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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
//===- AMDGPUGlobalISelUtils -------------------------------------*- C++ -*-==//
//
// 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
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUGLOBALISELUTILS_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUGLOBALISELUTILS_H
#include "llvm/ADT/DenseSet.h"
#include "llvm/CodeGen/Register.h"
#include <utility>
namespace llvm {
class MachineRegisterInfo;
class GCNSubtarget;
class GISelKnownBits;
class LLT;
class MachineFunction;
class MachineIRBuilder;
class RegisterBankInfo;
namespace AMDGPU {
/// Returns base register and constant offset.
std::pair<Register, unsigned>
getBaseWithConstantOffset(MachineRegisterInfo &MRI, Register Reg,
GISelKnownBits *KnownBits = nullptr,
bool CheckNUW = false);
// Currently finds S32/S64 lane masks that can be declared as divergent by
// uniformity analysis (all are phis at the moment).
// These are defined as i32/i64 in some IR intrinsics (not as i1).
// Tablegen forces(via telling that lane mask IR intrinsics are uniform) most of
// S32/S64 lane masks to be uniform, as this results in them ending up with sgpr
// reg class after instruction-select, don't search for all of them.
class IntrinsicLaneMaskAnalyzer {
SmallDenseSet<Register, 8> S32S64LaneMask;
MachineRegisterInfo &MRI;
public:
IntrinsicLaneMaskAnalyzer(MachineFunction &MF);
bool isS32S64LaneMask(Register Reg) const;
private:
void initLaneMaskIntrinsics(MachineFunction &MF);
// This will not be needed when we turn off LCSSA for global-isel.
void findLCSSAPhi(Register Reg);
};
void buildReadAnyLane(MachineIRBuilder &B, Register SgprDst, Register VgprSrc,
const RegisterBankInfo &RBI);
}
}
#endif
|
