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
|
//===----- SVEIntrinsicOpts - SVE ACLE Intrinsics Opts --------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Performs general IR level optimizations on SVE intrinsics.
//
// The main goal of this pass is to remove unnecessary reinterpret
// intrinsics (llvm.aarch64.sve.convert.[to|from].svbool), e.g:
//
// %1 = @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %a)
// %2 = @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %1)
//
// This pass also looks for ptest intrinsics & phi instructions where the
// operands are being needlessly converted to and from svbool_t.
//
//===----------------------------------------------------------------------===//
#include "Utils/AArch64BaseInfo.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/IntrinsicsAArch64.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/InitializePasses.h"
#include "llvm/Support/Debug.h"
using namespace llvm;
using namespace llvm::PatternMatch;
#define DEBUG_TYPE "sve-intrinsic-opts"
namespace llvm {
void initializeSVEIntrinsicOptsPass(PassRegistry &);
}
namespace {
struct SVEIntrinsicOpts : public ModulePass {
static char ID; // Pass identification, replacement for typeid
SVEIntrinsicOpts() : ModulePass(ID) {
initializeSVEIntrinsicOptsPass(*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override;
void getAnalysisUsage(AnalysisUsage &AU) const override;
private:
static IntrinsicInst *isReinterpretToSVBool(Value *V);
static bool optimizeIntrinsic(Instruction *I);
bool optimizeFunctions(SmallSetVector<Function *, 4> &Functions);
static bool optimizeConvertFromSVBool(IntrinsicInst *I);
static bool optimizePTest(IntrinsicInst *I);
static bool processPhiNode(IntrinsicInst *I);
};
} // end anonymous namespace
void SVEIntrinsicOpts::getAnalysisUsage(AnalysisUsage &AU) const {
AU.addRequired<DominatorTreeWrapperPass>();
AU.setPreservesCFG();
}
char SVEIntrinsicOpts::ID = 0;
static const char *name = "SVE intrinsics optimizations";
INITIALIZE_PASS_BEGIN(SVEIntrinsicOpts, DEBUG_TYPE, name, false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass);
INITIALIZE_PASS_END(SVEIntrinsicOpts, DEBUG_TYPE, name, false, false)
namespace llvm {
ModulePass *createSVEIntrinsicOptsPass() { return new SVEIntrinsicOpts(); }
} // namespace llvm
/// Returns V if it's a cast from <n x 16 x i1> (aka svbool_t), nullptr
/// otherwise.
IntrinsicInst *SVEIntrinsicOpts::isReinterpretToSVBool(Value *V) {
IntrinsicInst *I = dyn_cast<IntrinsicInst>(V);
if (!I)
return nullptr;
if (I->getIntrinsicID() != Intrinsic::aarch64_sve_convert_to_svbool)
return nullptr;
return I;
}
/// The function will remove redundant reinterprets casting in the presence
/// of the control flow
bool SVEIntrinsicOpts::processPhiNode(IntrinsicInst *X) {
SmallVector<Instruction *, 32> Worklist;
auto RequiredType = X->getType();
auto *PN = dyn_cast<PHINode>(X->getArgOperand(0));
assert(PN && "Expected Phi Node!");
// Don't create a new Phi unless we can remove the old one.
if (!PN->hasOneUse())
return false;
for (Value *IncValPhi : PN->incoming_values()) {
auto *Reinterpret = isReinterpretToSVBool(IncValPhi);
if (!Reinterpret ||
RequiredType != Reinterpret->getArgOperand(0)->getType())
return false;
}
// Create the new Phi
LLVMContext &Ctx = PN->getContext();
IRBuilder<> Builder(Ctx);
Builder.SetInsertPoint(PN);
PHINode *NPN = Builder.CreatePHI(RequiredType, PN->getNumIncomingValues());
Worklist.push_back(PN);
for (unsigned I = 0; I < PN->getNumIncomingValues(); I++) {
auto *Reinterpret = cast<Instruction>(PN->getIncomingValue(I));
NPN->addIncoming(Reinterpret->getOperand(0), PN->getIncomingBlock(I));
Worklist.push_back(Reinterpret);
}
// Cleanup Phi Node and reinterprets
X->replaceAllUsesWith(NPN);
X->eraseFromParent();
for (auto &I : Worklist)
if (I->use_empty())
I->eraseFromParent();
return true;
}
bool SVEIntrinsicOpts::optimizePTest(IntrinsicInst *I) {
IntrinsicInst *Op1 = dyn_cast<IntrinsicInst>(I->getArgOperand(0));
IntrinsicInst *Op2 = dyn_cast<IntrinsicInst>(I->getArgOperand(1));
if (Op1 && Op2 &&
Op1->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
Op2->getIntrinsicID() == Intrinsic::aarch64_sve_convert_to_svbool &&
Op1->getArgOperand(0)->getType() == Op2->getArgOperand(0)->getType()) {
Value *Ops[] = {Op1->getArgOperand(0), Op2->getArgOperand(0)};
Type *Tys[] = {Op1->getArgOperand(0)->getType()};
Module *M = I->getParent()->getParent()->getParent();
auto Fn = Intrinsic::getDeclaration(M, I->getIntrinsicID(), Tys);
auto CI = CallInst::Create(Fn, Ops, I->getName(), I);
I->replaceAllUsesWith(CI);
I->eraseFromParent();
if (Op1->use_empty())
Op1->eraseFromParent();
if (Op1 != Op2 && Op2->use_empty())
Op2->eraseFromParent();
return true;
}
return false;
}
bool SVEIntrinsicOpts::optimizeConvertFromSVBool(IntrinsicInst *I) {
assert(I->getIntrinsicID() == Intrinsic::aarch64_sve_convert_from_svbool &&
"Unexpected opcode");
// If the reinterpret instruction operand is a PHI Node
if (isa<PHINode>(I->getArgOperand(0)))
return processPhiNode(I);
// If we have a reinterpret intrinsic I of type A which is converting from
// another reinterpret Y of type B, and the source type of Y is A, then we can
// elide away both reinterprets if there are no other users of Y.
auto *Y = isReinterpretToSVBool(I->getArgOperand(0));
if (!Y)
return false;
Value *SourceVal = Y->getArgOperand(0);
if (I->getType() != SourceVal->getType())
return false;
I->replaceAllUsesWith(SourceVal);
I->eraseFromParent();
if (Y->use_empty())
Y->eraseFromParent();
return true;
}
bool SVEIntrinsicOpts::optimizeIntrinsic(Instruction *I) {
IntrinsicInst *IntrI = dyn_cast<IntrinsicInst>(I);
if (!IntrI)
return false;
switch (IntrI->getIntrinsicID()) {
case Intrinsic::aarch64_sve_convert_from_svbool:
return optimizeConvertFromSVBool(IntrI);
case Intrinsic::aarch64_sve_ptest_any:
case Intrinsic::aarch64_sve_ptest_first:
case Intrinsic::aarch64_sve_ptest_last:
return optimizePTest(IntrI);
default:
return false;
}
return true;
}
bool SVEIntrinsicOpts::optimizeFunctions(
SmallSetVector<Function *, 4> &Functions) {
bool Changed = false;
for (auto *F : Functions) {
DominatorTree *DT = &getAnalysis<DominatorTreeWrapperPass>(*F).getDomTree();
// Traverse the DT with an rpo walk so we see defs before uses, allowing
// simplification to be done incrementally.
BasicBlock *Root = DT->getRoot();
ReversePostOrderTraversal<BasicBlock *> RPOT(Root);
for (auto *BB : RPOT)
for (Instruction &I : make_early_inc_range(*BB))
Changed |= optimizeIntrinsic(&I);
}
return Changed;
}
bool SVEIntrinsicOpts::runOnModule(Module &M) {
bool Changed = false;
SmallSetVector<Function *, 4> Functions;
// Check for SVE intrinsic declarations first so that we only iterate over
// relevant functions. Where an appropriate declaration is found, store the
// function(s) where it is used so we can target these only.
for (auto &F : M.getFunctionList()) {
if (!F.isDeclaration())
continue;
switch (F.getIntrinsicID()) {
case Intrinsic::aarch64_sve_convert_from_svbool:
case Intrinsic::aarch64_sve_ptest_any:
case Intrinsic::aarch64_sve_ptest_first:
case Intrinsic::aarch64_sve_ptest_last:
for (auto I = F.user_begin(), E = F.user_end(); I != E;) {
auto *Inst = dyn_cast<Instruction>(*I++);
Functions.insert(Inst->getFunction());
}
break;
default:
break;
}
}
if (!Functions.empty())
Changed |= optimizeFunctions(Functions);
return Changed;
}
|