This patch introduces a new unrolling-based approach for lowering multi-dimensional `vector.from_elements` operations. **Implementation Details:** 1. **New Transform Pattern**: Added `UnrollFromElements` that unrolls a N-D(N>=2) from_elements op to a (N-1)-D from_elements op align the outermost dimension. 2. **Utility Functions**: Added `unrollVectorOp` to reuse the unroll algo of vector.gather for vector.from_elements. 3. **Integration**: Added the unrolling pattern to the convert-vector-to-llvm pass as a temporal transformation. 4. Use direct LLVM dialect operations instead of intermediate vector.insert operations for efficiency in `VectorFromElementsLowering`. **Example:** ```mlir // unroll %v = vector.from_elements %e0, %e1, %e2, %e3 : vector<2x2xf32> => %poison_2d = ub.poison : vector<2x2xf32> %vec_1d_0 = vector.from_elements %e0, %e1 : vector<2xf32> %vec_2d_0 = vector.insert %vec_1d_0, %poison_2d [0] : vector<2xf32> into vector<2x2xf32> %vec_1d_1 = vector.from_elements %e2, %e3 : vector<2xf32> %result = vector.insert %vec_1d_1, %vec_2d_0 [1] : vector<2xf32> into vector<2x2xf32> // convert-vector-to-llvm %v = vector.from_elements %e0, %e1, %e2, %e3 : vector<2x2xf32> => %poison_2d = ub.poison : vector<2x2xf32> %poison_2d_cast = builtin.unrealized_conversion_cast %poison_2d : vector<2x2xf32> to !llvm.array<2 x vector<2xf32>> %poison_1d_0 = llvm.mlir.poison : vector<2xf32> %c0_0 = llvm.mlir.constant(0 : i64) : i64 %vec_1d_0_0 = llvm.insertelement %e0, %poison_1d_0[%c0_0 : i64] : vector<2xf32> %c1_0 = llvm.mlir.constant(1 : i64) : i64 %vec_1d_0_1 = llvm.insertelement %e1, %vec_1d_0_0[%c1_0 : i64] : vector<2xf32> %vec_2d_0 = llvm.insertvalue %vec_1d_0_1, %poison_2d_cast[0] : !llvm.array<2 x vector<2xf32>> %poison_1d_1 = llvm.mlir.poison : vector<2xf32> %c0_1 = llvm.mlir.constant(0 : i64) : i64 %vec_1d_1_0 = llvm.insertelement %e2, %poison_1d_1[%c0_1 : i64] : vector<2xf32> %c1_1 = llvm.mlir.constant(1 : i64) : i64 %vec_1d_1_1 = llvm.insertelement %e3, %vec_1d_1_0[%c1_1 : i64] : vector<2xf32> %vec_2d_1 = llvm.insertvalue %vec_1d_1_1, %vec_2d_0[1] : !llvm.array<2 x vector<2xf32>> %result = builtin.unrealized_conversion_cast %vec_2d_1 : !llvm.array<2 x vector<2xf32>> to vector<2x2xf32> ``` --------- Co-authored-by: Nicolas Vasilache <Nico.Vasilache@amd.com> Co-authored-by: Yang Bai <yangb@nvidia.com> Co-authored-by: James Newling <james.newling@gmail.com> Co-authored-by: Diego Caballero <dieg0ca6aller0@gmail.com>
66 lines
2.4 KiB
C++
66 lines
2.4 KiB
C++
//===- LowerVectorFromElements.cpp - Lower 'vector.from_elements' op -----===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements target-independent rewrites and utilities to lower the
|
|
// 'vector.from_elements' operation.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Dialect/Vector/IR/VectorOps.h"
|
|
#include "mlir/Dialect/Vector/Transforms/LoweringPatterns.h"
|
|
|
|
#define DEBUG_TYPE "lower-vector-from-elements"
|
|
|
|
using namespace mlir;
|
|
|
|
namespace {
|
|
|
|
/// Unrolls 2 or more dimensional `vector.from_elements` ops by unrolling the
|
|
/// outermost dimension. For example:
|
|
/// ```
|
|
/// %v = vector.from_elements %e0, %e1, %e2, %e3, %e4, %e5 : vector<2x3xf32>
|
|
///
|
|
/// ==>
|
|
///
|
|
/// %0 = ub.poison : vector<2x3xf32>
|
|
/// %v0 = vector.from_elements %e0, %e1, %e2 : vector<3xf32>
|
|
/// %1 = vector.insert %v0, %0 [0] : vector<3xf32> into vector<2x3xf32>
|
|
/// %v1 = vector.from_elements %e3, %e4, %e5 : vector<3xf32>
|
|
/// %v = vector.insert %v1, %1 [1] : vector<3xf32> into vector<2x3xf32>
|
|
/// ```
|
|
///
|
|
/// When applied exhaustively, this will produce a sequence of 1-d from_elements
|
|
/// ops.
|
|
struct UnrollFromElements : OpRewritePattern<vector::FromElementsOp> {
|
|
using OpRewritePattern::OpRewritePattern;
|
|
|
|
LogicalResult matchAndRewrite(vector::FromElementsOp op,
|
|
PatternRewriter &rewriter) const override {
|
|
ValueRange allElements = op.getElements();
|
|
|
|
auto unrollFromElementsFn = [&](PatternRewriter &rewriter, Location loc,
|
|
VectorType subTy, int64_t index) {
|
|
size_t subTyNumElements = subTy.getNumElements();
|
|
assert((index + 1) * subTyNumElements <= allElements.size() &&
|
|
"out of bounds");
|
|
ValueRange subElements =
|
|
allElements.slice(index * subTyNumElements, subTyNumElements);
|
|
return vector::FromElementsOp::create(rewriter, loc, subTy, subElements);
|
|
};
|
|
|
|
return unrollVectorOp(op, rewriter, unrollFromElementsFn);
|
|
}
|
|
};
|
|
|
|
} // namespace
|
|
|
|
void mlir::vector::populateVectorFromElementsLoweringPatterns(
|
|
RewritePatternSet &patterns, PatternBenefit benefit) {
|
|
patterns.add<UnrollFromElements>(patterns.getContext(), benefit);
|
|
}
|