[mlir][VectorOps] Add conversion of 1-D vector.interleave ops to LLVM (2/4)

[MacDue]

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

[c-rhodes]

one minor comment, but otherwise LGTM, cheers

[llvmbot]

@llvm/pr-subscribers-mlir

Author: Benjamin Maxwell (MacDue)

Changes

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

---

Full diff: https://github.com/llvm/llvm-project/pull/80966.diff

2 Files Affected:

• (modified) mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp (+40-1)
• (modified) mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir (+37)

diff --git a/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp b/mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
index b66b55ae8d57ff..0d9a451d11ca87 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 1c13b16dfd9af3..a46f2e101f3c35 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>
+}

[banach-space]

LGTM