Name | Module | Coverage (%) | Time (s) | Nb Threads | Deviation (coverage) | Deviation (time) |
orig | compilers/gcc_3 | orig | compilers/gcc_3 | orig | compilers/gcc_3 | orig | compilers/gcc_3 | orig | compilers/gcc_3 |
dgemm_sve_big | libarmpl.so | 34.67 | 34.8 | 57.03 | 57.53 | 64 | 64 | 2.01 | 1.98 | 5.20 | 5.18 |
miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&) | exec | 18.81 | 18.83 | 30.94 | 31.13 | 64 | 64 | 4.10 | 4.11 | 4.88 | 4.91 |
miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<... | exec | 12.5 | 12.55 | 20.57 | 20.74 | 64 | 64 | 0.98 | 0.98 | 1.02 | 1.05 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::update(int) | exec | 8.87 | 8.83 | 14.59 | 14.6 | 64 | 64 | 0.83 | 0.80 | 1.99 | 1.96 |
interleave_2vl_sve_kernel_d | libarmpl.so | 6.39 | 6.4 | 10.5 | 10.59 | 64 | 64 | 2.46 | 2.47 | 3.96 | 4.01 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&) | exec | 5.25 | 5.22 | 8.64 | 8.64 | 64 | 64 | 0.98 | 0.98 | 0.90 | 0.90 |
strerrordesc_np | libc.so.6 | 2.7 | 2.55 | 4.43 | 4.22 | 64 | 64 | 0.16 | 0.28 | 0.38 | 0.51 |
dgemv_t_sve_kernel | libarmpl.so | 1.45 | 1.47 | 2.39 | 2.43 | 64 | 64 | 0.56 | 0.57 | 0.94 | 0.96 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 1.27 | 1.27 | 2.1 | 2.1 | 64 | 64 | 0.29 | 0.28 | 0.32 | 0.33 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool) | exec | 1.24 | 1.27 | 2.05 | 2.09 | 64 | 64 | 0.24 | 0.26 | 0.45 | 0.49 |
dgemv_n_sve_kernel | libarmpl.so | 0.97 | 0.98 | 1.6 | 1.62 | 64 | 64 | 0.40 | 0.40 | 0.65 | 0.66 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::resize(int, int) | exec | 0.8 | 0.76 | 1.31 | 1.26 | 64 | 64 | 0.07 | 0.06 | 0.07 | 0.07 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0.72 | 0.7 | 1.18 | 1.16 | 64 | 64 | 0.29 | 0.28 | 0.48 | 0.46 |
tran_interleave_3vl_sve_kernel_d | libarmpl.so | 0.64 | 0.66 | 1.06 | 1.09 | 64 | 64 | 0.09 | 0.08 | 0.18 | 0.17 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.58 | 0.57 | 0.95 | 0.95 | 64 | 64 | 0.14 | 0.14 | 0.25 | 0.25 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<... | exec | 0.54 | 0.54 | 0.89 | 0.9 | 64 | 64 | 0.10 | 0.10 | 0.17 | 0.18 |
interleave_3vl_sve_kernel_d | libarmpl.so | 0.38 | 0.38 | 0.63 | 0.62 | 64 | 64 | 0.12 | 0.11 | 0.20 | 0.18 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.3 | 0.3 | 0.5 | 0.49 | 64 | 64 | 0.08 | 0.07 | 0.14 | 0.12 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 0.25 | 0.26 | 0.41 | 0.42 | 64 | 64 | 0.07 | 0.06 | 0.08 | 0.08 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector&l... | exec | 0.16 | 0.16 | 0.26 | 0.26 | 64 | 64 | 0.01 | 0.01 | 0.02 | 0.02 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcplusplus::ParticleSet const&, int, double const*, double*, double*, double*, bool) | exec | 0.14 | 0.13 | 0.22 | 0.22 | 64 | 64 | 0.04 | 0.03 | 0.06 | 0.05 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool) | exec | 0.13 | 0.13 | 0.22 | 0.21 | 64 | 64 | 0.04 | 0.03 | 0.06 | 0.05 |
dgetrf7vn_ | libarmpl.so | 0.13 | 0.13 | 0.21 | 0.22 | 64 | 64 | 0.02 | 0.02 | 0.02 | 0.02 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.11 | 0.12 | 0.18 | 0.19 | 64 | 64 | 0.03 | 0.03 | 0.04 | 0.04 |
qmcplusplus::Vector<double, qmcplusplus::OMPallocator<double, qmcplusplus::Mallocator<double, 32ul> > >::resize(unsigned long, double) | exec | 0.1 | 0.09 | 0.17 | 0.15 | 64 | 64 | 0.05 | 0.05 | 0.06 | 0.06 |
dgeset | libarmpl.so | 0.09 | 0.09 | 0.15 | 0.15 | 64 | 64 | 0.02 | 0.02 | 0.03 | 0.04 |
main._omp_fn.1 | exec | 0.09 | 0.09 | 0.14 | 0.15 | 64 | 64 | 0.02 | 0.03 | 0.03 | 0.03 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&) | exec | 0.08 | 0.08 | 0.14 | 0.14 | 64 | 64 | 0.02 | 0.02 | 0.03 | 0.02 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.06 | 0.06 | 0.09 | 0.09 | 64 | 64 | 0.02 | 0.02 | 0.03 | 0.03 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 0.05 | 0.05 | 0.08 | 0.08 | 64 | 64 | 0.02 | 0.02 | 0.02 | 0.02 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&) | exec | 0.05 | 0.05 | 0.09 | 0.09 | 64 | 64 | 0.02 | 0.02 | 0.03 | 0.04 |
qmcplusplus::BsplineAllocator<double, 32ul, qmcplusplus::Mallocator<double, 32ul> >::setCoefficientsForOrbitals(int, int, Array<double, 3u>&, multi_UBspline_3d_d*) [clone ._omp_fn.0] | exec | 0.04 | 0.03 | 0.07 | 0.05 | 64 | 64 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::stop() | exec | 0.03 | 0.03 | 0.04 | 0.04 | 64 | 64 | 0.03 | 0.03 | 0.04 | 0.05 |
__munmap | libc.so.6 | 0.03 | 0.03 | 0.05 | 0.05 | 64 | 64 | 0.01 | 0.00 | 0.01 | 0.01 |
@plt_start@ | libarmpl.so | 0.03 | 0.03 | 0.05 | 0.04 | 64 | 64 | 0.01 | 0.01 | 0.02 | 0.02 |
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::start() | exec | 0.03 | 0.03 | 0.05 | 0.05 | 64 | 64 | 0.01 | 0.01 | 0.02 | 0.01 |
void armpl::clag::(anonymous namespace)::trsm_kernel<double, true, true, true, false, false>(double const*, long, long, double*, long, long, long, long) | libarmpl.so | 0.01 | 0.02 | 0.02 | 0.03 | 63 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.02 | 0.01 | 0.02 | 0.02 | 63 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
void armpl::clag::(anonymous namespace)::gemv_a_cntg_first<false, double, double, double, double>(long, long, double, double const*, long, long, double const*, long, double, double*, long) | libarmpl.so | 0.01 | 0.02 | 0.02 | 0.03 | 62 | 62 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::ParticleSet::makeMove(int, qmcplusplus::TinyVector<double, 3u> const&, bool) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 60 | 64 | 0.00 | 0.01 | 0.01 | 0.01 |
bool armpl::dispatch_atomic_sve<double>(armpl::armpl_trans, armpl::armpl_trans, long, long, long, double const*, long, double const*, long, double*, long, double, double) | libarmpl.so | 0.01 | 0.01 | 0.01 | 0.02 | 57 | 60 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 0.01 | 0.01 | 0.01 | 0.01 | 56 | 54 | 0.01 | 0.01 | 0.01 | 0.01 |
__libc_malloc | libc.so.6 | 0.01 | 0.01 | 0.01 | 0.01 | 55 | 57 | 0.00 | 0.00 | 0.01 | 0.01 |
qmcplusplus::ParticleSet::update(bool) | exec | 0.01 | 0.01 | 0.01 | 0.01 | 58 | 51 | 0.00 | 0.00 | 0.01 | 0.01 |
unknown_function | exec | 0.01 | 0.01 | 0.01 | 0.01 | 55 | 56 | 0.00 | 0.01 | 0.01 | 0.01 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double,... | exec | 0.01 | 0.01 | 0.01 | 0.01 | 63 | 64 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 57 | 59 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcplusplus::ParticleSet&, int, double const*) [clone .isra.0] | exec | 0.01 | 0.01 | 0.01 | 0.01 | 56 | 54 | 0.00 | 0.00 | 0.00 | 0.01 |
qmcplusplus::ParticleSet::acceptMove(int) | exec | 0.01 | 0.01 | 0.02 | 0.01 | 60 | 58 | 0.01 | 0.00 | 0.01 | 0.01 |
gomp_ialias_omp_get_level | libgomp.so.1.0.0 | 0.01 | 0.01 | 0.02 | 0.02 | 62 | 62 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 59 | 58 | 0.01 | 0.01 | 0.01 | 0.01 |
_ZZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE32ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_6atomicEKNSG_3dotEKNSG_5axpbyEKNSG_4gemvEEEEDaSD_ENKUlRS6_E_clISQ_EEbSR_ | libarmpl.so | 0.01 | 0.01 | 0.02 | 0.02 | 58 | 61 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 61 | 59 | 0.00 | 0.01 | 0.01 | 0.01 |
__exp_finite | libm.so.6 | 0.01 | 0.01 | 0.02 | 0.02 | 61 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
__dynamic_cast | libarmpl.so | 0.01 | 0.01 | 0.02 | 0.02 | 63 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::update(int) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 61 | 62 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, double*, double*, double*, int*) const | exec | 0.01 | 0.01 | 0.02 | 0.02 | 60 | 62 | 0.01 | 0.01 | 0.01 | 0.01 |
daxpy_sve_kernel | libarmpl.so | 0.01 | 0.01 | 0.02 | 0.02 | 61 | 57 | 0.01 | 0.01 | 0.01 | 0.01 |
gomp_team_barrier_wait_final | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 2 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::build_els(qmcplusplus::ParticleSet const&, StdRandom<double, std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul> >&a... | exec | 0 | 0 | 0 | 0 | 2 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> >::resize(unsigned long, double) | exec | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, ... | exec | 0 | 0 | 0 | 0 | 2 | 7 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::TimerManager<qmcplusplus::TimerType<std::chrono::_V2::system_clock> >::push_timer(qmcplusplus::TimerType<std::chrono::_V2::system_clock>*) | exec | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_aligned_alloc | libgomp.so.1.0.0 | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_12_4_NN | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
dtrsv_reference_ | libarmpl.so | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
dgetrf7rn_ | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
_dl_rtld_di_serinfo | ld-linux-aarch64.so.1 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::generic_sve_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::g... | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::BlasThreadingEnv::~BlasThreadingEnv() | exec | 0 | 0 | 0 | 0 | 2 | 4 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::generic_sve_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::g... | libarmpl.so | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
operator new(unsigned long) | libarmpl.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
dger_ | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
dtrtri_ | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
_ZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE16ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_5axpbyEKNSG_13outer_productEEEEDaSD_ | libarmpl.so | 0 | 0 | 0 | 0 | 3 | 7 | 0.00 | 0.00 | 0.00 | 0.00 |
__log_finite | libm.so.6 | 0 | 0 | 0 | 0 | 2 | 13 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::scal_impl<double, double, armpl::clag::spec::generic_sve_machine_spec>(int const*, double const*, double*, int const*) | libarmpl.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
dlamch_ | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::ParticleSet::create(std::vector<int, std::allocator<int> > const&) | exec | 0 | 0 | 0 | 0 | 4 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
dgetrf2_ | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 2 | 0.00 | 0.00 | 0.00 | 0.00 |
GOMP_parallel | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_6_4_NN | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
dgemm_ | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::evaluateLog(qmcplusplus::ParticleSet&) | exec | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::generic_sve_machine_spec>, armpl::clag::(anonymous namespace)::trsm_kernel_exec<double> >::operator()<armpl::clag::(anonymous ... | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 2 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_1_NN | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 4 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::generic_sve_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::g... | libarmpl.so | 0 | 0 | 0 | 0 | 2 | 2 | 0.00 | 0.00 | 0.00 | 0.00 |
dgetrf7wn_ | libarmpl.so | 0 | 0 | 0 | 0 | 1 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::DistanceTableAB::~DistanceTableAB() | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_int<long>(std::ostreambuf_iterator<char, std::char_traits<char> >... | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
dscal_ | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
dgetrf_smp_ | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
idamax_ | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_10_1_1_NN | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
dgetrf7rn_generic_sve_ | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
void trsm_reference<double>(char const*, char const*, char const*, char const*, int const*, int const*, double const*, double const*, int const*, double*, int const*) | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long) | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::ios_base::_M_call_callbacks(std::ios_base::event) | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
_Z22getNextLevelNumThreadsv._omp_fn.0#0x464d60 | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long) | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
qmcplusplus::ParticleSet::rejectMove(int) | exec | 0 | 0 | 0 | 0 | 4 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
std::chrono::_V2::system_clock::now() | libarmpl.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
qmcplusplus::TimerManager<qmcplusplus::TimerType<std::chrono::_V2::system_clock> >::initializeTimer(qmcplusplus::TimerType<std::chrono::_V2::system_clock>&) | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_mutate(unsigned long, unsigned long, char const*, unsigned long) | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::Vector<double, std::allocator<double> >::resize(unsigned long, double) | exec | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 |
qmcplusplus::RealSpacePositionsOMPTarget::setAllParticlePos(qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > > const&) | exec | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
__lll_lock_wait_private | libc.so.6 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
void qmcplusplus::expandSuperCell<qmcplusplus::ParticleSet>(qmcplusplus::ParticleSet&, qmcplusplus::Tensor<int, 3u> const&) | exec | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__aarch64_ldadd4_acq_rel | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
brk | libc.so.6 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__memcmpeq | libc.so.6 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
gomp_init_work_share | libgomp.so.1.0.0 | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 |
gomp_barrier_wait_end | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 1 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_ialias_omp_get_thread_num | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 1 | 2 | 0.00 | 0.00 | 0.00 | 0.00 |
dtrsm_reference_ | libarmpl.so | NA | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 |
gomp_team_end | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
sincos | libm.so.6 | NA | 0 | NA | 0 | NA | 6 | NA | 0.00 | NA | 0.00 |
getenv | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::restore(int) | exec | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
fminimum_mag_numf | libm.so.6 | 0 | 0 | 0 | 0 | 4 | 8 | 0.00 | 0.00 | 0.00 | 0.00 |
void geset<double>(double, long, long, double const*, long) | libarmpl.so | 0 | 0 | 0 | 0 | 11 | 15 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::TimerManager<qmcplusplus::TimerType<std::chrono::_V2::system_clock> >::pop_timer(qmcplusplus::TimerType<std::chrono::_V2::system_clock>*) | exec | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
idamax_kernel | libarmpl.so | 0 | 0 | 0 | 0 | 20 | 25 | 0.00 | 0.00 | 0.00 | 0.00 |
long armpl_get_system_l1_max_elements_generic_sve<double>() | libarmpl.so | 0 | 0 | 0 | 0 | 17 | 19 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::gemv<true, int, double, double, double, double, armpl::clag::spec::generic_sve_machine_spec>(char const*, int const*, int const*, double const*, double const*, int const*, double const*, int const*, double const*, double*, int cons... | libarmpl.so | 0 | 0 | 0 | 0 | 23 | 25 | 0.00 | 0.00 | 0.00 | 0.00 |
_ZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE32ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_6atomicEKNSG_3dotEKNSG_5axpbyEKNSG_4gemvEEEEDaSD_ | libarmpl.so | 0 | 0 | 0 | 0 | 24 | 15 | 0.00 | 0.00 | 0.00 | 0.00 |
dgemv_ | libarmpl.so | 0 | 0 | 0 | 0 | 22 | 28 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::VirtualParticleSet::makeMoves(qmcplusplus::ParticleSet const&, int, std::vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > > const&, bool, int) | exec | 0 | 0 | 0 | 0 | 27 | 28 | 0.00 | 0.00 | 0.00 | 0.00 |
__cxxabiv1::__si_class_type_info::__do_dyncast(long, __cxxabiv1::__class_type_info::__sub_kind, __cxxabiv1::__class_type_info const*, void const*, __cxxabiv1::__class_type_info const*, void const*, __cxxabiv1::__class_type_info::__dyncast_result&) co... | libarmpl.so | 0 | 0 | 0 | 0 | 20 | 21 | 0.00 | 0.00 | 0.00 | 0.00 |
dscal_sve_kernel | libarmpl.so | 0 | 0 | 0 | 0 | 19 | 29 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::RealSpacePositionsOMPTarget::setOneParticlePos(qmcplusplus::TinyVector<double, 3u> const&, unsigned long) | exec | 0 | 0 | 0 | 0 | 14 | 11 | 0.00 | 0.00 | 0.00 | 0.00 |
long armpl_get_system_l1_max_elements<double>() | libarmpl.so | 0 | 0 | 0 | 0 | 17 | 17 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_ialias_omp_get_ancestor_thread_num | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 15 | 17 | 0.00 | 0.00 | 0.00 | 0.00 |
strcmp | libc.so.6 | 0 | 0 | 0 | 0 | 18 | 24 | 0.00 | 0.00 | 0.00 | 0.00 |
_ZZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE32ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_6atomicEKNSG_3dotEKNSG_5axpbyEKNSG_4gemvEEEEDaSD_ENKUlRS6_E_clISK_EEbSR_ | libarmpl.so | 0 | 0 | 0 | 0 | 16 | 13 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_team_barrier_wait_end | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 13 | 16 | 0.00 | 0.00 | 0.00 | 0.00 |
bool armpl::dispatch_atomic<double>(armpl::armpl_trans, armpl::armpl_trans, long, long, long, double const*, long, double const*, long, double*, long, double, double) | libarmpl.so | 0 | 0 | 0 | 0 | 23 | 25 | 0.00 | 0.00 | 0.00 | 0.00 |
__libc_free | libc.so.6 | 0 | 0 | 0 | 0 | 28 | 37 | 0.00 | 0.00 | 0.00 | 0.00 |
_ZZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE16ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_5axpbyEKNSG_13outer_productEEEEDaSD_ENKUlRS6_E_clISM_EEbSN_ | libarmpl.so | 0 | 0 | 0.01 | 0.01 | 41 | 43 | 0.00 | 0.00 | 0.00 | 0.00 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0 | 0 | 0.01 | 0.01 | 39 | 41 | 0.00 | 0.00 | 0.00 | 0.00 |
__cxxabiv1::__vmi_class_type_info::__do_dyncast(long, __cxxabiv1::__class_type_info::__sub_kind, __cxxabiv1::__class_type_info const*, void const*, __cxxabiv1::__class_type_info const*, void const*, __cxxabiv1::__class_type_info::__dyncast_result&) co... | libarmpl.so | 0 | 0 | 0.01 | 0.01 | 43 | 46 | 0.00 | 0.00 | 0.01 | 0.01 |
_ZSt13__invoke_implIvZN5armpl4clag4gemmIdLNS1_4spec12problem_typeE0ENS3_24generic_sve_machine_specEEEvRKNS3_15problem_contextIT_XT0_ET1_EEEUlDpRT_E_JRKNS1_5strat12set_or_scaleERKNSG_6atomicERKNSG_3dotERKNSG_5axpbyERKNSG_4gemvERKNSG_13outer_productERKNSG_5s... | libarmpl.so | 0 | 0 | 0 | 0 | 9 | 10 | 0.00 | 0.00 | 0.00 | 0.00 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0 | 0 | 0.01 | 0 | 44 | 33 | 0.01 | 0.00 | 0.01 | 0.00 |
dlaswp_ | libarmpl.so | 0 | 0 | 0 | 0 | 25 | 26 | 0.00 | 0.00 | 0.00 | 0.00 |
__clone | libc.so.6 | 0 | 0 | 0.01 | 0.01 | 63 | 63 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0 | 0 | 0 | 0 | 35 | 34 | 0.00 | 0.00 | 0.00 | 0.00 |
__mmap | libc.so.6 | 0 | 0 | 0 | 0 | 29 | 30 | 0.00 | 0.00 | 0.00 | 0.00 |
syscall | libc.so.6 | 0 | 0 | 0.01 | 0.01 | 42 | 37 | 0.00 | 0.00 | 0.00 | 0.00 |
__mprotect | libc.so.6 | 0 | 0 | 0 | 0 | 36 | 26 | 0.00 | 0.00 | 0.00 | 0.00 |
lsame_ | libarmpl.so | 0 | 0 | 0 | 0 | 36 | 32 | 0.00 | 0.00 | 0.00 | 0.00 |
ddot_sve_kernel | libarmpl.so | 0 | 0 | 0 | 0 | 31 | 32 | 0.00 | 0.00 | 0.00 | 0.00 |
std::vector<qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 32ul> >, std::allocator<qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 32ul> > > >::resize(unsigned lo... | exec | 0 | 0 | 0 | 0 | 4 | 2 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::ParticleSet::getDistTableAB(int) const | exec | 0 | 0 | 0 | 0 | 13 | 13 | 0.00 | 0.00 | 0.00 | 0.00 |
timer_settime | libc.so.6 | 0 | 0 | 0 | 0 | 9 | 12 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_1_NT | libarmpl.so | 0 | 0 | 0 | 0 | 5 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::trsm<true, int, double, armpl::clag::spec::generic_sve_machine_spec>(char const*, char const*, char const*, char const*, int const*, int const*, double const*, double const*, int const*, double*, int const*) | libarmpl.so | 0 | 0 | 0 | 0 | 5 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_2_NT | libarmpl.so | 0 | 0 | 0 | 0 | 5 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_2_1_6_NT | libarmpl.so | 0 | 0 | 0 | 0 | 5 | 13 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_3_NT | libarmpl.so | 0 | 0 | 0 | 0 | 5 | 8 | 0.00 | 0.00 | 0.00 | 0.00 |
std::vector<qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> >, std::allocator<qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> > > >::_M_default_append(unsigned long) | exec | 0 | 0 | 0 | 0 | 6 | 7 | 0.00 | 0.00 | 0.00 | 0.00 |
__nss_database_lookup | libc.so.6 | 0 | 0 | 0 | 0 | 5 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
__libc_memalign | libc.so.6 | 0 | 0 | 0 | 0 | 5 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_4_NT | libarmpl.so | 0 | 0 | 0 | 0 | 4 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
__clock_gettime | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
@plt_start@ | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 5 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::ParticleSet::getDistTableAA(int) const | exec | 0 | 0 | 0 | 0 | 5 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_team_start | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 5 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
__default_morecore | libc.so.6 | 0 | 0 | 0 | 0 | 12 | 14 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::SoaDistanceTableAAOMPTarget(qmcplusplus::ParticleSet&) | exec | 0 | NA | 0 | NA | 6 | NA | 0.00 | NA | 0.00 | NA |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, ... | exec | 0 | 0 | 0 | 0 | 6 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
unknown_function | [vdso] | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::gemm<true, int, double, double, double, armpl::clag::spec::generic_sve_machine_spec>(char const*, char const*, int const*, int const*, int const*, double const*, double const*, int const*, double const*, int const*, double const*, d... | libarmpl.so | 0 | 0 | 0 | 0 | 9 | 10 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_2_1_7_NT | libarmpl.so | 0 | 0 | 0 | 0 | 12 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::RealSpacePositions::setAllParticlePos(qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > > const&) | exec | 0 | 0 | 0 | 0 | 13 | 8 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_init_task | libgomp.so.1.0.0 | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
armpl::vector_size_bytes() | libarmpl.so | 0 | 0 | 0 | 0 | 6 | 11 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::(anonymous namespace)::gemv_shim<true, double, &dgemv_t_sve_kernel>(long, long, double, double const*, long, long, double const*, long, double, double*, long) | libarmpl.so | 0 | 0 | 0 | 0 | 7 | 16 | 0.00 | 0.00 | 0.00 | 0.00 |
__tunable_get_val | ld-linux-aarch64.so.1 | 0 | 0 | 0 | 0 | 9 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::ger<true, int, false, double, armpl::clag::spec::generic_sve_machine_spec>(int const*, int const*, double const*, double const*, int const*, double const*, int const*, double*, int const*) | libarmpl.so | 0 | 0 | 0 | 0 | 7 | 13 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_resolve_num_threads | libgomp.so.1.0.0 | 0 | 0 | 0 | 0 | 9 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_2_1_5_NT | libarmpl.so | 0 | 0 | 0 | 0 | 7 | 12 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_2_1_8_NT | libarmpl.so | 0 | 0 | 0 | 0 | 7 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
gomp_ialias_omp_get_num_threads | libgomp.so.1.0.0 | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |