[mlir][ArmSME] Add rewrites to swap extract of extend

In mixed matmul lowering (e.g., i8 to i32) we're seeing the following
sequence:

  %0 = arith.extsi %src : vector<4x[8]xi8> to vector<4x[8]xi32>
  %1 = vector.extract %0[0] : vector<[8]xi32> from vector<4x[8]xi32>
  %lhs = vector.scalable.extract %1[0] : vector<[4]xi32> from vector<[8]xi32>

  ... (same for rhs)

  %2 = vector.outerproduct %lhs, %rhs, %acc vector<[4]xi32>, vector<[4]xi32>

  // x4 chained by accumulator

This chain of 4 outer products can be fused into a single 4-way widening
variant but the pass doesn't match on the IR, as it expects the source
of the inputs to be an extend and it can't look through the extracts.

This patch fixes this with two rewrites that swaps extract(extend) into
extend(extract).

Related to #78975, #79288.

Author: c-rhodes

mlir/lib/Dialect/ArmSME/Transforms/VectorLegalization.cpp

@@ -338,6 +338,105 @@ struct LegalizeTransferWriteOpsByDecomposition
   }
 };
 
+// Shuffles arith extend ops after vector.extract op.
+//
+// This transforms IR like:
+//   %0 = arith.extsi %src : vector<4x[8]xi8> to vector<4x[8]xi32>
+//   %1 = vector.extract %0[0] : vector<[8]xi32> from vector<4x[8]xi32>
+// Into:
+//   %0 = vector.extract %src[0] : vector<[8]xi8> from vector<4x[8]xi8>
+//   %1 = arith.extsi %0 : vector<[8]xi8> to vector<[8]xi32>
+//
+// This enables outer product fusion in the `-arm-sme-outer-product-fusion`
+// pass when the result is the input to an outer product.
+struct SwapVectorExtractOfArithExtend
+    : public OpRewritePattern<vector::ExtractOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(vector::ExtractOp extractOp,
+                                PatternRewriter &rewriter) const override {
+    VectorType resultType = llvm::dyn_cast<VectorType>(extractOp.getType());
+    if (!resultType)
+      return rewriter.notifyMatchFailure(extractOp,
+                                         "extracted type is not a vector type");
+
+    auto numScalableDims = llvm::count(resultType.getScalableDims(), true);
+    if (numScalableDims != 1)
+      return rewriter.notifyMatchFailure(
+          extractOp, "extracted type is not a 1-D scalable vector type");
+
+    auto *extendOp = extractOp.getVector().getDefiningOp();
+    if (!isa_and_present<arith::ExtSIOp, arith::ExtUIOp, arith::ExtFOp>(
+            extendOp))
+      return rewriter.notifyMatchFailure(extractOp,
+                                         "extract not from extend op");
+
+    auto loc = extractOp.getLoc();
+    StringAttr extendOpName = extendOp->getName().getIdentifier();
+    Value extendSource = extendOp->getOperand(0);
+
+    // Create new extract from source of extend.
+    Value newExtract = rewriter.create<vector::ExtractOp>(
+        loc, extendSource, extractOp.getMixedPosition());
+
+    // Extend new extract to original result type.
+    Operation *newExtend =
+        rewriter.create(loc, extendOpName, Value(newExtract), resultType);
+
+    rewriter.replaceOp(extractOp, newExtend->getResult(0));
+
+    return success();
+  }
+};
+
+// Shuffles arith extend ops after vector.scalable.extract op.
+//
+// This transforms IR like:
+//   %0 = arith.extsi %src : vector<[8]xi8> to vector<[8]xi32>
+//   %1 = vector.scalable.extract %0[0] : vector<[4]xi32> from vector<[8]xi32>
+// Into:
+//   %0 = vector.scalable.extract %src[0] : vector<[4]xi8> from vector<[8]xi8>
+//   %1 = arith.extsi %0 : vector<[4]xi8> to vector<[4]xi32>
+//
+// This enables outer product fusion in the `-arm-sme-outer-product-fusion`
+// pass when the result is the input to an outer product.
+struct SwapVectorScalableExtractOfArithExtend
+    : public OpRewritePattern<vector::ScalableExtractOp> {
+  using OpRewritePattern::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(vector::ScalableExtractOp extractOp,
+                                PatternRewriter &rewriter) const override {
+    auto *extendOp = extractOp.getSource().getDefiningOp();
+    if (!isa_and_present<arith::ExtSIOp, arith::ExtUIOp, arith::ExtFOp>(
+            extendOp))
+      return rewriter.notifyMatchFailure(extractOp,
+                                         "extract not from extend op");
+
+    auto loc = extractOp.getLoc();
+    VectorType resultType = extractOp.getResultVectorType();
+
+    Value extendSource = extendOp->getOperand(0);
+    StringAttr extendOpName = extendOp->getName().getIdentifier();
+    VectorType extendSourceVectorType =
+        cast<VectorType>(extendSource.getType());
+
+    // Create new extract from source of extend.
+    VectorType extractResultVectorType =
+        VectorType::Builder(resultType)
+            .setElementType(extendSourceVectorType.getElementType());
+    Value newExtract = rewriter.create<vector::ScalableExtractOp>(
+        loc, extractResultVectorType, extendSource, extractOp.getPos());
+
+    // Extend new extract to original result type.
+    Operation *newExtend =
+        rewriter.create(loc, extendOpName, Value(newExtract), resultType);
+
+    rewriter.replaceOp(extractOp, newExtend->getResult(0));
+
+    return success();
+  }
+};
+
 struct VectorLegalizationPass
     : public arm_sme::impl::VectorLegalizationBase<VectorLegalizationPass> {
   void runOnOperation() override {
@@ -358,6 +457,8 @@ struct VectorLegalizationPass
           return success();
         });
 
+    patterns.add<SwapVectorExtractOfArithExtend,
+                 SwapVectorScalableExtractOfArithExtend>(context);
     // Note: High benefit to ensure masked outer products are lowered first.
     patterns.add<LegalizeMaskedVectorOuterProductOpsByDecomposition>(
         converter, context, 1024);

mlir/test/Dialect/ArmSME/vector-legalization.mlir

@@ -266,3 +266,43 @@ func.func @transpose_f32_scalable_4x16_via_write(%src: memref<?x?xf32>, %dest: m
   vector.transfer_write %0, %dest[%c0, %c0] {permutation_map = #transpose, in_bounds = [true, true]} : vector<[4]x[16]xf32>, memref<?x?xf32>
   return
 }
+
+// -----
+
+// CHECK-LABEL: @extract_from_arith_ext(
+// CHECK-SAME:                          %[[SRC:.*]]: vector<4x[8]xi8>
+// CHECK: %[[EXTRACT:.*]] = vector.extract %[[SRC]][0] : vector<[8]xi8> from vector<4x[8]xi8>
+// CHECK: %[[EXTEND:.*]] = arith.extsi %[[EXTRACT]] : vector<[8]xi8> to vector<[8]xi32>
+// CHECK: return %[[EXTEND]]
+func.func @extract_from_arith_ext(%src: vector<4x[8]xi8>) -> vector<[8]xi32> {
+  %0 = arith.extsi %src : vector<4x[8]xi8> to vector<4x[8]xi32>
+  %1 = vector.extract %0[0] : vector<[8]xi32> from vector<4x[8]xi32>
+  return %1 : vector<[8]xi32>
+}
+
+// -----
+
+// CHECK-LABEL: @non_constant_extract_from_arith_ext(
+// CHECK-SAME:                                       %[[SRC:[a-z0-9]+]]: vector<4x[8]xi8>,
+// CHECK-SAME:                                       %[[DIM:[a-z0-9]+]]: index
+// CHECK: %[[EXTRACT:.*]] = vector.extract %[[SRC]][%[[DIM]]] : vector<[8]xi8> from vector<4x[8]xi8>
+// CHECK: %[[EXTEND:.*]] = arith.extsi %[[EXTRACT]] : vector<[8]xi8> to vector<[8]xi32>
+// CHECK: return %[[EXTEND]]
+func.func @non_constant_extract_from_arith_ext(%src: vector<4x[8]xi8>, %dim: index) -> vector<[8]xi32> {
+  %0 = arith.extsi %src : vector<4x[8]xi8> to vector<4x[8]xi32>
+  %1 = vector.extract %0[%dim] : vector<[8]xi32> from vector<4x[8]xi32>
+  return %1 : vector<[8]xi32>
+}
+
+// -----
+
+// CHECK-LABEL: @scalable_extract_from_arith_ext(
+// CHECK-SAME:                                   %[[SRC:.*]]: vector<[8]xi8>
+// CHECK: %[[EXTRACT:.*]] = vector.scalable.extract %[[SRC]][0] : vector<[4]xi8> from vector<[8]xi8>
+// CHECK: %[[EXTEND:.*]] = arith.extsi %[[EXTRACT]] : vector<[4]xi8> to vector<[4]xi32>
+// CHECK: return %[[EXTEND]]
+func.func @scalable_extract_from_arith_ext(%src: vector<[8]xi8>) -> vector<[4]xi32> {
+  %0 = arith.extsi %src : vector<[8]xi8> to vector<[8]xi32>
+  %1 = vector.scalable.extract %0[0] : vector<[4]xi32> from vector<[8]xi32>
+  return %1 : vector<[4]xi32>
+}