#include "AArch64.h"
#include "AArch64TargetMachine.h"
-#include "llvm/PassManager.h"
#include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/RegAllocRegistry.h"
+#include "llvm/IR/Function.h"
+#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetOptions.h"
EnableCCMP("aarch64-ccmp", cl::desc("Enable the CCMP formation pass"),
cl::init(true), cl::Hidden);
+static cl::opt<bool> EnableMCR("aarch64-mcr",
+ cl::desc("Enable the machine combiner pass"),
+ cl::init(true), cl::Hidden);
+
static cl::opt<bool>
EnableStPairSuppress("aarch64-stp-suppress", cl::desc("Suppress STP for AArch64"),
cl::init(true), cl::Hidden);
EnableLoadStoreOpt("aarch64-load-store-opt", cl::desc("Enable the load/store pair"
" optimization pass"), cl::init(true), cl::Hidden);
+static cl::opt<bool>
+EnableAtomicTidy("aarch64-atomic-cfg-tidy", cl::Hidden,
+ cl::desc("Run SimplifyCFG after expanding atomic operations"
+ " to make use of cmpxchg flow-based information"),
+ cl::init(true));
+
+static cl::opt<bool>
+EnableEarlyIfConversion("aarch64-enable-early-ifcvt", cl::Hidden,
+ cl::desc("Run early if-conversion"),
+ cl::init(true));
+
+static cl::opt<bool>
+EnableCondOpt("aarch64-condopt",
+ cl::desc("Enable the condition optimizer pass"),
+ cl::init(true), cl::Hidden);
+
+static cl::opt<bool>
+EnableA53Fix835769("aarch64-fix-cortex-a53-835769", cl::Hidden,
+ cl::desc("Work around Cortex-A53 erratum 835769"),
+ cl::init(false));
+
extern "C" void LLVMInitializeAArch64Target() {
// Register the target.
RegisterTargetMachine<AArch64leTargetMachine> X(TheAArch64leTarget);
RegisterTargetMachine<AArch64beTargetMachine> Y(TheAArch64beTarget);
-
- RegisterTargetMachine<AArch64leTargetMachine> Z(TheARM64leTarget);
- RegisterTargetMachine<AArch64beTargetMachine> W(TheARM64beTarget);
+ RegisterTargetMachine<AArch64leTargetMachine> Z(TheARM64Target);
}
/// TargetMachine ctor - Create an AArch64 architecture model.
CodeGenOpt::Level OL,
bool LittleEndian)
: LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL),
- Subtarget(TT, CPU, FS, LittleEndian),
- // This nested ternary is horrible, but DL needs to be properly
- // initialized
- // before TLInfo is constructed.
- DL(Subtarget.isTargetMachO()
- ? "e-m:o-i64:64-i128:128-n32:64-S128"
- : (LittleEndian ? "e-m:e-i64:64-i128:128-n32:64-S128"
- : "E-m:e-i64:64-i128:128-n32:64-S128")),
- InstrInfo(Subtarget), TLInfo(*this), FrameLowering(*this, Subtarget),
- TSInfo(*this) {
+ Subtarget(TT, CPU, FS, *this, LittleEndian), isLittle(LittleEndian) {
initAsmInfo();
}
+const AArch64Subtarget *
+AArch64TargetMachine::getSubtargetImpl(const Function &F) const {
+ AttributeSet FnAttrs = F.getAttributes();
+ Attribute CPUAttr =
+ FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-cpu");
+ Attribute FSAttr =
+ FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-features");
+
+ std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
+ ? CPUAttr.getValueAsString().str()
+ : TargetCPU;
+ std::string FS = !FSAttr.hasAttribute(Attribute::None)
+ ? FSAttr.getValueAsString().str()
+ : TargetFS;
+
+ auto &I = SubtargetMap[CPU + FS];
+ if (!I) {
+ // This needs to be done before we create a new subtarget since any
+ // creation will depend on the TM and the code generation flags on the
+ // function that reside in TargetOptions.
+ resetTargetOptions(F);
+ I = llvm::make_unique<AArch64Subtarget>(TargetTriple, CPU, FS, *this, isLittle);
+ }
+ return I.get();
+}
+
void AArch64leTargetMachine::anchor() { }
AArch64leTargetMachine::
class AArch64PassConfig : public TargetPassConfig {
public:
AArch64PassConfig(AArch64TargetMachine *TM, PassManagerBase &PM)
- : TargetPassConfig(TM, PM) {}
+ : TargetPassConfig(TM, PM) {
+ if (TM->getOptLevel() != CodeGenOpt::None)
+ substitutePass(&PostRASchedulerID, &PostMachineSchedulerID);
+ }
AArch64TargetMachine &getAArch64TargetMachine() const {
return getTM<AArch64TargetMachine>();
}
+ void addIRPasses() override;
bool addPreISel() override;
bool addInstSelector() override;
bool addILPOpts() override;
return new AArch64PassConfig(this, PM);
}
+void AArch64PassConfig::addIRPasses() {
+ // Always expand atomic operations, we don't deal with atomicrmw or cmpxchg
+ // ourselves.
+ addPass(createAtomicExpandPass(TM));
+
+ // Cmpxchg instructions are often used with a subsequent comparison to
+ // determine whether it succeeded. We can exploit existing control-flow in
+ // ldrex/strex loops to simplify this, but it needs tidying up.
+ if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
+ addPass(createCFGSimplificationPass());
+
+ TargetPassConfig::addIRPasses();
+}
+
// Pass Pipeline Configuration
bool AArch64PassConfig::addPreISel() {
// Run promote constant before global merge, so that the promoted constants
if (TM->getOptLevel() != CodeGenOpt::None)
addPass(createAArch64AddressTypePromotionPass());
- // Always expand atomic operations, we don't deal with atomicrmw or cmpxchg
- // ourselves.
- addPass(createAtomicExpandLoadLinkedPass(TM));
-
return false;
}
}
bool AArch64PassConfig::addILPOpts() {
+ if (EnableCondOpt)
+ addPass(createAArch64ConditionOptimizerPass());
if (EnableCCMP)
addPass(createAArch64ConditionalCompares());
- addPass(&EarlyIfConverterID);
+ if (EnableMCR)
+ addPass(&MachineCombinerID);
+ if (EnableEarlyIfConversion)
+ addPass(&EarlyIfConverterID);
if (EnableStPairSuppress)
addPass(createAArch64StorePairSuppressPass());
return true;
bool AArch64PassConfig::addPreRegAlloc() {
// Use AdvSIMD scalar instructions whenever profitable.
- if (TM->getOptLevel() != CodeGenOpt::None && EnableAdvSIMDScalar)
+ if (TM->getOptLevel() != CodeGenOpt::None && EnableAdvSIMDScalar) {
addPass(createAArch64AdvSIMDScalar());
+ // The AdvSIMD pass may produce copies that can be rewritten to
+ // be register coaleascer friendly.
+ addPass(&PeepholeOptimizerID);
+ }
return true;
}
// Change dead register definitions to refer to the zero register.
if (TM->getOptLevel() != CodeGenOpt::None && EnableDeadRegisterElimination)
addPass(createAArch64DeadRegisterDefinitions());
+ if (TM->getOptLevel() != CodeGenOpt::None &&
+ TM->getSubtarget<AArch64Subtarget>().isCortexA57() &&
+ usingDefaultRegAlloc())
+ // Improve performance for some FP/SIMD code for A57.
+ addPass(createAArch64A57FPLoadBalancing());
return true;
}
}
bool AArch64PassConfig::addPreEmitPass() {
+ if (EnableA53Fix835769)
+ addPass(createAArch64A53Fix835769());
// Relax conditional branch instructions if they're otherwise out of
// range of their destination.
addPass(createAArch64BranchRelaxation());
projects / oota-llvm.git / blobdiff