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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
|
//===--- NVPTX.cpp - Implement NVPTX target feature support ---------------===//
//
// 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 file implements NVPTX TargetInfo objects.
//
//===----------------------------------------------------------------------===//
#include "NVPTX.h"
#include "Targets.h"
#include "clang/Basic/Builtins.h"
#include "clang/Basic/MacroBuilder.h"
#include "clang/Basic/TargetBuiltins.h"
#include "llvm/ADT/StringSwitch.h"
using namespace clang;
using namespace clang::targets;
const Builtin::Info NVPTXTargetInfo::BuiltinInfo[] = {
#define BUILTIN(ID, TYPE, ATTRS) \
{#ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, nullptr},
#define LIBBUILTIN(ID, TYPE, ATTRS, HEADER) \
{#ID, TYPE, ATTRS, HEADER, ALL_LANGUAGES, nullptr},
#define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE) \
{#ID, TYPE, ATTRS, nullptr, ALL_LANGUAGES, FEATURE},
#include "clang/Basic/BuiltinsNVPTX.def"
};
const char *const NVPTXTargetInfo::GCCRegNames[] = {"r0"};
NVPTXTargetInfo::NVPTXTargetInfo(const llvm::Triple &Triple,
const TargetOptions &Opts,
unsigned TargetPointerWidth)
: TargetInfo(Triple) {
assert((TargetPointerWidth == 32 || TargetPointerWidth == 64) &&
"NVPTX only supports 32- and 64-bit modes.");
PTXVersion = 32;
for (const StringRef Feature : Opts.FeaturesAsWritten) {
if (!Feature.startswith("+ptx"))
continue;
PTXVersion = llvm::StringSwitch<unsigned>(Feature)
.Case("+ptx75", 75)
.Case("+ptx74", 74)
.Case("+ptx73", 73)
.Case("+ptx72", 72)
.Case("+ptx71", 71)
.Case("+ptx70", 70)
.Case("+ptx65", 65)
.Case("+ptx64", 64)
.Case("+ptx63", 63)
.Case("+ptx61", 61)
.Case("+ptx60", 60)
.Case("+ptx50", 50)
.Case("+ptx43", 43)
.Case("+ptx42", 42)
.Case("+ptx41", 41)
.Case("+ptx40", 40)
.Case("+ptx32", 32)
.Default(32);
}
TLSSupported = false;
VLASupported = false;
AddrSpaceMap = &NVPTXAddrSpaceMap;
UseAddrSpaceMapMangling = true;
// Define available target features
// These must be defined in sorted order!
NoAsmVariants = true;
GPU = CudaArch::SM_20;
if (TargetPointerWidth == 32)
resetDataLayout("e-p:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
else if (Opts.NVPTXUseShortPointers)
resetDataLayout(
"e-p3:32:32-p4:32:32-p5:32:32-i64:64-i128:128-v16:16-v32:32-n16:32:64");
else
resetDataLayout("e-i64:64-i128:128-v16:16-v32:32-n16:32:64");
// If possible, get a TargetInfo for our host triple, so we can match its
// types.
llvm::Triple HostTriple(Opts.HostTriple);
if (!HostTriple.isNVPTX())
HostTarget.reset(AllocateTarget(llvm::Triple(Opts.HostTriple), Opts));
// If no host target, make some guesses about the data layout and return.
if (!HostTarget) {
LongWidth = LongAlign = TargetPointerWidth;
PointerWidth = PointerAlign = TargetPointerWidth;
switch (TargetPointerWidth) {
case 32:
SizeType = TargetInfo::UnsignedInt;
PtrDiffType = TargetInfo::SignedInt;
IntPtrType = TargetInfo::SignedInt;
break;
case 64:
SizeType = TargetInfo::UnsignedLong;
PtrDiffType = TargetInfo::SignedLong;
IntPtrType = TargetInfo::SignedLong;
break;
default:
llvm_unreachable("TargetPointerWidth must be 32 or 64");
}
return;
}
// Copy properties from host target.
PointerWidth = HostTarget->getPointerWidth(/* AddrSpace = */ 0);
PointerAlign = HostTarget->getPointerAlign(/* AddrSpace = */ 0);
BoolWidth = HostTarget->getBoolWidth();
BoolAlign = HostTarget->getBoolAlign();
IntWidth = HostTarget->getIntWidth();
IntAlign = HostTarget->getIntAlign();
HalfWidth = HostTarget->getHalfWidth();
HalfAlign = HostTarget->getHalfAlign();
FloatWidth = HostTarget->getFloatWidth();
FloatAlign = HostTarget->getFloatAlign();
DoubleWidth = HostTarget->getDoubleWidth();
DoubleAlign = HostTarget->getDoubleAlign();
LongWidth = HostTarget->getLongWidth();
LongAlign = HostTarget->getLongAlign();
LongLongWidth = HostTarget->getLongLongWidth();
LongLongAlign = HostTarget->getLongLongAlign();
MinGlobalAlign = HostTarget->getMinGlobalAlign(/* TypeSize = */ 0);
NewAlign = HostTarget->getNewAlign();
DefaultAlignForAttributeAligned =
HostTarget->getDefaultAlignForAttributeAligned();
SizeType = HostTarget->getSizeType();
IntMaxType = HostTarget->getIntMaxType();
PtrDiffType = HostTarget->getPtrDiffType(/* AddrSpace = */ 0);
IntPtrType = HostTarget->getIntPtrType();
WCharType = HostTarget->getWCharType();
WIntType = HostTarget->getWIntType();
Char16Type = HostTarget->getChar16Type();
Char32Type = HostTarget->getChar32Type();
Int64Type = HostTarget->getInt64Type();
SigAtomicType = HostTarget->getSigAtomicType();
ProcessIDType = HostTarget->getProcessIDType();
UseBitFieldTypeAlignment = HostTarget->useBitFieldTypeAlignment();
UseZeroLengthBitfieldAlignment = HostTarget->useZeroLengthBitfieldAlignment();
UseExplicitBitFieldAlignment = HostTarget->useExplicitBitFieldAlignment();
ZeroLengthBitfieldBoundary = HostTarget->getZeroLengthBitfieldBoundary();
// This is a bit of a lie, but it controls __GCC_ATOMIC_XXX_LOCK_FREE, and
// we need those macros to be identical on host and device, because (among
// other things) they affect which standard library classes are defined, and
// we need all classes to be defined on both the host and device.
MaxAtomicInlineWidth = HostTarget->getMaxAtomicInlineWidth();
// Properties intentionally not copied from host:
// - LargeArrayMinWidth, LargeArrayAlign: Not visible across the
// host/device boundary.
// - SuitableAlign: Not visible across the host/device boundary, and may
// correctly be different on host/device, e.g. if host has wider vector
// types than device.
// - LongDoubleWidth, LongDoubleAlign: nvptx's long double type is the same
// as its double type, but that's not necessarily true on the host.
// TODO: nvcc emits a warning when using long double on device; we should
// do the same.
}
ArrayRef<const char *> NVPTXTargetInfo::getGCCRegNames() const {
return llvm::makeArrayRef(GCCRegNames);
}
bool NVPTXTargetInfo::hasFeature(StringRef Feature) const {
return llvm::StringSwitch<bool>(Feature)
.Cases("ptx", "nvptx", true)
.Default(false);
}
void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
MacroBuilder &Builder) const {
Builder.defineMacro("__PTX__");
Builder.defineMacro("__NVPTX__");
if (Opts.CUDAIsDevice) {
// Set __CUDA_ARCH__ for the GPU specified.
std::string CUDAArchCode = [this] {
switch (GPU) {
case CudaArch::GFX600:
case CudaArch::GFX601:
case CudaArch::GFX602:
case CudaArch::GFX700:
case CudaArch::GFX701:
case CudaArch::GFX702:
case CudaArch::GFX703:
case CudaArch::GFX704:
case CudaArch::GFX705:
case CudaArch::GFX801:
case CudaArch::GFX802:
case CudaArch::GFX803:
case CudaArch::GFX805:
case CudaArch::GFX810:
case CudaArch::GFX900:
case CudaArch::GFX902:
case CudaArch::GFX904:
case CudaArch::GFX906:
case CudaArch::GFX908:
case CudaArch::GFX909:
case CudaArch::GFX90a:
case CudaArch::GFX90c:
case CudaArch::GFX1010:
case CudaArch::GFX1011:
case CudaArch::GFX1012:
case CudaArch::GFX1013:
case CudaArch::GFX1030:
case CudaArch::GFX1031:
case CudaArch::GFX1032:
case CudaArch::GFX1033:
case CudaArch::GFX1034:
case CudaArch::GFX1035:
case CudaArch::Generic:
case CudaArch::LAST:
break;
case CudaArch::UNUSED:
case CudaArch::UNKNOWN:
assert(false && "No GPU arch when compiling CUDA device code.");
return "";
case CudaArch::SM_20:
return "200";
case CudaArch::SM_21:
return "210";
case CudaArch::SM_30:
return "300";
case CudaArch::SM_32:
return "320";
case CudaArch::SM_35:
return "350";
case CudaArch::SM_37:
return "370";
case CudaArch::SM_50:
return "500";
case CudaArch::SM_52:
return "520";
case CudaArch::SM_53:
return "530";
case CudaArch::SM_60:
return "600";
case CudaArch::SM_61:
return "610";
case CudaArch::SM_62:
return "620";
case CudaArch::SM_70:
return "700";
case CudaArch::SM_72:
return "720";
case CudaArch::SM_75:
return "750";
case CudaArch::SM_80:
return "800";
case CudaArch::SM_86:
return "860";
}
llvm_unreachable("unhandled CudaArch");
}();
Builder.defineMacro("__CUDA_ARCH__", CUDAArchCode);
}
}
ArrayRef<Builtin::Info> NVPTXTargetInfo::getTargetBuiltins() const {
return llvm::makeArrayRef(BuiltinInfo, clang::NVPTX::LastTSBuiltin -
Builtin::FirstTSBuiltin);
}
|
