a70aa7bb0d
This has been a major TODO for a very long time, and is necessary for establishing a proper dialect-free dependency layering for the Transforms library. Code was moved to effectively two main locations: * Affine/ There was quite a bit of affine dialect related code in Transforms/ do to historical reasons (of a time way into MLIR's past). The following headers were moved to: Transforms/LoopFusionUtils.h -> Dialect/Affine/LoopFusionUtils.h Transforms/LoopUtils.h -> Dialect/Affine/LoopUtils.h Transforms/Utils.h -> Dialect/Affine/Utils.h The following transforms were also moved: AffineLoopFusion, AffinePipelineDataTransfer, LoopCoalescing * SCF/ Only one SCF pass was in Transforms/ (likely accidentally placed here): ParallelLoopCollapsing The SCF specific utilities in LoopUtils have been moved to SCF/Utils.h * Misc: mlir::moveLoopInvariantCode was also moved to LoopLikeInterface.h given that it is a simple utility defined in terms of LoopLikeOpInterface. Differential Revision: https://reviews.llvm.org/D117848
46 lines
1.6 KiB
C++
46 lines
1.6 KiB
C++
//===- ParallelLoopCollapsing.cpp - Pass collapsing parallel loop indices -===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "PassDetail.h"
|
|
#include "mlir/Dialect/SCF/Passes.h"
|
|
#include "mlir/Dialect/SCF/SCF.h"
|
|
#include "mlir/Dialect/SCF/Utils.h"
|
|
#include "mlir/Transforms/RegionUtils.h"
|
|
#include "llvm/Support/CommandLine.h"
|
|
#include "llvm/Support/Debug.h"
|
|
|
|
#define DEBUG_TYPE "parallel-loop-collapsing"
|
|
|
|
using namespace mlir;
|
|
|
|
namespace {
|
|
struct ParallelLoopCollapsing
|
|
: public SCFParallelLoopCollapsingBase<ParallelLoopCollapsing> {
|
|
void runOnOperation() override {
|
|
Operation *module = getOperation();
|
|
|
|
module->walk([&](scf::ParallelOp op) {
|
|
// The common case for GPU dialect will be simplifying the ParallelOp to 3
|
|
// arguments, so we do that here to simplify things.
|
|
llvm::SmallVector<std::vector<unsigned>, 3> combinedLoops;
|
|
if (!clCollapsedIndices0.empty())
|
|
combinedLoops.push_back(clCollapsedIndices0);
|
|
if (!clCollapsedIndices1.empty())
|
|
combinedLoops.push_back(clCollapsedIndices1);
|
|
if (!clCollapsedIndices2.empty())
|
|
combinedLoops.push_back(clCollapsedIndices2);
|
|
collapseParallelLoops(op, combinedLoops);
|
|
});
|
|
}
|
|
};
|
|
} // namespace
|
|
|
|
std::unique_ptr<Pass> mlir::createParallelLoopCollapsingPass() {
|
|
return std::make_unique<ParallelLoopCollapsing>();
|
|
}
|