File: AMDGPUMachineFunction.h

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2~deb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 995,836 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (84 lines) | stat: -rw-r--r-- 2,179 bytes parent folder | download | duplicates (2)
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
//===-- AMDGPUMachineFunctionInfo.h -------------------------------*- 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_AMDGPUMACHINEFUNCTION_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEFUNCTION_H

#include "llvm/ADT/DenseMap.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "Utils/AMDGPUBaseInfo.h"

namespace llvm {

class GCNSubtarget;

class AMDGPUMachineFunction : public MachineFunctionInfo {
  /// A map to keep track of local memory objects and their offsets within the
  /// local memory space.
  SmallDenseMap<const GlobalValue *, unsigned, 4> LocalMemoryObjects;

protected:
  uint64_t ExplicitKernArgSize = 0; // Cache for this.
  Align MaxKernArgAlign;        // Cache for this.

  /// Number of bytes in the LDS that are being used.
  unsigned LDSSize = 0;

  // State of MODE register, assumed FP mode.
  AMDGPU::SIModeRegisterDefaults Mode;

  // Kernels + shaders. i.e. functions called by the driver and not called
  // by other functions.
  bool IsEntryFunction = false;

  bool NoSignedZerosFPMath = false;

  // Function may be memory bound.
  bool MemoryBound = false;

  // Kernel may need limited waves per EU for better performance.
  bool WaveLimiter = false;

public:
  AMDGPUMachineFunction(const MachineFunction &MF);

  uint64_t getExplicitKernArgSize() const {
    return ExplicitKernArgSize;
  }

  unsigned getMaxKernArgAlign() const { return MaxKernArgAlign.value(); }

  unsigned getLDSSize() const {
    return LDSSize;
  }

  AMDGPU::SIModeRegisterDefaults getMode() const {
    return Mode;
  }

  bool isEntryFunction() const {
    return IsEntryFunction;
  }

  bool hasNoSignedZerosFPMath() const {
    return NoSignedZerosFPMath;
  }

  bool isMemoryBound() const {
    return MemoryBound;
  }

  bool needsWaveLimiter() const {
    return WaveLimiter;
  }

  unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalVariable &GV);
};

}
#endif