-------------------------------------------------------------------------------- I1 cache: 65536 B, 64 B, 4-way associative D1 cache: 32768 B, 64 B, 8-way associative LL cache: 67108864 B, 64 B, 64-way associative Command: /usr/home/liquid/.rustup/toolchains/w-profiling/bin/rustc --crate-name blake2b_simd --edition=2018 src/lib.rs --error-format=json --json=diagnostic-rendered-ansi,artifacts,future-incompat --crate-type lib --emit=dep-info,metadata,link -C opt-level=3 -C embed-bitcode=no --cfg feature="default" --cfg feature="std" -C metadata=eb6e9e7df5b3e369 -C extra-filename=-eb6e9e7df5b3e369 --out-dir /usr/home/liquid/tmp/.tmp8cWTDY/target/release/deps -L dependency=/usr/home/liquid/tmp/.tmp8cWTDY/target/release/deps --extern arrayref=/usr/home/liquid/tmp/.tmp8cWTDY/target/release/deps/libarrayref-8fff99c49c173f1f.rmeta --extern arrayvec=/usr/home/liquid/tmp/.tmp8cWTDY/target/release/deps/libarrayvec-342b8efb123441af.rmeta --extern constant_time_eq=/usr/home/liquid/tmp/.tmp8cWTDY/target/release/deps/libconstant_time_eq-d8824ac9ae83b830.rmeta -Adeprecated -Aunknown-lints -Zincremental-verify-ich Data file: results/cgout-w-profiling-blake2b_simd-1.0.0-Opt-Full Events recorded: Ir Events shown: Ir Event sort order: Ir Thresholds: 0.1 Include dirs: User annotated: Auto-annotation: on -------------------------------------------------------------------------------- Ir -------------------------------------------------------------------------------- 19,334,160,724 (100.0%) PROGRAM TOTALS -------------------------------------------------------------------------------- Ir file:function -------------------------------------------------------------------------------- 2,338,524,170 (12.10%) ???:computeKnownBits(llvm::Value const*, llvm::APInt const&, llvm::KnownBits&, unsigned int, (anonymous namespace)::Query const&) 1,181,442,834 ( 6.11%) ???:llvm::ConstantDataSequential::getElementAsConstant(unsigned int) const 830,680,530 ( 4.30%) ???:computeKnownBits(llvm::Value const*, llvm::KnownBits&, unsigned int, (anonymous namespace)::Query const&) [clone .llvm.15619146473165121143] 601,771,754 ( 3.11%) ???:llvm::isNonEscapingLocalObject(llvm::Value const*, llvm::SmallDenseMap, llvm::detail::DenseMapPair >*) 599,011,770 ( 3.10%) ???:computeKnownBitsFromAssume(llvm::Value const*, llvm::KnownBits&, unsigned int, (anonymous namespace)::Query const&) 557,965,010 ( 2.89%) ???:computeKnownBitsFromOperator(llvm::Operator const*, llvm::APInt const&, llvm::KnownBits&, unsigned int, (anonymous namespace)::Query const&) 525,278,125 ( 2.72%) ???:llvm::DataLayout::getTypeSizeInBits(llvm::Type*) const 524,773,158 ( 2.71%) ???:llvm::SelectionDAG::computeKnownBits(llvm::SDValue, llvm::APInt const&, unsigned int) const 337,885,543 ( 1.75%) ???:getTargetConstantBitsFromNode(llvm::SDValue, unsigned int, llvm::APInt&, llvm::SmallVectorImpl&, bool, bool) 262,183,849 ( 1.36%) ./malloc/malloc.c:_int_free 247,322,004 ( 1.28%) ???:llvm::Constant::getAggregateElement(unsigned int) const 245,152,060 ( 1.27%) ./malloc/malloc.c:_int_malloc 242,490,675 ( 1.25%) ???:llvm::X86TargetLowering::computeKnownBitsForTargetNode(llvm::SDValue, llvm::KnownBits&, llvm::APInt const&, llvm::SelectionDAG const&, unsigned int) const 232,958,710 ( 1.20%) ???:llvm::DecodePSHUFBMask(llvm::ArrayRef, llvm::APInt const&, llvm::SmallVectorImpl&) 166,197,055 ( 0.86%) ???:llvm::InstCombinerImpl::run() 163,517,650 ( 0.85%) ./malloc/malloc.c:malloc 161,076,953 ( 0.83%) ???:getTargetShuffleMaskIndices(llvm::SDValue, unsigned int, llvm::SmallVectorImpl&, llvm::APInt&) 138,322,111 ( 0.72%) ???:llvm::BasicAAResult::alias(llvm::MemoryLocation const&, llvm::MemoryLocation const&, llvm::AAQueryInfo&) 123,674,103 ( 0.64%) ???:SimplifyAddInst(llvm::Value*, llvm::Value*, bool, bool, llvm::SimplifyQuery const&, unsigned int) [clone .llvm.1619516508949622737] 114,516,722 ( 0.59%) ???:combineInstructionsOverFunction(llvm::Function&, llvm::InstCombineWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::ProfileSummaryInfo*, unsigned int, llvm::LoopInfo*) 113,941,729 ( 0.59%) ???:llvm::Type::getPrimitiveSizeInBits() const 112,728,653 ( 0.58%) ???:llvm::MachineInstr::findRegisterDefOperandIdx(llvm::Register, bool, bool, llvm::TargetRegisterInfo const*) const 92,347,622 ( 0.48%) ???:llvm::InlineFunction(llvm::CallBase&, llvm::InlineFunctionInfo&, llvm::AAResults*, bool, llvm::Function*) 92,062,036 ( 0.48%) ???:llvm::PointerMayBeCaptured(llvm::Value const*, llvm::CaptureTracker*, unsigned int) 83,391,297 ( 0.43%) ???:llvm::SmallVectorImpl::assign(unsigned long, llvm::APInt const&) 82,993,334 ( 0.43%) ???:llvm::DataLayout::getAlignment(llvm::Type*, bool) const 82,492,823 ( 0.43%) ./malloc/malloc.c:free 80,580,614 ( 0.42%) ???:llvm::BasicAAResult::getModRefInfo(llvm::CallBase const*, llvm::MemoryLocation const&, llvm::AAQueryInfo&) 77,851,568 ( 0.40%) ???:llvm::FPPassManager::runOnFunction(llvm::Function&) 77,475,955 ( 0.40%) ???:(anonymous namespace)::RAGreedy::trySplit(llvm::LiveInterval&, llvm::AllocationOrder&, llvm::SmallVectorImpl&, llvm::SmallSet > const&) 77,365,094 ( 0.40%) ???:void llvm::SmallVectorImpl::append(llvm::APInt const*, llvm::APInt const*) 72,781,017 ( 0.38%) ./string/../sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S:__memset_avx2_erms 72,015,554 ( 0.37%) ???:(anonymous namespace)::PromoteMem2Reg::run() 67,184,904 ( 0.35%) ???:llvm::InstCombinerImpl::SimplifyDemandedUseBits(llvm::Value*, llvm::APInt, llvm::KnownBits&, unsigned int, llvm::Instruction*) 66,599,406 ( 0.34%) ???:bool llvm::DenseMapBase*, llvm::DenseMapInfo<(anonymous namespace)::SimpleValue>, llvm::detail::DenseMapPair<(anonymous namespace)::SimpleValue, llvm::ScopedHashTableVal<(anonymous namespace)::SimpleValue, llvm::Value*>*> >, (anonymous namespace)::SimpleValue, llvm::ScopedHashTableVal<(anonymous namespace)::SimpleValue, llvm::Value*>*, llvm::DenseMapInfo<(anonymous namespace)::SimpleValue>, llvm::detail::DenseMapPair<(anonymous namespace)::SimpleValue, llvm::ScopedHashTableVal<(anonymous namespace)::SimpleValue, llvm::Value*>*> >::LookupBucketFor<(anonymous namespace)::SimpleValue>((anonymous namespace)::SimpleValue const&, llvm::detail::DenseMapPair<(anonymous namespace)::SimpleValue, llvm::ScopedHashTableVal<(anonymous namespace)::SimpleValue, llvm::Value*>*> const*&) const 66,598,604 ( 0.34%) ???:llvm::SelectionDAG::Combine(llvm::CombineLevel, llvm::AAResults*, llvm::CodeGenOpt::Level) 65,977,031 ( 0.34%) ???:llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) 64,681,712 ( 0.33%) ???:llvm::ScheduleDAGMILive::updatePressureDiffs(llvm::ArrayRef) 64,577,409 ( 0.33%) ???:llvm::AnalysisManager::getResultImpl(llvm::AnalysisKey*, llvm::Function&) 64,565,547 ( 0.33%) ???:getShuffleDemandedElts(llvm::ShuffleVectorInst const*, llvm::APInt const&, llvm::APInt&, llvm::APInt&) 64,486,349 ( 0.33%) ???:runCVP(llvm::Module&) [clone .llvm.11785992503873176614] 62,561,434 ( 0.32%) ???:llvm::TargetLibraryInfoImpl::getLibFunc(llvm::Function const&, llvm::LibFunc&) const 62,297,553 ( 0.32%) ???:llvm::ScheduleDAGInstrs::addPhysRegDeps(llvm::SUnit*, unsigned int) 61,270,375 ( 0.32%) ???:(anonymous namespace)::eliminateDeadStores(llvm::Function&, llvm::AAResults&, llvm::MemorySSA&, llvm::DominatorTree&, llvm::PostDominatorTree&, llvm::TargetLibraryInfo const&, llvm::LoopInfo const&) [clone .llvm.5769264623867638418] 59,528,760 ( 0.31%) ./string/../sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S:__memcmp_avx2_movbe 58,784,908 ( 0.30%) ???:(anonymous namespace)::RAGreedy::tryAssign(llvm::LiveInterval&, llvm::AllocationOrder&, llvm::SmallVectorImpl&, llvm::SmallSet > const&) 58,701,703 ( 0.30%) ???:(anonymous namespace)::PruningFunctionCloner::CloneBlock(llvm::BasicBlock const*, llvm::ilist_iterator, false, true>, std::vector >&) 58,570,209 ( 0.30%) ???:llvm::ValueHandleBase::AddToUseList() 57,572,241 ( 0.30%) ???:getTargetShuffleMask(llvm::SDNode*, llvm::MVT, bool, llvm::SmallVectorImpl&, llvm::SmallVectorImpl&, bool&) 55,985,149 ( 0.29%) ???:llvm::KnownBits::computeForAddCarry(llvm::KnownBits const&, llvm::KnownBits const&, llvm::KnownBits const&) 55,886,581 ( 0.29%) ???:llvm::APInt::zextOrTrunc(unsigned int) const 55,348,054 ( 0.29%) ???:llvm::AnalysisManager::invalidate(llvm::Function&, llvm::PreservedAnalyses const&) 51,828,733 ( 0.27%) ???:llvm::EVT::getVectorNumElements() const 49,005,176 ( 0.25%) ???:llvm::InstCombinerImpl::visitAdd(llvm::BinaryOperator&) 48,611,381 ( 0.25%) ???:llvm::AttributeList::addAttributes(llvm::LLVMContext&, unsigned int, llvm::AttrBuilder const&) const 48,247,666 ( 0.25%) ???:llvm::Constant::getSplatValue(bool) const 47,893,659 ( 0.25%) ???:llvm::SimplifyInstruction(llvm::Instruction*, llvm::SimplifyQuery const&, llvm::OptimizationRemarkEmitter*) 46,791,527 ( 0.24%) ???:llvm::APInt::insertBits(llvm::APInt const&, unsigned int) 46,060,979 ( 0.24%) ./string/../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:__memcpy_avx_unaligned_erms 45,583,979 ( 0.24%) ???:llvm::LiveIntervalUnion::Query::collectInterferingVRegs(unsigned int) 43,966,305 ( 0.23%) ???:llvm::Type::isSizedDerivedType(llvm::SmallPtrSetImpl*) const 42,664,355 ( 0.22%) ???:CompareValueComplexity(llvm::EquivalenceClasses&, llvm::LoopInfo const*, llvm::Value*, llvm::Value*, unsigned int) 42,096,440 ( 0.22%) ???:llvm::SROA::runOnAlloca(llvm::AllocaInst&) 40,655,121 ( 0.21%) ???:(anonymous namespace)::JoinVals::computeAssignment(unsigned int, (anonymous namespace)::JoinVals&) 36,756,792 ( 0.19%) ???:llvm::SelectionDAGISel::SelectCodeCommon(llvm::SDNode*, unsigned char const*, unsigned int) 35,919,541 ( 0.19%) ???:llvm::BitstreamCursor::readRecord(unsigned int, llvm::SmallVectorImpl&, llvm::StringRef*) 35,278,705 ( 0.18%) ???:llvm::DomTreeBuilder::SemiNCAInfo >::CalculateFromScratch(llvm::DominatorTreeBase&, llvm::DomTreeBuilder::SemiNCAInfo >::BatchUpdateInfo*) 34,281,754 ( 0.18%) ???:llvm::Intrinsic::getDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef) 33,978,733 ( 0.18%) ./malloc/malloc.c:malloc_consolidate 33,307,296 ( 0.17%) ???:CompareSCEVComplexity(llvm::EquivalenceClasses&, llvm::EquivalenceClasses&, llvm::LoopInfo const*, llvm::SCEV const*, llvm::SCEV const*, llvm::DominatorTree&, unsigned int) 33,276,268 ( 0.17%) ???:ComputeNumSignBitsImpl(llvm::Value const*, llvm::APInt const&, unsigned int, (anonymous namespace)::Query const&) [clone .llvm.15619146473165121143] 32,955,406 ( 0.17%) ???:llvm::MDTuple::getImpl(llvm::LLVMContext&, llvm::ArrayRef, llvm::Metadata::StorageType, bool) 32,621,879 ( 0.17%) ???:(anonymous namespace)::LazyValueInfoImpl::solve() [clone .llvm.4316243980339171764] 32,434,081 ( 0.17%) ???:llvm::SROA::splitAlloca(llvm::AllocaInst&, llvm::sroa::AllocaSlices&) 31,702,869 ( 0.16%) ???:llvm::TargetLowering::SimplifyDemandedVectorElts(llvm::SDValue, llvm::APInt const&, llvm::APInt&, llvm::APInt&, llvm::TargetLowering::TargetLoweringOpt&, unsigned int, bool) const 31,415,012 ( 0.16%) ???:llvm::computeConstantRange(llvm::Value const*, bool, llvm::AssumptionCache*, llvm::Instruction const*, unsigned int) 30,313,458 ( 0.16%) ???:updateCGAndAnalysisManagerForPass(llvm::LazyCallGraph&, llvm::LazyCallGraph::SCC&, llvm::LazyCallGraph::Node&, llvm::AnalysisManager&, llvm::CGSCCUpdateResult&, llvm::AnalysisManager&, bool) [clone .llvm.5426518467876156712] 29,960,431 ( 0.15%) ???:llvm::TargetLowering::SimplifyDemandedBits(llvm::SDValue, llvm::APInt const&, llvm::APInt const&, llvm::KnownBits&, llvm::TargetLowering::TargetLoweringOpt&, unsigned int, bool) const 29,627,302 ( 0.15%) ???:llvm::SROA::rewritePartition(llvm::AllocaInst&, llvm::sroa::AllocaSlices&, llvm::sroa::Partition&) 28,002,799 ( 0.14%) ???:(anonymous namespace)::EarlyCSE::run() [clone .llvm.7062997131228810369] 27,673,332 ( 0.14%) ???:(anonymous namespace)::MachineCopyPropagation::runOnMachineFunction(llvm::MachineFunction&) 26,708,849 ( 0.14%) ./malloc/malloc.c:unlink_chunk.constprop.0 25,662,849 ( 0.13%) ???:llvm::InstCombinerImpl::visitXor(llvm::BinaryOperator&) 25,457,701 ( 0.13%) ???:llvm::AttributeSetNode::get(llvm::LLVMContext&, llvm::AttrBuilder const&) 24,820,585 ( 0.13%) ???:llvm::AAResults::getModRefInfo(llvm::Instruction const*, llvm::Optional const&, llvm::AAQueryInfo&) 24,491,753 ( 0.13%) /tmp/gcc-build/x86_64-unknown-linux-gnu/libstdc++-v3/libsupc++/../../../../gcc-5.5.0/libstdc++-v3/libsupc++/new_op.cc:operator new(unsigned long) 24,401,753 ( 0.13%) ???:SimplifyICmpInst(unsigned int, llvm::Value*, llvm::Value*, llvm::SimplifyQuery const&, unsigned int) [clone .llvm.1619516508949622737] 23,776,612 ( 0.12%) ???:llvm::GVN::processBlock(llvm::BasicBlock*) 23,006,319 ( 0.12%) ???:getTargetConstantBitsFromNode(llvm::SDValue, unsigned int, llvm::APInt&, llvm::SmallVectorImpl&, bool, bool)::$_105::operator()(llvm::APInt&, llvm::ArrayRef) const 22,844,013 ( 0.12%) ???:llvm::ScalarEvolution::getAddExpr(llvm::SmallVectorImpl&, llvm::SCEV::NoWrapFlags, unsigned int) 22,803,619 ( 0.12%) ???:llvm::ScheduleDAGInstrs::addVRegDefDeps(llvm::SUnit*, unsigned int) 22,730,959 ( 0.12%) ???:llvm::SROA::runImpl(llvm::Function&, llvm::DominatorTree&, llvm::AssumptionCache&) 22,373,264 ( 0.12%) ???:llvm::Instruction::eraseFromParent() 21,660,672 ( 0.11%) ???:llvm::KnownBits::commonBits(llvm::KnownBits const&, llvm::KnownBits const&) 21,599,700 ( 0.11%) ???:llvm::removeUnreachableBlocks(llvm::Function&, llvm::DomTreeUpdater*, llvm::MemorySSAUpdater*) 21,512,230 ( 0.11%) ???:llvm::Value::stripAndAccumulateConstantOffsets(llvm::DataLayout const&, llvm::APInt&, bool, llvm::function_ref) const 21,456,225 ( 0.11%) ???:llvm::AAResults::Model::getModRefBehavior(llvm::CallBase const*) 21,008,104 ( 0.11%) ???:llvm::DemandedBits::isInstructionDead(llvm::Instruction*) 20,700,003 ( 0.11%) ???:llvm::AttributeList::get(llvm::LLVMContext&, llvm::ArrayRef) 20,339,265 ( 0.11%) ???:(anonymous namespace)::LazyValueInfoImpl::getEdgeValue(llvm::Value*, llvm::BasicBlock*, llvm::BasicBlock*, llvm::Instruction*) [clone .llvm.4316243980339171764] 19,862,172 ( 0.10%) ???:llvm::Instruction::setMetadata(unsigned int, llvm::MDNode*) 19,801,440 ( 0.10%) ???:llvm::VirtRegAuxInfo::weightCalcHelper(llvm::LiveInterval&, llvm::SlotIndex*, llvm::SlotIndex*) 19,751,698 ( 0.10%) ???:llvm::InstCombinerImpl::visitLoadInst(llvm::LoadInst&) -------------------------------------------------------------------------------- The following files chosen for auto-annotation could not be found: -------------------------------------------------------------------------------- ./malloc/malloc.c ./string/../sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S ./string/../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S ./string/../sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S /tmp/gcc-build/x86_64-unknown-linux-gnu/libstdc++-v3/libsupc++/../../../../gcc-5.5.0/libstdc++-v3/libsupc++/new_op.cc