[Mlir-commits] [mlir] [mlir][VectorOps] Add conversion of 1-D vector.interleave ops to LLVM (PR #80966)

Benjamin Maxwell llvmlistbot at llvm.org
Wed Feb 7 02:14:42 PST 2024


https://github.com/MacDue created https://github.com/llvm/llvm-project/pull/80966

The 1-D case directly maps to LLVM intrinsics. The n-D case will be
handled by unrolling to 1-D first (in a later patch).

Depends on: #80965 

>From 4b442eeb377cfcb60a0d05cf6f1ec6ba735c3152 Mon Sep 17 00:00:00 2001
From: Benjamin Maxwell <benjamin.maxwell at arm.com>
Date: Wed, 7 Feb 2024 09:53:22 +0000
Subject: [PATCH 1/2] [mlir][VectorOps] Add vector.interleave operation

The interleave operation constructs a new vector by interleaving the
elements from the trailing (or final) dimension of two input vectors,
returning a new vector where the trailing dimension is twice the size.

Note that for the n-D case this differs from the interleaving possible
with `vector.shuffle`, which would only operate on the leading
dimension.

Another key difference is this operation supports scalable vectors,
though currently a general LLVM lowering is limited to the case where
only the trailing dimension is scalable.

Example:
```mlir
%0 = vector.interleave %a, %b
            : vector<[4]xi32>     ; yields vector<[8]xi32>
%1 = vector.interleave %c, %d
            : vector<8xi8>        ; yields vector<16xi8>
%2 = vector.interleave %e, %f
            : vector<f16>         ; yields vector<2xf16>
%3 = vector.interleave %g, %h
            : vector<2x4x[2]xf64> ; yields vector<2x4x[4]xf64>
%4 = vector.interleave %i, %j
            : vector<6x3xf32>     ; yields vector<6x6xf32>
```

Note: This change alone does not add any lowerings.
---
 .../mlir/Dialect/Vector/IR/VectorOps.td       | 63 +++++++++++++++++++
 mlir/test/Dialect/Vector/ops.mlir             | 35 +++++++++++
 2 files changed, 98 insertions(+)

diff --git a/mlir/include/mlir/Dialect/Vector/IR/VectorOps.td b/mlir/include/mlir/Dialect/Vector/IR/VectorOps.td
index bc08f8d07fb0d..6d50b0654bc57 100644
--- a/mlir/include/mlir/Dialect/Vector/IR/VectorOps.td
+++ b/mlir/include/mlir/Dialect/Vector/IR/VectorOps.td
@@ -478,6 +478,69 @@ def Vector_ShuffleOp :
   let hasCanonicalizer = 1;
 }
 
+def Vector_InterleaveOp :
+  Vector_Op<"interleave", [Pure,
+    AllTypesMatch<["lhs", "rhs"]>,
+    TypesMatchWith<
+    "type of 'result' is double the width of the inputs",
+    "lhs", "result",
+    [{
+      [&]() -> ::mlir::VectorType {
+        auto vectorType = ::llvm::cast<mlir::VectorType>($_self);
+        ::mlir::VectorType::Builder builder(vectorType);
+        if (vectorType.getRank() == 0) {
+          static constexpr int64_t v2xty_shape[] = { 2 };
+          return builder.setShape(v2xty_shape);
+        }
+        auto lastDim = vectorType.getRank() - 1;
+        return builder.setDim(lastDim, vectorType.getDimSize(lastDim) * 2);
+      }()
+    }]>]> {
+  let summary = "constructs a vector by interleaving two input vectors";
+  let description = [{
+    The interleave operation constructs a new vector by interleaving the
+    elements from the trailing (or final) dimension of two input vectors,
+    returning a new vector where the trailing dimension is twice the size.
+
+    Note that for the n-D case this differs from the interleaving possible with
+    `vector.shuffle`, which would only operate on the leading dimension.
+
+    Another key difference is this operation supports scalable vectors, though
+    currently a general LLVM lowering is limited to the case where only the
+    trailing dimension is scalable.
+
+    Example:
+    ```mlir
+    %0 = vector.interleave %a, %b
+               : vector<[4]xi32>     ; yields vector<[8]xi32>
+    %1 = vector.interleave %c, %d
+               : vector<8xi8>        ; yields vector<16xi8>
+    %2 = vector.interleave %e, %f
+               : vector<f16>         ; yields vector<2xf16>
+    %3 = vector.interleave %g, %h
+               : vector<2x4x[2]xf64> ; yields vector<2x4x[4]xf64>
+    %4 = vector.interleave %i, %j
+               : vector<6x3xf32>     ; yields vector<6x6xf32>
+    ```
+  }];
+
+  let arguments = (ins AnyVectorOfAnyRank:$lhs, AnyVectorOfAnyRank:$rhs);
+  let results = (outs AnyVector:$result);
+
+  let assemblyFormat = [{
+    $lhs `,` $rhs  attr-dict `:` type($lhs)
+  }];
+
+  let extraClassDeclaration = [{
+    VectorType getSourceVectorType() {
+      return ::llvm::cast<VectorType>(getLhs().getType());
+    }
+    VectorType getResultVectorType() {
+      return ::llvm::cast<VectorType>(getResult().getType());
+    }
+  }];
+}
+
 def Vector_ExtractElementOp :
   Vector_Op<"extractelement", [Pure,
      TypesMatchWith<"result type matches element type of vector operand",
diff --git a/mlir/test/Dialect/Vector/ops.mlir b/mlir/test/Dialect/Vector/ops.mlir
index 2f8530e7c171a..79a80be4f8b20 100644
--- a/mlir/test/Dialect/Vector/ops.mlir
+++ b/mlir/test/Dialect/Vector/ops.mlir
@@ -1081,3 +1081,38 @@ func.func @fastmath(%x: vector<42xf32>) -> f32 {
   %min = vector.reduction <minnumf>, %x fastmath<reassoc,nnan,ninf> : vector<42xf32> into f32
   return %min: f32
 }
+
+// CHECK-LABEL: @interleave_0d
+func.func @interleave_0d(%a: vector<f32>, %b: vector<f32>) -> vector<2xf32> {
+  // CHECK: vector.interleave %{{.*}}, %{{.*}} : vector<f32>
+  %0 = vector.interleave %a, %b : vector<f32>
+  return %0 : vector<2xf32>
+}
+
+// CHECK-LABEL: @interleave_1d
+func.func @interleave_1d(%a: vector<4xf32>, %b: vector<4xf32>) -> vector<8xf32> {
+  // CHECK: vector.interleave %{{.*}}, %{{.*}} : vector<4xf32>
+  %0 = vector.interleave %a, %b : vector<4xf32>
+  return %0 : vector<8xf32>
+}
+
+// CHECK-LABEL: @interleave_1d_scalable
+func.func @interleave_1d_scalable(%a: vector<[8]xi16>, %b: vector<[8]xi16>) -> vector<[16]xi16> {
+  // CHECK: vector.interleave %{{.*}}, %{{.*}} : vector<[8]xi16>
+  %0 = vector.interleave %a, %b : vector<[8]xi16>
+  return %0 : vector<[16]xi16>
+}
+
+// CHECK-LABEL: @interleave_2d
+func.func @interleave_2d(%a: vector<2x8xf32>, %b: vector<2x8xf32>) -> vector<2x16xf32> {
+  // CHECK: vector.interleave %{{.*}}, %{{.*}} : vector<2x8xf32>
+  %0 = vector.interleave %a, %b : vector<2x8xf32>
+  return %0 : vector<2x16xf32>
+}
+
+// CHECK-LABEL: @interleave_2d_scalable
+func.func @interleave_2d_scalable(%a: vector<2x[2]xf64>, %b: vector<2x[2]xf64>) -> vector<2x[4]xf64> {
+  // CHECK: vector.interleave %{{.*}}, %{{.*}} : vector<2x[2]xf64>
+  %0 = vector.interleave %a, %b : vector<2x[2]xf64>
+  return %0 : vector<2x[4]xf64>
+}

>From c2047adb5672ec8eaa05e16f34dbbb794a0eba6c Mon Sep 17 00:00:00 2001
From: Benjamin Maxwell <benjamin.maxwell at arm.com>
Date: Wed, 7 Feb 2024 09:56:42 +0000
Subject: [PATCH 2/2] [mlir][VectorOps] Add conversion of 1-D vector.interleave
 ops to LLVM

The 1-D case directly maps to LLVM intrinsics. The n-D case will be
handled by unrolling to 1-D first (in a later patch).
---
 .../VectorToLLVM/ConvertVectorToLLVM.cpp      | 41 ++++++++++++++++++-
 .../VectorToLLVM/vector-to-llvm.mlir          | 37 +++++++++++++++++
 2 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
index b66b55ae8d57f..0d9a451d11ca8 100644
--- a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
+++ b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
@@ -1734,6 +1734,44 @@ struct VectorSplatNdOpLowering : public ConvertOpToLLVMPattern<SplatOp> {
   }
 };
 
+/// Conversion pattern for a `vector.interleave`.
+/// This supports fixed-sized vectors and scalable vectors.
+struct VectorInterleaveOpLowering
+    : public ConvertOpToLLVMPattern<vector::InterleaveOp> {
+  using ConvertOpToLLVMPattern::ConvertOpToLLVMPattern;
+
+  LogicalResult
+  matchAndRewrite(vector::InterleaveOp interleaveOp, OpAdaptor adaptor,
+                  ConversionPatternRewriter &rewriter) const override {
+    VectorType resultType = interleaveOp.getResultVectorType();
+    // n-D interleaves should have been lowered already.
+    if (resultType.getRank() != 1)
+      return failure();
+    // If the result is rank 1, then this directly maps to LLVM.
+    if (resultType.isScalable()) {
+      rewriter.replaceOpWithNewOp<LLVM::experimental_vector_interleave2>(
+          interleaveOp, typeConverter->convertType(resultType),
+          adaptor.getLhs(), adaptor.getRhs());
+      return success();
+    }
+    // Lower fixed-size interleaves to a shufflevector. While the
+    // vector.interleave2 intrinsic supports fixed and scalable vectors, the
+    // langref still recommends fixed-vectors use shufflevector, see:
+    // https://llvm.org/docs/LangRef.html#id876.
+    int64_t resultVectorSize = resultType.getNumElements();
+    SmallVector<int32_t> interleaveShuffleMask;
+    interleaveShuffleMask.reserve(resultVectorSize);
+    for (int i = 0, end = resultVectorSize / 2; i < end; ++i) {
+      interleaveShuffleMask.push_back(i);
+      interleaveShuffleMask.push_back((resultVectorSize / 2) + i);
+    }
+    rewriter.replaceOpWithNewOp<LLVM::ShuffleVectorOp>(
+        interleaveOp, adaptor.getLhs(), adaptor.getRhs(),
+        interleaveShuffleMask);
+    return success();
+  }
+};
+
 } // namespace
 
 /// Populate the given list with patterns that convert from Vector to LLVM.
@@ -1758,7 +1796,8 @@ void mlir::populateVectorToLLVMConversionPatterns(
                VectorExpandLoadOpConversion, VectorCompressStoreOpConversion,
                VectorSplatOpLowering, VectorSplatNdOpLowering,
                VectorScalableInsertOpLowering, VectorScalableExtractOpLowering,
-               MaskedReductionOpConversion>(converter);
+               MaskedReductionOpConversion, VectorInterleaveOpLowering>(
+      converter);
   // Transfer ops with rank > 1 are handled by VectorToSCF.
   populateVectorTransferLoweringPatterns(patterns, /*maxTransferRank=*/1);
 }
diff --git a/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir b/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
index 1c13b16dfd9af..a46f2e101f3c3 100644
--- a/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
+++ b/mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir
@@ -2460,3 +2460,40 @@ func.func @make_fixed_vector_of_scalable_vector(%f : f64) -> vector<3x[2]xf64>
   %res = vector.broadcast %f : f64 to vector<3x[2]xf64>
   return %res : vector<3x[2]xf64>
 }
+
+// -----
+
+// CHECK-LABEL: @vector_interleave_0d
+//  CHECK-SAME:     %[[LHS:.*]]: vector<i8>, %[[RHS:.*]]: vector<i8>)
+func.func @vector_interleave_0d(%a: vector<i8>, %b: vector<i8>) -> vector<2xi8> {
+  // CHECK: %[[LHS_RANK1:.*]] = builtin.unrealized_conversion_cast %[[LHS]] : vector<i8> to vector<1xi8>
+  // CHECK: %[[RHS_RANK1:.*]] = builtin.unrealized_conversion_cast %[[RHS]] : vector<i8> to vector<1xi8>
+  // CHECK: %[[ZIP:.*]] = llvm.shufflevector %[[LHS_RANK1]], %[[RHS_RANK1]] [0, 1] : vector<1xi8>
+  // CHECK: return %[[ZIP]]
+  %0 = vector.interleave %a, %b : vector<i8>
+  return %0 : vector<2xi8>
+}
+
+// -----
+
+// CHECK-LABEL: @vector_interleave_1d
+//  CHECK-SAME:     %[[LHS:.*]]: vector<8xf32>, %[[RHS:.*]]: vector<8xf32>)
+func.func @vector_interleave_1d(%a: vector<8xf32>, %b: vector<8xf32>) -> vector<16xf32>
+{
+  // CHECK: %[[ZIP:.*]] = llvm.shufflevector %[[LHS]], %[[RHS]] [0, 8, 1, 9, 2, 10, 3, 11, 4, 12, 5, 13, 6, 14, 7, 15] : vector<8xf32>
+  // CHECK: return %[[ZIP]]
+  %0 = vector.interleave %a, %b : vector<8xf32>
+  return %0 : vector<16xf32>
+}
+
+// -----
+
+// CHECK-LABEL: @vector_interleave_1d_scalable
+//  CHECK-SAME:     %[[LHS:.*]]: vector<[4]xi32>, %[[RHS:.*]]: vector<[4]xi32>)
+func.func @vector_interleave_1d_scalable(%a: vector<[4]xi32>, %b: vector<[4]xi32>) -> vector<[8]xi32>
+{
+  // CHECK: %[[ZIP:.*]] = "llvm.intr.experimental.vector.interleave2"(%[[LHS]], %[[RHS]]) : (vector<[4]xi32>, vector<[4]xi32>) -> vector<[8]xi32>
+  // CHECK: return %[[ZIP]]
+  %0 = vector.interleave %a, %b : vector<[4]xi32>
+  return %0 : vector<[8]xi32>
+}



More information about the Mlir-commits mailing list