Loading examples/controller/log.5Oct16.controller.g++.1→examples/controller/log.27Nov18.controller.g++.1 +30 −23 Original line number Diff line number Diff line LAMMPS (5 Oct 2016) LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # 3d Lennard-Jones melt, thermostatted by fix controller units lj Loading @@ -12,6 +13,7 @@ Created orthogonal box = (0 0 0) to (16.796 16.796 16.796) 1 by 1 by 1 MPI processor grid create_atoms 1 box Created 4000 atoms Time spent = 0.00062418 secs mass 1 1.0 velocity all create 1.44 87287 loop geom Loading @@ -32,13 +34,18 @@ fix tstat all langevin v_tcontrol 0.5 0.5 2938940 thermo 50 run 500 Neighbor list info ... 1 neighbor list requests update every 20 steps, delay 0 steps, check no max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2.8 ghost atom cutoff = 2.8 binsize = 1.4 -> bins = 12 12 12 Memory usage per processor = 2.19271 Mbytes binsize = 1.4, bins = 12 12 12 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair lj/cut, perpetual attributes: half, newton on pair build: half/bin/atomonly/newton stencil: half/bin/3d/newton bin: standard Per MPI rank memory allocation (min/avg/max) = 3.221 | 3.221 | 3.221 Mbytes Step Temp E_pair E_mol TotEng Press 0 1.44 -6.7733681 0 -4.6139081 -5.0199732 50 0.61784238 -5.9328913 0 -5.0063594 -0.8309723 Loading @@ -51,20 +58,20 @@ Step Temp E_pair E_mol TotEng Press 400 0.49885979 -6.157314 0 -5.4092114 -2.1544075 450 0.50261633 -6.1458076 0 -5.3920716 -2.1080502 500 0.51198903 -6.1441158 0 -5.3763242 -2.0677941 Loop time of 1.51804 on 1 procs for 500 steps with 4000 atoms Loop time of 1.55006 on 1 procs for 500 steps with 4000 atoms Performance: 142288.277 tau/day, 329.371 timesteps/s 99.9% CPU use with 1 MPI tasks x no OpenMP threads Performance: 139349.249 tau/day, 322.568 timesteps/s 99.0% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 1.2152 | 1.2152 | 1.2152 | 0.0 | 80.05 Neigh | 0.16464 | 0.16464 | 0.16464 | 0.0 | 10.85 Comm | 0.022342 | 0.022342 | 0.022342 | 0.0 | 1.47 Output | 0.00020981 | 0.00020981 | 0.00020981 | 0.0 | 0.01 Modify | 0.10936 | 0.10936 | 0.10936 | 0.0 | 7.20 Other | | 0.006292 | | | 0.41 Pair | 1.2115 | 1.2115 | 1.2115 | 0.0 | 78.16 Neigh | 0.18784 | 0.18784 | 0.18784 | 0.0 | 12.12 Comm | 0.027217 | 0.027217 | 0.027217 | 0.0 | 1.76 Output | 0.00033712 | 0.00033712 | 0.00033712 | 0.0 | 0.02 Modify | 0.1171 | 0.1171 | 0.1171 | 0.0 | 7.55 Other | | 0.006078 | | | 0.39 Nlocal: 4000 ave 4000 max 4000 min Histogram: 1 0 0 0 0 0 0 0 0 0 Loading @@ -90,7 +97,7 @@ fix 10 all controller 100 1.0 0.5 0.0 0.0 c_thermo_t # run with controller run 2500 Memory usage per processor = 2.19271 Mbytes Per MPI rank memory allocation (min/avg/max) = 3.221 | 3.221 | 3.221 Mbytes Step Temp E_pair E_mol TotEng Press 500 0.51198903 -6.1441158 0 -5.3763242 -2.0677941 550 0.50342035 -6.1446822 0 -5.3897404 -2.0872641 Loading Loading @@ -143,20 +150,20 @@ Step Temp E_pair E_mol TotEng Press 2900 1.5287303 -4.8393493 0 -2.546827 5.3276564 2950 1.5175567 -4.8779763 0 -2.6022104 5.1592321 3000 1.5038518 -4.8714664 0 -2.6162526 5.1494048 Loop time of 7.82673 on 1 procs for 2500 steps with 4000 atoms Loop time of 7.9877 on 1 procs for 2500 steps with 4000 atoms Performance: 137988.733 tau/day, 319.418 timesteps/s 99.9% CPU use with 1 MPI tasks x no OpenMP threads Performance: 135207.915 tau/day, 312.981 timesteps/s 99.0% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 6.2774 | 6.2774 | 6.2774 | 0.0 | 80.21 Neigh | 0.85491 | 0.85491 | 0.85491 | 0.0 | 10.92 Comm | 0.11304 | 0.11304 | 0.11304 | 0.0 | 1.44 Output | 0.00090504 | 0.00090504 | 0.00090504 | 0.0 | 0.01 Modify | 0.55013 | 0.55013 | 0.55013 | 0.0 | 7.03 Other | | 0.0303 | | | 0.39 Pair | 6.2628 | 6.2628 | 6.2628 | 0.0 | 78.41 Neigh | 0.97669 | 0.97669 | 0.97669 | 0.0 | 12.23 Comm | 0.13389 | 0.13389 | 0.13389 | 0.0 | 1.68 Output | 0.0015631 | 0.0015631 | 0.0015631 | 0.0 | 0.02 Modify | 0.58344 | 0.58344 | 0.58344 | 0.0 | 7.30 Other | | 0.02927 | | | 0.37 Nlocal: 4000 ave 4000 max 4000 min Histogram: 1 0 0 0 0 0 0 0 0 0 Loading examples/controller/log.5Oct16.controller.g++.4→examples/controller/log.27Nov18.controller.g++.4 +30 −23 Original line number Diff line number Diff line LAMMPS (5 Oct 2016) LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # 3d Lennard-Jones melt, thermostatted by fix controller units lj Loading @@ -12,6 +13,7 @@ Created orthogonal box = (0 0 0) to (16.796 16.796 16.796) 1 by 2 by 2 MPI processor grid create_atoms 1 box Created 4000 atoms Time spent = 0.000405788 secs mass 1 1.0 velocity all create 1.44 87287 loop geom Loading @@ -32,13 +34,18 @@ fix tstat all langevin v_tcontrol 0.5 0.5 2938940 thermo 50 run 500 Neighbor list info ... 1 neighbor list requests update every 20 steps, delay 0 steps, check no max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2.8 ghost atom cutoff = 2.8 binsize = 1.4 -> bins = 12 12 12 Memory usage per processor = 2.10344 Mbytes binsize = 1.4, bins = 12 12 12 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair lj/cut, perpetual attributes: half, newton on pair build: half/bin/atomonly/newton stencil: half/bin/3d/newton bin: standard Per MPI rank memory allocation (min/avg/max) = 2.705 | 2.705 | 2.705 Mbytes Step Temp E_pair E_mol TotEng Press 0 1.44 -6.7733681 0 -4.6139081 -5.0199732 50 0.61546984 -5.9273631 0 -5.0043892 -0.80234884 Loading @@ -51,20 +58,20 @@ Step Temp E_pair E_mol TotEng Press 400 0.50869337 -6.1435002 0 -5.3806509 -2.0654599 450 0.50821435 -6.1436659 0 -5.381535 -2.0660991 500 0.51057155 -6.138733 0 -5.3730671 -2.0305015 Loop time of 0.474689 on 4 procs for 500 steps with 4000 atoms Loop time of 0.469437 on 4 procs for 500 steps with 4000 atoms Performance: 455034.992 tau/day, 1053.322 timesteps/s 99.7% CPU use with 4 MPI tasks x no OpenMP threads Performance: 460125.812 tau/day, 1065.106 timesteps/s 97.7% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 0.31692 | 0.32816 | 0.35039 | 2.3 | 69.13 Neigh | 0.042872 | 0.044288 | 0.046693 | 0.7 | 9.33 Comm | 0.043676 | 0.070658 | 0.084897 | 6.0 | 14.89 Output | 0.00025439 | 0.0002867 | 0.00030446 | 0.1 | 0.06 Modify | 0.02728 | 0.028604 | 0.030571 | 0.8 | 6.03 Other | | 0.002697 | | | 0.57 Pair | 0.31917 | 0.32582 | 0.32979 | 0.7 | 69.41 Neigh | 0.048915 | 0.051251 | 0.053828 | 0.8 | 10.92 Comm | 0.054731 | 0.059151 | 0.069726 | 2.5 | 12.60 Output | 0.00028014 | 0.00033808 | 0.00048709 | 0.0 | 0.07 Modify | 0.02967 | 0.031206 | 0.033305 | 0.8 | 6.65 Other | | 0.00167 | | | 0.36 Nlocal: 1000 ave 1027 max 969 min Histogram: 1 0 0 1 0 0 0 0 1 1 Loading @@ -90,7 +97,7 @@ fix 10 all controller 100 1.0 0.5 0.0 0.0 c_thermo_t # run with controller run 2500 Memory usage per processor = 2.10344 Mbytes Per MPI rank memory allocation (min/avg/max) = 2.705 | 2.705 | 2.705 Mbytes Step Temp E_pair E_mol TotEng Press 500 0.51057155 -6.138733 0 -5.3730671 -2.0305015 550 0.50420106 -6.1501845 0 -5.394072 -2.095219 Loading Loading @@ -143,20 +150,20 @@ Step Temp E_pair E_mol TotEng Press 2900 1.4994026 -4.8400966 0 -2.591555 5.3231654 2950 1.5057915 -4.8842358 0 -2.6261131 5.1645778 3000 1.5038806 -4.8661399 0 -2.610883 5.2228747 Loop time of 2.33203 on 4 procs for 2500 steps with 4000 atoms Loop time of 2.39888 on 4 procs for 2500 steps with 4000 atoms Performance: 463116.726 tau/day, 1072.029 timesteps/s 99.9% CPU use with 4 MPI tasks x no OpenMP threads Performance: 450209.527 tau/day, 1042.152 timesteps/s 97.4% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 1.6173 | 1.6621 | 1.7135 | 3.2 | 71.27 Neigh | 0.2201 | 0.22394 | 0.23011 | 0.9 | 9.60 Comm | 0.22619 | 0.29012 | 0.33801 | 8.8 | 12.44 Output | 0.001302 | 0.0013426 | 0.0013707 | 0.1 | 0.06 Modify | 0.13805 | 0.14195 | 0.14664 | 0.9 | 6.09 Other | | 0.01257 | | | 0.54 Pair | 1.6469 | 1.6659 | 1.7027 | 1.7 | 69.45 Neigh | 0.25338 | 0.26008 | 0.26833 | 1.2 | 10.84 Comm | 0.24458 | 0.30644 | 0.33939 | 6.6 | 12.77 Output | 0.0012605 | 0.0020466 | 0.0043511 | 2.9 | 0.09 Modify | 0.15009 | 0.15611 | 0.16933 | 2.0 | 6.51 Other | | 0.008278 | | | 0.35 Nlocal: 1000 ave 1014 max 988 min Histogram: 2 0 0 0 0 0 0 0 1 1 Loading Loading
examples/controller/log.5Oct16.controller.g++.1→examples/controller/log.27Nov18.controller.g++.1 +30 −23 Original line number Diff line number Diff line LAMMPS (5 Oct 2016) LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # 3d Lennard-Jones melt, thermostatted by fix controller units lj Loading @@ -12,6 +13,7 @@ Created orthogonal box = (0 0 0) to (16.796 16.796 16.796) 1 by 1 by 1 MPI processor grid create_atoms 1 box Created 4000 atoms Time spent = 0.00062418 secs mass 1 1.0 velocity all create 1.44 87287 loop geom Loading @@ -32,13 +34,18 @@ fix tstat all langevin v_tcontrol 0.5 0.5 2938940 thermo 50 run 500 Neighbor list info ... 1 neighbor list requests update every 20 steps, delay 0 steps, check no max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2.8 ghost atom cutoff = 2.8 binsize = 1.4 -> bins = 12 12 12 Memory usage per processor = 2.19271 Mbytes binsize = 1.4, bins = 12 12 12 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair lj/cut, perpetual attributes: half, newton on pair build: half/bin/atomonly/newton stencil: half/bin/3d/newton bin: standard Per MPI rank memory allocation (min/avg/max) = 3.221 | 3.221 | 3.221 Mbytes Step Temp E_pair E_mol TotEng Press 0 1.44 -6.7733681 0 -4.6139081 -5.0199732 50 0.61784238 -5.9328913 0 -5.0063594 -0.8309723 Loading @@ -51,20 +58,20 @@ Step Temp E_pair E_mol TotEng Press 400 0.49885979 -6.157314 0 -5.4092114 -2.1544075 450 0.50261633 -6.1458076 0 -5.3920716 -2.1080502 500 0.51198903 -6.1441158 0 -5.3763242 -2.0677941 Loop time of 1.51804 on 1 procs for 500 steps with 4000 atoms Loop time of 1.55006 on 1 procs for 500 steps with 4000 atoms Performance: 142288.277 tau/day, 329.371 timesteps/s 99.9% CPU use with 1 MPI tasks x no OpenMP threads Performance: 139349.249 tau/day, 322.568 timesteps/s 99.0% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 1.2152 | 1.2152 | 1.2152 | 0.0 | 80.05 Neigh | 0.16464 | 0.16464 | 0.16464 | 0.0 | 10.85 Comm | 0.022342 | 0.022342 | 0.022342 | 0.0 | 1.47 Output | 0.00020981 | 0.00020981 | 0.00020981 | 0.0 | 0.01 Modify | 0.10936 | 0.10936 | 0.10936 | 0.0 | 7.20 Other | | 0.006292 | | | 0.41 Pair | 1.2115 | 1.2115 | 1.2115 | 0.0 | 78.16 Neigh | 0.18784 | 0.18784 | 0.18784 | 0.0 | 12.12 Comm | 0.027217 | 0.027217 | 0.027217 | 0.0 | 1.76 Output | 0.00033712 | 0.00033712 | 0.00033712 | 0.0 | 0.02 Modify | 0.1171 | 0.1171 | 0.1171 | 0.0 | 7.55 Other | | 0.006078 | | | 0.39 Nlocal: 4000 ave 4000 max 4000 min Histogram: 1 0 0 0 0 0 0 0 0 0 Loading @@ -90,7 +97,7 @@ fix 10 all controller 100 1.0 0.5 0.0 0.0 c_thermo_t # run with controller run 2500 Memory usage per processor = 2.19271 Mbytes Per MPI rank memory allocation (min/avg/max) = 3.221 | 3.221 | 3.221 Mbytes Step Temp E_pair E_mol TotEng Press 500 0.51198903 -6.1441158 0 -5.3763242 -2.0677941 550 0.50342035 -6.1446822 0 -5.3897404 -2.0872641 Loading Loading @@ -143,20 +150,20 @@ Step Temp E_pair E_mol TotEng Press 2900 1.5287303 -4.8393493 0 -2.546827 5.3276564 2950 1.5175567 -4.8779763 0 -2.6022104 5.1592321 3000 1.5038518 -4.8714664 0 -2.6162526 5.1494048 Loop time of 7.82673 on 1 procs for 2500 steps with 4000 atoms Loop time of 7.9877 on 1 procs for 2500 steps with 4000 atoms Performance: 137988.733 tau/day, 319.418 timesteps/s 99.9% CPU use with 1 MPI tasks x no OpenMP threads Performance: 135207.915 tau/day, 312.981 timesteps/s 99.0% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 6.2774 | 6.2774 | 6.2774 | 0.0 | 80.21 Neigh | 0.85491 | 0.85491 | 0.85491 | 0.0 | 10.92 Comm | 0.11304 | 0.11304 | 0.11304 | 0.0 | 1.44 Output | 0.00090504 | 0.00090504 | 0.00090504 | 0.0 | 0.01 Modify | 0.55013 | 0.55013 | 0.55013 | 0.0 | 7.03 Other | | 0.0303 | | | 0.39 Pair | 6.2628 | 6.2628 | 6.2628 | 0.0 | 78.41 Neigh | 0.97669 | 0.97669 | 0.97669 | 0.0 | 12.23 Comm | 0.13389 | 0.13389 | 0.13389 | 0.0 | 1.68 Output | 0.0015631 | 0.0015631 | 0.0015631 | 0.0 | 0.02 Modify | 0.58344 | 0.58344 | 0.58344 | 0.0 | 7.30 Other | | 0.02927 | | | 0.37 Nlocal: 4000 ave 4000 max 4000 min Histogram: 1 0 0 0 0 0 0 0 0 0 Loading
examples/controller/log.5Oct16.controller.g++.4→examples/controller/log.27Nov18.controller.g++.4 +30 −23 Original line number Diff line number Diff line LAMMPS (5 Oct 2016) LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # 3d Lennard-Jones melt, thermostatted by fix controller units lj Loading @@ -12,6 +13,7 @@ Created orthogonal box = (0 0 0) to (16.796 16.796 16.796) 1 by 2 by 2 MPI processor grid create_atoms 1 box Created 4000 atoms Time spent = 0.000405788 secs mass 1 1.0 velocity all create 1.44 87287 loop geom Loading @@ -32,13 +34,18 @@ fix tstat all langevin v_tcontrol 0.5 0.5 2938940 thermo 50 run 500 Neighbor list info ... 1 neighbor list requests update every 20 steps, delay 0 steps, check no max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2.8 ghost atom cutoff = 2.8 binsize = 1.4 -> bins = 12 12 12 Memory usage per processor = 2.10344 Mbytes binsize = 1.4, bins = 12 12 12 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair lj/cut, perpetual attributes: half, newton on pair build: half/bin/atomonly/newton stencil: half/bin/3d/newton bin: standard Per MPI rank memory allocation (min/avg/max) = 2.705 | 2.705 | 2.705 Mbytes Step Temp E_pair E_mol TotEng Press 0 1.44 -6.7733681 0 -4.6139081 -5.0199732 50 0.61546984 -5.9273631 0 -5.0043892 -0.80234884 Loading @@ -51,20 +58,20 @@ Step Temp E_pair E_mol TotEng Press 400 0.50869337 -6.1435002 0 -5.3806509 -2.0654599 450 0.50821435 -6.1436659 0 -5.381535 -2.0660991 500 0.51057155 -6.138733 0 -5.3730671 -2.0305015 Loop time of 0.474689 on 4 procs for 500 steps with 4000 atoms Loop time of 0.469437 on 4 procs for 500 steps with 4000 atoms Performance: 455034.992 tau/day, 1053.322 timesteps/s 99.7% CPU use with 4 MPI tasks x no OpenMP threads Performance: 460125.812 tau/day, 1065.106 timesteps/s 97.7% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 0.31692 | 0.32816 | 0.35039 | 2.3 | 69.13 Neigh | 0.042872 | 0.044288 | 0.046693 | 0.7 | 9.33 Comm | 0.043676 | 0.070658 | 0.084897 | 6.0 | 14.89 Output | 0.00025439 | 0.0002867 | 0.00030446 | 0.1 | 0.06 Modify | 0.02728 | 0.028604 | 0.030571 | 0.8 | 6.03 Other | | 0.002697 | | | 0.57 Pair | 0.31917 | 0.32582 | 0.32979 | 0.7 | 69.41 Neigh | 0.048915 | 0.051251 | 0.053828 | 0.8 | 10.92 Comm | 0.054731 | 0.059151 | 0.069726 | 2.5 | 12.60 Output | 0.00028014 | 0.00033808 | 0.00048709 | 0.0 | 0.07 Modify | 0.02967 | 0.031206 | 0.033305 | 0.8 | 6.65 Other | | 0.00167 | | | 0.36 Nlocal: 1000 ave 1027 max 969 min Histogram: 1 0 0 1 0 0 0 0 1 1 Loading @@ -90,7 +97,7 @@ fix 10 all controller 100 1.0 0.5 0.0 0.0 c_thermo_t # run with controller run 2500 Memory usage per processor = 2.10344 Mbytes Per MPI rank memory allocation (min/avg/max) = 2.705 | 2.705 | 2.705 Mbytes Step Temp E_pair E_mol TotEng Press 500 0.51057155 -6.138733 0 -5.3730671 -2.0305015 550 0.50420106 -6.1501845 0 -5.394072 -2.095219 Loading Loading @@ -143,20 +150,20 @@ Step Temp E_pair E_mol TotEng Press 2900 1.4994026 -4.8400966 0 -2.591555 5.3231654 2950 1.5057915 -4.8842358 0 -2.6261131 5.1645778 3000 1.5038806 -4.8661399 0 -2.610883 5.2228747 Loop time of 2.33203 on 4 procs for 2500 steps with 4000 atoms Loop time of 2.39888 on 4 procs for 2500 steps with 4000 atoms Performance: 463116.726 tau/day, 1072.029 timesteps/s 99.9% CPU use with 4 MPI tasks x no OpenMP threads Performance: 450209.527 tau/day, 1042.152 timesteps/s 97.4% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- Pair | 1.6173 | 1.6621 | 1.7135 | 3.2 | 71.27 Neigh | 0.2201 | 0.22394 | 0.23011 | 0.9 | 9.60 Comm | 0.22619 | 0.29012 | 0.33801 | 8.8 | 12.44 Output | 0.001302 | 0.0013426 | 0.0013707 | 0.1 | 0.06 Modify | 0.13805 | 0.14195 | 0.14664 | 0.9 | 6.09 Other | | 0.01257 | | | 0.54 Pair | 1.6469 | 1.6659 | 1.7027 | 1.7 | 69.45 Neigh | 0.25338 | 0.26008 | 0.26833 | 1.2 | 10.84 Comm | 0.24458 | 0.30644 | 0.33939 | 6.6 | 12.77 Output | 0.0012605 | 0.0020466 | 0.0043511 | 2.9 | 0.09 Modify | 0.15009 | 0.15611 | 0.16933 | 2.0 | 6.51 Other | | 0.008278 | | | 0.35 Nlocal: 1000 ave 1014 max 988 min Histogram: 2 0 0 0 0 0 0 0 1 1 Loading
