OV - Compare Functions

Functions

Name	Module	Coverage (%)	Time (s)	Nb Threads	Deviation (coverage)	Deviation (time)
Name	Module	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	23.63	23.55	75.12	75.09	80	80	0.19	0.21	0.66	0.72
dgemm_vanilla_big_no_prefetch	libarmpl_mp.so	NA	27.4	NA	87.36	NA	80	NA	0.19	NA	0.64
dgemm_vanilla_big_no_prefetch	libarmpl.so	27.28	NA	86.74	NA	80	NA	0.17	NA	0.58	NA
void miniqmcreference::MultiBsplineEvalRef::evaluate_vgh<double>(qmcplusplus::bspline_traits<double, 3u>::SplineType const, double, double, double, double, double, double, unsigned long)	exec	11.01	11.05	35	35.24	80	80	0.14	0.12	0.42	0.37
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::update(int)	exec	5.85	5.82	18.6	18.57	80	80	0.11	0.09	0.33	0.29
n_interleave_kernel_d6	libarmpl.so	10.24	NA	32.54	NA	80	NA	0.12	NA	0.36	NA
n_interleave_kernel_d6	libarmpl_mp.so	NA	10.18	NA	32.46	NA	80	NA	0.10	NA	0.34
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)	exec	3.24	3.23	10.3	10.3	80	80	0.07	0.07	0.22	0.22
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	2.44	2.44	7.77	7.77	80	80	0.08	0.08	0.24	0.26
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)	exec	1.64	1.62	5.2	5.17	80	80	0.08	0.08	0.25	0.24
dgemv_t_neon_kernel_serial	libarmpl.so	3.18	NA	10.1	NA	80	NA	0.06	NA	0.20	NA
dgemv_t_neon_kernel_serial	libarmpl_mp.so	NA	3.16	NA	10.09	NA	80	NA	0.07	NA	0.21
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)	exec	1.19	1.19	3.8	3.8	80	80	0.04	0.04	0.12	0.14
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)	exec	1.08	1.07	3.43	3.4	80	80	0.04	0.04	0.14	0.13
__memcpy	libastring_aarch64.so	1.04	1.03	3.3	3.28	80	80	0.05	0.05	0.16	0.15
dgemv_n_neon_kernel	libarmpl.so	1.78	NA	5.66	NA	80	NA	0.06	NA	0.18	NA
dgemv_n_neon_kernel	libarmpl_mp.so	NA	1.77	NA	5.64	NA	80	NA	0.06	NA	0.18
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	0.84	0.85	2.66	2.7	80	80	0.03	0.04	0.10	0.12
qmcplusplus::BsplineFunctor<double>::evaluateVGL(int, int, int, double const, double, double, double, double, int) const [clone .109] [clone .extracted]	exec	0.75	0.74	2.37	2.36	80	80	0.04	0.03	0.13	0.10
__memset	libastring_aarch64.so	0.65	0.65	2.06	2.09	80	80	0.04	0.04	0.12	0.12
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateGL(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<...	exec	0.62	0.63	1.98	2.01	80	80	0.03	0.02	0.08	0.07
qmcplusplus::SPOSet::evaluateDetRatios(qmcplusplus::VirtualParticleSet const&, qmcplusplus::Vector<double, std::allocator<double> >&, qmcplusplus::Vector<double, std::allocator<double> > const&, std::vector<double, st...	exec	0.53	0.53	1.68	1.68	80	80	0.03	0.03	0.10	0.09
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evalGrad(qmcplusplus::ParticleSet&, int)	exec	0.5	0.49	1.58	1.58	80	80	0.03	0.03	0.08	0.09
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libomp_with_lse.so	0.38	0.35	1.22	1.11	80	80	0.10	0.10	0.31	0.33
t_interleave_kernel_d8	libarmpl_mp.so	NA	0.41	NA	1.32	NA	80	NA	0.02	NA	0.08
t_interleave_kernel_d8	libarmpl.so	0.39	NA	1.24	NA	80	NA	0.02	NA	0.08	NA
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)	exec	0.18	0.19	0.56	0.59	80	80	0.03	0.03	0.08	0.09
qmcplusplus::DiracMatrix<double, double>::invert_transpose(qmcplusplus::Matrix<double, std::allocator<double> > const&, qmcplusplus::Matrix<double, std::allocator<double> >&, double&, double&)	exec	0.13	0.13	0.42	0.4	80	80	0.03	0.01	0.08	0.04
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)	exec	0.1	0.1	0.31	0.32	80	80	0.01	0.01	0.04	0.04
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::evaluateLog(qmcplusplus::ParticleSet&, qmcplusplus::ParticleAttrib<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector&l...	exec	0.07	0.08	0.22	0.26	80	80	0.00	0.01	0.01	0.02
dgeset	libarmpl.so	0.13	NA	0.42	NA	80	NA	0.01	NA	0.04	NA
dgeset	libarmpl_mp.so	NA	0.13	NA	0.4	NA	80	NA	0.02	NA	0.05
qmcplusplus::NonLocalPP<double>::evaluate(qmcplusplus::ParticleSet const&, qmcplusplus::WaveFunction&)	exec	0.06	0.06	0.19	0.2	80	80	0.01	0.01	0.03	0.04
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&)	exec	0.05	0.06	0.17	0.19	80	80	0.01	0.02	0.04	0.05
dgetrf7vn_	libarmpl.so	0.1	NA	0.3	NA	80	NA	0.01	NA	0.02	NA
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)	exec	0.05	0.05	0.15	0.17	80	80	0.01	0.01	0.02	0.02
n_interleave_kernel_d8	libarmpl_mp.so	NA	0.1	NA	0.32	NA	80	NA	0.01	NA	0.04
dgetrf7vn_	libarmpl_mp.so	NA	0.1	NA	0.33	NA	80	NA	0.01	NA	0.04
n_interleave_kernel_d8	libarmpl.so	0.1	NA	0.32	NA	80	NA	0.01	NA	0.04	NA
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::start()	exec	0.04	0.04	0.12	0.11	80	80	0.01	0.01	0.02	0.03
qmcplusplus::Vector<double, std::allocator<double> >::resize(unsigned long, double)	exec	0.03	0.04	0.1	0.13	80	80	0.01	0.01	0.02	0.02
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	0.06	NA	0.19	NA	80	NA	0.01	NA	0.04
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcplusplus::ParticleSet&, int, double const*)	exec	0.03	0.03	0.1	0.1	80	80	0.01	0.01	0.02	0.02
__kmp_api_omp_get_level	libomp_with_lse.so	0.03	0.03	0.09	0.08	80	80	0.01	0.01	0.03	0.02
miniqmcreference::einspline_spo_ref<double>::evaluate_v(qmcplusplus::ParticleSet const&, int)	exec	0.03	0.03	0.08	0.09	80	80	0.01	0.01	0.02	0.02
void armpl::clag::(anonymous namespace)::trsm_kernel<double, true, true, true, false, false>(double const, long, long, double, long, long, long, long)	libarmpl.so	0.05	NA	0.15	NA	80	NA	0.01	NA	0.03	NA
qmcplusplus::WaveFunction::evalGrad(qmcplusplus::ParticleSet&, int)	exec	0.02	0.02	0.07	0.07	80	80	0.01	0.01	0.02	0.02
qmcplusplus::TimerType<std::chrono::_V2::system_clock>::stop()	exec	0.02	0.02	0.06	0.06	80	80	0.02	0.03	0.08	0.09
.omp_outlined..64	exec	0.02	0.02	0.07	0.07	80	80	0.01	0.01	0.02	0.02
qmcplusplus::WaveFunction::ratioGrad(qmcplusplus::ParticleSet&, int, qmcplusplus::TinyVector<double, 3u>&)	exec	0.02	0.02	0.06	0.06	80	80	0.01	0.01	0.02	0.02
__kmp_get_global_thread_id_reg	libomp_with_lse.so	0.02	0.02	0.07	0.06	80	80	0.01	0.01	0.02	0.02
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool)	exec	0.02	0.02	0.05	0.05	80	80	0.01	0.00	0.02	0.01
unknown_function	exec	0.02	0.02	0.05	0.05	80	80	0.01	0.00	0.02	0.01
@plt_start@	libarmpl_mp.so	NA	0.03	NA	0.11	NA	80	NA	0.01	NA	0.03
@plt_start@	libarmpl.so	0.03	NA	0.1	NA	80	NA	0.01	NA	0.02	NA
miniqmcreference::einspline_spo_ref<double>::evaluate_vgh(qmcplusplus::ParticleSet const&, int)	exec	0.01	0.02	0.04	0.05	80	80	0.01	0.00	0.02	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	0.03	NA	0.08	NA	80	NA	0.01	NA	0.02
qmcplusplus::ParticleSet::acceptMove(int)	exec	0.02	0.01	0.05	0.05	80	80	0.01	0.00	0.02	0.01
__strcmp	libastring_aarch64.so	0.01	0.01	0.02	0.02	78	78	0.00	0.00	0.01	0.01
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int)	exec	0.01	0.01	0.02	0.02	79	77	0.00	0.00	0.01	0.01
miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::evalGrad(qmcplusplus::ParticleSet&, int)	exec	0.01	0.01	0.02	0.02	80	80	0.00	0.00	0.01	0.01
qmcplusplus::ParticleSet::update(bool)	exec	0.01	0.01	0.02	0.02	77	80	0.00	0.00	0.01	0.01
__dynamic_cast	libarmpl_mp.so	NA	0.02	NA	0.06	NA	80	NA	0.01	NA	0.02
qmcplusplus::Vector<qmcplusplus::TinyVector<double, 3u>, std::allocator<qmcplusplus::TinyVector<double, 3u> > >::resize(unsigned long, qmcplusplus::TinyVector<double, 3u>)	exec	0.01	0.01	0.02	0.02	80	80	0.00	0.00	0.01	0.01
qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int)	exec	0.01	0.01	0.02	0.02	77	76	0.00	0.00	0.01	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	0.02	NA	0.06	NA	80	NA	0.01	NA	0.02
void armpl::clag::blas3_gemv::operator()<double, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_machine_spec> const&) const	libarmpl_mp.so	NA	0.02	NA	0.08	NA	80	NA	0.01	NA	0.02
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::acceptMove(qmcplusplus::ParticleSet&, int)	exec	0.01	0.01	0.02	0.02	79	79	0.00	0.00	0.01	0.01
qmcplusplus::ParticleSet::computeNewPosDistTables(int, qmcplusplus::TinyVector<double, 3u> const&, bool)	exec	0.01	0.01	0.02	0.02	80	80	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	0.04	0.04	80	80	0.00	0.00	0.01	0.01
qmcplusplus::WaveFunction::evaluateRatios(qmcplusplus::VirtualParticleSet&, std::vector<double, std::allocator<double> >&)	exec	0.01	0.01	0.04	0.04	80	80	0.00	0.00	0.01	0.02
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::move(qmcplusplus::ParticleSet const&, qmcplusplus::TinyVector<double, 3u> const&, int, bool)	exec	0.01	0.01	0.05	0.05	80	80	0.00	0.00	0.01	0.02
__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	0.02	NA	0.05	NA	80	NA	0.01	NA	0.02	NA
void armpl::clag::blas3_gemv::operator()<double, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_machine_spec> const&) const	libarmpl.so	0.02	NA	0.06	NA	80	NA	0.01	NA	0.02	NA
__exp_finite	libamath_neoverse-n1.so	0.01	0.01	0.04	0.04	80	80	0.00	0.00	0.01	0.02
miniqmcreference::einspline_spo_ref<double>::evaluate(qmcplusplus::ParticleSet const&, int, qmcplusplus::Vector<double, std::allocator<double> >&)	exec	0.01	0.01	0.04	0.04	80	80	0.00	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	0.04	0.03	80	80	0.00	0.00	0.01	0.01
qmcplusplus::ParticleSet::makeMove(int, qmcplusplus::TinyVector<double, 3u> const&, bool)	exec	0.01	0.01	0.03	0.03	79	79	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.so	0.02	NA	0.07	NA	80	NA	0.01	NA	0.02	NA
__dynamic_cast	libarmpl.so	0.02	NA	0.05	NA	80	NA	0.00	NA	0.02	NA
__kmp_get_ancestor_thread_num	libomp_with_lse.so	0.01	0.01	0.03	0.02	80	78	0.00	0.00	0.01	0.01
__GI___sched_yield	libc-2.28.so	0.01	0.01	0.03	0.02	80	78	0.00	0.00	0.01	0.01
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::recompute(qmcplusplus::ParticleSet&)	exec	0.01	0.01	0.03	0.03	80	80	0.00	0.00	0.01	0.01
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::update(int)	exec	0.01	0.01	0.03	0.03	80	79	0.00	0.00	0.01	0.02
unknown_function	Unknown module	0.01	0.01	0.02	0.03	80	81	0.89	1.01	0.01	0.01
bool armpl::dispatch_atomic_neon<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	0.04	NA	80	NA	0.00	NA	0.01	NA
daxpy_kernel	libarmpl_mp.so	NA	0.01	NA	0.04	NA	79	NA	0.01	NA	0.03
dlaswp_	libarmpl.so	0.01	NA	0.04	NA	80	NA	0.00	NA	0.01	NA
ddot_kernel	libarmpl_mp.so	NA	0.01	NA	0.02	NA	79	NA	0.00	NA	0.01
dlaswp_	libarmpl_mp.so	NA	0.01	NA	0.04	NA	80	NA	0.00	NA	0.01
daxpy_kernel	libarmpl.so	0.01	NA	0.04	NA	80	NA	0.01	NA	0.03	NA
void armpl::clag::gemv<true, int, double, double, double, double, armpl::clag::spec::neoverse_n1_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	0.01	NA	0.02	NA	79	NA	0.00	NA	0.01
void armpl::clag::gemm<true, int, double, double, double, armpl::clag::spec::neoverse_n1_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	0.01	NA	0.02	NA	79	NA	0.00	NA	0.01	NA
lsame_	libarmpl_mp.so	NA	0.01	NA	0.02	NA	76	NA	0.00	NA	0.01
void armpl::clag::ger<true, int, false, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, int const, double const, double const, int const, double const, int const, double, int const*)	libarmpl_mp.so	NA	0.01	NA	0.02	NA	79	NA	0.00	NA	0.01
bool armpl::dispatch_atomic_neon<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	0.03	NA	80	NA	0.00	NA	0.01
void armpl::clag::gemv<true, int, double, double, double, double, armpl::clag::spec::neoverse_n1_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	0.01	NA	0.02	NA	78	NA	0.00	NA	0.01	NA
lsame_	libarmpl.so	0.01	NA	0.02	NA	78	NA	0.00	NA	0.01	NA
void armpl::clag::(anonymous namespace)::outer_product_terminal<void ()(long, double, double const, double, double*, long, long)>::operator()<armpl::clag::general_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> >...	libarmpl_mp.so	NA	0.01	NA	0.02	NA	76	NA	0.00	NA	0.01
ddot_kernel	libarmpl.so	0.01	NA	0.02	NA	80	NA	0.00	NA	0.01	NA
void geset<double>(double, long, long, double const*, long)	libarmpl_mp.so	NA	0	NA	0	NA	42	NA	0.00	NA	0.00
void armpl::clag::gemm<true, int, double, double, double, armpl::clag::spec::neoverse_n1_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	36	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::axpy_axpby_shim<double, &daxpy_kernel>(long, double, double const, double, double, long, long)	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
dscal_kernel	libarmpl_mp.so	NA	0	NA	0	NA	30	NA	0.00	NA	0.00
idamax_kernel	libarmpl_mp.so	NA	0	NA	0	NA	37	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::c_copy<double, armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)> >::operator()<armpl::clag::(anonymous namespace)...	libarmpl_mp.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
dger_	libarmpl_mp.so	NA	0	NA	0.01	NA	72	NA	0.00	NA	0.01
__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	0.01	NA	69	NA	0.00	NA	0.01
bool armpl::clag::gemm_atomic::use<armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_machine_spec> >(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29,...	libarmpl_mp.so	NA	0	NA	0	NA	42	NA	0.00	NA	0.00
dgemv_	libarmpl_mp.so	NA	0	NA	0.01	NA	64	NA	0.00	NA	0.01
_ZSt13__invoke_implIvZN5armpl4clag4gemmIdLNS1_4spec12problem_typeE29ENS3_24neoverse_n1_machine_specEEEvRKNS3_15problem_contextIT_XT0_ET1_EEEUlDpRT_E_JRKNS1_18blas3_set_or_scaleERKNS1_11gemm_atomicERKNS1_9blas1_dotERKNS1_11blas1_axpbyERKNS1_10blas3_gemvEEES...	libarmpl_mp.so	NA	0	NA	0.01	NA	64	NA	0.00	NA	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_mp.so	NA	0	NA	0.01	NA	63	NA	0.00	NA	0.01
void armpl::clag::(anonymous namespace)::neon_interleave::operator()<double const, double>(armpl::clag::general_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> > const&, armpl::clag::(anonymous namespace)::interle...	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
__kmp_api_omp_get_thread_num	libomp_with_lse.so	NA	0	NA	0.02	NA	74	NA	0.00	NA	0.01
__kmp_get_max_active_levels	libomp_with_lse.so	NA	0	NA	0	NA	24	NA	0.00	NA	0.00
@plt_start@	mca_pmix_pmix3x.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
std::vector<qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> >, std::allocator<qmcplusplus::Vector<double, qmcplusplus::Mallocator<double, 32ul> > > >::_M_default_append(unsigned long) [clone .47] [clone...	exec	0	0	0	0	1	2	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	1	1	0.00	0.00	0.00	0.00
qmcplusplus::TimerManager<qmcplusplus::TimerType<std::chrono::_V2::system_clock> >::initializeTimer(qmcplusplus::TimerType<std::chrono::_V2::system_clock>&)	exec	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
__kmp_api_omp_get_num_threads	libomp_with_lse.so	0	0	0	0	1	3	0.00	0.00	0.00	0.00
__GI___fxstat	libc-2.28.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
qmcplusplus::BlasThreadingEnv::BlasThreadingEnv(int)	exec	0	0	0	0	1	1	0.00	0.00	0.00	0.00
__math_divzero	libamath_neoverse-n1.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
_ZSt13__invoke_implIvZN5armpl4clag4gemmIdLNS1_4spec12problem_typeE0ENS3_24neoverse_n1_machine_specEEEvRKNS3_15problem_contextIT_XT0_ET1_EEEUlDpRT_E_JRKNS1_18blas3_set_or_scaleERKNS1_11gemm_atomicERKNS1_9blas1_dotERKNS1_11blas1_axpbyERKNS1_10blas3_gemvERKNS...	libarmpl_mp.so	NA	0	NA	0	NA	8	NA	0.00	NA	0.00
std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, int, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::...	exec	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
__aarch64_swp4_acq	libpthread-2.28.so	0	0	0	0	1	1	0.00	0.00	0.00	0.00
__GI_strncmp	libc-2.28.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
@plt_start@	libopen-pal.so.40.30.2	0	0	0	0	1	1	0.00	0.00	0.00	0.00
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::DiracDeterminantRef(std::unique_ptr<qmcplusplus::SPOSet, std::default_delete<qmcplusplus::SPOSet> >, int, int)	exec	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
ucs_async_handler_dispatch	libucs.so.0.0.0	0	0	0	0	1	1	0.00	0.00	0.00	0.00
__GI___pthread_rwlock_rdlock	libpthread-2.28.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
do_lookup_x	ld-2.28.so	0	0	0	0	1	1	0.00	0.00	0.00	0.00
__aarch64_cas4_acq	libpthread-2.28.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)>::operator()<armpl::clag::(anonymous namespace)::interleaved_matrix<double>, armpl::clag::(anonymous...	libarmpl_mp.so	NA	0	NA	0	NA	27	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>::operator()<armpl::clag::(anonymous namespace)::triangular_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> >, armpl::c...	libarmpl_mp.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
kernel_dgemm_6_1_6_NT	libarmpl_mp.so	NA	0	NA	0	NA	21	NA	0.00	NA	0.00
bool std::has_facet<std::ctype<char> >(std::locale const&)	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
void armpl::clag::scal_impl<double, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, double const, double, int const)	libarmpl_mp.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
__nv_dgetrf_nag__F1L101_1_	libarmpl_mp.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
with_errno	libamath_neoverse-n1.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::SoaDistanceTableABOMPTarget<double, 3u, 40>::~SoaDistanceTableABOMPTarget()	exec	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
opal_mem_hooks_release_hook	libopen-pal.so.40.30.2	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
void armpl::clag::gemm_basic::operator()<double, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)0, armpl::clag::spec::neoverse_n1_machine_spec> const&) const	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)>::operator()<armpl::clag::(anonymous namespace)::interleaved_matrix<double>, armpl::clag::(anonymous...	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
qmcplusplus::DistanceTableAB::~DistanceTableAB()	exec	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::(anonymous namespace)::trsm_kernel_exec<double> >::operator()<armpl::clag::(anonymous ...	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
dgetrf7xn_	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
qmcplusplus::createDynamicCoordinates(qmcplusplus::DynamicCoordinateKind)	exec	NA	0	NA	0	NA	1	NA	0.00	NA	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	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
__wait_lookup_done	libpthread-2.28.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
PrimeNumberSet<unsigned int>::PrimeNumberSet()	exec	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
strcmp	ld-2.28.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
.text@start	libmlx5.so.1.24.44.0	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
__kmp_fork_barrier(int, int)	libomp_with_lse.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
ucs_async_thread_func	libucs.so.0.0.0	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
frexpf128	libm-2.28.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
miniqmcreference::DiracDeterminantRef<qmcplusplus::DelayedUpdate<double, double> >::resize(int, int)	exec	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
_dl_fixup	ld-2.28.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
__aarch64_swp4_rel	libpthread-2.28.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
qmcplusplus::BsplineFunctor<double>::setupParameters(int, double, double, std::vector<double, std::allocator<double> >&)	exec	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::gemv_shim<true, double, &dgemv_t_neon_kernel_serial>(long, long, double, double const, long, long, double const, long, double, double*, long)	libarmpl_mp.so	NA	0	NA	0	NA	23	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
void armpl::clag::blas1_axpby::operator()<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_mach...	libarmpl_mp.so	NA	0	NA	0	NA	2	NA	0.00	NA	0.00
bool armpl::clag::gemm_atomic::use<armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)0, armpl::clag::spec::neoverse_n1_machine_spec> >(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)0, a...	libarmpl_mp.so	NA	0	NA	0	NA	9	NA	0.00	NA	0.00
kernel_dgemm_2_1_2_NT	libarmpl_mp.so	NA	0	NA	0	NA	9	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::gemv_shim<false, double, &dgemv_n_neon_kernel>(long, long, double, double const, long, long, double const, long, double, double*, long)	libarmpl_mp.so	NA	0	NA	0	NA	8	NA	0.00	NA	0.00
kernel_dgemm_3_1_3_NT	libarmpl_mp.so	NA	0	NA	0	NA	6	NA	0.00	NA	0.00
dtrsm_reference_	libarmpl_mp.so	NA	0	NA	0	NA	7	NA	0.00	NA	0.00
dgetrf2_	libarmpl_mp.so	NA	0	NA	0	NA	7	NA	0.00	NA	0.00
kernel_dgemm_1_1_1_NT	libarmpl_mp.so	NA	0	NA	0	NA	9	NA	0.00	NA	0.00
void armpl::clag::blas1_axpby::operator()<double, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)46, armpl::clag::spec::neoverse_n1_machine_spec> const&) const	libarmpl_mp.so	NA	0	NA	0	NA	13	NA	0.00	NA	0.00
kernel_dgemm_5_1_5_NT	libarmpl_mp.so	NA	0	NA	0	NA	19	NA	0.00	NA	0.00
void armpl::clag::(anonymous namespace)::axpby_fallback<false, double, double, double>(long, double, double const, double, double, long, long)	libarmpl_mp.so	NA	0	NA	0	NA	14	NA	0.00	NA	0.00
operator delete(void*)	libarmpl_mp.so	NA	0	NA	0	NA	16	NA	0.00	NA	0.00
kernel_dgemm_4_1_4_NT	libarmpl_mp.so	NA	0	NA	0	NA	15	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	2	NA	0.00	NA	0.00
dgemm_	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::neoverse_n1_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	6	NA	0.00	NA	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	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
void armpl::clag::gerb<true, int, false, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, int const, double const, double const, int const, double const, int const, double const, double, int const)	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
__kmp_barrier	libomp_with_lse.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
.omp_outlined..16	exec	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
armpl::clag::use_overrides()	libarmpl_mp.so	NA	0	NA	0	NA	6	NA	0.00	NA	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
__kmp_api_omp_get_max_active_levels	libomp_with_lse.so	NA	0	NA	0	NA	6	NA	0.00	NA	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
dtrsv_reference_	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
kernel_dgemm_1_1_1_NN	libarmpl_mp.so	NA	0	NA	0	NA	3	NA	0.00	NA	0.00
void armpl::clag::scal_impl<double, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, double const, double, int const)	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
__kmpc_bound_num_threads	libomp_with_lse.so	0	0	0	0	4	2	0.00	0.00	0.00	0.00
dscal_	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
dscal_kernel	libarmpl.so	0	NA	0	NA	19	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	16	20	0.00	0.00	0.00	0.00
__kmp_now_nsec	libomp_with_lse.so	0	0	0	0	16	19	0.00	0.00	0.00	0.00
__kmp_serialized_parallel	libomp_with_lse.so	0	0	0	0	14	30	0.00	0.00	0.00	0.00
kernel_dgemm_4_1_4_NT	libarmpl.so	0	NA	0	NA	16	NA	0.00	NA	0.00	NA
qmcplusplus::WaveFunction::restore(int)	exec	0	0	0	0	13	7	0.00	0.00	0.00	0.00
qmcplusplus::ParticleSet::rejectMove(int)	exec	0	0	0	0	19	20	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	17	30	0.00	0.00	0.00	0.00
void geset<double>(double, long, long, double const*, long)	libarmpl.so	0	NA	0	NA	23	NA	0.00	NA	0.00	NA
__math_invalid	libamath_neoverse-n1.so	0	0	0	0	18	7	0.00	0.00	0.00	0.00
void armpl::clag::(anonymous namespace)::axpby_fallback<false, double, double, double>(long, double, double const, double, double, long, long)	libarmpl.so	0	NA	0	NA	26	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::gemv_shim<true, double, &dgemv_t_neon_kernel_serial>(long, long, double, double const, long, long, double const, long, double, double*, long)	libarmpl.so	0	NA	0	NA	19	NA	0.00	NA	0.00	NA
__kmp_api_omp_get_ancestor_thread_num	libomp_with_lse.so	0	0	0	0	32	41	0.00	0.00	0.00	0.00
kernel_dgemm_5_1_5_NT	libarmpl.so	0	NA	0	NA	12	NA	0.00	NA	0.00	NA
__divtf3	libgcc_s.so.1	0	0	0	0	14	10	0.00	0.00	0.00	0.00
__logl_finite	libm-2.28.so	0	0	0	0	10	14	0.00	0.00	0.00	0.00
.omp_outlined..11	exec	0	0	0	0	10	9	0.00	0.00	0.00	0.00
__kmpc_fork_call	libomp_with_lse.so	0	0	0	0	9	11	0.00	0.00	0.00	0.00
kernel_dgemm_1_1_1_NN	libarmpl.so	0	NA	0	NA	7	NA	0.00	NA	0.00	NA
sincos	libm-2.28.so	0	0	0	0	12	6	0.00	0.00	0.00	0.00
kernel_dgemm_2_1_2_NT	libarmpl.so	0	NA	0	NA	10	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>::operator()<armpl::clag::(anonymous namespace)::triangular_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> >, armpl::c...	libarmpl.so	0	NA	0	NA	9	NA	0.00	NA	0.00	NA
kernel_dgemm_6_1_6_NT	libarmpl.so	0	NA	0	NA	12	NA	0.00	NA	0.00	NA
kernel_dgemm_3_1_3_NT	libarmpl.so	0	NA	0	NA	8	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)>::operator()<armpl::clag::(anonymous namespace)::interleaved_matrix<double>, armpl::clag::(anonymous...	libarmpl.so	0	NA	0	NA	11	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	12	11	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
qmcplusplus::SoaDistanceTableAAOMPTarget<double, 3u, 40>::evaluate(qmcplusplus::ParticleSet&)	exec	0	0	0	0	34	29	0.00	0.00	0.00	0.00
qmcplusplus::ParticleSet::getDistTableAA(int) const	exec	0	0	0	0	31	19	0.00	0.00	0.00	0.00
dgemv_	libarmpl.so	0	NA	0.01	NA	66	NA	0.00	NA	0.01	NA
qmcplusplus::ParticleSet::getDistTableAB(int) const	exec	0	0	0.01	0.01	67	57	0.00	0.00	0.01	0.01
__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	0.01	NA	67	NA	0.00	NA	0.01	NA
dger_	libarmpl.so	0	NA	0.01	NA	70	NA	0.00	NA	0.01	NA
void armpl::clag::(anonymous namespace)::neon_interleave::operator()<double const, double>(armpl::clag::general_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> > const&, armpl::clag::(anonymous namespace)::interle...	libarmpl.so	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
__fd_log_1	libamath_neoverse-n1.so	0	0	0.01	0.01	65	57	0.00	0.00	0.01	0.01
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	0.01	0.01	67	67	0.00	0.00	0.01	0.01
void armpl::clag::(anonymous namespace)::outer_product_terminal<void ()(long, double, double const, double, double*, long, long)>::operator()<armpl::clag::general_matrix<armpl::clag::(anonymous namespace)::matrix_base<double const> >...	libarmpl.so	0	NA	0.01	NA	73	NA	0.00	NA	0.01	NA
qmcplusplus::Vector<double, qmcplusplus::OMPallocator<double, qmcplusplus::Mallocator<double, 32ul> > >::resize(unsigned long, double)	exec	0	0	0.02	0.01	74	76	0.00	0.00	0.01	0.01
miniqmcreference::OneBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::acceptMove(qmcplusplus::ParticleSet&, int)	exec	0	0	0.01	0.01	71	68	0.00	0.00	0.01	0.01
void armpl::clag::ger<true, int, false, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, int const, double const, double const, int const, double const, int const, double, int const*)	libarmpl.so	0	NA	0.02	NA	77	NA	0.00	NA	0.01	NA
f64xsubf128	libm-2.28.so	0	0	0.01	0.01	80	80	0.00	0.00	0.00	0.00
__kmp_fork_call	libomp_with_lse.so	0	0	0	0	32	23	0.00	0.00	0.00	0.00
_ZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE29ENS2_24neoverse_n1_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_18blas3_set_or_scaleEKNS0_11gemm_atomicEKNS0_9blas1_dotEKNS0_11blas1_axpbyEKNS0_10blas3_gemvEEEEDaSD_	libarmpl.so	0	NA	0.01	NA	62	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.so	0	NA	0.01	NA	57	NA	0.00	NA	0.01	NA
__kmp_yield	libomp_with_lse.so	0	0	0	0	39	28	0.00	0.00	0.00	0.00
@plt_start@	libomp_with_lse.so	0	0	0	0	37	39	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	34	39	0.00	0.00	0.00	0.00
idamax_kernel	libarmpl.so	0	NA	0	NA	36	NA	0.00	NA	0.00	NA
unknown_function	[vdso]	0	0	0.01	0.01	52	50	0.01	0.00	0.02	0.01
qmcplusplus::DelayedUpdate<double, double>::updateInvMat(qmcplusplus::Matrix<double, std::allocator<double> >&)	exec	0	0	0	0	41	43	0.00	0.00	0.00	0.00
void armpl::clag::(anonymous namespace)::c_copy<double, armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)> >::operator()<armpl::clag::(anonymous namespace)...	libarmpl.so	0	NA	0	NA	52	NA	0.00	NA	0.00	NA
qmcplusplus::RealSpacePositionsOMPTarget::setOneParticlePos(qmcplusplus::TinyVector<double, 3u> const&, unsigned long)	exec	0	0	0.01	0.01	57	52	0.00	0.00	0.00	0.00
_dl_tlsdesc_return	ld-2.28.so	0	0	0	0	48	44	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	45	46	0.00	0.00	0.00	0.00
bool armpl::clag::gemm_atomic::use<armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29, armpl::clag::spec::neoverse_n1_machine_spec> >(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)29,...	libarmpl.so	0	NA	0	NA	47	NA	0.00	NA	0.00	NA
idamax_	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
__kmp_resume_if_soft_paused	libomp_with_lse.so	0	0	0	0	7	10	0.00	0.00	0.00	0.00
_ZZZN5armpl4clag4gemmIdLNS0_4spec12problem_typeE29ENS2_24neoverse_n1_machine_specEEEvRKNS2_15problem_contextIT_XT0_ET1_EEENKUlDpRT_E_clIJKNS0_18blas3_set_or_scaleEKNS0_11gemm_atomicEKNS0_9blas1_dotEKNS0_11blas1_axpbyEKNS0_10blas3_gemvEEEEDaSD_ENKUlRS6_E_cl...	libarmpl.so	0	NA	0	NA	6	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	0	0	0	1	1	0.00	0.00	0.00	0.00
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::resize() [clone .41] [clone .extracted]	exec	0	0	0	0	2	2	0.00	0.00	0.00	0.00
uct_ud_iface_timer	libuct_ib.so.0.0.0	0	0	0	0	1	1	0.00	0.00	0.00	0.00
__kmpc_serialized_parallel	libomp_with_lse.so	0	0	0	0	2	7	0.00	0.00	0.00	0.00
__kmpc_end_master	libomp_with_lse.so	0	0	0	0	2	3	0.00	0.00	0.00	0.00
qmcplusplus::WaveFunction::evaluateGL(qmcplusplus::ParticleSet&)	exec	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
qmcplusplus::BlasThreadingEnv::~BlasThreadingEnv()	exec	0	0	0	0	2	3	0.00	0.00	0.00	0.00
dtrsm_	libarmpl.so	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl.so	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
__kmp_invoke_microtask	libomp_with_lse.so	0	0	0	0	2	2	0.00	0.00	0.00	0.00
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::(anonymous namespace)::trsm_kernel_exec<double> >::operator()<armpl::clag::(anonymous ...	libarmpl.so	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
dgetrf7xn_	libarmpl.so	0	NA	0	NA	2	NA	0.00	NA	0.00	NA
@plt_start@	libucs.so.0.0.0	0	0	0	0	1	1	0.00	0.00	0.00	0.00
ucs_async_thread_spinlock_try_block	libucs.so.0.0.0	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
ucs_async_dispatch_handlers	libucs.so.0.0.0	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::kernel_exec<void ()(double const, double const, double, long, long, long, long, double, double)>::operator()<armpl::clag::(anonymous namespace)::interleaved_matrix<double>, armpl::clag::(anonymous...	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
std::locale::locale()	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
void armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
dlamch_	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
ucs_async_dispatch_timerq	libucs.so.0.0.0	0	0	0	0	1	1	0.00	0.00	0.00	0.00
dgetrf_nag_	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
dgetrf7sn_	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
ucs_async_handler_get	libucs.so.0.0.0	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
kernel_dgemm_2_6_4_NN	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
___kmp_free	libomp_with_lse.so	0	0	0	0	2	2	0.00	0.00	0.00	0.00
std::__cxx11::basic_stringbuf<char, std::char_traits<char>, std::allocator<char> >::_M_pbump(char, char, long)	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
qmcplusplus::RealSpacePositions::resize(unsigned long)	exec	0	0	0	0	7	6	0.00	0.00	0.00	0.00
double std::generate_canonical<double, 53ul, std::mersenne_twister_engine<unsigned long, 32ul, 624ul, 397ul, 31ul, 2567483615ul, 11ul, 4294967295ul, 7ul, 2636928640ul, 15ul, 4022730752ul, 18ul, 1812433253ul> >(std::mersenne_twister_engine<un...	exec	0	0	0	0	3	3	0.00	0.00	0.00	0.00
pthread_spin_lock	libpthread-2.28.so	0	NA	0	NA	3	NA	2.31	NA	0.00	NA
dgemm_	libarmpl.so	0	NA	0	NA	4	NA	0.00	NA	0.00	NA
armpl::clag::use_overrides()	libarmpl.so	0	NA	0	NA	5	NA	0.00	NA	0.00	NA
qmcplusplus::RealSpacePositionsOMPTarget::getAllParticlePos() const	exec	0	0	0	0	5	4	0.00	0.00	0.00	0.00
__kmpc_end_serialized_parallel	libomp_with_lse.so	0	0	0	0	5	6	0.00	0.00	0.00	0.00
__kmpc_master	libomp_with_lse.so	0	0	0	0	5	3	0.00	0.00	0.00	0.00
std::chrono::_V2::system_clock::now()	libarmpl.so	0	NA	0	NA	1	NA	0.00	NA	0.00	NA
dgetrf2_	libarmpl.so	0	NA	0	NA	5	NA	0.00	NA	0.00	NA
__memmove	libastring_aarch64.so	0	0	0	0	5	7	0.00	0.00	0.00	0.00
operator delete(void*)	libarmpl.so	0	NA	0	NA	5	NA	0.00	NA	0.00	NA
kernel_dgemm_1_1_1_NT	libarmpl.so	0	NA	0	NA	5	NA	0.00	NA	0.00	NA
__kmp_push_current_task_to_thread	libomp_with_lse.so	0	0	0	0	6	3	0.00	0.00	0.00	0.00
___kmp_allocate	libomp_with_lse.so	0	0	0	0	6	5	0.00	0.00	0.00	0.00
__fixunstfdi	libgcc_s.so.1	0	0	0	0	3	1	0.00	0.00	0.00	0.00
void armpl::clag::trsm<true, int, double, armpl::clag::spec::neoverse_n1_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	4	NA	0.00	NA	0.00	NA
void armpl::clag::(anonymous namespace)::gemv_shim<false, double, &dgemv_n_neon_kernel>(long, long, double, double const, long, long, double const, long, double, double*, long)	libarmpl.so	0	NA	0	NA	4	NA	0.00	NA	0.00	NA
qmcplusplus::SoaDistanceTableABOMPTarget<double, 3u, 40>::getPerTargetPctlStrideSize() const	exec	0	NA	0	NA	3	NA	0.00	NA	0.00	NA
__GI_epoll_pwait	libc-2.28.so	0	0	0	0	1	1	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	3	3	0.00	0.00	0.00	0.00
ucs_event_set_wait	libucs.so.0.0.0	0	0	0	0	1	1	0.00	0.00	0.00	0.00
void armpl::clag::(anonymous namespace)::axpy_axpby_shim<double, &daxpy_kernel>(long, double, double const, double, double, long, long)	libarmpl.so	0	NA	0	NA	4	NA	0.00	NA	0.00	NA
void armpl::clag::gerb<true, int, false, double, armpl::clag::spec::neoverse_n1_machine_spec>(int const, int const, double const, double const, int const, double const, int const, double const, double, int const)	libarmpl.so	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::neoverse_n1_machine_spec>, armpl::clag::triangular_solve_resident<armpl::clag::(anonymous namespace)::gemm_exec<armpl::clag::spec::n...	libarmpl.so	0	NA	0	NA	3	NA	0.00	NA	0.00	NA
dtrsm_reference_	libarmpl.so	0	NA	0	NA	4	NA	0.00	NA	0.00	NA
void armpl::clag::gemm_basic::operator()<double, armpl::clag::spec::neoverse_n1_machine_spec>(armpl::clag::spec::problem_context<double, (armpl::clag::spec::problem_type)0, armpl::clag::spec::neoverse_n1_machine_spec> const&) const	libarmpl.so	0	NA	0	NA	3	NA	0.00	NA	0.00	NA
__kmp_join_call	libomp_with_lse.so	0	0	0	0	4	4	0.00	0.00	0.00	0.00
@plt_start@	libamath_neoverse-n1.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00
@plt_start@	libarmflang.so	NA	0	NA	0	NA	1	NA	0.00	NA	0.00

	orig	compilers/armclang_3
Uncheck all modules
exec	54.39 %	54.32 %
libarmpl.so	43.43 %
libastring_aarch64.so	1.7 %	1.69 %
libomp_with_lse.so	0.44 %	0.41 %
Unknown module	0.01 %	0.01 %
libamath_neoverse-n1.so	0.01 %	0.01 %
libc-2.28.so	0.01 %	0.01 %
[vdso]	0 %	0 %
libarmflang.so
ld-2.28.so	0 %	0 %
libucs.so.0.0.0	0 %	0 %
libpthread-2.28.so	0 %	0 %
mca_pmix_pmix3x.so	0 %
libmlx5.so.1.24.44.0
libuct_ib.so.0.0.0	0 %	0 %
libarmpl_mp.so
libm-2.28.so	0 %	0 %
libgcc_s.so.1	0 %	0 %
libopen-pal.so.40.30.2	0 %	0 %

Report Configuration

▶Filters

Functions