| | | | | | | 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 | 1x128 | 1x128 | 1x128 | 1x128 | 1x128 | 1x128 | 1x128 | 1x128 |
|---|
| libgromacs.so.8:0xcf6f33 | _INTERNAL6ff1e610::nbnxn_kernel_cpu(PairlistSet const&, Nbnx... | kerneldispatch.cpp:266 | 0 | 0 | runtime | parallel | 128 | 28.149 | 10.0 E3 | 4.332 | 4.331 | 15.4 | 1.182 | 1.058 |
| libgromacs.so.8:0x145340d | gmx_pme_do(gmx_pme_t*, gmx::ArrayRef<gmx::BasicVector<float>... | pme.cpp:1292 | 0 | 0 | runtime | parallel | 128 | 15.614 | 10.0 E3 | 4.642 | 4.627 | 29.7 | 1.423 | 1.062 |
| libgromacs.so.8:0xcc4c5f | _INTERNALe5e96b6b::nbnxn_atomdata_add_nbat_f_to_f_reduce(nbn... | atomdata.cpp:1157 | 0 | 0 | runtime | parallel | 128 | 3.822 | 10.0 E3 | 1.449 | 1.448 | 37.9 | 1.611 | 1.019 |
| libgromacs.so.8:0x133b438 | gmx::constrain_lincs(bool, t_inputrec const&, long, gmx::Lin... | lincs.cpp:2534 | 0 | 0 | runtime | parallel | 128 | 3.319 | 10.0 E3 | 1.674 | 1.616 | 50.4 | 2.018 | 1.022 |
| libgromacs.so.8:0x1475976 | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:936 | 0 | 0 | runtime | parallel | 128 | 2.346 | 10.0 E3 | 0.579 | 0.578 | 24.7 | 1.328 | 1.007 |
| libgromacs.so.8:0x145359a | gmx_pme_do(gmx_pme_t*, gmx::ArrayRef<gmx::BasicVector<float>... | pme.cpp:1397 | 0 | 0 | runtime | parallel | 128 | 1.746 | 10.0 E3 | 0.546 | 0.545 | 31.3 | 1.455 | 1.007 |
| libgromacs.so.8:0x147e0bb | fft5d_plan_3d(int, int, int, tmpi_comm_**, int, t_complex**,... | fft5d.cpp:630 | 0 | 0 | runtime | parallel | 128 | 1.489 | 6.00 | 77.0 E-3 | 77.0 E-3 | 5.17 | 1.055 | 1.001 |
| libgromacs.so.8:0x1475a9e | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:1010 | 0 | 0 | runtime | parallel | 128 | 1.430 | 10.0 E3 | 0.460 | 0.458 | 32.2 | 1.474 | 1.006 |
| libgromacs.so.8:0xcc2787 | nbnxn_atomdata_copy_x_to_nbat_x(Nbnxm::GridSet const&, gmx::... | atomdata.cpp:964 | 0 | 0 | runtime | parallel | 128 | 1.378 | 9.80 E3 | 0.719 | 0.717 | 52.1 | 2.090 | 1.009 |
| libgromacs.so.8:0x1441389 | _INTERNAL87cdf56b::calcBondedForces(InteractionDefinitions c... | listed_forces.cpp:387 | 0 | 0 | runtime | parallel | 128 | 1.120 | 10.0 E3 | 0.235 | 0.234 | 21.0 | 1.266 | 1.003 |
| libgromacs.so.8:0x147589d | spread_on_grid(gmx_pme_t const*, PmeAtomComm*, pmegrids_t co... | pme_spread.cpp:910 | 0 | 0 | runtime | parallel | 128 | 1.003 | 10.0 E3 | 0.321 | 0.320 | 32.0 | 1.471 | 1.004 |
| libgromacs.so.8:0x130cfab | L__ZN3gmx11Constraints4Impl5applyEbblifNS_19ArrayRefWithPadd... | constr.cpp:590 | 0 | 0 | runtime | parallel | 128 | 0.928 | 10.0 E3 | 0.312 | 0.311 | 33.6 | 1.507 | 1.004 |
| libgromacs.so.8:0x1383f13 | gmx::Update::Impl::finish_update(t_inputrec const&, bool, in... | update.cpp:1660 | 0 | 0 | runtime | parallel | 128 | 0.558 | 10.0 E3 | 0.107 | 0.106 | 19.3 | 1.238 | 1.001 |
| libgromacs.so.8:0x137c61e | gmx::Update::Impl::update_coords(t_inputrec const&, long, in... | update.cpp:1710 | 0 | 0 | runtime | parallel | 128 | 0.519 | 10.0 E3 | 0.161 | 0.160 | 31.0 | 1.450 | 1.002 |
| libgromacs.so.8:0xea3d78 | void _INTERNAL7b844c87::gmx::(anonymous namespace)::reduceTh... | threaded_force_buffer.cpp:170 | 0 | 0 | runtime | parallel | 128 | 0.501 | 10.0 E3 | 0.253 | 0.252 | 50.6 | 2.024 | 1.003 |
| libgromacs.so.8:0xe39f8a | dd_make_local_constraints(gmx_domdec_t*, int, gmx_mtop_t con... | domdec_constraints.cpp:430 | 0 | 0 | runtime | parallel | 128 | 0.488 | 202 | 0.475 | 0.475 | 97.2 | 36.332 | 1.006 |
| libgromacs.so.8:0xde3654 | PairlistSet::constructPairlists(gmx::InteractionLocality, Nb... | pairlist.cpp:4059 | 0 | 0 | runtime | parallel | 128 | 0.392 | 201 | 59.6 E-3 | 59.6 E-3 | 15.2 | 1.179 | 1.001 |
| libgromacs.so.8:0x1460a4e | unwrap_periodic_pmegrid(gmx_pme_t*, float*) | pme_grid.cpp:529 | 0 | 0 | runtime | parallel | 128 | 0.293 | 10.0 E3 | 0.150 | 0.148 | 51.1 | 2.045 | 1.002 |
| libgromacs.so.8:0xdfb333 | PairlistSet::dispatchPruneKernel(nbnxn_atomdata_t const*, gm... | prunekerneldispatch.cpp:69 | 0 | 0 | runtime | parallel | 128 | 0.260 | 1.00 E3 | 63.6 E-3 | 63.5 E-3 | 24.5 | 1.324 | 1.001 |
| libgromacs.so.8:0x1461234 | unwrap_periodic_pmegrid(gmx_pme_t*, float*) | pme_grid.cpp:512 | 0 | 0 | runtime | parallel | 128 | 0.170 | 10.0 E3 | 78.4 E-3 | 76.5 E-3 | 46.2 | 1.857 | 1.001 |
| libgromacs.so.8:0x13715eb | _INTERNALa39f5004::setupForceOutputs(ForceHelperBuffers*, gm... | sim_util.cpp:473 | 0 | 0 | runtime | parallel | 128 | 0.131 | 10.0 E3 | 46.0 E-3 | 45.0 E-3 | 35.0 | 1.540 | 1.001 |
| libgromacs.so.8:0xcc4478 | reduceForces(nbnxn_atomdata_t*, gmx::AtomLocality, Nbnxm::Gr... | atomdata.cpp:1231 | 0 | 0 | runtime | parallel | 128 | 98.3 E-3 | 10.0 E3 | 35.4 E-3 | 34.3 E-3 | 36.0 | 1.562 | 1.000 |
| libgromacs.so.8:0xdf10af | _INTERNAL15b136ef::rebalanceSimpleLists(gmx::ArrayRef<NbnxnP... | pairlist.cpp:3782 | 0 | 0 | runtime | parallel | 128 | 81.8 E-3 | 201 | 60.3 E-3 | 60.3 E-3 | 73.7 | 3.806 | 1.001 |
| libgromacs.so.8:0x14422d4 | setup_bonded_threading(bonded_threading_t*, int, bool, Inter... | manage_threading.cpp:396 | 0 | 0 | runtime | parallel | 128 | 73.0 E-3 | 202 | 17.7 E-3 | 17.7 E-3 | 24.2 | 1.320 | 1.000 |
| libgromacs.so.8:0xe4c44f | _INTERNALed97dceb::make_local_bondeds_excls(gmx_domdec_t con... | localtopology.cpp:846 | 0 | 0 | runtime | parallel | 128 | 71.4 E-3 | 202 | 26.7 E-3 | 26.7 E-3 | 37.5 | 1.599 | 1.000 |
| libgromacs.so.8:0xcede7d | Nbnxm::Grid::setCellIndices(int, int, Nbnxm::GridSetData*, g... | grid.cpp:1483 | 0 | 0 | runtime | parallel | 128 | 59.0 E-3 | 202 | 27.5 E-3 | 27.5 E-3 | 46.6 | 1.872 | 1.000 |
| libgromacs.so.8:0x1346239 | _INTERNAL96cc8366::calc_ke_part_normal(gmx::ArrayRef<gmx::Ba... | md_support.cpp:113 | 0 | 0 | runtime | parallel | 128 | 58.7 E-3 | 2.00 E3 | 22.3 E-3 | 22.0 E-3 | 38.0 | 1.612 | 1.000 |
| libgromacs.so.8:0x13702ad | _INTERNALa39f5004::postProcessForces(t_commrec const*, long,... | sim_util.cpp:149 | 0 | 0 | runtime | parallel | 128 | 23.0 E-3 | 1.00 E3 | 8.21 E-3 | 8.05 E-3 | 35.7 | 1.556 | 1.000 |
| libgromacs.so.8:0x134803a | atoms2md(gmx_mtop_t const&, t_inputrec const&, int, gmx::Arr... | mdatoms.cpp:266 | 0 | 0 | runtime | parallel | 128 | 17.2 E-3 | 202 | 2.67 E-3 | 2.65 E-3 | 15.5 | 1.184 | 1.000 |
| libgromacs.so.8:0x1342d9b | gmx::set_lincs(InteractionDefinitions const&, int, gmx::Arra... | lincs.cpp:2246 | 0 | 0 | runtime | parallel | 128 | 16.6 E-3 | 202 | 4.79 E-3 | 4.76 E-3 | 28.8 | 1.405 | 1.000 |
| libgromacs.so.8:0x1306639 | calc_vir(int, float const (*) [3], float const (*) [3], floa... | calcvir.cpp:109 | 0 | 0 | runtime | parallel | 128 | 14.8 E-3 | 1.00 E3 | 5.11 E-3 | 5.00 E-3 | 34.4 | 1.525 | 1.000 |
| libgromacs.so.8:0x1371848 | _INTERNALa39f5004::setupForceOutputs(ForceHelperBuffers*, gm... | sim_util.cpp:473 | 0 | 0 | runtime | parallel | 128 | 14.4 E-3 | 1.00 E3 | 5.54 E-3 | 5.43 E-3 | 38.5 | 1.626 | 1.000 |
| libgromacs.so.8:0x133fe63 | _INTERNAL3f4b4497::gmx::set_lincs_matrix(_INTERNAL3f4b4497::... | lincs.cpp:1397 | 0 | 0 | runtime | parallel | 128 | 12.6 E-3 | 202 | 5.15 E-3 | 4.94 E-3 | 40.7 | 1.688 | 1.000 |
| libgromacs.so.8:0x1340c0a | _INTERNAL3f4b4497::gmx::lincs_thread_setup(_INTERNAL3f4b4497... | lincs.cpp:1686 | 0 | 0 | runtime | parallel | 128 | 11.7 E-3 | 202 | 3.53 E-3 | 3.51 E-3 | 30.3 | 1.435 | 1.000 |
| libgromacs.so.8:0xcf42ae | Nbnxm::GridSet::putOnGrid(float const (*) [3], int, float co... | gridset.cpp:212 | 0 | 0 | runtime | parallel | 128 | 9.17 E-3 | 202 | 2.23 E-3 | 2.21 E-3 | 24.4 | 1.322 | 1.000 |
| libgromacs.so.8:0xe64b84 | dd_redistribute_cg(_IO_FILE*, long, gmx_domdec_t*, int*, t_s... | redistribute.cpp:624 | 0 | 0 | runtime | parallel | 128 | 9.15 E-3 | 201 | 2.37 E-3 | 2.35 E-3 | 25.9 | 1.350 | 1.000 |
| libgromacs.so.8:0xea95cc | gmx::ThreadedForceBuffer<float [4]>::ThreadedForceBuffer(int... | threaded_force_buffer.cpp:230 | 0 | 0 | runtime | parallel | 128 | 8.28 E-3 | 1.00 | 107 E-6 | 105 E-6 | 1.29 | 1.013 | 1.000 |
| libgromacs.so.8:0x134109f | _INTERNAL3f4b4497::gmx::lincs_thread_setup(_INTERNAL3f4b4497... | lincs.cpp:1745 | 0 | 0 | runtime | parallel | 128 | 6.98 E-3 | 202 | 2.57 E-3 | 2.54 E-3 | 36.8 | 1.582 | 1.000 |
| libgromacs.so.8:0x1392bce | _INTERNAL7ad953f0::do_stopcm_grp(t_mdatoms const&, gmx::Arra... | vcm.cpp:372 | 0 | 0 | runtime | parallel | 128 | 2.19 E-3 | 102 | 1.19 E-3 | 1.08 E-3 | 54.2 | 2.183 | 1.000 |
| libgromacs.so.8:0x138e990 | calc_vcm_grp(t_mdatoms const&, gmx::ArrayRef<gmx::BasicVecto... | vcm.cpp:170 | 0 | 0 | runtime | parallel | 128 | 2.08 E-3 | 102 | 1.01 E-3 | 898 E-6 | 48.5 | 1.943 | 1.000 |
| libgromacs.so.8:0x14e85e3 | _INTERNAL5aaa8544::set_affinity(t_commrec const*, int, int, ... | threadaffinity.cpp:315 | 0 | 0 | runtime | parallel | 128 | 256 E-6 | 1.00 | 69.7 E-6 | 68.3 E-6 | 27.2 | 1.373 | 1.000 |
| libgromacs.so.8:0x1475176 | pme_init_all_work(pme_solve_work_t**, int, int) | pme_solve.cpp:143 | 0 | 0 | runtime | parallel | 128 | 22.0 E-6 | 1.00 | 4.16 E-6 | 4.03 E-6 | 18.9 | 1.233 | 1.000 |
| libgromacs.so.8:0xe8d37a | gmx_ekindata_t::gmx_ekindata_t(gmx::ArrayRef<float const>, E... | group.cpp:76 | 0 | 0 | runtime | parallel | 128 | 15.7 E-6 | 1.00 | 5.51 E-6 | 5.36 E-6 | 35.1 | 1.542 | 1.000 |
| libgromacs.so.8:0x1457670 | PmeAtomComm::PmeAtomComm(tmpi_comm_*, int, int, int, bool) | pme.cpp:320 | 0 | 0 | runtime | parallel | 128 | 14.7 E-6 | 1.00 | 5.21 E-6 | 5.07 E-6 | 35.5 | 1.550 | 1.000 |
