llvm/mlir/lib/Transforms/ParallelLoopCollapsing.cpp

//===- 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 "mlir/Dialect/LoopOps/LoopOps.h"
#include "mlir/Dialect/StandardOps/IR/Ops.h"
#include "mlir/Pass/Pass.h"
#include "mlir/Transforms/LoopUtils.h"
#include "mlir/Transforms/Passes.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 PassWrapper<ParallelLoopCollapsing, OperationPass<>> {
/// Include the generated pass utilities.
#define GEN_PASS_ParallelLoopCollapsing
#include "mlir/Transforms/Passes.h.inc"

  ParallelLoopCollapsing() = default;
  ParallelLoopCollapsing(const ParallelLoopCollapsing &) {}
  void runOnOperation() override {
    Operation *module = getOperation();

    module->walk([&](loop::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.size())
        combinedLoops.push_back(clCollapsedIndices0);
      if (clCollapsedIndices1.size())
        combinedLoops.push_back(clCollapsedIndices1);
      if (clCollapsedIndices2.size())
        combinedLoops.push_back(clCollapsedIndices2);
      collapseParallelLoops(op, combinedLoops);
    });
  }
};

} // namespace

std::unique_ptr<Pass> mlir::createParallelLoopCollapsingPass() {
  return std::make_unique<ParallelLoopCollapsing>();
}