auto armpl::clag::execute_strategy<16ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> >, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> >(std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> > const&, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> const&) - Load Distribution

minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value


minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value

auto armpl::clag::execute_strategy<16ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> >, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> >(std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> > const&, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> const&) - Sorted Load Distribution

minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value


minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value

auto armpl::clag::execute_strategy<16ul, std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> >, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> >(std::tuple<armpl::clag::matmul::set_or_scale, armpl::clag::matmul::compressed_general_matrix_vector, armpl::clag::matmul::symmetric_matrix_vector, armpl::clag::matmul::compressed_symmetric_matrix_vector, armpl::clag::matmul::compressed_rank_one_update, armpl::clag::matmul::out_of_place_matmul_left, armpl::clag::matmul::out_of_place_matmul_right, armpl::clag::matmul::atomic, armpl::clag::matmul::dot, armpl::clag::matmul::axpby, armpl::clag::matmul::gemv, armpl::clag::matmul::outer_product, armpl::clag::matmul::small, armpl::clag::matmul::basic, armpl::clag::matmul::sequential, armpl::clag::matmul::large<true>, armpl::clag::matmul::large_no_sync<false>, armpl::clag::matmul::rank_k_update_large, armpl::clag::matmul::rank_k_update_basic, armpl::clag::matmul::rank_one_update, armpl::clag::matmul::gemm_reference, armpl::clag::matmul::symm_hemm_l_reference, armpl::clag::matmul::symm_hemm_r_reference, armpl::clag::matmul::syrk_herk_reference, armpl::clag::matmul::backstop, armpl::clag::matmul::large_no_sync<true> > const&, armpl::clag::spec::problem_context<armpl::clag::matmul::matmul3<armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double const> >, armpl::clag::general_matrix<armpl::clag::matrix_base<double> >, double>, armpl::clag::spec::sve_architecture_spec> const&) - Load Distribution All Threads

minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value


minmedavgmax
Percentile Index10 20 30 40 50 60 70 80 90 100
Value
Coverage (%)NameSource LocationModule
79.96+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]DelayedUpdate.h:190exec
void qmcplusplus::DelayedUpdat[...]DelayedUpdate.h:153exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:129exec
qmcplusplus::WaveFunction::acc[...]stl_vector.h:993exec
main.omp_outlined.62miniqmc.cpp:450exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
3.51+void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::getrf<true, [...]libarmpl_lp64.so
qmcplusplus::DiracMatrix<doubl[...]BLAS.hpp:790exec
miniqmcreference::DiracDetermi[...]DelayedUpdate.h:79exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:238exec
qmcplusplus::WaveFunction::eva[...]WaveFunction.cpp:171exec
main.omp_outlinedminiqmc.cpp:379exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
2.61+void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::getrf<true, [...]libarmpl_lp64.so
qmcplusplus::DiracMatrix<doubl[...]BLAS.hpp:790exec
miniqmcreference::DiracDetermi[...]DelayedUpdate.h:79exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:238exec
qmcplusplus::WaveFunction::eva[...]WaveFunction.cpp:171exec
main.omp_outlinedminiqmc.cpp:379exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.86+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]BLAS.hpp:249exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:148exec
qmcplusplus::WaveFunction::com[...]NewTimer.h:249exec
main.omp_outlined.62miniqmc.cpp:461exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.61+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]DelayedUpdate.h:192exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:148exec
qmcplusplus::WaveFunction::com[...]NewTimer.h:249exec
main.omp_outlined.62miniqmc.cpp:461exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.47+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]DelayedUpdate.h:192exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:148exec
qmcplusplus::WaveFunction::com[...]WaveFunction.cpp:236exec
main.omp_outlined.62miniqmc.cpp:461exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.40+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]DelayedUpdate.h:190exec
void qmcplusplus::DelayedUpdat[...]DelayedUpdate.h:153exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:129exec
qmcplusplus::WaveFunction::acc[...]stl_vector.h:993exec
main.omp_outlined.62miniqmc.cpp:450exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_fork_calllibomp.so
__kmpc_fork_calllibomp.so
mainminiqmc.cpp:409exec
__libc_start_call_mainlibc.so.6
__libc_start_mainlibc.so.6
_startnew_allocator.h:172exec
1.29+void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::getrf<true, [...]libarmpl_lp64.so
qmcplusplus::DiracMatrix<doubl[...]BLAS.hpp:790exec
miniqmcreference::DiracDetermi[...]DelayedUpdate.h:79exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:238exec
qmcplusplus::WaveFunction::eva[...]WaveFunction.cpp:171exec
main.omp_outlinedminiqmc.cpp:379exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.14+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::gemm<true, i[...]libarmpl_lp64.so
qmcplusplus::DelayedUpdate<dou[...]BLAS.hpp:249exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:148exec
qmcplusplus::WaveFunction::com[...]WaveFunction.cpp:236exec
main.omp_outlined.62miniqmc.cpp:461exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.11+void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::triangular_s[...]libarmpl_lp64.so
void armpl::clag::triangular_s[...]libarmpl_lp64.so
void armpl::clag::triangular_s[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::getrf<true, [...]libarmpl_lp64.so
qmcplusplus::DiracMatrix<doubl[...]BLAS.hpp:790exec
miniqmcreference::DiracDetermi[...]DelayedUpdate.h:79exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:238exec
qmcplusplus::WaveFunction::eva[...]WaveFunction.cpp:171exec
main.omp_outlinedminiqmc.cpp:379exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
1.04+void armpl::clag::compute_impl[...]libarmpl_lp64.so
auto armpl::clag::execute_stra[...]libarmpl_lp64.so
void armpl::clag::compute_impl[...]libarmpl_lp64.so
void armpl::clag::getrf<true, [...]libarmpl_lp64.so
qmcplusplus::DiracMatrix<doubl[...]BLAS.hpp:790exec
miniqmcreference::DiracDetermi[...]DelayedUpdate.h:79exec
miniqmcreference::DiracDetermi[...]DiracDeterminantRef.cpp:238exec
qmcplusplus::WaveFunction::eva[...]WaveFunction.cpp:171exec
main.omp_outlinedminiqmc.cpp:379exec
__kmp_invoke_microtasklibomp.so
__kmp_invoke_task_funclibomp.so
__kmp_launch_threadlibomp.so
__kmp_launch_worker(void*)libomp.so
start_threadlibc.so.6
thread_startlibc.so.6
×