Name | Module | Coverage (%) | Time (s) | Nb Threads | Deviation (coverage) | Deviation (time) |
orig | compilers/armclang_3 | orig | compilers/armclang_3 | orig | compilers/armclang_3 | orig | compilers/armclang_3 | orig | compilers/armclang_3 |
void miniqmcreference::MultiBsplineEvalRef::evaluate_v<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, unsigned long) | exec | 20.1 | 19.88 | 31.55 | 31.58 | 64 | 64 | 4.33 | 4.27 | 4.90 | 4.95 |
dgemm_sve_big | libarmpl.so | 35.3 | NA | 55.42 | NA | 64 | NA | 2.13 | NA | 5.06 | NA |
dgemm_sve_big | libarmpl_mp.so | NA | 34.93 | NA | 55.51 | NA | 64 | NA | 2.09 | NA | 5.09 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::update(int) | exec | 9.4 | 9.33 | 14.76 | 14.83 | 64 | 64 | 0.76 | 0.74 | 1.63 | 1.62 |
void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const*, double, double, double, double*, double*, double*, unsigned long) | exec | 8.83 | 8.67 | 13.85 | 13.78 | 64 | 64 | 0.60 | 0.60 | 1.57 | 1.57 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&) | exec | 4.21 | 4.16 | 6.6 | 6.61 | 64 | 64 | 0.79 | 0.78 | 0.84 | 0.86 |
interleave_2vl_sve_kernel_d | libarmpl.so | 6.6 | NA | 10.37 | NA | 64 | NA | 2.43 | NA | 3.83 | NA |
interleave_2vl_sve_kernel_d | libarmpl_mp.so | NA | 6.58 | NA | 10.46 | NA | 64 | NA | 2.31 | NA | 3.72 |
void qmcplusplus::DTD_BConds<double, 3u, 40>::computeDistances<qmcplusplus::TinyVector<double, 3u>, qmcplusplus::VectorSoAContainer<double, 3u, qmcplusplus::Mallocator<double, 32ul> >, qmcplusplus::VectorSoAContainer<double, 3... | exec | 1.45 | 1.39 | 2.28 | 2.22 | 64 | 64 | 0.20 | 0.20 | 0.39 | 0.39 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 1.36 | 1.38 | 2.14 | 2.19 | 64 | 64 | 0.26 | 0.26 | 0.29 | 0.29 |
std::vector<double, qmcplusplus::Mallocator<double, 32ul> >::_M_default_append(unsigned long) | exec | 0.86 | 1.27 | 1.35 | 2.02 | 64 | 64 | 0.05 | 0.19 | 0.10 | 0.28 |
__sched_yield | libc.so.6 | 0.97 | 0.98 | 1.53 | 1.55 | 64 | 64 | 0.26 | 0.30 | 0.33 | 0.38 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0.93 | 0.89 | 1.46 | 1.42 | 64 | 64 | 0.20 | 0.20 | 0.36 | 0.36 |
dgemv_t_sve_kernel | libarmpl.so | 1.61 | NA | 2.53 | NA | 64 | NA | 0.49 | NA | 0.83 | NA |
dgemv_t_sve_kernel | libarmpl_mp.so | NA | 1.59 | NA | 2.53 | NA | 64 | NA | 0.48 | NA | 0.81 |
qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >::resize(unsigned long, qmcplusplus::TinyVector<double, 3u>) | exec | 0.62 | 0.88 | 0.97 | 1.4 | 64 | 64 | 0.03 | 0.09 | 0.03 | 0.12 |
qmcplusplus::Vector<double, std::allocator<double> >::resize(unsigned long, double) | exec | 0.59 | 0.83 | 0.93 | 1.32 | 64 | 64 | 0.03 | 0.08 | 0.04 | 0.10 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.7 | 0.7 | 1.1 | 1.11 | 64 | 64 | 0.08 | 0.08 | 0.13 | 0.14 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<... | exec | 0.54 | 0.55 | 0.85 | 0.87 | 64 | 64 | 0.10 | 0.10 | 0.17 | 0.17 |
dgemv_n_sve_kernel | libarmpl_mp.so | NA | 1.06 | NA | 1.68 | NA | 64 | NA | 0.33 | NA | 0.55 |
dgemv_n_sve_kernel | libarmpl.so | 1.06 | NA | 1.66 | NA | 64 | NA | 0.35 | NA | 0.57 | NA |
qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const*, double*, double*, double*, double*, int*) const | exec | 0.53 | 0.52 | 0.83 | 0.82 | 64 | 64 | 0.06 | 0.06 | 0.09 | 0.10 |
__memcpy | libastring.so | 0.5 | 0.49 | 0.79 | 0.79 | 64 | 64 | 0.05 | 0.07 | 0.11 | 0.13 |
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 | 0.42 | 0.41 | 0.67 | 0.66 | 64 | 64 | 0.06 | 0.06 | 0.06 | 0.07 |
tran_interleave_3vl_sve_kernel_d | libarmpl.so | 0.67 | NA | 1.05 | NA | 64 | NA | 0.09 | NA | 0.18 | NA |
tran_interleave_3vl_sve_kernel_d | libarmpl_mp.so | NA | 0.67 | NA | 1.07 | NA | 64 | NA | 0.10 | NA | 0.19 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.33 | 0.33 | 0.52 | 0.52 | 64 | 64 | 0.06 | 0.06 | 0.11 | 0.11 |
qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<double, std::allocator<double> > const&, std::vector<double, st... | exec | 0.24 | 0.25 | 0.37 | 0.4 | 64 | 64 | 0.06 | 0.07 | 0.07 | 0.08 |
interleave_3vl_sve_kernel_d | libarmpl.so | 0.41 | NA | 0.65 | NA | 64 | NA | 0.11 | NA | 0.19 | NA |
interleave_3vl_sve_kernel_d | libarmpl_mp.so | NA | 0.41 | NA | 0.66 | NA | 64 | NA | 0.12 | NA | 0.19 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0.15 | 0.15 | 0.24 | 0.24 | 64 | 64 | 0.02 | 0.03 | 0.03 | 0.04 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.14 | 0.14 | 0.22 | 0.22 | 64 | 64 | 0.03 | 0.02 | 0.04 | 0.03 |
kmp_flag_64<false, true>::wait(kmp_info*, int, void*) | libomp.so | 0.09 | 0.1 | 0.14 | 0.16 | 60 | 63 | 0.05 | 0.06 | 0.07 | 0.08 |
qmcplusplus::Vector<double, qmcplusplus::OMPallocator<double, qmcplusplus::Mallocator<double, 32ul> > >::resize(unsigned long, double) | exec | 0.08 | 0.1 | 0.12 | 0.16 | 64 | 64 | 0.02 | 0.06 | 0.03 | 0.07 |
qmcplusplus::DiracMatrix<double, double>::invert_transpose(qmcplusplus::Matrix<double, std::allocator<double> > const&, qmcplusplus::Matrix<double, std::allocator<double> >&, double&, double&) | exec | 0.09 | 0.09 | 0.14 | 0.15 | 64 | 64 | 0.01 | 0.01 | 0.02 | 0.01 |
qmcplusplus::NonLocalPP<double>::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&) | exec | 0.08 | 0.08 | 0.12 | 0.13 | 64 | 64 | 0.03 | 0.02 | 0.03 | 0.03 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&) | exec | 0.08 | 0.08 | 0.13 | 0.13 | 64 | 64 | 0.02 | 0.02 | 0.02 | 0.02 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.07 | 0.07 | 0.11 | 0.11 | 64 | 64 | 0.02 | 0.02 | 0.03 | 0.03 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector&l... | exec | 0.07 | 0.07 | 0.11 | 0.11 | 64 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
dgetrf7vn_ | libarmpl_mp.so | NA | 0.13 | NA | 0.21 | NA | 64 | NA | 0.02 | NA | 0.02 |
dgetrf7vn_ | libarmpl.so | 0.13 | NA | 0.21 | NA | 64 | NA | 0.02 | NA | 0.02 | NA |
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 |
dgeset | libarmpl.so | 0.08 | NA | 0.13 | NA | 64 | NA | 0.02 | NA | 0.03 | NA |
dgeset | libarmpl_mp.so | NA | 0.08 | NA | 0.13 | NA | 64 | NA | 0.02 | NA | 0.03 |
.omp_outlined..11 | exec | 0.04 | 0.04 | 0.07 | 0.07 | 64 | 64 | 0.00 | 0.00 | 0.00 | 0.00 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcplusplus::ParticleSet&, int, double const*) | exec | 0.04 | 0.04 | 0.06 | 0.06 | 64 | 64 | 0.01 | 0.01 | 0.02 | 0.02 |
__munmap | libc.so.6 | 0.03 | 0.03 | 0.05 | 0.05 | 64 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::start() | exec | 0.03 | 0.03 | 0.05 | 0.05 | 64 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
__kmp_api_omp_get_level | libomp.so | 0.02 | 0.02 | 0.03 | 0.03 | 64 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::einspline_spo_ref<double>::evaluate_v(qmcplusplus::ParticleSet const&, int) | exec | 0.02 | 0.02 | 0.03 | 0.03 | 62 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::stop() | exec | 0.02 | 0.02 | 0.04 | 0.04 | 64 | 64 | 0.03 | 0.03 | 0.04 | 0.05 |
@plt_start@ | libarmpl_mp.so | NA | 0.03 | NA | 0.05 | NA | 64 | NA | 0.01 | NA | 0.02 |
qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.01 | 0.02 | 0.02 | 0.03 | 60 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
@plt_start@ | libarmpl.so | 0.03 | NA | 0.04 | NA | 64 | NA | 0.01 | NA | 0.02 | NA |
__kmp_get_global_thread_id_reg | libomp.so | 0.01 | 0.02 | 0.02 | 0.03 | 64 | 64 | 0.01 | 0.01 | 0.01 | 0.01 |
__libc_malloc | libc.so.6 | 0.01 | 0.01 | 0.01 | 0.01 | 53 | 51 | 0.00 | 0.00 | 0.01 | 0.01 |
void qmcplusplus::DelayedUpdate<double, double>::acceptRow<qmcplusplus::Vector<double, std::allocator<double> > >(qmcplusplus::Matrix<double, std::allocator<double> >&, int, qmcplusplus::Vector<double, std::alloca... | exec | 0.01 | 0.01 | 0.01 | 0.01 | 53 | 54 | 0.01 | 0.00 | 0.01 | 0.01 |
void qmcplusplus::DelayedUpdate<double, double>::getInvRow<qmcplusplus::Vector<double, std::allocator<double> > >(qmcplusplus::Matrix<double, std::allocator<double> > const&, int, qmcplusplus::Vector<double, std::... | exec | 0.01 | 0.01 | 0.01 | 0.01 | 58 | 54 | 0.01 | 0.00 | 0.01 | 0.01 |
miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&) | exec | 0.01 | 0.01 | 0.01 | 0.01 | 50 | 55 | 0.00 | 0.00 | 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_mp.so | NA | 0.02 | NA | 0.03 | NA | 63 | NA | 0.01 | NA | 0.01 |
unknown_function | exec | 0.01 | 0.01 | 0.01 | 0.01 | 47 | 47 | 0.00 | 0.00 | 0.01 | 0.01 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&) | exec | 0.01 | 0.01 | 0.01 | 0.01 | 58 | 61 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::(anonymous namespace)::trsm_kernel<double, true, true, true, false, false>(double const*, long, long, double*, long, long, long, long) | libarmpl_mp.so | NA | 0.02 | NA | 0.03 | NA | 64 | NA | 0.01 | NA | 0.01 |
qmcplusplus::ParticleSet::update(bool) | exec | 0.01 | 0.01 | 0.01 | 0.01 | 54 | 58 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.01 | 0.01 | 0.01 | 0.02 | 56 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::ParticleSet::acceptMove(int) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 57 | 59 | 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 | 0.02 | NA | 0.03 | NA | 64 | NA | 0.01 | NA | 0.01 | NA |
qmcplusplus::WaveFunction::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 60 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
.omp_outlined..64 | exec | 0.01 | 0.01 | 0.02 | 0.02 | 63 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check() | libomp.so | 0.01 | 0.01 | 0.02 | 0.02 | 55 | 58 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 60 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int) | exec | 0.01 | 0.01 | 0.02 | 0.01 | 61 | 59 | 0.01 | 0.00 | 0.01 | 0.01 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 58 | 63 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool) | exec | 0.01 | 0.01 | 0.02 | 0.01 | 57 | 58 | 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 | 58 | 60 | 0.01 | 0.01 | 0.01 | 0.01 |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::update(int) | exec | 0.01 | 0.01 | 0.02 | 0.01 | 61 | 59 | 0.01 | 0.01 | 0.01 | 0.01 |
miniqmcreference::einspline_spo_ref<double>::evaluate_vgh(qmcplusplus::ParticleSet const&, int) | exec | 0.01 | 0.01 | 0.02 | 0.02 | 62 | 60 | 0.01 | 0.01 | 0.01 | 0.01 |
__exp_finite | libamath.so | 0.01 | 0.01 | 0.01 | 0.02 | 59 | 61 | 0.00 | 0.01 | 0.01 | 0.01 |
__dynamic_cast | libarmpl.so | 0.01 | NA | 0.02 | NA | 62 | NA | 0.01 | NA | 0.01 | NA |
_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 | NA | 0.02 | NA | 62 | NA | 0.01 | NA | 0.01 | NA |
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 | NA | 0.02 | NA | 62 | NA | 0.01 | NA | 0.01 | NA |
__dynamic_cast | libarmpl_mp.so | NA | 0.01 | NA | 0.02 | NA | 64 | NA | 0.01 | NA | 0.01 |
__kmp_get_max_active_levels | libomp.so | NA | 0.01 | NA | 0.02 | NA | 60 | NA | 0.01 | NA | 0.01 |
_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_mp.so | NA | 0.01 | NA | 0.01 | NA | 48 | NA | 0.00 | NA | 0.01 |
daxpy_sve_kernel | libarmpl_mp.so | NA | 0.01 | NA | 0.02 | NA | 58 | NA | 0.01 | NA | 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_mp.so | NA | 0.01 | NA | 0.02 | NA | 63 | NA | 0.01 | NA | 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_mp.so | NA | 0.01 | NA | 0.02 | NA | 57 | NA | 0.00 | NA | 0.01 |
__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_mp.so | NA | 0.01 | NA | 0.01 | NA | 53 | NA | 0.01 | NA | 0.01 |
daxpy_sve_kernel | libarmpl.so | 0.01 | NA | 0.02 | NA | 57 | NA | 0.01 | NA | 0.01 | NA |
_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 | 0.01 | NA | 0.01 | NA | 52 | NA | 0.00 | NA | 0.01 | NA |
__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 | 0.01 | NA | 0.01 | NA | 58 | NA | 0.00 | NA | 0.01 | NA |
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 | NA | 0.01 | NA | 57 | NA | 0.00 | NA | 0.01 | NA |
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_mp.so | NA | 0 | NA | 0 | NA | 17 | NA | 0.00 | NA | 0.00 |
_ZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE32ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_6atomicEKNSG_3dotEKNSG_5axpbyEKNSG_4gemvEEEEDaSD_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 16 | NA | 0.00 | NA | 0.00 |
idamax_kernel | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 34 | NA | 0.00 | NA | 0.00 |
ddot_sve_kernel | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 34 | NA | 0.00 | NA | 0.00 |
lsame_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 28 | NA | 0.00 | NA | 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_clISM_EEbSR_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 13 | NA | 0.00 | NA | 0.00 |
armpl::clag::spec::thread_throttle() | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 20 | NA | 0.00 | NA | 0.00 |
dlaswp_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 25 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 24 | NA | 0.00 | NA | 0.00 |
long armpl_get_system_l1_max_elements<double>() | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 17 | NA | 0.00 | NA | 0.00 |
dgemv_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 22 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 20 | NA | 0.00 | NA | 0.00 |
void BoxMuller2::generate<StdRandom<double, std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul> > >(StdRandom<double, std::m... | exec | NA | 0 | NA | 0 | NA | 26 | NA | 0.00 | NA | 0.00 |
long armpl_get_system_l1_max_elements_generic_sve<double>() | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 17 | NA | 0.00 | NA | 0.00 |
sincos | libm.so.6 | NA | 0 | NA | 0 | NA | 33 | NA | 0.00 | NA | 0.00 |
dscal_sve_kernel | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 16 | NA | 0.00 | NA | 0.00 |
_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_mp.so | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
pthread_cond_signal | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> >::~Vector() | exec | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__nptl_death_event | libc.so.6 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::resize() | exec | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__kmp_now_nsec | libomp.so | 0 | 0 | 0 | 0 | 1 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
__open | libc.so.6 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::BlasThreadingEnv::~BlasThreadingEnv() | exec | 0 | 0 | 0 | 0 | 1 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
.omp_outlined..16 | exec | 0 | 0 | 0 | 0 | 1 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::evaluateGL(qmcplusplus::ParticleSet&) | exec | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
__errno_location | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
@plt_start@ | libamath.so | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmpc_master | libomp.so | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
_dl_rtld_di_serinfo | ld-linux-aarch64.so.1 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::setupTimers() | exec | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
_dl_catch_error | ld-linux-aarch64.so.1 | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
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_mp.so | NA | 0 | NA | 0 | NA | 13 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_2_1_8_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 13 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
__nss_database_lookup | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
void armpl::clag::scal_impl<double, double, armpl::clag::spec::generic_sve_machine_spec>(armpl::clag::spec::problem_context_2T<double, double, (armpl::clag::spec::problem_type)44, armpl::clag::spec::generic_sve_machine_spec> const&) | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
std::chrono::_V2::system_clock::now() | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
dgetrf7sn_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
__kmp_barrier | libomp.so | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 |
dgetrf7xn_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
operator delete(void*) | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 |
armpl::vector_size_bytes() | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 2 | 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_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
qmcplusplus::BlasThreadingEnv::BlasThreadingEnv(int) | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::DiracDeterminantRef(std::unique_ptr<qmcplusplus::SPOSet, std::default_delete<qmcplusplus::SPOSet> >, int, int) | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
qmcplusplus::DistanceTableAA::~DistanceTableAA() | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
__kmpc_barrier | libomp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
psiginfo | libc.so.6 | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_5_2_1_NN | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
dtrsm_ | libarmpl_mp.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 |
__kmp_pop_current_task_from_thread | libomp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
brk | libc.so.6 | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
__kmp_hyper_barrier_gather(barrier_type, kmp_info*, int, int, void (*)(void*, void*), void*) | libomp.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 13 | NA | 0.00 | NA | 0.00 |
dgemm_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 |
qmcplusplus::RealSpacePositions::resize(unsigned long) | exec | NA | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_1_1_1_NN | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 9 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_2_1_6_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 9 | NA | 0.00 | NA | 0.00 |
void geset<double>(double, long, long, double const*, long) | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 8 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_1_1_2_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 8 | NA | 0.00 | NA | 0.00 |
_ZZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE16ENS2_24generic_sve_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_5strat12set_or_scaleEKNSG_5axpbyEKNSG_13outer_productEEEEDaSD_ENKUlRS6_E_clISK_EEbSN_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 7 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_2_1_7_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 9 | NA | 0.00 | NA | 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_clISO_EEbSR_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 11 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_1_1_3_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 10 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 12 | NA | 0.00 | NA | 0.00 |
__kmp_api_omp_get_max_active_levels | libomp.so | NA | 0 | NA | 0 | NA | 10 | NA | 0.00 | NA | 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 | NA | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_2_1_5_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 6 | NA | 0.00 | NA | 0.00 |
__nv_dgetrf_smp__F1L101_1_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 |
void armpl::clag::(anonymous namespace)::axpy_axpby_shim<double, &daxpy_sve_kernel>(long, double, double const*, double, double*, long, long) | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
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_mp.so | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
dtrsm_reference_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
void armpl::clag::scal_impl<double, double, armpl::clag::spec::generic_sve_machine_spec>(int const*, double const*, double*, int const*) | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_1_1_4_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 7 | NA | 0.00 | NA | 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_mp.so | NA | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 |
dger_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 |
__kmpc_global_thread_num | libomp.so | NA | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 |
dgetrf2_ | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 6 | NA | 0.00 | NA | 0.00 |
kernel_sve_dgemm_1_1_1_NT | libarmpl_mp.so | NA | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 |
operator new(unsigned long) | libarmpl.so | 0 | NA | 0 | NA | 1 | 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 | 4 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
dscal_ | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
unknown_function | [vdso] | 0 | 0 | 0 | 0 | 9 | 12 | 0.01 | 0.01 | 0.01 | 0.01 |
__tunable_get_val | ld-linux-aarch64.so.1 | 0 | 0 | 0 | 0 | 14 | 7 | 0.00 | 0.00 | 0.00 | 0.00 |
__fd_log_1 | libamath.so | 0 | 0 | 0 | 0 | 14 | 17 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::ParticleSet::getDistTableAB(int) const | exec | 0 | 0 | 0 | 0 | 13 | 15 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::SPOSet::evaluate_notranspose(qmcplusplus::ParticleSet const&, int, int, qmcplusplus::Matrix<double, std::allocator<double> >&, qmcplusplus::Matrix<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus:... | exec | 0 | 0 | 0 | 0 | 14 | 14 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmp_fork_call | libomp.so | 0 | 0 | 0 | 0 | 15 | 10 | 0.00 | 0.00 | 0.00 | 0.00 |
dscal_sve_kernel | libarmpl.so | 0 | NA | 0 | NA | 11 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::DelayedUpdate<double, double>::updateInvMat(qmcplusplus::Matrix<double, std::allocator<double> >&) | exec | 0 | 0 | 0 | 0 | 20 | 17 | 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 | NA | 0 | NA | 15 | NA | 0.00 | NA | 0.00 | NA |
long armpl_get_system_l1_max_elements<double>() | libarmpl.so | 0 | NA | 0 | NA | 18 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::resize() | exec | 0 | 0 | 0 | 0 | 19 | 18 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::RealSpacePositionsOMPTarget::setOneParticlePos(qmcplusplus::TinyVector<double, 3u> const&, unsigned long) | exec | 0 | 0 | 0 | 0 | 20 | 24 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmp_api_omp_get_ancestor_thread_num | libomp.so | 0 | 0 | 0 | 0 | 12 | 16 | 0.00 | 0.00 | 0.00 | 0.00 |
void geset<double>(double, long, long, double const*, long) | libarmpl.so | 0 | NA | 0 | NA | 9 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_2_1_7_NT | libarmpl.so | 0 | NA | 0 | NA | 9 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::ParticleSet::getDistTableAA(int) const | exec | 0 | 0 | 0 | 0 | 9 | 14 | 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 | NA | 0 | NA | 9 | NA | 0.00 | NA | 0.00 | NA |
__kmp_yield | libomp.so | 0 | 0 | 0 | 0 | 8 | 13 | 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 | NA | 0 | NA | 11 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_1_3_NT | libarmpl.so | 0 | NA | 0 | NA | 10 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&) | exec | 0 | 0 | 0 | 0 | 11 | 12 | 0.00 | 0.00 | 0.00 | 0.00 |
armpl::vector_size_bytes() | libarmpl.so | 0 | NA | 0 | NA | 7 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_2_1_5_NT | libarmpl.so | 0 | NA | 0 | NA | 11 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_1_4_NT | libarmpl.so | 0 | NA | 0 | NA | 11 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_2_1_8_NT | libarmpl.so | 0 | NA | 0 | NA | 8 | NA | 0.00 | NA | 0.00 | NA |
__libc_free | libc.so.6 | 0 | 0 | 0 | 0 | 20 | 29 | 0.00 | 0.00 | 0.00 | 0.00 |
dlaswp_ | libarmpl.so | 0 | NA | 0 | NA | 23 | NA | 0.00 | NA | 0.00 | NA |
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0 | 0 | 0.01 | 0.01 | 38 | 42 | 0.00 | 0.00 | 0.00 | 0.00 |
__clone | libc.so.6 | 0 | 0 | 0.01 | 0.01 | 63 | 64 | 0.00 | 0.00 | 0.00 | 0.00 |
__mprotect | libc.so.6 | 0 | 0 | 0.01 | 0 | 46 | 20 | 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 | 37 | 30 | 0.00 | 0.00 | 0.00 | 0.00 |
lsame_ | libarmpl.so | 0 | NA | 0 | NA | 28 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int) | exec | 0 | 0 | 0.01 | 0.01 | 43 | 41 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::ParticleSet::computeNewPosDistTables(int, qmcplusplus::TinyVector<double, 3u> const&, bool) | exec | 0 | 0 | 0.01 | 0.01 | 45 | 42 | 0.00 | 0.00 | 0.00 | 0.01 |
ddot_sve_kernel | libarmpl.so | 0 | NA | 0.01 | NA | 46 | NA | 0.00 | NA | 0.00 | NA |
_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 | NA | 0 | NA | 8 | NA | 0.00 | NA | 0.00 | NA |
__kmp_get_ancestor_thread_num | libomp.so | 0 | 0 | 0.01 | 0.01 | 45 | 40 | 0.00 | 0.00 | 0.01 | 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 | NA | 0 | NA | 23 | NA | 0.00 | NA | 0.00 | NA |
__mmap | libc.so.6 | 0 | 0 | 0 | 0 | 28 | 23 | 0.00 | 0.00 | 0.00 | 0.00 |
@plt_start@ | libomp.so | 0 | 0 | 0 | 0 | 26 | 26 | 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 | NA | 0 | NA | 24 | NA | 0.00 | NA | 0.00 | NA |
__default_morecore | libc.so.6 | 0 | 0 | 0 | 0 | 22 | 22 | 0.00 | 0.00 | 0.00 | 0.00 |
long armpl_get_system_l1_max_elements_generic_sve<double>() | libarmpl.so | 0 | NA | 0 | NA | 22 | NA | 0.00 | NA | 0.01 | NA |
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 | NA | 0 | NA | 20 | NA | 0.00 | NA | 0.00 | NA |
__strcmp | libastring.so | 0 | 0 | 0 | 0 | 30 | 27 | 0.00 | 0.00 | 0.00 | 0.00 |
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&) | exec | 0 | 0 | 0 | 0 | 23 | 26 | 0.00 | 0.00 | 0.00 | 0.00 |
idamax_kernel | libarmpl.so | 0 | NA | 0 | NA | 30 | NA | 0.00 | NA | 0.00 | NA |
__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 | NA | 0 | NA | 19 | NA | 0.00 | NA | 0.01 | NA |
dgemv_ | libarmpl.so | 0 | NA | 0 | NA | 27 | NA | 0.00 | NA | 0.00 | NA |
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 | NA | 0 | NA | 23 | NA | 0.00 | NA | 0.00 | NA |
dgetrf7sn_ | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__kmpc_fork_call | libomp.so | 0 | 0 | 0 | 0 | 8 | 5 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmpc_end_serialized_parallel | libomp.so | 0 | 0 | 0 | 0 | 7 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
dgemm_ | libarmpl.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
dger_ | libarmpl.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
dgetrf_smp_ | libarmpl.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
__kmp_invoke_microtask | libomp.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::RealSpacePositionsOMPTarget::getAllParticlePos() const | 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 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul>::operator()() | exec | 0 | 0 | 0 | 0 | 3 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
___kmp_free | libomp.so | 0 | 0 | 0 | 0 | 3 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmpc_bound_num_threads | libomp.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, ... | exec | 0 | 0 | 0 | 0 | 3 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
timer_settime | libc.so.6 | 0 | 0 | 0 | 0 | 3 | 6 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::RealSpacePositionsOMPTarget::setAllParticlePos(qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > > const&) | exec | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
__lll_lock_wake_private | libc.so.6 | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
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 | 1 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_6_4_NN | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
void armpl::clag::(anonymous namespace)::axpy_axpby_shim<double, &daxpy_sve_kernel>(long, double, double const*, double, double*, long, long) | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
ilaenvkernel_generic_sve_ | libarmpl.so | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::RealSpacePositions::setAllParticlePos(qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > > const&) | exec | 0 | 0 | 0 | 0 | 2 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
__memmove | libastring.so | 0 | 0 | 0 | 0 | 2 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::ParticleSet::rejectMove(int) | exec | 0 | 0 | 0 | 0 | 2 | 4 | 0.00 | 0.00 | 0.00 | 0.00 |
qmcplusplus::WaveFunction::restore(int) | exec | 0 | 0 | 0 | 0 | 2 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
__lll_lock_wait_private | libc.so.6 | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
__kmp_join_call | libomp.so | 0 | 0 | 0 | 0 | 2 | 7 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_2_1_6_NT | libarmpl.so | 0 | NA | 0 | NA | 7 | NA | 0.00 | NA | 0.00 | NA |
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 |
__kmp_api_omp_get_num_threads | libomp.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::TimerManager<qmcplusplus::TimerType<std::chrono::_V2::system_clock> >::push_timer(qmcplusplus::TimerType<std::chrono::_V2::system_clock>*) | exec | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 | NA |
__madvise | libc.so.6 | 0 | 0 | 0 | 0 | 5 | 36 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmp_push_current_task_to_thread | libomp.so | 0 | 0 | 0 | 0 | 5 | 4 | 0.00 | 0.00 | 0.00 | 0.00 |
dtrsm_reference_ | libarmpl.so | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_1_1_NN | libarmpl.so | 0 | NA | 0 | NA | 4 | NA | 0.00 | NA | 0.00 | NA |
kernel_sve_dgemm_1_1_1_NT | libarmpl.so | 0 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 | NA |
__kmp_serialized_parallel | libomp.so | 0 | 0 | 0 | 0 | 6 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmp_resume_if_soft_paused | libomp.so | 0 | 0 | 0 | 0 | 6 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
kernel_sve_dgemm_1_1_2_NT | libarmpl.so | 0 | NA | 0 | NA | 6 | NA | 0.00 | NA | 0.00 | NA |
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 | NA | 0 | NA | 5 | NA | 0.00 | NA | 0.00 | NA |
__clock_gettime | libc.so.6 | 0 | 0 | 0 | 0 | 1 | 1 | 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> > > >::_M_default_append(u... | exec | 0 | 0 | 0 | 0 | 4 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmpc_serialized_parallel | libomp.so | 0 | 0 | 0 | 0 | 4 | 1 | 0.00 | 0.00 | 0.00 | 0.00 |
idamax_ | libarmpl.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
void armpl::clag::(anonymous namespace)::gemv_shim<false, double, &dgemv_n_sve_kernel>(long, long, double, double const*, long, long, double const*, long, double, double*, long) | libarmpl.so | 0 | NA | 0 | NA | 2 | NA | 0.00 | NA | 0.00 | NA |
dgetrf2_ | libarmpl.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
__math_invalid | libamath.so | 0 | 0 | 0 | 0 | 3 | 9 | 0.00 | 0.00 | 0.00 | 0.00 |
__kmp_serial_fork_call(ident*, int, fork_context_e, int, void (*)(int*, int*, ...), int (*)(int), kmp_info*, kmp_team*, ompt_data_t*, void**, ompt_data_t**, std::__va_list*) | libomp.so | 0 | 0 | 0 | 0 | 3 | 5 | 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::(anonymous namespace)::trsm_kernel_exec<double> >::operator()<armpl::clag::(anonymous ... | libarmpl.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
dtrsv_reference_ | libarmpl.so | 0 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
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 | NA | 0 | NA | 3 | NA | 0.00 | NA | 0.00 | NA |
qmcplusplus::WaveFunction::evaluateLog(qmcplusplus::ParticleSet&) | exec | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |
___kmp_allocate | libomp.so | 0 | 0 | 0 | 0 | 4 | 3 | 0.00 | 0.00 | 0.00 | 0.00 |
__bcmp | libastring.so | NA | 0 | NA | 0 | NA | 1 | NA | 0.00 | NA | 0.00 |