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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
//===-- 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 "Utils/AMDGPUBaseInfo.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
namespace llvm {
class AMDGPUSubtarget;
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.
uint32_t LDSSize = 0;
uint32_t GDSSize = 0;
/// Number of bytes in the LDS allocated statically. This field is only used
/// in the instruction selector and not part of the machine function info.
uint32_t StaticLDSSize = 0;
uint32_t StaticGDSSize = 0;
/// Align for dynamic shared memory if any. Dynamic shared memory is
/// allocated directly after the static one, i.e., LDSSize. Need to pad
/// LDSSize to ensure that dynamic one is aligned accordingly.
/// The maximal alignment is updated during IR translation or lowering
/// stages.
Align DynLDSAlign;
// Flag to check dynamic LDS usage by kernel.
bool UsesDynamicLDS = false;
// Kernels + shaders. i.e. functions called by the hardware and not called
// by other functions.
bool IsEntryFunction = false;
// Entry points called by other functions instead of directly by the hardware.
bool IsModuleEntryFunction = false;
// Functions with the amdgpu_cs_chain or amdgpu_cs_chain_preserve CC.
bool IsChainFunction = 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 Function &F, const AMDGPUSubtarget &ST);
uint64_t getExplicitKernArgSize() const {
return ExplicitKernArgSize;
}
Align getMaxKernArgAlign() const { return MaxKernArgAlign; }
uint32_t getLDSSize() const {
return LDSSize;
}
uint32_t getGDSSize() const {
return GDSSize;
}
bool isEntryFunction() const {
return IsEntryFunction;
}
bool isModuleEntryFunction() const { return IsModuleEntryFunction; }
bool isChainFunction() const { return IsChainFunction; }
// The stack is empty upon entry to this function.
bool isBottomOfStack() const {
return isEntryFunction() || isChainFunction();
}
bool hasNoSignedZerosFPMath() const {
return NoSignedZerosFPMath;
}
bool isMemoryBound() const {
return MemoryBound;
}
bool needsWaveLimiter() const {
return WaveLimiter;
}
unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalVariable &GV) {
return allocateLDSGlobal(DL, GV, DynLDSAlign);
}
unsigned allocateLDSGlobal(const DataLayout &DL, const GlobalVariable &GV,
Align Trailing);
static std::optional<uint32_t> getLDSKernelIdMetadata(const Function &F);
static std::optional<uint32_t> getLDSAbsoluteAddress(const GlobalValue &GV);
Align getDynLDSAlign() const { return DynLDSAlign; }
void setDynLDSAlign(const Function &F, const GlobalVariable &GV);
void setUsesDynamicLDS(bool DynLDS);
bool isDynamicLDSUsed() const;
};
}
#endif
|
