1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
|
//===- 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/SCF.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 ParallelLoopCollapsingBase<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.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>();
}
|
