File: AMDGPUUnifyDivergentExitNodes.h

package info (click to toggle)
llvm-toolchain-21 1%3A21.1.6-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 2,245,028 kB
  • sloc: cpp: 7,619,726; ansic: 1,434,018; asm: 1,058,748; python: 252,740; f90: 94,671; objc: 70,685; lisp: 42,813; pascal: 18,401; sh: 8,601; ml: 5,111; perl: 4,720; makefile: 3,675; awk: 3,523; javascript: 2,409; xml: 892; fortran: 770
file content (36 lines) | stat: -rw-r--r-- 1,511 bytes parent folder | download | duplicates (13)
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
//===- AMDGPUUnifyDivergentExitNodes.h ------------------------------------===//
//
// 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 is a variant of the UnifyFunctionExitNodes pass. Rather than ensuring
// there is at most one ret and one unreachable instruction, it ensures there is
// at most one divergent exiting block.
//
// StructurizeCFG can't deal with multi-exit regions formed by branches to
// multiple return nodes. It is not desirable to structurize regions with
// uniform branches, so unifying those to the same return block as divergent
// branches inhibits use of scalar branching. It still can't deal with the case
// where one branch goes to return, and one unreachable. Replace unreachable in
// this case with a return.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUUNIFYDIVERGENTEXITNODES_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUUNIFYDIVERGENTEXITNODES_H

#include "AMDGPU.h"

namespace llvm {
class AMDGPUUnifyDivergentExitNodesPass
    : public PassInfoMixin<AMDGPUUnifyDivergentExitNodesPass> {
public:
  PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUUNIFYDIVERGENTEXITNODES_H