rewriter.create<arith::ConstantIndexOp>(sliceOp.getLoc(), 0));
+  Operation *read = rewriter.create<vector::TransferReadOp>(
+      sliceOp.getLoc(), vecType, source, readIndices, padValue,
+      ArrayRef<bool>{readInBounds});
 
-    // 2. Get the vector shape and in-bounds attributes
-    SmallVector<int64_t> vecShape;
-    SmallVector<bool> readInBounds;
-    SmallVector<bool> writeInBounds;
-    size_t rankDiff = resultType.getRank() - sourceType.getRank();
-    for (unsigned i = 0; i < sourceType.getRank(); ++i) {
-      if (!sourceType.isDynamicDim(i)) {
-        vecShape.push_back(sourceType.getDimSize(i));
-        // Source shape is statically known: Neither read nor write are
-        // out-of-bounds.
-        readInBounds.push_back(true);
-        writeInBounds.push_back(true);
-      } else if (!resultType.isDynamicDim(i)) {
-        // Source shape is not statically known, but result shape is.
-        // Vectorize with size of result shape. This may be larger than the
-        // source size.
-        // FIXME: Using rankDiff implies that the source tensor is inserted at
-        // the end of the destination tensor. However, that's not required.
-        vecShape.push_back(resultType.getDimSize(rankDiff + i));
-        // Read may be out-of-bounds because the result size could be larger
-        // than the source size.
-        readInBounds.push_back(false);
-        // Write will in-bounds provided that the corresponding write idx is 0.
-        // To keep this logic simple, conservatively mark as out-of-bounds.
-        writeInBounds.push_back(false);
-      } else {
-        // Neither source nor result dim of padOp is static. Cannot vectorize
-        // the copy.
-        // TODO: Add support for masking
-        return failure();
-      }
+  // If vector sizes are user provided, make sure to mask xfer_read.
+  if (!inputVectorSizes.empty()) {
+    auto *srcDefOp = source.getDefiningOp();
+    if (!srcDefOp) {
+      LDBG("Unable to get the defining Op of " << sliceOp);
+      return failure();
     }
-    auto vecType = VectorType::get(vecShape, sourceType.getElementType());
 
-    // 3. Generate TransferReadOp.
-    SmallVector<Value> readIndices(
-        vecType.getRank(),
-        rewriter.create<arith::ConstantIndexOp>(sliceOp.getLoc(), 0));
-    auto read = rewriter.create<vector::TransferReadOp>(
-        sliceOp.getLoc(), vecType, sliceOp.getSource(), readIndices, padValue,
-        ArrayRef<bool>{readInBounds});
+    ReifiedRankedShapedTypeDims reifiedSrcSizes;
+    LogicalResult status =
+        cast<ReifyRankedShapedTypeOpInterface>(srcDefOp).reifyResultShapes(
+            rewriter, reifiedSrcSizes);
+    if (status.failed()) {
+      LDBG("Unable to reify result shapes of " << sliceOp);
+      return failure();
+    }
 
-    // 4. Generate TransferWriteOp.
-    auto writeIndices = getValueOrCreateConstantIndexOp(
-        rewriter, sliceOp.getLoc(), sliceOp.getMixedOffsets());
+    // Create the mask
+    SmallVector<int64_t> readMaskShape(
+        sliceOp.getSource().getType().getShape());
+    auto readMaskType = VectorType::get(inputVectorSizes, rewriter.getI1Type());
+    Value maskOp = rewriter.create<vector::CreateMaskOp>(
+        sliceOp.getLoc(), readMaskType, reifiedSrcSizes[0]);
 
-    // 5. Finalize
-    rewriter.replaceOpWithNewOp<vector::TransferWriteOp>(
-        sliceOp, read, sliceOp.getDest(), writeIndices,
-        ArrayRef<bool>{writeInBounds});
+    // Mask the xfer_read Op
+    read = mlir::vector::maskOperation(rewriter, read, maskOp);
+  }
 
-    return success();
+  // 4. Generate TransferWriteOp.
+  if (!inputVectorSizes.empty() &&
+      ShapedType::isDynamicShape(resultType.getShape())) {
+    LDBG("TODO: Masking of xfer_write when vectorising " << sliceOp);
+    return failure();
   }
-};
+
+  auto writeIndices = getValueOrCreateConstantIndexOp(
+      rewriter, sliceOp.getLoc(), sliceOp.getMixedOffsets());
+
+  // 5. Finalize
+  Operation *write = rewriter.create<vector::TransferWriteOp>(
+      sliceOp.getLoc(), read->getResult(0), sliceOp.getDest(), writeIndices,
+      ArrayRef<bool>{writeInBounds});
+  newResults.push_back(write->getResult(0));
+
+  return success();
+}
 
 /// Rewrite use of tensor::PadOp result in InsertSliceOp. E.g.:
 /// ```
@@ -2778,11 +2847,6 @@ struct PadOpVectorizationWithInsertSlicePattern
   }
 };
 
-void mlir::linalg::populateInsertSliceVectorizationPatterns(
-    RewritePatternSet &patterns) {
-  patterns.add<InsertSliceVectorizePattern>(patterns.getContext());
-}
-
 void mlir::linalg::populatePadOpVectorizationPatterns(
     RewritePatternSet &patterns, PatternBenefit baseBenefit) {
   patterns.add<PadOpVectorizationWithTransferReadPattern,