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
|
//===- SpeculativeExecution.cpp ---------------------------------*- 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
//
//===----------------------------------------------------------------------===//
//
// This pass hoists instructions to enable speculative execution on
// targets where branches are expensive. This is aimed at GPUs. It
// currently works on simple if-then and if-then-else
// patterns.
//
// Removing branches is not the only motivation for this
// pass. E.g. consider this code and assume that there is no
// addressing mode for multiplying by sizeof(*a):
//
// if (b > 0)
// c = a[i + 1]
// if (d > 0)
// e = a[i + 2]
//
// turns into
//
// p = &a[i + 1];
// if (b > 0)
// c = *p;
// q = &a[i + 2];
// if (d > 0)
// e = *q;
//
// which could later be optimized to
//
// r = &a[i];
// if (b > 0)
// c = r[1];
// if (d > 0)
// e = r[2];
//
// Later passes sink back much of the speculated code that did not enable
// further optimization.
//
// This pass is more aggressive than the function SpeculativeyExecuteBB in
// SimplifyCFG. SimplifyCFG will not speculate if no selects are introduced and
// it will speculate at most one instruction. It also will not speculate if
// there is a value defined in the if-block that is only used in the then-block.
// These restrictions make sense since the speculation in SimplifyCFG seems
// aimed at introducing cheap selects, while this pass is intended to do more
// aggressive speculation while counting on later passes to either capitalize on
// that or clean it up.
//
// If the pass was created by calling
// createSpeculativeExecutionIfHasBranchDivergencePass or the
// -spec-exec-only-if-divergent-target option is present, this pass only has an
// effect on targets where TargetTransformInfo::hasBranchDivergence() is true;
// on other targets, it is a nop.
//
// This lets you include this pass unconditionally in the IR pass pipeline, but
// only enable it for relevant targets.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Scalar/SpeculativeExecution.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Operator.h"
#include "llvm/InitializePasses.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
using namespace llvm;
#define DEBUG_TYPE "speculative-execution"
// The risk that speculation will not pay off increases with the
// number of instructions speculated, so we put a limit on that.
static cl::opt<unsigned> SpecExecMaxSpeculationCost(
"spec-exec-max-speculation-cost", cl::init(7), cl::Hidden,
cl::desc("Speculative execution is not applied to basic blocks where "
"the cost of the instructions to speculatively execute "
"exceeds this limit."));
// Speculating just a few instructions from a larger block tends not
// to be profitable and this limit prevents that. A reason for that is
// that small basic blocks are more likely to be candidates for
// further optimization.
static cl::opt<unsigned> SpecExecMaxNotHoisted(
"spec-exec-max-not-hoisted", cl::init(5), cl::Hidden,
cl::desc("Speculative execution is not applied to basic blocks where the "
"number of instructions that would not be speculatively executed "
"exceeds this limit."));
static cl::opt<bool> SpecExecOnlyIfDivergentTarget(
"spec-exec-only-if-divergent-target", cl::init(false), cl::Hidden,
cl::desc("Speculative execution is applied only to targets with divergent "
"branches, even if the pass was configured to apply only to all "
"targets."));
namespace {
class SpeculativeExecutionLegacyPass : public FunctionPass {
public:
static char ID;
explicit SpeculativeExecutionLegacyPass(bool OnlyIfDivergentTarget = false)
: FunctionPass(ID), OnlyIfDivergentTarget(OnlyIfDivergentTarget ||
SpecExecOnlyIfDivergentTarget),
Impl(OnlyIfDivergentTarget) {}
void getAnalysisUsage(AnalysisUsage &AU) const override;
bool runOnFunction(Function &F) override;
StringRef getPassName() const override {
if (OnlyIfDivergentTarget)
return "Speculatively execute instructions if target has divergent "
"branches";
return "Speculatively execute instructions";
}
private:
// Variable preserved purely for correct name printing.
const bool OnlyIfDivergentTarget;
SpeculativeExecutionPass Impl;
};
} // namespace
char SpeculativeExecutionLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(SpeculativeExecutionLegacyPass, "speculative-execution",
"Speculatively execute instructions", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_END(SpeculativeExecutionLegacyPass, "speculative-execution",
"Speculatively execute instructions", false, false)
void SpeculativeExecutionLegacyPass::getAnalysisUsage(AnalysisUsage &AU) const {
AU.addRequired<TargetTransformInfoWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
AU.setPreservesCFG();
}
bool SpeculativeExecutionLegacyPass::runOnFunction(Function &F) {
if (skipFunction(F))
return false;
auto *TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
return Impl.runImpl(F, TTI);
}
namespace llvm {
bool SpeculativeExecutionPass::runImpl(Function &F, TargetTransformInfo *TTI) {
if (OnlyIfDivergentTarget && !TTI->hasBranchDivergence()) {
LLVM_DEBUG(dbgs() << "Not running SpeculativeExecution because "
"TTI->hasBranchDivergence() is false.\n");
return false;
}
this->TTI = TTI;
bool Changed = false;
for (auto& B : F) {
Changed |= runOnBasicBlock(B);
}
return Changed;
}
bool SpeculativeExecutionPass::runOnBasicBlock(BasicBlock &B) {
BranchInst *BI = dyn_cast<BranchInst>(B.getTerminator());
if (BI == nullptr)
return false;
if (BI->getNumSuccessors() != 2)
return false;
BasicBlock &Succ0 = *BI->getSuccessor(0);
BasicBlock &Succ1 = *BI->getSuccessor(1);
if (&B == &Succ0 || &B == &Succ1 || &Succ0 == &Succ1) {
return false;
}
// Hoist from if-then (triangle).
if (Succ0.getSinglePredecessor() != nullptr &&
Succ0.getSingleSuccessor() == &Succ1) {
return considerHoistingFromTo(Succ0, B);
}
// Hoist from if-else (triangle).
if (Succ1.getSinglePredecessor() != nullptr &&
Succ1.getSingleSuccessor() == &Succ0) {
return considerHoistingFromTo(Succ1, B);
}
// Hoist from if-then-else (diamond), but only if it is equivalent to
// an if-else or if-then due to one of the branches doing nothing.
if (Succ0.getSinglePredecessor() != nullptr &&
Succ1.getSinglePredecessor() != nullptr &&
Succ1.getSingleSuccessor() != nullptr &&
Succ1.getSingleSuccessor() != &B &&
Succ1.getSingleSuccessor() == Succ0.getSingleSuccessor()) {
// If a block has only one instruction, then that is a terminator
// instruction so that the block does nothing. This does happen.
if (Succ1.size() == 1) // equivalent to if-then
return considerHoistingFromTo(Succ0, B);
if (Succ0.size() == 1) // equivalent to if-else
return considerHoistingFromTo(Succ1, B);
}
return false;
}
static InstructionCost ComputeSpeculationCost(const Instruction *I,
const TargetTransformInfo &TTI) {
switch (Operator::getOpcode(I)) {
case Instruction::GetElementPtr:
case Instruction::Add:
case Instruction::Mul:
case Instruction::And:
case Instruction::Or:
case Instruction::Select:
case Instruction::Shl:
case Instruction::Sub:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::Xor:
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::Call:
case Instruction::BitCast:
case Instruction::PtrToInt:
case Instruction::IntToPtr:
case Instruction::AddrSpaceCast:
case Instruction::FPToUI:
case Instruction::FPToSI:
case Instruction::UIToFP:
case Instruction::SIToFP:
case Instruction::FPExt:
case Instruction::FPTrunc:
case Instruction::FAdd:
case Instruction::FSub:
case Instruction::FMul:
case Instruction::FDiv:
case Instruction::FRem:
case Instruction::FNeg:
case Instruction::ICmp:
case Instruction::FCmp:
case Instruction::Trunc:
case Instruction::Freeze:
case Instruction::ExtractElement:
case Instruction::InsertElement:
case Instruction::ShuffleVector:
case Instruction::ExtractValue:
case Instruction::InsertValue:
return TTI.getUserCost(I, TargetTransformInfo::TCK_SizeAndLatency);
default:
return InstructionCost::getInvalid(); // Disallow anything not explicitly
// listed.
}
}
bool SpeculativeExecutionPass::considerHoistingFromTo(
BasicBlock &FromBlock, BasicBlock &ToBlock) {
SmallPtrSet<const Instruction *, 8> NotHoisted;
const auto AllPrecedingUsesFromBlockHoisted = [&NotHoisted](const User *U) {
// Debug variable has special operand to check it's not hoisted.
if (const auto *DVI = dyn_cast<DbgVariableIntrinsic>(U)) {
return all_of(DVI->location_ops(), [&NotHoisted](Value *V) {
if (const auto *I = dyn_cast_or_null<Instruction>(V)) {
if (!NotHoisted.contains(I))
return true;
}
return false;
});
}
// Usially debug label instrinsic corresponds to label in LLVM IR. In these
// cases we should not move it here.
// TODO: Possible special processing needed to detect it is related to a
// hoisted instruction.
if (isa<DbgLabelInst>(U))
return false;
for (const Value *V : U->operand_values()) {
if (const Instruction *I = dyn_cast<Instruction>(V)) {
if (NotHoisted.contains(I))
return false;
}
}
return true;
};
InstructionCost TotalSpeculationCost = 0;
unsigned NotHoistedInstCount = 0;
for (const auto &I : FromBlock) {
const InstructionCost Cost = ComputeSpeculationCost(&I, *TTI);
if (Cost.isValid() && isSafeToSpeculativelyExecute(&I) &&
AllPrecedingUsesFromBlockHoisted(&I)) {
TotalSpeculationCost += Cost;
if (TotalSpeculationCost > SpecExecMaxSpeculationCost)
return false; // too much to hoist
} else {
// Debug info instrinsics should not be counted for threshold.
if (!isa<DbgInfoIntrinsic>(I))
NotHoistedInstCount++;
if (NotHoistedInstCount > SpecExecMaxNotHoisted)
return false; // too much left behind
NotHoisted.insert(&I);
}
}
for (auto I = FromBlock.begin(); I != FromBlock.end();) {
// We have to increment I before moving Current as moving Current
// changes the list that I is iterating through.
auto Current = I;
++I;
if (!NotHoisted.count(&*Current)) {
Current->moveBefore(ToBlock.getTerminator());
}
}
return true;
}
FunctionPass *createSpeculativeExecutionPass() {
return new SpeculativeExecutionLegacyPass();
}
FunctionPass *createSpeculativeExecutionIfHasBranchDivergencePass() {
return new SpeculativeExecutionLegacyPass(/* OnlyIfDivergentTarget = */ true);
}
SpeculativeExecutionPass::SpeculativeExecutionPass(bool OnlyIfDivergentTarget)
: OnlyIfDivergentTarget(OnlyIfDivergentTarget ||
SpecExecOnlyIfDivergentTarget) {}
PreservedAnalyses SpeculativeExecutionPass::run(Function &F,
FunctionAnalysisManager &AM) {
auto *TTI = &AM.getResult<TargetIRAnalysis>(F);
bool Changed = runImpl(F, TTI);
if (!Changed)
return PreservedAnalyses::all();
PreservedAnalyses PA;
PA.preserveSet<CFGAnalyses>();
return PA;
}
} // namespace llvm
|