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
133
134
135
136
137
138
139
|
//===- AMDGPUAnnotateKernelFeaturesPass.cpp -------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
/// \file This pass propagates the uniform-work-group-size attribute from
/// kernels to leaf functions when possible. It also adds additional attributes
/// to hint ABI lowering optimizations later.
//
//===----------------------------------------------------------------------===//
#include "AMDGPU.h"
#include "GCNSubtarget.h"
#include "llvm/Analysis/CallGraph.h"
#include "llvm/Analysis/CallGraphSCCPass.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/IntrinsicsAMDGPU.h"
#include "llvm/IR/IntrinsicsR600.h"
#include "llvm/Target/TargetMachine.h"
#define DEBUG_TYPE "amdgpu-annotate-kernel-features"
using namespace llvm;
namespace {
class AMDGPUAnnotateKernelFeatures : public CallGraphSCCPass {
private:
const TargetMachine *TM = nullptr;
bool addFeatureAttributes(Function &F);
public:
static char ID;
AMDGPUAnnotateKernelFeatures() : CallGraphSCCPass(ID) {}
bool doInitialization(CallGraph &CG) override;
bool runOnSCC(CallGraphSCC &SCC) override;
StringRef getPassName() const override {
return "AMDGPU Annotate Kernel Features";
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
CallGraphSCCPass::getAnalysisUsage(AU);
}
};
} // end anonymous namespace
char AMDGPUAnnotateKernelFeatures::ID = 0;
char &llvm::AMDGPUAnnotateKernelFeaturesID = AMDGPUAnnotateKernelFeatures::ID;
INITIALIZE_PASS(AMDGPUAnnotateKernelFeatures, DEBUG_TYPE,
"Add AMDGPU function attributes", false, false)
bool AMDGPUAnnotateKernelFeatures::addFeatureAttributes(Function &F) {
bool HaveStackObjects = false;
bool Changed = false;
bool HaveCall = false;
bool IsFunc = !AMDGPU::isEntryFunctionCC(F.getCallingConv());
for (BasicBlock &BB : F) {
for (Instruction &I : BB) {
if (isa<AllocaInst>(I)) {
HaveStackObjects = true;
continue;
}
if (auto *CB = dyn_cast<CallBase>(&I)) {
const Function *Callee =
dyn_cast<Function>(CB->getCalledOperand()->stripPointerCasts());
// Note the occurrence of indirect call.
if (!Callee) {
if (!CB->isInlineAsm())
HaveCall = true;
continue;
}
Intrinsic::ID IID = Callee->getIntrinsicID();
if (IID == Intrinsic::not_intrinsic) {
HaveCall = true;
Changed = true;
}
}
}
}
// TODO: We could refine this to captured pointers that could possibly be
// accessed by flat instructions. For now this is mostly a poor way of
// estimating whether there are calls before argument lowering.
if (!IsFunc && HaveCall) {
F.addFnAttr("amdgpu-calls");
Changed = true;
}
if (HaveStackObjects) {
F.addFnAttr("amdgpu-stack-objects");
Changed = true;
}
return Changed;
}
bool AMDGPUAnnotateKernelFeatures::runOnSCC(CallGraphSCC &SCC) {
bool Changed = false;
for (CallGraphNode *I : SCC) {
Function *F = I->getFunction();
// Ignore functions with graphics calling conventions, these are currently
// not allowed to have kernel arguments.
if (!F || F->isDeclaration() || AMDGPU::isGraphics(F->getCallingConv()))
continue;
// Add feature attributes
Changed |= addFeatureAttributes(*F);
}
return Changed;
}
bool AMDGPUAnnotateKernelFeatures::doInitialization(CallGraph &CG) {
auto *TPC = getAnalysisIfAvailable<TargetPassConfig>();
if (!TPC)
report_fatal_error("TargetMachine is required");
TM = &TPC->getTM<TargetMachine>();
return false;
}
Pass *llvm::createAMDGPUAnnotateKernelFeaturesPass() {
return new AMDGPUAnnotateKernelFeatures();
}
|
