| | | | | | | requested parallelism | walltime sum (s) | nb instances | any sync average per thread time (s) | any wait average per thread time (s) | parallelism overhead (%) | local speedup if perfectly balanced | global speedup if perfectly balanced |
|---|
| start addr | function name | source location | level | ancestor thread num | invoker | parallel or teams | 1x52 | 1x52 | 1x52 | 1x52 | 1x52 | 1x52 | 1x52 | 1x52 |
|---|
| libgromacs_mpi.so.7:0x46c648 | nonbonded_verlet_t::dispatchNonbondedKernel(gmx::Interaction... | kerneldispatch.cpp:382 | 0 | 0 | runtime | parallel | 52 | 27.667 | 10.0 E3 | 1.016 | 1.015 | 3.67 | 1.038 | 1.021 |
| libgromacs_mpi.so.7:0x91e7a4 | gmx_pme_do(gmx_pme_t*, gmx::ArrayRef<gmx::BasicVector<float>... | pme.cpp:1383 | 0 | 0 | runtime | parallel | 52 | 4.207 | 10.0 E3 | 0.352 | 0.343 | 8.38 | 1.091 | 1.007 |
| libgromacs_mpi.so.7:0x931600 | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:1005 | 0 | 0 | runtime | parallel | 52 | 1.912 | 10.0 E3 | 0.315 | 0.314 | 16.5 | 1.197 | 1.007 |
| libgromacs_mpi.so.7:0x90df20 | ListedForces::calculate(gmx_wallcycle*, float const (*) [3],... | listed_forces.cpp:385 | 0 | 0 | runtime | parallel | 52 | 1.794 | 10.0 E3 | 0.175 | 0.174 | 9.73 | 1.108 | 1.004 |
| libgromacs_mpi.so.7:0x8633f4 | gmx::constrain_lincs(bool, t_inputrec const&, long, gmx::Lin... | lincs.cpp:2483 | 0 | 0 | runtime | parallel | 52 | 1.779 | 10.0 E3 | 0.726 | 0.698 | 40.8 | 1.690 | 1.015 |
| libgromacs_mpi.so.7:0x91e878 | gmx_pme_do(gmx_pme_t*, gmx::ArrayRef<gmx::BasicVector<float>... | pme.cpp:1417 | 0 | 0 | runtime | parallel | 52 | 1.697 | 10.0 E3 | 0.343 | 0.342 | 20.2 | 1.253 | 1.007 |
| libgromacs_mpi.so.7:0x931654 | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:1030 | 0 | 0 | runtime | parallel | 52 | 1.118 | 10.0 E3 | 0.226 | 0.225 | 20.2 | 1.253 | 1.005 |
| libgromacs_mpi.so.7:0x9366e0 | fft5d_plan_3d(int, int, int, ompi_communicator_t**, int, t_c... | fft5d.cpp:632 | 0 | 0 | runtime | parallel | 52 | 0.971 | 6.00 | 12.9 E-3 | 12.9 E-3 | 1.32 | 1.013 | 1.000 |
| libgromacs_mpi.so.7:0x460034 | reduceForces(nbnxn_atomdata_t*, gmx::AtomLocality, Nbnxm::Gr... | atomdata.cpp:1262 | 0 | 0 | runtime | parallel | 52 | 0.621 | 10.0 E3 | 0.110 | 0.109 | 17.7 | 1.215 | 1.002 |
| libgromacs_mpi.so.7:0x83fb4c | gmx::Constraints::Impl::apply(bool, bool, long, int, float, ... | constr.cpp:611 | 0 | 0 | runtime | parallel | 52 | 0.458 | 10.0 E3 | 70.6 E-3 | 69.8 E-3 | 15.4 | 1.182 | 1.001 |
| libgromacs_mpi.so.7:0x4be434 | PairlistSet::constructPairlists(gmx::InteractionLocality, Nb... | cyclecounter.h:196 | 0 | 0 | runtime | parallel | 52 | 0.441 | 126 | 40.5 E-3 | 40.4 E-3 | 9.18 | 1.101 | 1.001 |
| libgromacs_mpi.so.7:0x4cd940 | nonbonded_verlet_t::dispatchPruneKernelCpu(gmx::InteractionL... | prunekerneldispatch.cpp:97 | 0 | 0 | runtime | parallel | 52 | 0.342 | 876 | 10.7 E-3 | 10.6 E-3 | 3.13 | 1.032 | 1.000 |
| libgromacs_mpi.so.7:0x9315a8 | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:936 | 0 | 0 | runtime | parallel | 52 | 0.325 | 10.0 E3 | 39.8 E-3 | 39.1 E-3 | 12.3 | 1.140 | 1.001 |
| libgromacs_mpi.so.7:0x887cd8 | gmx::Update::Impl::update_coords(t_inputrec const&, long, in... | update.cpp:1818 | 0 | 0 | runtime | parallel | 52 | 0.319 | 10.0 E3 | 44.2 E-3 | 43.4 E-3 | 13.8 | 1.161 | 1.001 |
| libgromacs_mpi.so.7:0x53e2ec | gmx::ThreadedForceBuffer<float [4]>::reduce(gmx::ForceWithSh... | threaded_force_buffer.cpp:170 | 0 | 0 | runtime | parallel | 52 | 0.288 | 10.0 E3 | 86.2 E-3 | 85.5 E-3 | 29.9 | 1.426 | 1.002 |
| libgromacs_mpi.so.7:0x45fd0c | nbnxn_atomdata_copy_x_to_nbat_x(Nbnxm::GridSet const&, gmx::... | atomdata.cpp:1023 | 0 | 0 | runtime | parallel | 52 | 0.163 | 9.88 E3 | 70.1 E-3 | 69.3 E-3 | 43.0 | 1.753 | 1.001 |
| libgromacs_mpi.so.7:0x4f39d4 | dd_make_local_constraints(gmx_domdec_t*, int, gmx_mtop_t con... | domdec_constraints.cpp:492 | 0 | 0 | runtime | parallel | 52 | 0.143 | 127 | 0.132 | 0.132 | 92.4 | 13.187 | 1.003 |
| libgromacs_mpi.so.7:0x46007c | reduceForces(nbnxn_atomdata_t*, gmx::AtomLocality, Nbnxm::Gr... | atomdata.cpp:1272 | 0 | 0 | runtime | parallel | 52 | 0.130 | 10.0 E3 | 42.4 E-3 | 41.6 E-3 | 32.6 | 1.483 | 1.001 |
| libgromacs_mpi.so.7:0x887f60 | gmx::Update::Impl::finish_update(t_inputrec const&, bool, in... | wallcycle.h:268 | 0 | 0 | runtime | parallel | 52 | 0.109 | 10.0 E3 | 29.4 E-3 | 28.7 E-3 | 27.0 | 1.369 | 1.001 |
| libgromacs_mpi.so.7:0x882f94 | setupForceOutputs(ForceHelperBuffers*, gmx::ArrayRefWithPadd... | sim_util.cpp:473 | 0 | 0 | runtime | parallel | 52 | 90.8 E-3 | 10.0 E3 | 27.3 E-3 | 26.6 E-3 | 30.1 | 1.431 | 1.001 |
| libgromacs_mpi.so.7:0x923d20 | unwrap_periodic_pmegrid(gmx_pme_t*, float*) | pme_grid.cpp:543 | 0 | 0 | runtime | parallel | 52 | 87.7 E-3 | 10.0 E3 | 34.6 E-3 | 33.8 E-3 | 39.4 | 1.650 | 1.001 |
| libgromacs_mpi.so.7:0x923cd4 | unwrap_periodic_pmegrid(gmx_pme_t*, float*) | pme_grid.cpp:529 | 0 | 0 | runtime | parallel | 52 | 71.2 E-3 | 10.0 E3 | 27.7 E-3 | 26.9 E-3 | 38.9 | 1.638 | 1.001 |
| libgromacs_mpi.so.7:0x4ff094 | dd_make_local_top(gmx_domdec_t const&, gmx_domdec_zones_t co... | arrayref.h:254 | 0 | 0 | runtime | parallel | 52 | 61.4 E-3 | 127 | 26.8 E-3 | 26.8 E-3 | 43.7 | 1.776 | 1.001 |
| libgromacs_mpi.so.7:0x867754 | compute_globals(gmx_global_stat*, t_commrec*, t_inputrec con... | md_support.cpp:113 | 0 | 0 | runtime | parallel | 52 | 58.3 E-3 | 2.00 E3 | 10.7 E-3 | 10.6 E-3 | 18.4 | 1.226 | 1.000 |
| libgromacs_mpi.so.7:0x4bee44 | PairlistSet::constructPairlists(gmx::InteractionLocality, Nb... | stl_vector.h:111 | 0 | 0 | runtime | parallel | 52 | 25.8 E-3 | 126 | 4.67 E-3 | 4.65 E-3 | 18.1 | 1.221 | 1.000 |
| libgromacs_mpi.so.7:0x83e8d4 | calc_vir(int, float const (*) [3], float const (*) [3], floa... | calcvir.cpp:109 | 0 | 0 | runtime | parallel | 52 | 20.8 E-3 | 1.00 E3 | 4.10 E-3 | 4.02 E-3 | 19.7 | 1.245 | 1.000 |
| libgromacs_mpi.so.7:0x468c0c | Nbnxm::Grid::setCellIndices(int, int, Nbnxm::GridSetData*, g... | grid.cpp:1502 | 0 | 0 | runtime | parallel | 52 | 17.1 E-3 | 127 | 6.99 E-3 | 6.98 E-3 | 40.9 | 1.693 | 1.000 |
| libgromacs_mpi.so.7:0x90f7bc | setup_bonded_threading(bonded_threading_t*, int, bool, Inter... | manage_threading.cpp:407 | 0 | 0 | runtime | parallel | 52 | 14.4 E-3 | 127 | 852 E-6 | 840 E-6 | 5.90 | 1.063 | 1.000 |
| libgromacs_mpi.so.7:0x8836b0 | postProcessForces(t_commrec const*, long, t_nrnb*, gmx_wallc... | vec.h:538 | 0 | 0 | runtime | parallel | 52 | 10.7 E-3 | 1.00 E3 | 2.94 E-3 | 2.87 E-3 | 27.5 | 1.380 | 1.000 |
| libgromacs_mpi.so.7:0x883134 | setupForceOutputs(ForceHelperBuffers*, gmx::ArrayRefWithPadd... | sim_util.cpp:473 | 0 | 0 | runtime | parallel | 52 | 8.95 E-3 | 1.00 E3 | 2.42 E-3 | 2.34 E-3 | 27.0 | 1.370 | 1.000 |
| libgromacs_mpi.so.7:0x9753a8 | gmx_set_thread_affinity(gmx::MDLogger const&, t_commrec cons... | threadaffinity.cpp:353 | 0 | 0 | runtime | parallel | 52 | 8.90 E-3 | 1.00 | 7.37 E-3 | 7.37 E-3 | 82.8 | 5.806 | 1.000 |
| libgromacs_mpi.so.7:0x8696fc | atoms2md(gmx_mtop_t const&, t_inputrec const&, int, gmx::Arr... | mdatoms.cpp:503 | 0 | 0 | runtime | parallel | 52 | 6.89 E-3 | 127 | 898 E-6 | 888 E-6 | 13.0 | 1.150 | 1.000 |
| libgromacs_mpi.so.7:0x861370 | gmx::set_lincs(InteractionDefinitions const&, int, gmx::Arra... | lincs.cpp:2215 | 0 | 0 | runtime | parallel | 52 | 4.68 E-3 | 127 | 1.08 E-3 | 1.07 E-3 | 23.1 | 1.300 | 1.000 |
| libgromacs_mpi.so.7:0x50fb20 | dd_redistribute_cg(_IO_FILE*, long, gmx_domdec_t*, int*, t_s... | redistribute.cpp:679 | 0 | 0 | runtime | parallel | 52 | 4.10 E-3 | 126 | 813 E-6 | 802 E-6 | 19.8 | 1.247 | 1.000 |
| libgromacs_mpi.so.7:0x861684 | gmx::set_lincs(InteractionDefinitions const&, int, gmx::Arra... | lincs.cpp:1673 | 0 | 0 | runtime | parallel | 52 | 4.01 E-3 | 127 | 1.37 E-3 | 1.36 E-3 | 34.1 | 1.518 | 1.000 |
| libgromacs_mpi.so.7:0x861f68 | gmx::set_lincs_matrix(gmx::Lincs*, gmx::ArrayRef<float const... | lincs.cpp:1361 | 0 | 0 | runtime | parallel | 52 | 3.98 E-3 | 127 | 1.89 E-3 | 1.83 E-3 | 47.5 | 1.906 | 1.000 |
| libgromacs_mpi.so.7:0x861794 | gmx::set_lincs(InteractionDefinitions const&, int, gmx::Arra... | lincs.cpp:1725 | 0 | 0 | runtime | parallel | 52 | 2.32 E-3 | 127 | 935 E-6 | 925 E-6 | 40.3 | 1.675 | 1.000 |
| libgromacs_mpi.so.7:0x46aa7c | Nbnxm::GridSet::putOnGrid(float const (*) [3], int, float co... | gridset.cpp:233 | 0 | 0 | runtime | parallel | 52 | 1.59 E-3 | 127 | 377 E-6 | 367 E-6 | 23.6 | 1.309 | 1.000 |
| libgromacs_mpi.so.7:0x8941a0 | calc_vcm_grp(t_mdatoms const&, gmx::ArrayRef<gmx::BasicVecto... | vcm.cpp:170 | 0 | 0 | runtime | parallel | 52 | 1.39 E-3 | 102 | 573 E-6 | 542 E-6 | 41.1 | 1.698 | 1.000 |
| libgromacs_mpi.so.7:0x895168 | process_and_stopcm_grp(_IO_FILE*, t_vcm*, t_mdatoms const&, ... | vcm.cpp:618 | 0 | 0 | runtime | parallel | 52 | 1.34 E-3 | 102 | 562 E-6 | 537 E-6 | 42.0 | 1.723 | 1.000 |
| libgromacs_mpi.so.7:0x53dbac | gmx::ThreadedForceBuffer<float [4]>::ThreadedForceBuffer(int... | threaded_force_buffer.cpp:243 | 0 | 0 | runtime | parallel | 52 | 156 E-6 | 1.00 | 85.7 E-6 | 85.6 E-6 | 54.9 | 2.218 | 1.000 |
| libgromacs_mpi.so.7:0x92cf38 | pme_init_all_work(pme_solve_work_t**, int, int) | pme_solve.cpp:153 | 0 | 0 | runtime | parallel | 52 | 21.9 E-6 | 1.00 | 5.11 E-6 | 5.00 E-6 | 23.3 | 1.305 | 1.000 |
| libgromacs_mpi.so.7:0x921ec4 | void std::vector<PmeAtomComm, std::allocator<PmeAtomComm> >:... | stl_uninitialized.h:1031 | 0 | 0 | runtime | parallel | 52 | 7.65 E-6 | 1.00 | 2.96 E-6 | 2.83 E-6 | 38.7 | 1.632 | 1.000 |
| libgromacs_mpi.so.7:0x52a3e0 | gmx_ekindata_t::gmx_ekindata_t(int, float, int) | group.cpp:88 | 0 | 0 | runtime | parallel | 52 | 6.66 E-6 | 1.00 | 2.75 E-6 | 2.63 E-6 | 41.3 | 1.702 | 1.000 |
