1b2c8f104f
Currently, `GeneralizePadOpPattern` is grouped under `populatePadOpVectorizationPatterns`. However, as noted in #111349, this transformation "decomposes" rather than "vectorizes" `tensor.pad`. As such, it functions as: * a vectorization _pre-processing_ transformation, not * a vectorization transformation itself. To clarify its purpose, this PR turns `GeneralizePadOpPattern` into a standalone transformation by: * introducing a dedicated `populateDecomposePadPatterns` method, * adding a `apply_patterns.linalg.decompose_pad` Transform Dialect Op, * removing it from `populatePadOpVectorizationPatterns`. In addition, to better reflect its role, it is renamed as "decomposition" rather then "generalization". This is in line with the recent renaming of similar ops, i.e. tensor.pack/tensor.unpack Ops in #116439.
32 lines
1.2 KiB
C++
32 lines
1.2 KiB
C++
//===- TensorToLinalg.cpp - Tensor to Linalg Patterns ---------------------===//
|
|
//
|
|
// 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 patterns to convert Tensor dialect to Linalg dialect.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Conversion/TensorToLinalg/TensorToLinalg.h"
|
|
#include "mlir/Dialect/Linalg/Transforms/Transforms.h"
|
|
#include "mlir/Dialect/Tensor/IR/Tensor.h"
|
|
#include "mlir/IR/AffineMap.h"
|
|
#include "llvm/Support/Debug.h"
|
|
|
|
#define DEBUG_TYPE "tensor-to-linalg-pattern"
|
|
|
|
using namespace mlir;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Pattern population
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
void mlir::populateTensorToLinalgPatterns(RewritePatternSet &patterns) {
|
|
// TODO: Add the remaining patterns, e.g. to decompose Pack/Unpack Ops.
|
|
// Alternatively, delete this file.
|
|
patterns.add<mlir::linalg::DecomposePadOpPattern>(patterns.getContext());
|
|
}
|