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
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
|
//===-- LLVMTargetMachine.cpp - Implement the LLVMTargetMachine class -----===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements the LLVMTargetMachine class.
//
//===----------------------------------------------------------------------===//
#include "llvm/Target/TargetMachine.h"
#include "llvm/PassManager.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Assembly/PrintModulePass.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/MachineFunctionAnalysis.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/GCStrategy.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCInstrInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/Target/TargetAsmInfo.h"
#include "llvm/Target/TargetData.h"
#include "llvm/Target/TargetInstrInfo.h"
#include "llvm/Target/TargetRegisterInfo.h"
#include "llvm/Target/TargetRegistry.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/FormattedStream.h"
using namespace llvm;
namespace llvm {
bool EnableFastISel;
}
static cl::opt<bool> DisablePostRA("disable-post-ra", cl::Hidden,
cl::desc("Disable Post Regalloc"));
static cl::opt<bool> DisableBranchFold("disable-branch-fold", cl::Hidden,
cl::desc("Disable branch folding"));
static cl::opt<bool> DisableTailDuplicate("disable-tail-duplicate", cl::Hidden,
cl::desc("Disable tail duplication"));
static cl::opt<bool> DisableEarlyTailDup("disable-early-taildup", cl::Hidden,
cl::desc("Disable pre-register allocation tail duplication"));
static cl::opt<bool> DisableCodePlace("disable-code-place", cl::Hidden,
cl::desc("Disable code placement"));
static cl::opt<bool> DisableSSC("disable-ssc", cl::Hidden,
cl::desc("Disable Stack Slot Coloring"));
static cl::opt<bool> DisableMachineLICM("disable-machine-licm", cl::Hidden,
cl::desc("Disable Machine LICM"));
static cl::opt<bool> DisablePostRAMachineLICM("disable-postra-machine-licm",
cl::Hidden,
cl::desc("Disable Machine LICM"));
static cl::opt<bool> DisableMachineSink("disable-machine-sink", cl::Hidden,
cl::desc("Disable Machine Sinking"));
static cl::opt<bool> DisableLSR("disable-lsr", cl::Hidden,
cl::desc("Disable Loop Strength Reduction Pass"));
static cl::opt<bool> DisableCGP("disable-cgp", cl::Hidden,
cl::desc("Disable Codegen Prepare"));
static cl::opt<bool> PrintLSR("print-lsr-output", cl::Hidden,
cl::desc("Print LLVM IR produced by the loop-reduce pass"));
static cl::opt<bool> PrintISelInput("print-isel-input", cl::Hidden,
cl::desc("Print LLVM IR input to isel pass"));
static cl::opt<bool> PrintGCInfo("print-gc", cl::Hidden,
cl::desc("Dump garbage collector data"));
static cl::opt<bool> ShowMCEncoding("show-mc-encoding", cl::Hidden,
cl::desc("Show encoding in .s output"));
static cl::opt<bool> ShowMCInst("show-mc-inst", cl::Hidden,
cl::desc("Show instruction structure in .s output"));
static cl::opt<bool> EnableMCLogging("enable-mc-api-logging", cl::Hidden,
cl::desc("Enable MC API logging"));
static cl::opt<bool> VerifyMachineCode("verify-machineinstrs", cl::Hidden,
cl::desc("Verify generated machine code"),
cl::init(getenv("LLVM_VERIFY_MACHINEINSTRS")!=NULL));
static cl::opt<cl::boolOrDefault>
AsmVerbose("asm-verbose", cl::desc("Add comments to directives."),
cl::init(cl::BOU_UNSET));
static bool getVerboseAsm() {
switch (AsmVerbose) {
default:
case cl::BOU_UNSET: return TargetMachine::getAsmVerbosityDefault();
case cl::BOU_TRUE: return true;
case cl::BOU_FALSE: return false;
}
}
// Enable or disable FastISel. Both options are needed, because
// FastISel is enabled by default with -fast, and we wish to be
// able to enable or disable fast-isel independently from -O0.
static cl::opt<cl::boolOrDefault>
EnableFastISelOption("fast-isel", cl::Hidden,
cl::desc("Enable the \"fast\" instruction selector"));
LLVMTargetMachine::LLVMTargetMachine(const Target &T, StringRef Triple,
StringRef CPU, StringRef FS,
Reloc::Model RM, CodeModel::Model CM)
: TargetMachine(T, Triple, CPU, FS) {
CodeGenInfo = T.createMCCodeGenInfo(Triple, RM, CM);
AsmInfo = T.createMCAsmInfo(Triple);
}
bool LLVMTargetMachine::addPassesToEmitFile(PassManagerBase &PM,
formatted_raw_ostream &Out,
CodeGenFileType FileType,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Add common CodeGen passes.
MCContext *Context = 0;
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Context))
return true;
assert(Context != 0 && "Failed to get MCContext");
if (hasMCSaveTempLabels())
Context->setAllowTemporaryLabels(false);
const MCAsmInfo &MAI = *getMCAsmInfo();
OwningPtr<MCStreamer> AsmStreamer;
switch (FileType) {
default: return true;
case CGFT_AssemblyFile: {
MCInstPrinter *InstPrinter =
getTarget().createMCInstPrinter(MAI.getAssemblerDialect(), MAI);
// Create a code emitter if asked to show the encoding.
MCCodeEmitter *MCE = 0;
TargetAsmBackend *TAB = 0;
if (ShowMCEncoding) {
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
MCE = getTarget().createCodeEmitter(*getInstrInfo(), STI, *Context);
TAB = getTarget().createAsmBackend(getTargetTriple());
}
MCStreamer *S = getTarget().createAsmStreamer(*Context, Out,
getVerboseAsm(),
hasMCUseLoc(),
hasMCUseCFI(),
InstPrinter,
MCE, TAB,
ShowMCInst);
AsmStreamer.reset(S);
break;
}
case CGFT_ObjectFile: {
// Create the code emitter for the target if it exists. If not, .o file
// emission fails.
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
MCCodeEmitter *MCE = getTarget().createCodeEmitter(*getInstrInfo(), STI,
*Context);
TargetAsmBackend *TAB = getTarget().createAsmBackend(getTargetTriple());
if (MCE == 0 || TAB == 0)
return true;
AsmStreamer.reset(getTarget().createObjectStreamer(getTargetTriple(),
*Context, *TAB, Out, MCE,
hasMCRelaxAll(),
hasMCNoExecStack()));
AsmStreamer.get()->InitSections();
break;
}
case CGFT_Null:
// The Null output is intended for use for performance analysis and testing,
// not real users.
AsmStreamer.reset(createNullStreamer(*Context));
break;
}
if (EnableMCLogging)
AsmStreamer.reset(createLoggingStreamer(AsmStreamer.take(), errs()));
// Create the AsmPrinter, which takes ownership of AsmStreamer if successful.
FunctionPass *Printer = getTarget().createAsmPrinter(*this, *AsmStreamer);
if (Printer == 0)
return true;
// If successful, createAsmPrinter took ownership of AsmStreamer.
AsmStreamer.take();
PM.add(Printer);
PM.add(createGCInfoDeleter());
return false;
}
/// addPassesToEmitMachineCode - Add passes to the specified pass manager to
/// get machine code emitted. This uses a JITCodeEmitter object to handle
/// actually outputting the machine code and resolving things like the address
/// of functions. This method should returns true if machine code emission is
/// not supported.
///
bool LLVMTargetMachine::addPassesToEmitMachineCode(PassManagerBase &PM,
JITCodeEmitter &JCE,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Add common CodeGen passes.
MCContext *Ctx = 0;
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Ctx))
return true;
addCodeEmitter(PM, OptLevel, JCE);
PM.add(createGCInfoDeleter());
return false; // success!
}
/// addPassesToEmitMC - Add passes to the specified pass manager to get
/// machine code emitted with the MCJIT. This method returns true if machine
/// code is not supported. It fills the MCContext Ctx pointer which can be
/// used to build custom MCStreamer.
///
bool LLVMTargetMachine::addPassesToEmitMC(PassManagerBase &PM,
MCContext *&Ctx,
raw_ostream &Out,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Add common CodeGen passes.
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Ctx))
return true;
if (hasMCSaveTempLabels())
Ctx->setAllowTemporaryLabels(false);
// Create the code emitter for the target if it exists. If not, .o file
// emission fails.
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
MCCodeEmitter *MCE = getTarget().createCodeEmitter(*getInstrInfo(),STI, *Ctx);
TargetAsmBackend *TAB = getTarget().createAsmBackend(getTargetTriple());
if (MCE == 0 || TAB == 0)
return true;
OwningPtr<MCStreamer> AsmStreamer;
AsmStreamer.reset(getTarget().createObjectStreamer(getTargetTriple(), *Ctx,
*TAB, Out, MCE,
hasMCRelaxAll(),
hasMCNoExecStack()));
AsmStreamer.get()->InitSections();
// Create the AsmPrinter, which takes ownership of AsmStreamer if successful.
FunctionPass *Printer = getTarget().createAsmPrinter(*this, *AsmStreamer);
if (Printer == 0)
return true;
// If successful, createAsmPrinter took ownership of AsmStreamer.
AsmStreamer.take();
PM.add(Printer);
return false; // success!
}
static void printNoVerify(PassManagerBase &PM, const char *Banner) {
if (PrintMachineCode)
PM.add(createMachineFunctionPrinterPass(dbgs(), Banner));
}
static void printAndVerify(PassManagerBase &PM,
const char *Banner) {
if (PrintMachineCode)
PM.add(createMachineFunctionPrinterPass(dbgs(), Banner));
if (VerifyMachineCode)
PM.add(createMachineVerifierPass(Banner));
}
/// addCommonCodeGenPasses - Add standard LLVM codegen passes used for both
/// emitting to assembly files or machine code output.
///
bool LLVMTargetMachine::addCommonCodeGenPasses(PassManagerBase &PM,
CodeGenOpt::Level OptLevel,
bool DisableVerify,
MCContext *&OutContext) {
// Standard LLVM-Level Passes.
// Basic AliasAnalysis support.
// Add TypeBasedAliasAnalysis before BasicAliasAnalysis so that
// BasicAliasAnalysis wins if they disagree. This is intended to help
// support "obvious" type-punning idioms.
PM.add(createTypeBasedAliasAnalysisPass());
PM.add(createBasicAliasAnalysisPass());
// Before running any passes, run the verifier to determine if the input
// coming from the front-end and/or optimizer is valid.
if (!DisableVerify)
PM.add(createVerifierPass());
// Run loop strength reduction before anything else.
if (OptLevel != CodeGenOpt::None && !DisableLSR) {
PM.add(createLoopStrengthReducePass(getTargetLowering()));
if (PrintLSR)
PM.add(createPrintFunctionPass("\n\n*** Code after LSR ***\n", &dbgs()));
}
PM.add(createGCLoweringPass());
// Make sure that no unreachable blocks are instruction selected.
PM.add(createUnreachableBlockEliminationPass());
// Turn exception handling constructs into something the code generators can
// handle.
switch (getMCAsmInfo()->getExceptionHandlingType()) {
case ExceptionHandling::SjLj:
// SjLj piggy-backs on dwarf for this bit. The cleanups done apply to both
// Dwarf EH prepare needs to be run after SjLj prepare. Otherwise,
// catch info can get misplaced when a selector ends up more than one block
// removed from the parent invoke(s). This could happen when a landing
// pad is shared by multiple invokes and is also a target of a normal
// edge from elsewhere.
PM.add(createSjLjEHPass(getTargetLowering()));
// FALLTHROUGH
case ExceptionHandling::DwarfCFI:
case ExceptionHandling::ARM:
case ExceptionHandling::Win64:
PM.add(createDwarfEHPass(this));
break;
case ExceptionHandling::None:
PM.add(createLowerInvokePass(getTargetLowering()));
// The lower invoke pass may create unreachable code. Remove it.
PM.add(createUnreachableBlockEliminationPass());
break;
}
if (OptLevel != CodeGenOpt::None && !DisableCGP)
PM.add(createCodeGenPreparePass(getTargetLowering()));
PM.add(createStackProtectorPass(getTargetLowering()));
addPreISel(PM, OptLevel);
if (PrintISelInput)
PM.add(createPrintFunctionPass("\n\n"
"*** Final LLVM Code input to ISel ***\n",
&dbgs()));
// All passes which modify the LLVM IR are now complete; run the verifier
// to ensure that the IR is valid.
if (!DisableVerify)
PM.add(createVerifierPass());
// Standard Lower-Level Passes.
// Install a MachineModuleInfo class, which is an immutable pass that holds
// all the per-module stuff we're generating, including MCContext.
TargetAsmInfo *TAI = new TargetAsmInfo(*this);
MachineModuleInfo *MMI = new MachineModuleInfo(*getMCAsmInfo(),
*getRegisterInfo(),
&getTargetLowering()->getObjFileLowering(),
TAI);
PM.add(MMI);
OutContext = &MMI->getContext(); // Return the MCContext specifically by-ref.
// Set up a MachineFunction for the rest of CodeGen to work on.
PM.add(new MachineFunctionAnalysis(*this, OptLevel));
// Enable FastISel with -fast, but allow that to be overridden.
if (EnableFastISelOption == cl::BOU_TRUE ||
(OptLevel == CodeGenOpt::None && EnableFastISelOption != cl::BOU_FALSE))
EnableFastISel = true;
// Ask the target for an isel.
if (addInstSelector(PM, OptLevel))
return true;
// Print the instruction selected machine code...
printAndVerify(PM, "After Instruction Selection");
// Expand pseudo-instructions emitted by ISel.
PM.add(createExpandISelPseudosPass());
// Pre-ra tail duplication.
if (OptLevel != CodeGenOpt::None && !DisableEarlyTailDup) {
PM.add(createTailDuplicatePass(true));
printAndVerify(PM, "After Pre-RegAlloc TailDuplicate");
}
// Optimize PHIs before DCE: removing dead PHI cycles may make more
// instructions dead.
if (OptLevel != CodeGenOpt::None)
PM.add(createOptimizePHIsPass());
// If the target requests it, assign local variables to stack slots relative
// to one another and simplify frame index references where possible.
PM.add(createLocalStackSlotAllocationPass());
if (OptLevel != CodeGenOpt::None) {
// With optimization, dead code should already be eliminated. However
// there is one known exception: lowered code for arguments that are only
// used by tail calls, where the tail calls reuse the incoming stack
// arguments directly (see t11 in test/CodeGen/X86/sibcall.ll).
PM.add(createDeadMachineInstructionElimPass());
printAndVerify(PM, "After codegen DCE pass");
if (!DisableMachineLICM)
PM.add(createMachineLICMPass());
PM.add(createMachineCSEPass());
if (!DisableMachineSink)
PM.add(createMachineSinkingPass());
printAndVerify(PM, "After Machine LICM, CSE and Sinking passes");
PM.add(createPeepholeOptimizerPass());
printAndVerify(PM, "After codegen peephole optimization pass");
}
// Run pre-ra passes.
if (addPreRegAlloc(PM, OptLevel))
printAndVerify(PM, "After PreRegAlloc passes");
// Perform register allocation.
PM.add(createRegisterAllocator(OptLevel));
printAndVerify(PM, "After Register Allocation");
// Perform stack slot coloring and post-ra machine LICM.
if (OptLevel != CodeGenOpt::None) {
// FIXME: Re-enable coloring with register when it's capable of adding
// kill markers.
if (!DisableSSC)
PM.add(createStackSlotColoringPass(false));
// Run post-ra machine LICM to hoist reloads / remats.
if (!DisablePostRAMachineLICM)
PM.add(createMachineLICMPass(false));
printAndVerify(PM, "After StackSlotColoring and postra Machine LICM");
}
// Run post-ra passes.
if (addPostRegAlloc(PM, OptLevel))
printAndVerify(PM, "After PostRegAlloc passes");
PM.add(createLowerSubregsPass());
printAndVerify(PM, "After LowerSubregs");
// Insert prolog/epilog code. Eliminate abstract frame index references...
PM.add(createPrologEpilogCodeInserter());
printAndVerify(PM, "After PrologEpilogCodeInserter");
// Run pre-sched2 passes.
if (addPreSched2(PM, OptLevel))
printAndVerify(PM, "After PreSched2 passes");
// Second pass scheduler.
if (OptLevel != CodeGenOpt::None && !DisablePostRA) {
PM.add(createPostRAScheduler(OptLevel));
printAndVerify(PM, "After PostRAScheduler");
}
// Branch folding must be run after regalloc and prolog/epilog insertion.
if (OptLevel != CodeGenOpt::None && !DisableBranchFold) {
PM.add(createBranchFoldingPass(getEnableTailMergeDefault()));
printNoVerify(PM, "After BranchFolding");
}
// Tail duplication.
if (OptLevel != CodeGenOpt::None && !DisableTailDuplicate) {
PM.add(createTailDuplicatePass(false));
printNoVerify(PM, "After TailDuplicate");
}
PM.add(createGCMachineCodeAnalysisPass());
if (PrintGCInfo)
PM.add(createGCInfoPrinter(dbgs()));
if (OptLevel != CodeGenOpt::None && !DisableCodePlace) {
PM.add(createCodePlacementOptPass());
printNoVerify(PM, "After CodePlacementOpt");
}
if (addPreEmitPass(PM, OptLevel))
printNoVerify(PM, "After PreEmit passes");
return false;
}
|