diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.16 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.16 deleted file mode 100644 index 20d3faaf7f..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.16 +++ /dev/null @@ -1,92 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task - -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve -kspace_style scafacos ewald 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver ewald ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.313 | 3.501 | 3.689 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49647271 0 0.49647271 0 0 - 10 300 0.051135063 0.014582562 0.44286522 0.02180093 0.46466616 0 0.0043601861 - 20 300 0.10210872 0.058693359 0.37869251 0.087746571 0.46643909 0 0.017549314 - 30 300 0.15278506 0.13468789 0.26730177 0.2013584 0.46866017 0 0.040271679 - 40 300 0.19430375 0.50949535 0.083356437 0.76169555 0.84505198 0 0.15233911 - 50 300 0.23220921 1.1731116 -0.055261984 1.7538018 1.6985399 0 0.35076037 - 60 300 0.27002859 1.3589639 -0.33351524 2.031651 1.6981358 0 0.4063302 - 70 300 0.30781388 1.6482648 -0.76570045 2.4641559 1.6984554 0 0.49283118 - 80 300 0.34566283 2.8640899 -2.4038488 4.2818144 1.8779656 0 0.85636288 - 90 300 0.38424087 93.168442 -2.5911448 139.28682 136.69568 0 27.857364 - 100 300 0.42331123 94.146897 -1.3480439 140.74961 139.40157 0 28.149922 -Loop time of 0.423331 on 16 procs for 100 steps with 300 atoms - -Performance: 102047.913 tau/day, 236.222 timesteps/s -99.2% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 2.5988e-05 | 3.6508e-05 | 5.5075e-05 | 0.0 | 0.01 -Kspace | 0.41852 | 0.41925 | 0.41976 | 0.1 | 99.04 -Neigh | 0.00023413 | 0.00056887 | 0.0012875 | 0.0 | 0.13 -Comm | 0.0019519 | 0.0022772 | 0.0027158 | 0.5 | 0.54 -Output | 0.00028276 | 0.00030752 | 0.0003624 | 0.0 | 0.07 -Modify | 8.3685e-05 | 0.0001286 | 0.00018764 | 0.0 | 0.03 -Other | | 0.000758 | | | 0.18 - -Nlocal: 18.75 ave 39 max 6 min -Histogram: 6 1 1 0 1 2 2 1 1 1 -Nghost: 122.812 ave 195 max 63 min -Histogram: 8 0 0 0 0 0 0 1 3 4 -Neighs: 160.625 ave 598 max 13 min -Histogram: 8 2 1 1 1 0 0 2 0 1 - -Total # of neighbors = 2570 -Ave neighs/atom = 8.56667 -Neighbor list builds = 23 -Dangerous builds = 16 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.8 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.8 deleted file mode 100644 index d26138522a..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.ewald.8 +++ /dev/null @@ -1,92 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task - -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve -kspace_style scafacos ewald 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver ewald ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.317 | 3.317 | 3.317 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49647271 0 0.49647271 0 0 - 10 300 0.057411432 0.014718629 0.45088339 0.02200435 0.47288774 0 0.00440087 - 20 300 0.11482716 0.05922597 0.38470912 0.088542825 0.47325194 0 0.017708565 - 30 300 0.17278481 0.13587829 0.27058048 0.20313804 0.47371852 0 0.040627608 - 40 300 0.23021507 0.51353118 0.088432648 0.76772911 0.85616176 0 0.15354582 - 50 300 0.28812647 1.1760001 -0.058088247 1.7581201 1.7000319 0 0.35162403 - 60 300 0.34651113 1.3627885 -0.33736672 2.0373688 1.7000021 0 0.40747376 - 70 300 0.40509939 1.6529365 -0.77082139 2.4711401 1.7003187 0 0.49422802 - 80 300 0.46342874 2.9569837 -2.4624654 4.4206907 1.9582253 0 0.88413814 - 90 300 0.52329254 81.642726 -2.5370215 122.05588 119.51885 0 24.411175 - 100 300 0.58335209 85.047974 -1.128107 127.14672 126.01861 0 25.429344 -Loop time of 0.583369 on 8 procs for 100 steps with 300 atoms - -Performance: 74052.598 tau/day, 171.418 timesteps/s -99.7% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 4.0531e-05 | 4.6492e-05 | 4.8876e-05 | 0.0 | 0.01 -Kspace | 0.57805 | 0.5785 | 0.57893 | 0.0 | 99.17 -Neigh | 0.00062275 | 0.00091892 | 0.0013313 | 0.0 | 0.16 -Comm | 0.002604 | 0.0028289 | 0.0031538 | 0.3 | 0.48 -Output | 0.0002265 | 0.0002434 | 0.00029039 | 0.0 | 0.04 -Modify | 0.00016117 | 0.00017747 | 0.00019884 | 0.0 | 0.03 -Other | | 0.00065 | | | 0.11 - -Nlocal: 37.5 ave 46 max 31 min -Histogram: 2 0 0 2 1 0 2 0 0 1 -Nghost: 203.875 ave 212 max 192 min -Histogram: 1 0 1 0 0 2 1 0 0 3 -Neighs: 321.625 ave 599 max 112 min -Histogram: 1 2 0 1 1 0 1 1 0 1 - -Total # of neighbors = 2573 -Ave neighs/atom = 8.57667 -Neighbor list builds = 23 -Dangerous builds = 16 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.16 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.16 deleted file mode 100644 index c9c1e0d155..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.16 +++ /dev/null @@ -1,99 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -kspace_style scafacos fmm 1.0e-3 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.313 | 3.501 | 3.689 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 - 10 300 0.023007393 0.015455559 0.47335833 0.02310606 0.49646439 0 0.020399823 - 20 300 0.045746088 0.06229069 0.40334177 0.093124582 0.49646635 0 0.032069642 - 30 300 0.068123341 0.14310163 0.28254277 0.21393694 0.49647971 0 0.05220548 - 40 300 0.090359211 0.52929788 0.089669015 0.79130033 0.88096934 0 0.16124903 - 50 300 0.11304998 1.1963022 -0.082792461 1.7884718 1.7056794 0 0.35493462 - 60 300 0.13585806 1.3928167 -0.37659239 2.082261 1.7056686 0 0.40389911 - 70 300 0.15867376 1.7069009 -0.84571914 2.5518169 1.7060978 0 0.48217274 - 80 300 0.18324137 15.358343 -3.368063 22.960722 19.592659 0 4.4798757 - 90 300 0.20960689 42.280432 -2.1623864 63.209247 61.04686 0 12.56977 - 100 300 0.23539281 41.48079 -0.89904529 62.013782 61.114736 0 12.372788 -Loop time of 0.235411 on 16 procs for 100 steps with 300 atoms - -Performance: 183509.107 tau/day, 424.790 timesteps/s -97.9% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 3.2425e-05 | 4.4718e-05 | 6.1274e-05 | 0.0 | 0.02 -Kspace | 0.23097 | 0.23143 | 0.2318 | 0.1 | 98.31 -Neigh | 0.00015116 | 0.00035347 | 0.00075746 | 0.0 | 0.15 -Comm | 0.0020316 | 0.002282 | 0.0025339 | 0.3 | 0.97 -Output | 0.00034404 | 0.00037053 | 0.00042701 | 0.0 | 0.16 -Modify | 9.3937e-05 | 0.00014532 | 0.00018811 | 0.0 | 0.06 -Other | | 0.0007878 | | | 0.33 - -Nlocal: 18.75 ave 36 max 6 min -Histogram: 4 3 1 0 0 1 2 1 2 2 -Nghost: 127 ave 196 max 71 min -Histogram: 8 0 0 0 0 0 0 1 6 1 -Neighs: 153.688 ave 491 max 10 min -Histogram: 8 1 1 1 1 1 0 0 0 3 - -Total # of neighbors = 2459 -Ave neighs/atom = 8.19667 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.2 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.2 deleted file mode 100644 index 1a9bc77146..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.2 +++ /dev/null @@ -1,99 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -kspace_style scafacos fmm 1.0e-3 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.354 | 3.354 | 3.355 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 - 10 300 0.038181543 0.015455559 0.47335833 0.02310606 0.49646439 0 0.020399823 - 20 300 0.076276302 0.06229069 0.40334177 0.093124582 0.49646635 0 0.032069642 - 30 300 0.11437607 0.14310163 0.28254277 0.21393694 0.49647971 0 0.05220548 - 40 300 0.15244293 0.52929788 0.089669015 0.79130033 0.88096934 0 0.16124903 - 50 300 0.19081283 1.1963022 -0.082792461 1.7884718 1.7056794 0 0.35493462 - 60 300 0.22923493 1.3928167 -0.37659239 2.082261 1.7056686 0 0.40389911 - 70 300 0.26754427 1.7069009 -0.84571914 2.5518169 1.7060978 0 0.48217274 - 80 300 0.30721259 15.358343 -3.368063 22.960722 19.592659 0 4.4798757 - 90 300 0.34865618 42.280432 -2.1623864 63.209247 61.04686 0 12.56977 - 100 300 0.39100981 41.48079 -0.89904529 62.013782 61.114736 0 12.372788 -Loop time of 0.391022 on 2 procs for 100 steps with 300 atoms - -Performance: 110479.760 tau/day, 255.740 timesteps/s -99.6% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 8.0109e-05 | 8.1539e-05 | 8.297e-05 | 0.0 | 0.02 -Kspace | 0.38534 | 0.38582 | 0.3863 | 0.1 | 98.67 -Neigh | 0.0014851 | 0.0019699 | 0.0024548 | 1.1 | 0.50 -Comm | 0.0019314 | 0.0020101 | 0.0020888 | 0.2 | 0.51 -Output | 0.00014496 | 0.00017297 | 0.00020099 | 0.0 | 0.04 -Modify | 0.0005033 | 0.00052273 | 0.00054216 | 0.0 | 0.13 -Other | | 0.0004461 | | | 0.11 - -Nlocal: 150 ave 159 max 141 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 392 ave 395 max 389 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 1229.5 ave 1773 max 686 min -Histogram: 1 0 0 0 0 0 0 0 0 1 - -Total # of neighbors = 2459 -Ave neighs/atom = 8.19667 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.4 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.4 deleted file mode 100644 index eae3f2b840..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.4 +++ /dev/null @@ -1,99 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 1 by 2 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -kspace_style scafacos fmm 1.0e-3 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.333 | 3.333 | 3.333 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 - 10 300 0.029414415 0.015455559 0.47335833 0.02310606 0.49646439 0 0.020399823 - 20 300 0.058616877 0.06229069 0.40334177 0.093124582 0.49646635 0 0.032069642 - 30 300 0.087769508 0.14310163 0.28254277 0.21393694 0.49647971 0 0.05220548 - 40 300 0.1168611 0.52929788 0.089669015 0.79130033 0.88096934 0 0.16124903 - 50 300 0.14482284 1.1963022 -0.082792461 1.7884718 1.7056794 0 0.35493462 - 60 300 0.17198443 1.3928167 -0.37659239 2.082261 1.7056686 0 0.40389911 - 70 300 0.19868851 1.7069009 -0.84571914 2.5518169 1.7060978 0 0.48217274 - 80 300 0.22835517 15.358343 -3.368063 22.960722 19.592659 0 4.4798757 - 90 300 0.26023602 42.280432 -2.1623864 63.209247 61.04686 0 12.56977 - 100 300 0.29043221 41.48079 -0.89904529 62.013782 61.114736 0 12.372788 -Loop time of 0.290448 on 4 procs for 100 steps with 300 atoms - -Performance: 148735.741 tau/day, 344.296 timesteps/s -99.0% CPU use with 4 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 5.9605e-05 | 6.187e-05 | 6.4135e-05 | 0.0 | 0.02 -Kspace | 0.28551 | 0.28584 | 0.28604 | 0.0 | 98.41 -Neigh | 0.00077796 | 0.0010615 | 0.0013225 | 0.7 | 0.37 -Comm | 0.002372 | 0.0024325 | 0.002497 | 0.1 | 0.84 -Output | 0.00025368 | 0.0002659 | 0.00029516 | 0.0 | 0.09 -Modify | 0.00030279 | 0.00031865 | 0.00033021 | 0.0 | 0.11 -Other | | 0.0004706 | | | 0.16 - -Nlocal: 75 ave 81 max 70 min -Histogram: 2 0 0 0 0 0 0 1 0 1 -Nghost: 282.5 ave 290 max 274 min -Histogram: 1 0 0 1 0 0 0 0 1 1 -Neighs: 614.75 ave 981 max 285 min -Histogram: 1 1 0 0 0 0 0 1 0 1 - -Total # of neighbors = 2459 -Ave neighs/atom = 8.19667 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.8 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.8 deleted file mode 100644 index feb7e2a5a6..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.8 +++ /dev/null @@ -1,99 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -kspace_style scafacos fmm 1.0e-3 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.317 | 3.317 | 3.317 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 - 10 300 0.026465416 0.015455559 0.47335833 0.02310606 0.49646439 0 0.020399823 - 20 300 0.057377338 0.06229069 0.40334177 0.093124582 0.49646635 0 0.032069642 - 30 300 0.088356495 0.14310163 0.28254277 0.21393694 0.49647971 0 0.05220548 - 40 300 0.11900806 0.52929788 0.089669015 0.79130033 0.88096934 0 0.16124903 - 50 300 0.15157914 1.1963022 -0.082792461 1.7884718 1.7056794 0 0.35493462 - 60 300 0.18608141 1.3928167 -0.37659239 2.082261 1.7056686 0 0.40389911 - 70 300 0.21956491 1.7069009 -0.84571914 2.5518169 1.7060978 0 0.48217274 - 80 300 0.24269128 15.358343 -3.368063 22.960722 19.592659 0 4.4798757 - 90 300 0.26847005 42.280432 -2.1623864 63.209247 61.04686 0 12.56977 - 100 300 0.29283834 41.48079 -0.89904529 62.013782 61.114736 0 12.372788 -Loop time of 0.292855 on 8 procs for 100 steps with 300 atoms - -Performance: 147513.337 tau/day, 341.466 timesteps/s -98.4% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 4.7207e-05 | 5.5045e-05 | 6.9618e-05 | 0.0 | 0.02 -Kspace | 0.28739 | 0.28773 | 0.2881 | 0.0 | 98.25 -Neigh | 0.00040698 | 0.00060901 | 0.00082922 | 0.0 | 0.21 -Comm | 0.0029533 | 0.0031788 | 0.0034056 | 0.3 | 1.09 -Output | 0.00029063 | 0.00030866 | 0.00035119 | 0.0 | 0.11 -Modify | 0.00018978 | 0.00022188 | 0.00026703 | 0.0 | 0.08 -Other | | 0.0007486 | | | 0.26 - -Nlocal: 37.5 ave 45 max 31 min -Histogram: 1 1 1 1 1 0 1 0 1 1 -Nghost: 200 ave 209 max 189 min -Histogram: 1 0 0 0 1 4 0 0 0 2 -Neighs: 307.375 ave 514 max 115 min -Histogram: 2 1 0 1 1 0 0 0 1 2 - -Total # of neighbors = 2459 -Ave neighs/atom = 8.19667 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.16 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.16 deleted file mode 100644 index d6e7cbea37..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.16 +++ /dev/null @@ -1,92 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task - -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.313 | 3.501 | 3.689 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49683273 0 0.49683273 0 0.016561091 - 10 300 0.015678644 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 - 20 300 0.031283855 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 - 30 300 0.046878099 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 - 40 300 0.062416077 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 - 50 300 0.078029871 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 - 60 300 0.093806505 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 - 70 300 0.1096344 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 - 80 300 0.12532592 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 - 90 300 0.14175463 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 - 100 300 0.15838337 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 -Loop time of 0.158406 on 16 procs for 100 steps with 300 atoms - -Performance: 272716.448 tau/day, 631.288 timesteps/s -99.4% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 2.718e-05 | 3.7491e-05 | 5.6744e-05 | 0.0 | 0.02 -Kspace | 0.15435 | 0.15482 | 0.15516 | 0.1 | 97.74 -Neigh | 0.00014806 | 0.0003508 | 0.00074744 | 0.0 | 0.22 -Comm | 0.0016866 | 0.0019967 | 0.0023787 | 0.5 | 1.26 -Output | 0.00027871 | 0.00033027 | 0.00038028 | 0.0 | 0.21 -Modify | 8.0347e-05 | 0.00011933 | 0.00016522 | 0.0 | 0.08 -Other | | 0.0007506 | | | 0.47 - -Nlocal: 18.75 ave 33 max 6 min -Histogram: 2 6 0 0 0 0 2 1 2 3 -Nghost: 128.875 ave 198 max 71 min -Histogram: 7 1 0 0 0 0 0 1 5 2 -Neighs: 153.812 ave 490 max 14 min -Histogram: 8 0 3 0 1 1 0 0 1 2 - -Total # of neighbors = 2461 -Ave neighs/atom = 8.20333 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.2 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.2 deleted file mode 100644 index fb863797f3..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.2 +++ /dev/null @@ -1,92 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task - -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.354 | 3.354 | 3.355 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49683273 0 0.49683273 0 0.016561091 - 10 300 0.044083834 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 - 20 300 0.088379145 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 - 30 300 0.13264704 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 - 40 300 0.17687225 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 - 50 300 0.22116137 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 - 60 300 0.26515126 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 - 70 300 0.30891085 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 - 80 300 0.35292292 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 - 90 300 0.39845228 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 - 100 300 0.44492316 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 -Loop time of 0.444937 on 2 procs for 100 steps with 300 atoms - -Performance: 97092.373 tau/day, 224.751 timesteps/s -100.0% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 7.7248e-05 | 7.844e-05 | 7.9632e-05 | 0.0 | 0.02 -Kspace | 0.43932 | 0.43979 | 0.44026 | 0.1 | 98.84 -Neigh | 0.0014915 | 0.0019662 | 0.0024409 | 1.1 | 0.44 -Comm | 0.0019331 | 0.0019941 | 0.0020552 | 0.1 | 0.45 -Output | 0.00013781 | 0.00016308 | 0.00018835 | 0.0 | 0.04 -Modify | 0.00050378 | 0.00050449 | 0.00050521 | 0.0 | 0.11 -Other | | 0.0004425 | | | 0.10 - -Nlocal: 150 ave 157 max 143 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 399 ave 402 max 396 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 1230.5 ave 1756 max 705 min -Histogram: 1 0 0 0 0 0 0 0 0 1 - -Total # of neighbors = 2461 -Ave neighs/atom = 8.20333 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.8 b/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.8 deleted file mode 100644 index a6f9228673..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.8 +++ /dev/null @@ -1,92 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task - -units lj -atom_style charge - -read_data data.cloud_wall - orthogonal box = (0 0 0) to (10 10 10) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 300 atoms - -velocity all set 0.0 0.0 0.0 mom no - -pair_style zero 1.0 -pair_coeff * * - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 - -thermo_style custom step atoms cpu temp pe ke etotal ecoul press - -run_style verlet - -#dump simple all custom 1000 id x y z vx vy vz -#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass -#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass -#dump_modify dmpvtk pad 7 - -thermo 10 -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 10 10 10 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.317 | 3.317 | 3.317 Mbytes -Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press - 0 300 0 0 0.49683273 0 0.49683273 0 0.016561091 - 10 300 0.01961565 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 - 20 300 0.039346695 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 - 30 300 0.059037447 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 - 40 300 0.078732729 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 - 50 300 0.098586798 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 - 60 300 0.11857247 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 - 70 300 0.1385541 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 - 80 300 0.15850091 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 - 90 300 0.17892075 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 - 100 300 0.19964767 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 -Loop time of 0.199664 on 8 procs for 100 steps with 300 atoms - -Performance: 216363.074 tau/day, 500.840 timesteps/s -99.4% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 4.5061e-05 | 4.7535e-05 | 5.3167e-05 | 0.0 | 0.02 -Kspace | 0.19551 | 0.19584 | 0.19611 | 0.0 | 98.08 -Neigh | 0.00041366 | 0.00060952 | 0.00082064 | 0.0 | 0.31 -Comm | 0.0021496 | 0.0022282 | 0.0024025 | 0.2 | 1.12 -Output | 0.0002346 | 0.00024167 | 0.00027847 | 0.0 | 0.12 -Modify | 0.00016665 | 0.00017652 | 0.0001924 | 0.0 | 0.09 -Other | | 0.0005245 | | | 0.26 - -Nlocal: 37.5 ave 42 max 33 min -Histogram: 2 1 0 1 0 0 1 0 1 2 -Nghost: 202.25 ave 212 max 194 min -Histogram: 1 0 2 1 0 2 0 1 0 1 -Neighs: 307.625 ave 505 max 129 min -Histogram: 3 0 0 1 1 0 0 0 1 2 - -Total # of neighbors = 2461 -Ave neighs/atom = 8.20333 -Neighbor list builds = 15 -Dangerous builds = 0 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.16 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.16 deleted file mode 100644 index 2fc46da3cd..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.16 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 4 MPI processor grid - 4096 atoms - Time spent = 0.000462294 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos ewald 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver ewald ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.501 | 3.501 | 3.501 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475938 0 0.50185691 -nan - 10 1.500011 -1.747529 0 0.50193816 -nan - 20 1.5000023 -1.7475152 0 0.50193898 -nan - 30 1.4999308 -1.747404 0 0.50194285 -nan - 40 1.4997722 -1.7471622 0 0.50194686 -nan - 50 1.4995835 -1.746878 0 0.50194808 -nan - 60 1.4996054 -1.7469114 0 0.50194749 -nan - 70 1.5004341 -1.7481558 0 0.50194592 -nan - 80 1.5033218 -1.7524875 0 0.50194458 -nan - 90 1.5108306 -1.7637462 0 0.50194636 -nan - 100 1.5292479 -1.7913449 0 0.50196695 -nan -Loop time of 80.2777 on 16 procs for 100 steps with 4096 atoms - -Performance: 538.132 tau/day, 1.246 timesteps/s -99.8% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0003705 | 0.00039807 | 0.00048542 | 0.0 | 0.00 -Kspace | 80.262 | 80.263 | 80.264 | 0.0 | 99.98 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.010191 | 0.011419 | 0.012416 | 0.6 | 0.01 -Output | 0.00028253 | 0.00033158 | 0.0004065 | 0.0 | 0.00 -Modify | 0.00082541 | 0.0008464 | 0.00087833 | 0.0 | 0.00 -Other | | 0.001511 | | | 0.00 - -Nlocal: 256 ave 256 max 256 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Nghost: 2816 ave 2816 max 2816 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Neighs: 32768 ave 32768 max 32768 min -Histogram: 16 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:01:22 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.2 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.2 deleted file mode 100644 index b6bf41de24..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.2 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 1 by 1 by 2 MPI processor grid - 4096 atoms - Time spent = 0.000344753 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos ewald 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver ewald ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.574 | 4.574 | 4.574 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475938 0 0.50185691 11.99707 - 10 1.500011 -1.747529 0 0.50193816 11.997158 - 20 1.5000023 -1.7475152 0 0.50193898 11.997089 - 30 1.4999308 -1.747404 0 0.50194285 11.996517 - 40 1.4997722 -1.7471622 0 0.50194686 11.995248 - 50 1.4995835 -1.746878 0 0.50194808 11.993739 - 60 1.4996054 -1.7469114 0 0.50194749 11.993914 - 70 1.5004341 -1.7481558 0 0.50194592 12.000543 - 80 1.5033218 -1.7524875 0 0.50194458 12.023638 - 90 1.5108306 -1.7637462 0 0.50194636 12.083694 - 100 1.5292479 -1.7913449 0 0.50196695 12.230996 -Loop time of 566.796 on 2 procs for 100 steps with 4096 atoms - -Performance: 76.218 tau/day, 0.176 timesteps/s -100.0% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0010231 | 0.0010413 | 0.0010595 | 0.1 | 0.00 -Kspace | 566.77 | 566.77 | 566.77 | 0.0 | 99.99 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.019707 | 0.01982 | 0.019932 | 0.1 | 0.00 -Output | 0.0002656 | 0.00029266 | 0.00031972 | 0.0 | 0.00 -Modify | 0.0055575 | 0.0055707 | 0.0055838 | 0.0 | 0.00 -Other | | 0.002497 | | | 0.00 - -Nlocal: 2048 ave 2048 max 2048 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Nghost: 7168 ave 7168 max 7168 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Neighs: 262144 ave 262144 max 262144 min -Histogram: 2 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:09:38 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.8 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.8 deleted file mode 100644 index 4a1a5b91ed..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.8 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 2 MPI processor grid - 4096 atoms - Time spent = 0.000232935 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos ewald 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver ewald ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.508 | 3.508 | 3.508 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475938 0 0.50185691 -nan - 10 1.500011 -1.747529 0 0.50193816 -nan - 20 1.5000023 -1.7475152 0 0.50193898 -nan - 30 1.4999308 -1.747404 0 0.50194285 -nan - 40 1.4997722 -1.7471622 0 0.50194686 -nan - 50 1.4995835 -1.746878 0 0.50194808 -nan - 60 1.4996054 -1.7469114 0 0.50194749 -nan - 70 1.5004341 -1.7481558 0 0.50194592 -nan - 80 1.5033218 -1.7524875 0 0.50194458 -nan - 90 1.5108306 -1.7637462 0 0.50194636 -nan - 100 1.5292479 -1.7913449 0 0.50196695 -nan -Loop time of 154.44 on 8 procs for 100 steps with 4096 atoms - -Performance: 279.720 tau/day, 0.647 timesteps/s -99.9% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00049257 | 0.00051311 | 0.00059295 | 0.0 | 0.00 -Kspace | 154.42 | 154.42 | 154.42 | 0.0 | 99.99 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.012076 | 0.013177 | 0.014308 | 0.8 | 0.01 -Output | 0.00025177 | 0.00028065 | 0.00030136 | 0.0 | 0.00 -Modify | 0.0015776 | 0.0017182 | 0.0018268 | 0.2 | 0.00 -Other | | 0.001309 | | | 0.00 - -Nlocal: 512 ave 512 max 512 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Nghost: 3584 ave 3584 max 3584 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Neighs: 65536 ave 65536 max 65536 min -Histogram: 8 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:02:38 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.16 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.16 deleted file mode 100644 index 4bd0c3d4f3..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.16 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 4 MPI processor grid - 4096 atoms - Time spent = 0.000400543 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos fmm 0.001 -kspace_modify scafacos tolerance energy - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.501 | 3.501 | 3.501 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475646 0 0.50188608 10.44368 - 10 1.5000016 -1.7475671 0 0.50188602 10.44369 - 20 1.4999827 -1.7475388 0 0.50188592 10.443564 - 30 1.4999016 -1.7474173 0 0.5018858 10.443023 - 40 1.4997356 -1.7471685 0 0.50188572 10.441917 - 50 1.4995414 -1.7468771 0 0.5018858 10.440623 - 60 1.4995587 -1.7469027 0 0.50188622 10.440739 - 70 1.5003837 -1.7481389 0 0.50188727 10.446238 - 80 1.5032684 -1.7524625 0 0.50188958 10.465466 - 90 1.5107749 -1.763714 0 0.50189507 10.515502 - 100 1.52919 -1.791306 0 0.50191895 10.638261 -Loop time of 4.23774 on 16 procs for 100 steps with 4096 atoms - -Performance: 10194.102 tau/day, 23.597 timesteps/s -99.6% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00038028 | 0.00040729 | 0.00046206 | 0.0 | 0.01 -Kspace | 4.2206 | 4.2211 | 4.2216 | 0.0 | 99.61 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.011439 | 0.012491 | 0.013172 | 0.4 | 0.29 -Output | 0.00042915 | 0.000489 | 0.00061274 | 0.0 | 0.01 -Modify | 0.00093102 | 0.00099151 | 0.0010982 | 0.0 | 0.02 -Other | | 0.002255 | | | 0.05 - -Nlocal: 256 ave 256 max 256 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Nghost: 2816 ave 2816 max 2816 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Neighs: 32768 ave 32768 max 32768 min -Histogram: 16 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:06 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.2 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.2 deleted file mode 100644 index 50dcc99393..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.2 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 1 by 1 by 2 MPI processor grid - 4096 atoms - Time spent = 0.0003407 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos fmm 0.001 -kspace_modify scafacos tolerance energy - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.574 | 4.574 | 4.574 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475646 0 0.50188608 10.44368 - 10 1.5000016 -1.7475671 0 0.50188602 10.44369 - 20 1.4999827 -1.7475388 0 0.50188592 10.443564 - 30 1.4999016 -1.7474173 0 0.5018858 10.443023 - 40 1.4997356 -1.7471685 0 0.50188572 10.441917 - 50 1.4995414 -1.7468771 0 0.5018858 10.440623 - 60 1.4995587 -1.7469027 0 0.50188622 10.440739 - 70 1.5003837 -1.7481389 0 0.50188727 10.446238 - 80 1.5032684 -1.7524625 0 0.50188958 10.465466 - 90 1.5107749 -1.763714 0 0.50189507 10.515502 - 100 1.52919 -1.791306 0 0.50191895 10.638261 -Loop time of 17.9401 on 2 procs for 100 steps with 4096 atoms - -Performance: 2408.014 tau/day, 5.574 timesteps/s -99.9% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0010042 | 0.0010235 | 0.0010428 | 0.1 | 0.01 -Kspace | 17.912 | 17.912 | 17.912 | 0.0 | 99.84 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.018252 | 0.018528 | 0.018804 | 0.2 | 0.10 -Output | 0.00034094 | 0.00035989 | 0.00037885 | 0.0 | 0.00 -Modify | 0.0055602 | 0.0056567 | 0.0057533 | 0.1 | 0.03 -Other | | 0.002716 | | | 0.02 - -Nlocal: 2048 ave 2048 max 2048 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Nghost: 7168 ave 7168 max 7168 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Neighs: 262144 ave 262144 max 262144 min -Histogram: 2 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:19 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.8 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.8 deleted file mode 100644 index 02a5528c59..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.8 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 2 MPI processor grid - 4096 atoms - Time spent = 0.000236988 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos fmm 0.001 -kspace_modify scafacos tolerance energy - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.508 | 3.508 | 3.508 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475646 0 0.50188608 10.44368 - 10 1.5000016 -1.7475671 0 0.50188602 10.44369 - 20 1.4999827 -1.7475388 0 0.50188592 10.443564 - 30 1.4999016 -1.7474173 0 0.5018858 10.443023 - 40 1.4997356 -1.7471685 0 0.50188572 10.441917 - 50 1.4995414 -1.7468771 0 0.5018858 10.440623 - 60 1.4995587 -1.7469027 0 0.50188622 10.440739 - 70 1.5003837 -1.7481389 0 0.50188727 10.446238 - 80 1.5032684 -1.7524625 0 0.50188958 10.465466 - 90 1.5107749 -1.763714 0 0.50189507 10.515502 - 100 1.52919 -1.791306 0 0.50191895 10.638261 -Loop time of 5.96037 on 8 procs for 100 steps with 4096 atoms - -Performance: 7247.876 tau/day, 16.777 timesteps/s -99.8% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00049591 | 0.0005368 | 0.00056005 | 0.0 | 0.01 -Kspace | 5.94 | 5.941 | 5.9419 | 0.0 | 99.68 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.013702 | 0.014631 | 0.015768 | 0.6 | 0.25 -Output | 0.00044751 | 0.00048846 | 0.00058961 | 0.0 | 0.01 -Modify | 0.0016675 | 0.0017205 | 0.0017893 | 0.1 | 0.03 -Other | | 0.001971 | | | 0.03 - -Nlocal: 512 ave 512 max 512 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Nghost: 3584 ave 3584 max 3584 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Neighs: 65536 ave 65536 max 65536 min -Histogram: 8 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:07 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.16 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.16 deleted file mode 100644 index 6e6e8f6e94..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.16 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 4 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 4 MPI processor grid - 4096 atoms - Time spent = 0.000361443 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.501 | 3.501 | 3.501 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7477245 0 0.50172614 10.443537 - 10 1.5000176 -1.7475898 0 0.50188725 10.443798 - 20 1.5000161 -1.7475262 0 0.50194874 10.443843 - 30 1.4999486 -1.7474019 0 0.50197176 10.443413 - 40 1.4997889 -1.7471525 0 0.50198161 10.442357 - 50 1.4995945 -1.7468614 0 0.50198122 10.441061 - 60 1.499609 -1.7468813 0 0.50198309 10.44116 - 70 1.5004314 -1.7481179 0 0.50197962 10.446638 - 80 1.5033149 -1.7524495 0 0.50197233 10.46585 - 90 1.5108219 -1.7637095 0 0.50197005 10.515883 - 100 1.529239 -1.7913105 0 0.501988 10.638649 -Loop time of 1.56685 on 16 procs for 100 steps with 4096 atoms - -Performance: 27571.239 tau/day, 63.822 timesteps/s -99.8% CPU use with 16 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00036407 | 0.00040755 | 0.00047517 | 0.0 | 0.03 -Kspace | 1.5521 | 1.553 | 1.5536 | 0.0 | 99.12 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.009537 | 0.010175 | 0.011894 | 0.6 | 0.65 -Output | 0.000319 | 0.00039139 | 0.00052881 | 0.0 | 0.02 -Modify | 0.00086999 | 0.00097834 | 0.0010362 | 0.0 | 0.06 -Other | | 0.001859 | | | 0.12 - -Nlocal: 256 ave 256 max 256 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Nghost: 2816 ave 2816 max 2816 min -Histogram: 16 0 0 0 0 0 0 0 0 0 -Neighs: 32768 ave 32768 max 32768 min -Histogram: 16 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.2 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.2 deleted file mode 100644 index 72a53c48ff..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.2 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 1 by 1 by 2 MPI processor grid - 4096 atoms - Time spent = 0.0003438 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.574 | 4.574 | 4.574 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7477245 0 0.50172614 10.443537 - 10 1.5000176 -1.7475898 0 0.50188725 10.443798 - 20 1.5000161 -1.7475262 0 0.50194874 10.443843 - 30 1.4999486 -1.7474019 0 0.50197176 10.443413 - 40 1.4997889 -1.7471525 0 0.50198161 10.442357 - 50 1.4995945 -1.7468614 0 0.50198122 10.441061 - 60 1.499609 -1.7468813 0 0.50198309 10.44116 - 70 1.5004314 -1.7481179 0 0.50197962 10.446638 - 80 1.5033149 -1.7524495 0 0.50197233 10.46585 - 90 1.5108219 -1.7637095 0 0.50197005 10.515883 - 100 1.529239 -1.7913105 0 0.501988 10.638649 -Loop time of 9.38943 on 2 procs for 100 steps with 4096 atoms - -Performance: 4600.920 tau/day, 10.650 timesteps/s -99.9% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0010064 | 0.0010065 | 0.0010066 | 0.0 | 0.01 -Kspace | 9.3602 | 9.3603 | 9.3604 | 0.0 | 99.69 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.019444 | 0.01968 | 0.019916 | 0.2 | 0.21 -Output | 0.00033355 | 0.00035357 | 0.0003736 | 0.0 | 0.00 -Modify | 0.0055819 | 0.0056176 | 0.0056534 | 0.0 | 0.06 -Other | | 0.002495 | | | 0.03 - -Nlocal: 2048 ave 2048 max 2048 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Nghost: 7168 ave 7168 max 7168 min -Histogram: 2 0 0 0 0 0 0 0 0 0 -Neighs: 262144 ave 262144 max 262144 min -Histogram: 2 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:11 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.8 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.8 deleted file mode 100644 index b5e889dfc1..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.8 +++ /dev/null @@ -1,102 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.NaCl - orthogonal box = (0 0 0) to (1 1 1) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 8 atoms - -replicate 8 8 8 - orthogonal box = (0 0 0) to (8 8 8) - 2 by 2 by 2 MPI processor grid - 4096 atoms - Time spent = 0.000324488 secs - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance field - -timestep 0.005 -thermo 10 - -run 100 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 8 8 8 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 3.508 | 3.508 | 3.508 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7477245 0 0.50172614 10.443537 - 10 1.5000176 -1.7475898 0 0.50188725 10.443798 - 20 1.5000161 -1.7475262 0 0.50194874 10.443843 - 30 1.4999486 -1.7474019 0 0.50197176 10.443413 - 40 1.4997889 -1.7471525 0 0.50198161 10.442357 - 50 1.4995945 -1.7468614 0 0.50198122 10.441061 - 60 1.499609 -1.7468813 0 0.50198309 10.44116 - 70 1.5004314 -1.7481179 0 0.50197962 10.446638 - 80 1.5033149 -1.7524495 0 0.50197233 10.46585 - 90 1.5108219 -1.7637095 0 0.50197005 10.515883 - 100 1.529239 -1.7913105 0 0.501988 10.638649 -Loop time of 2.88506 on 8 procs for 100 steps with 4096 atoms - -Performance: 14973.700 tau/day, 34.661 timesteps/s -99.6% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.000489 | 0.00051507 | 0.00052857 | 0.0 | 0.02 -Kspace | 2.8657 | 2.866 | 2.8664 | 0.0 | 99.34 -Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.014354 | 0.014851 | 0.015097 | 0.2 | 0.51 -Output | 0.00037169 | 0.00042769 | 0.00054169 | 0.0 | 0.01 -Modify | 0.0015774 | 0.0016578 | 0.0018044 | 0.2 | 0.06 -Other | | 0.001645 | | | 0.06 - -Nlocal: 512 ave 512 max 512 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Nghost: 3584 ave 3584 max 3584 min -Histogram: 8 0 0 0 0 0 0 0 0 0 -Neighs: 65536 ave 65536 max 65536 min -Histogram: 8 0 0 0 0 0 0 0 0 0 - -Total # of neighbors = 524288 -Ave neighs/atom = 128 -Neighbor list builds = 0 -Dangerous builds = 0 -Total wall time: 0:00:03 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p3m.2 b/examples/USER/scafacos/log.08Aug18.scafacos.g++.p3m.2 deleted file mode 100644 index e69de29bb2..0000000000 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.2 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.2 deleted file mode 100644 index 1ffab0ca6a..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.2 +++ /dev/null @@ -1,105 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos direct 0.001 - -timestep 0.005 -thermo 1 -run 20 -Setting up ScaFaCoS with solver direct ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 6.48 | 6.861 | 7.243 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777512 0 272.51604 0.17462195 - 5 286.36222 -4.382053 0 424.73173 0.26918926 - 6 481.42206 -4.3095567 0 717.1014 0.45274088 - 7 488.59167 -3.8685194 0 728.2861 0.45956866 - 8 497.85287 -3.0417966 0 742.99073 0.46838116 - 9 499.61615 -3.419003 0 745.2558 0.46983345 - 10 502.63684 -2.8360961 0 750.36521 0.47280809 - 11 504.4846 -2.7628105 0 753.20736 0.47462793 - 12 506.54485 -2.8460356 0 756.21142 0.47651441 - 13 508.27211 -2.730935 0 758.91482 0.47813752 - 14 510.57045 -2.6094877 0 762.48033 0.48031431 - 15 513.14798 -2.7150827 0 766.23717 0.48275229 - 16 515.78124 -2.3961811 0 770.50201 0.48526333 - 17 515.70265 -2.2982683 0 770.48215 0.48526617 - 18 515.7081 -2.1515983 0 770.63699 0.48530393 - 19 515.74906 -2.0581436 0 770.79182 0.48530977 - 20 515.70883 -1.8922577 0 770.89742 0.48527105 -Loop time of 0.284007 on 2 procs for 20 steps with 1000 atoms - -Performance: 30421.778 tau/day, 70.421 timesteps/s -99.1% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00022578 | 0.00022626 | 0.00022674 | 0.0 | 0.08 -Kspace | 0.18253 | 0.20503 | 0.22752 | 5.0 | 72.19 -Neigh | 0.05363 | 0.076239 | 0.098848 | 8.2 | 26.84 -Comm | 0.0014737 | 0.0016443 | 0.0018148 | 0.4 | 0.58 -Output | 0.000247 | 0.00032353 | 0.00040007 | 0.0 | 0.11 -Modify | 0.00029159 | 0.00029731 | 0.00030303 | 0.0 | 0.10 -Other | | 0.0002506 | | | 0.09 - -Nlocal: 500 ave 516 max 484 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 456.5 ave 475 max 438 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 123908 ave 172139 max 75678 min -Histogram: 1 0 0 0 0 0 0 0 0 1 - -Total # of neighbors = 247817 -Ave neighs/atom = 247.817 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.8 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.8 deleted file mode 100644 index e72ade73b5..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.8 +++ /dev/null @@ -1,105 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos direct 0.001 - -timestep 0.005 -thermo 1 -run 20 -Setting up ScaFaCoS with solver direct ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.164 | 4.26 | 4.546 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777512 0 272.51604 0.17462195 - 5 286.36222 -4.382053 0 424.73173 0.26918926 - 6 481.42206 -4.3095567 0 717.1014 0.45274088 - 7 488.59167 -3.8685194 0 728.2861 0.45956866 - 8 497.85287 -3.0417966 0 742.99073 0.46838116 - 9 499.61615 -3.419003 0 745.2558 0.46983345 - 10 502.63684 -2.8360961 0 750.36521 0.47280809 - 11 504.4846 -2.7628105 0 753.20736 0.47462793 - 12 506.54485 -2.8460356 0 756.21142 0.47651441 - 13 508.27211 -2.730935 0 758.91482 0.47813752 - 14 510.57045 -2.6094877 0 762.48033 0.48031431 - 15 513.14798 -2.7150827 0 766.23717 0.48275229 - 16 515.78124 -2.3961811 0 770.50201 0.48526333 - 17 515.70265 -2.2982683 0 770.48215 0.48526617 - 18 515.7081 -2.1515983 0 770.63699 0.48530393 - 19 515.74906 -2.0581436 0 770.79182 0.48530977 - 20 515.70883 -1.8922577 0 770.89742 0.48527105 -Loop time of 0.0883947 on 8 procs for 20 steps with 1000 atoms - -Performance: 97743.448 tau/day, 226.258 timesteps/s -99.2% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0002284 | 0.00024167 | 0.00029922 | 0.0 | 0.27 -Kspace | 0.055725 | 0.063153 | 0.071883 | 2.4 | 71.44 -Neigh | 0.012251 | 0.021348 | 0.029026 | 4.3 | 24.15 -Comm | 0.0025573 | 0.0029825 | 0.0034359 | 0.5 | 3.37 -Output | 0.00034451 | 0.00044149 | 0.00057721 | 0.0 | 0.50 -Modify | 7.8917e-05 | 8.437e-05 | 8.9407e-05 | 0.0 | 0.10 -Other | | 0.0001439 | | | 0.16 - -Nlocal: 125 ave 133 max 113 min -Histogram: 2 0 0 0 0 1 1 0 2 2 -Nghost: 773.625 ave 788 max 764 min -Histogram: 1 1 2 1 1 0 0 0 1 1 -Neighs: 30977.1 ave 50690 max 10447 min -Histogram: 1 1 1 0 1 1 0 0 2 1 - -Total # of neighbors = 247817 -Ave neighs/atom = 247.817 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.2 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.2 deleted file mode 100644 index e8e614004d..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.2 +++ /dev/null @@ -1,109 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos fmm 0.001 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 -thermo 1 - -run 20 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 6.48 | 6.861 | 7.243 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417141 0 1.6235786 0.0015676581 - 1 18.780412 -10.770009 0 17.372438 0.016719188 - 2 65.294131 -11.084501 0 86.758754 0.06035827 - 3 121.92555 -7.0612033 0 175.64423 0.1140457 - 4 185.71165 -5.8781334 0 272.41077 0.17455524 - 5 286.28339 -4.3800108 0 424.61565 0.26911306 - 6 481.28097 -4.3052012 0 716.89433 0.45262045 - 7 487.26022 -3.8672741 0 726.29216 0.45830216 - 8 493.65478 -3.0242687 0 736.71742 0.46443761 - 9 495.66203 -3.4336343 0 739.31592 0.46613014 - 10 498.41831 -2.8837072 0 743.99613 0.46887706 - 11 499.20944 -2.7724783 0 745.29287 0.46966875 - 12 500.97345 -2.8281484 0 747.88057 0.47126462 - 13 507.46412 -2.7752775 0 757.65971 0.47728761 - 14 525.35729 -2.5749814 0 784.67292 0.49422171 - 15 563.9578 -2.9982381 0 842.09253 0.53043696 - 16 645.47602 -2.5519203 0 964.69389 0.60730795 - 17 647.09276 -2.2568468 0 967.41166 0.60891914 - 18 647.12596 -2.2791003 0 967.43915 0.60900309 - 19 647.24862 -2.2495226 0 967.65253 0.60908339 - 20 647.51175 -2.0239179 0 968.27244 0.60932598 -Loop time of 0.701186 on 2 procs for 20 steps with 1000 atoms - -Performance: 12321.981 tau/day, 28.523 timesteps/s -99.7% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00022388 | 0.00022912 | 0.00023437 | 0.0 | 0.03 -Kspace | 0.60189 | 0.62405 | 0.64621 | 2.8 | 89.00 -Neigh | 0.051681 | 0.073973 | 0.096265 | 8.2 | 10.55 -Comm | 0.0016983 | 0.0018919 | 0.0020854 | 0.4 | 0.27 -Output | 0.00034356 | 0.00044572 | 0.00054789 | 0.0 | 0.06 -Modify | 0.00031281 | 0.0003171 | 0.00032139 | 0.0 | 0.05 -Other | | 0.0002786 | | | 0.04 - -Nlocal: 500 ave 509 max 491 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 455.5 ave 467 max 444 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 122171 ave 171834 max 72508 min -Histogram: 1 0 0 0 0 0 0 0 0 1 - -Total # of neighbors = 244342 -Ave neighs/atom = 244.342 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.8 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.8 deleted file mode 100644 index 22d1140813..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.8 +++ /dev/null @@ -1,109 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos fmm 0.001 -kspace_modify scafacos tolerance energy_rel -kspace_modify scafacos fmm_tuning 1 -ScaFaCoS setting fmm inhomogen tuning ... - -timestep 0.005 -thermo 1 - -run 20 -Setting up ScaFaCoS with solver fmm ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.164 | 4.26 | 4.546 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417141 0 1.6235786 0.0015676581 - 1 18.780412 -10.770009 0 17.372438 0.016719188 - 2 65.294131 -11.084501 0 86.758754 0.06035827 - 3 121.92555 -7.0612033 0 175.64423 0.1140457 - 4 185.71165 -5.8781334 0 272.41077 0.17455524 - 5 286.28339 -4.3800108 0 424.61565 0.26911306 - 6 481.28097 -4.3052012 0 716.89433 0.45262045 - 7 487.26022 -3.8672741 0 726.29216 0.45830216 - 8 493.65478 -3.0242687 0 736.71742 0.46443761 - 9 495.66203 -3.4336343 0 739.31592 0.46613014 - 10 498.41831 -2.8837072 0 743.99613 0.46887706 - 11 499.20944 -2.7724783 0 745.29287 0.46966875 - 12 500.97345 -2.8281484 0 747.88057 0.47126462 - 13 507.46412 -2.7752775 0 757.65971 0.47728761 - 14 525.35729 -2.5749814 0 784.67292 0.49422171 - 15 563.9578 -2.9982381 0 842.09253 0.53043696 - 16 645.47602 -2.5519203 0 964.69389 0.60730795 - 17 647.09276 -2.2568468 0 967.41166 0.60891914 - 18 647.12596 -2.2791003 0 967.43915 0.60900309 - 19 647.24862 -2.2495226 0 967.65253 0.60908339 - 20 647.51175 -2.0239179 0 968.27244 0.60932598 -Loop time of 0.569395 on 8 procs for 20 steps with 1000 atoms - -Performance: 15174.000 tau/day, 35.125 timesteps/s -99.3% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.00021982 | 0.00023353 | 0.0002408 | 0.0 | 0.04 -Kspace | 0.53679 | 0.54466 | 0.55292 | 0.8 | 95.66 -Neigh | 0.011844 | 0.02033 | 0.028357 | 4.2 | 3.57 -Comm | 0.0028894 | 0.0031579 | 0.0034704 | 0.4 | 0.55 -Output | 0.0005579 | 0.00067073 | 0.0008719 | 0.0 | 0.12 -Modify | 0.0001018 | 0.00011405 | 0.00012612 | 0.0 | 0.02 -Other | | 0.0002268 | | | 0.04 - -Nlocal: 125 ave 137 max 111 min -Histogram: 1 1 0 0 0 2 2 1 0 1 -Nghost: 768.875 ave 788 max 761 min -Histogram: 4 0 2 0 0 0 1 0 0 1 -Neighs: 30542.8 ave 48077 max 10011 min -Histogram: 1 1 1 0 1 1 0 0 0 3 - -Total # of neighbors = 244342 -Ave neighs/atom = 244.342 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.2 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.2 deleted file mode 100644 index bd7e7fee1f..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.2 +++ /dev/null @@ -1,107 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 1 by 1 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance potential - -timestep 0.005 -thermo 1 - -run 20 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 6.48 | 6.861 | 7.243 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777511 0 272.51603 0.17462194 - 5 286.36221 -4.3820531 0 424.73172 0.26918925 - 6 481.42203 -4.3095567 0 717.10136 0.45274086 - 7 488.59165 -3.8685193 0 728.28607 0.45956865 - 8 497.85288 -3.0417938 0 742.99075 0.46838117 - 9 499.61619 -3.4190063 0 745.25585 0.46983349 - 10 502.63691 -2.8360951 0 750.36531 0.47280815 - 11 504.4847 -2.7628089 0 753.20751 0.47462802 - 12 506.54494 -2.8460319 0 756.21157 0.4765145 - 13 508.2722 -2.7309328 0 758.91497 0.47813761 - 14 510.57053 -2.6094792 0 762.48045 0.48031438 - 15 513.14804 -2.7150819 0 766.23726 0.48275234 - 16 515.78127 -2.3961749 0 770.50206 0.48526336 - 17 515.70267 -2.2982581 0 770.48219 0.48526619 - 18 515.70813 -2.1516075 0 770.63702 0.48530395 - 19 515.74908 -2.0581483 0 770.79185 0.48530979 - 20 515.70881 -1.892235 0 770.89742 0.48527104 -Loop time of 0.701267 on 2 procs for 20 steps with 1000 atoms - -Performance: 12320.557 tau/day, 28.520 timesteps/s -99.6% CPU use with 2 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0002265 | 0.00022769 | 0.00022888 | 0.0 | 0.03 -Kspace | 0.60195 | 0.62374 | 0.64554 | 2.8 | 88.95 -Neigh | 0.05268 | 0.074592 | 0.096504 | 8.0 | 10.64 -Comm | 0.0015199 | 0.0016934 | 0.0018668 | 0.4 | 0.24 -Output | 0.00031519 | 0.00041544 | 0.0005157 | 0.0 | 0.06 -Modify | 0.00029492 | 0.00030565 | 0.00031638 | 0.0 | 0.04 -Other | | 0.000288 | | | 0.04 - -Nlocal: 500 ave 516 max 484 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 456.5 ave 475 max 438 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 123908 ave 172139 max 75678 min -Histogram: 1 0 0 0 0 0 0 0 0 1 - -Total # of neighbors = 247817 -Ave neighs/atom = 247.817 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.4 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.4 deleted file mode 100644 index 8a7e591f9a..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.4 +++ /dev/null @@ -1,107 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 1 by 2 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance potential - -timestep 0.005 -thermo 1 - -run 20 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.837 | 5.123 | 5.6 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777511 0 272.51603 0.17462194 - 5 286.36221 -4.3820531 0 424.73172 0.26918925 - 6 481.42203 -4.3095567 0 717.10136 0.45274086 - 7 488.59165 -3.8685193 0 728.28607 0.45956865 - 8 497.85288 -3.0417938 0 742.99075 0.46838117 - 9 499.61619 -3.4190063 0 745.25585 0.46983349 - 10 502.63691 -2.8360951 0 750.36531 0.47280815 - 11 504.4847 -2.7628089 0 753.20751 0.47462802 - 12 506.54494 -2.8460319 0 756.21157 0.4765145 - 13 508.2722 -2.7309328 0 758.91497 0.47813761 - 14 510.57053 -2.6094792 0 762.48045 0.48031438 - 15 513.14804 -2.7150819 0 766.23726 0.48275234 - 16 515.78127 -2.3961749 0 770.50206 0.48526336 - 17 515.70267 -2.2982581 0 770.48219 0.48526619 - 18 515.70813 -2.1516075 0 770.63702 0.48530395 - 19 515.74908 -2.0581483 0 770.79185 0.48530979 - 20 515.70881 -1.892235 0 770.89742 0.48527104 -Loop time of 0.427495 on 4 procs for 20 steps with 1000 atoms - -Performance: 20210.785 tau/day, 46.784 timesteps/s -99.7% CPU use with 4 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0002327 | 0.00023341 | 0.00023437 | 0.0 | 0.05 -Kspace | 0.36897 | 0.38411 | 0.39988 | 1.9 | 89.85 -Neigh | 0.023831 | 0.039796 | 0.055124 | 6.1 | 9.31 -Comm | 0.0022776 | 0.0025444 | 0.0028152 | 0.4 | 0.60 -Output | 0.00033784 | 0.0004344 | 0.00057077 | 0.0 | 0.10 -Modify | 0.00016117 | 0.00016713 | 0.00017095 | 0.0 | 0.04 -Other | | 0.0002093 | | | 0.05 - -Nlocal: 250 ave 259 max 238 min -Histogram: 1 0 0 1 0 0 0 0 0 2 -Nghost: 672.25 ave 683 max 663 min -Histogram: 2 0 0 0 0 0 0 0 1 1 -Neighs: 61954.2 ave 97157 max 25016 min -Histogram: 1 0 0 1 0 0 1 0 0 1 - -Total # of neighbors = 247817 -Ave neighs/atom = 247.817 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.8 b/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.8 deleted file mode 100644 index 13922c09ac..0000000000 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.8 +++ /dev/null @@ -1,107 +0,0 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) - using 1 OpenMP thread(s) per MPI task -# Point dipoles in a 2d box - -units lj -atom_style charge - -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) - 2 by 2 by 2 MPI processor grid - reading atoms ... - 1000 atoms -change_box all boundary f f f - -velocity all create 1.5 49893 - -neighbor 1.0 bin -neigh_modify delay 0 - -fix 1 all nve - -# LAMMPS computes pairwise and long-range Coulombics - -#pair_style coul/long 3.0 -#pair_coeff * * -#kspace_style pppm 1.0e-3 - -# Scafacos computes entire long-range Coulombics -# use dummy pair style to perform atom sorting - -pair_style zero 1.0 -pair_coeff * * - -#fix 2 all scafacos p3m tolerance field 0.001 - -kspace_style scafacos p2nfft 0.001 -kspace_modify scafacos tolerance potential - -timestep 0.005 -thermo 1 - -run 20 -Setting up ScaFaCoS with solver p2nfft ... -Neighbor list info ... - update every 1 steps, delay 0 steps, check yes - max neighbors/atom: 2000, page size: 100000 - master list distance cutoff = 2 - ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 - 1 neighbor lists, perpetual/occasional/extra = 1 0 0 - (1) pair zero, 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) = 4.164 | 4.26 | 4.546 Mbytes -Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777511 0 272.51603 0.17462194 - 5 286.36221 -4.3820531 0 424.73172 0.26918925 - 6 481.42203 -4.3095567 0 717.10136 0.45274086 - 7 488.59165 -3.8685193 0 728.28607 0.45956865 - 8 497.85288 -3.0417938 0 742.99075 0.46838117 - 9 499.61619 -3.4190063 0 745.25585 0.46983349 - 10 502.63691 -2.8360951 0 750.36531 0.47280815 - 11 504.4847 -2.7628089 0 753.20751 0.47462802 - 12 506.54494 -2.8460319 0 756.21157 0.4765145 - 13 508.2722 -2.7309328 0 758.91497 0.47813761 - 14 510.57053 -2.6094792 0 762.48045 0.48031438 - 15 513.14804 -2.7150819 0 766.23726 0.48275234 - 16 515.78127 -2.3961749 0 770.50206 0.48526336 - 17 515.70267 -2.2982581 0 770.48219 0.48526619 - 18 515.70813 -2.1516075 0 770.63702 0.48530395 - 19 515.74908 -2.0581483 0 770.79185 0.48530979 - 20 515.70881 -1.892235 0 770.89742 0.48527104 -Loop time of 0.242145 on 8 procs for 20 steps with 1000 atoms - -Performance: 35681.038 tau/day, 82.595 timesteps/s -99.2% CPU use with 8 MPI tasks x 1 OpenMP threads - -MPI task timing breakdown: -Section | min time | avg time | max time |%varavg| %total ---------------------------------------------------------------- -Pair | 0.0002315 | 0.00023672 | 0.00024652 | 0.0 | 0.10 -Kspace | 0.20915 | 0.21666 | 0.22564 | 1.3 | 89.48 -Neigh | 0.012218 | 0.021341 | 0.029026 | 4.3 | 8.81 -Comm | 0.0028954 | 0.0031248 | 0.0033553 | 0.3 | 1.29 -Output | 0.00039291 | 0.00049406 | 0.00066066 | 0.0 | 0.20 -Modify | 8.7976e-05 | 9.2953e-05 | 9.7752e-05 | 0.0 | 0.04 -Other | | 0.0001938 | | | 0.08 - -Nlocal: 125 ave 133 max 113 min -Histogram: 2 0 0 0 0 1 1 0 2 2 -Nghost: 773.625 ave 788 max 764 min -Histogram: 1 1 2 1 1 0 0 0 1 1 -Neighs: 30977.1 ave 50690 max 10447 min -Histogram: 1 1 1 0 1 1 0 0 2 1 - -Total # of neighbors = 247817 -Ave neighs/atom = 247.817 -Neighbor list builds = 19 -Dangerous builds = 18 -Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.1 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.1 new file mode 100644 index 0000000000..e0b10de95e --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.1 @@ -0,0 +1,92 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task + +units lj +atom_style charge + +read_data data.cloud_wall + orthogonal box = (0 0 0) to (10 10 10) + 1 by 1 by 1 MPI processor grid + reading atoms ... + 300 atoms + +velocity all set 0.0 0.0 0.0 mom no + +pair_style zero 1.0 +pair_coeff * * + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve +kspace_style scafacos ewald 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 + +thermo_style custom step atoms cpu temp pe ke etotal ecoul press + +run_style verlet + +#dump simple all custom 1000 id x y z vx vy vz +#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass +#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass +#dump_modify dmpvtk pad 7 + +thermo 10 +run 100 +Setting up ScaFaCoS with solver ewald ... +WARNING: Virial computation for Ewald not available (src/USER-SCAFACOS/scafacos.cpp:107) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 10 10 10 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 3.34 | 3.34 | 3.34 Mbytes +Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press + 0 300 0 0 0.49647271 0 0.49647271 0 0 + 10 300 0.13361073 0.015454603 0.47336798 0.023104631 0.49647261 0 0.0046209262 + 20 300 0.26624846 0.062286838 0.40335451 0.093118823 0.49647334 0 0.018623765 + 30 300 0.39882493 0.14309258 0.2825546 0.21392341 0.49647801 0 0.042784682 + 40 300 0.53216863 0.52823732 0.08958779 0.78971479 0.87930258 0 0.15794296 + 50 300 0.66626191 1.1912156 -0.082808834 1.7808674 1.6980585 0 0.35617347 + 60 300 0.80045819 1.3877079 -0.37658402 2.0746234 1.6980393 0 0.41492467 + 70 300 0.93514919 1.7017671 -0.84569366 2.5441418 1.6984482 0 0.50882837 + 80 300 1.0722892 15.128456 -3.370646 22.617042 19.246396 0 4.5234083 + 90 300 1.2106726 41.994547 -2.2024419 62.781847 60.579406 0 12.556369 + 100 300 1.3514247 41.352114 -0.92449496 61.821411 60.896916 0 12.364282 +Loop time of 1.35144 on 1 procs for 100 steps with 300 atoms + +Performance: 31966.000 tau/day, 73.995 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 | 2.718e-05 | 2.718e-05 | 2.718e-05 | 0.0 | 0.00 +Kspace | 1.3486 | 1.3486 | 1.3486 | 0.0 | 99.79 +Neigh | 0.0019956 | 0.0019956 | 0.0019956 | 0.0 | 0.15 +Comm | 0.00027394 | 0.00027394 | 0.00027394 | 0.0 | 0.02 +Output | 0.00013924 | 0.00013924 | 0.00013924 | 0.0 | 0.01 +Modify | 0.00023341 | 0.00023341 | 0.00023341 | 0.0 | 0.02 +Other | | 0.000195 | | | 0.01 + +Nlocal: 300 ave 300 max 300 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 374 ave 374 max 374 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 2465 ave 2465 max 2465 min +Histogram: 1 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 2465 +Ave neighs/atom = 8.21667 +Neighbor list builds = 15 +Dangerous builds = 0 +Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.4 new file mode 100644 index 0000000000..f881ed003a --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.ewald.g++.4 @@ -0,0 +1,92 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task + +units lj +atom_style charge + +read_data data.cloud_wall + orthogonal box = (0 0 0) to (10 10 10) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 300 atoms + +velocity all set 0.0 0.0 0.0 mom no + +pair_style zero 1.0 +pair_coeff * * + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve +kspace_style scafacos ewald 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 + +thermo_style custom step atoms cpu temp pe ke etotal ecoul press + +run_style verlet + +#dump simple all custom 1000 id x y z vx vy vz +#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass +#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass +#dump_modify dmpvtk pad 7 + +thermo 10 +run 100 +Setting up ScaFaCoS with solver ewald ... +WARNING: Virial computation for Ewald not available (src/USER-SCAFACOS/scafacos.cpp:107) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 10 10 10 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 3.333 | 3.333 | 3.333 Mbytes +Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press + 0 300 0 0 0.49647271 0 0.49647271 0 0 + 10 300 0.04107213 0.015454603 0.47336798 0.023104631 0.49647261 0 0.0046209262 + 20 300 0.083310604 0.062286838 0.40335451 0.093118823 0.49647334 0 0.018623765 + 30 300 0.12387085 0.14309258 0.2825546 0.21392341 0.49647801 0 0.042784682 + 40 300 0.1672492 0.52823732 0.08958779 0.78971479 0.87930258 0 0.15794296 + 50 300 0.21049809 1.1912156 -0.082808834 1.7808674 1.6980585 0 0.35617347 + 60 300 0.25216699 1.3877079 -0.37658402 2.0746234 1.6980393 0 0.41492467 + 70 300 0.29355645 1.7017671 -0.84569366 2.5441418 1.6984482 0 0.50882837 + 80 300 0.33713698 15.128456 -3.370646 22.617042 19.246396 0 4.5234083 + 90 300 0.38109112 41.994547 -2.2024419 62.781847 60.579406 0 12.556369 + 100 300 0.4267664 41.352114 -0.92449496 61.821411 60.896916 0 12.364282 +Loop time of 0.426857 on 4 procs for 100 steps with 300 atoms + +Performance: 101204.784 tau/day, 234.270 timesteps/s +97.1% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 1.6689e-05 | 1.8835e-05 | 2.2173e-05 | 0.0 | 0.00 +Kspace | 0.42368 | 0.42384 | 0.42405 | 0.0 | 99.29 +Neigh | 0.00040579 | 0.00056726 | 0.00075126 | 0.0 | 0.13 +Comm | 0.0010395 | 0.0010909 | 0.001189 | 0.2 | 0.26 +Output | 0.00015545 | 0.00034326 | 0.00090313 | 0.0 | 0.08 +Modify | 9.8705e-05 | 0.00010544 | 0.00011539 | 0.0 | 0.02 +Other | | 0.0008868 | | | 0.21 + +Nlocal: 75 ave 81 max 70 min +Histogram: 2 0 0 0 0 0 0 1 0 1 +Nghost: 282.5 ave 290 max 274 min +Histogram: 1 0 0 1 0 0 0 0 1 1 +Neighs: 616.25 ave 983 max 283 min +Histogram: 1 1 0 0 0 0 0 1 0 1 + +Total # of neighbors = 2465 +Ave neighs/atom = 8.21667 +Neighbor list builds = 15 +Dangerous builds = 0 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.1 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.1 similarity index 51% rename from examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.1 index 714ce85a5f..da0c698187 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.fmm.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.1 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task units lj atom_style charge @@ -59,41 +58,41 @@ Neighbor list info ... Per MPI rank memory allocation (min/avg/max) = 3.34 | 3.34 | 3.34 Mbytes Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 - 10 300 0.063865185 0.015455559 0.47335833 0.02310606 0.49646439 0 0.020399823 - 20 300 0.12760854 0.06229069 0.40334177 0.093124582 0.49646635 0 0.032069642 - 30 300 0.19143319 0.14310163 0.28254277 0.21393694 0.49647971 0 0.05220548 - 40 300 0.25553131 0.52929788 0.089669015 0.79130033 0.88096934 0 0.16124903 - 50 300 0.31961966 1.1963022 -0.082792461 1.7884718 1.7056794 0 0.35493462 - 60 300 0.38388991 1.3928167 -0.37659239 2.082261 1.7056686 0 0.40389911 - 70 300 0.44797421 1.7069009 -0.84571914 2.5518169 1.7060978 0 0.48217274 - 80 300 0.50961447 15.358343 -3.368063 22.960722 19.592659 0 4.4798757 - 90 300 0.57181501 42.280432 -2.1623864 63.209247 61.04686 0 12.56977 - 100 300 0.63501096 41.48079 -0.89904529 62.013782 61.114736 0 12.372788 -Loop time of 0.635022 on 1 procs for 100 steps with 300 atoms + 10 300 0.025602102 0.015455672 0.47336221 0.023106229 0.49646844 0 0.020399986 + 20 300 0.051156282 0.062291145 0.40334518 0.093125262 0.49647044 0 0.032069892 + 30 300 0.076699495 0.14310262 0.28254543 0.21393842 0.49648385 0 0.052205865 + 40 300 0.10232902 0.52932294 0.089676201 0.79133779 0.88101399 0 0.16125676 + 50 300 0.12800455 1.1962334 -0.082794531 1.788369 1.7055744 0 0.35491397 + 60 300 0.1537931 1.3927481 -0.37659486 2.0821585 1.7055636 0 0.40387853 + 70 300 0.17947531 1.7068337 -0.84572368 2.5517165 1.7059928 0 0.4821525 + 80 300 0.20517826 15.509932 -3.369527 23.187348 19.817821 0 4.5251521 + 90 300 0.23049045 42.26862 -2.0785273 63.191586 61.113059 0 12.569033 + 100 300 0.25625205 41.459415 -0.88546313 61.981825 61.096362 0 12.36685 +Loop time of 0.256263 on 1 procs for 100 steps with 300 atoms -Performance: 68029.122 tau/day, 157.475 timesteps/s -99.7% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 168576.488 tau/day, 390.223 timesteps/s +99.4% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 9.0837e-05 | 9.0837e-05 | 9.0837e-05 | 0.0 | 0.01 -Kspace | 0.62877 | 0.62877 | 0.62877 | 0.0 | 99.01 -Neigh | 0.0035319 | 0.0035319 | 0.0035319 | 0.0 | 0.56 -Comm | 0.0010211 | 0.0010211 | 0.0010211 | 0.0 | 0.16 -Output | 0.00014758 | 0.00014758 | 0.00014758 | 0.0 | 0.02 -Modify | 0.0010428 | 0.0010428 | 0.0010428 | 0.0 | 0.16 -Other | | 0.0004218 | | | 0.07 +Pair | 2.7895e-05 | 2.7895e-05 | 2.7895e-05 | 0.0 | 0.01 +Kspace | 0.25335 | 0.25335 | 0.25335 | 0.0 | 98.86 +Neigh | 0.0020251 | 0.0020251 | 0.0020251 | 0.0 | 0.79 +Comm | 0.00027776 | 0.00027776 | 0.00027776 | 0.0 | 0.11 +Output | 0.00014305 | 0.00014305 | 0.00014305 | 0.0 | 0.06 +Modify | 0.0002346 | 0.0002346 | 0.0002346 | 0.0 | 0.09 +Other | | 0.0002046 | | | 0.08 Nlocal: 300 ave 300 max 300 min Histogram: 1 0 0 0 0 0 0 0 0 0 Nghost: 374 ave 374 max 374 min Histogram: 1 0 0 0 0 0 0 0 0 0 -Neighs: 2459 ave 2459 max 2459 min +Neighs: 2461 ave 2461 max 2461 min Histogram: 1 0 0 0 0 0 0 0 0 0 -Total # of neighbors = 2459 -Ave neighs/atom = 8.19667 +Total # of neighbors = 2461 +Ave neighs/atom = 8.20333 Neighbor list builds = 15 Dangerous builds = 0 Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.4 new file mode 100644 index 0000000000..30fa988863 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.fmm.g++.4 @@ -0,0 +1,98 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +units lj +atom_style charge + +read_data data.cloud_wall + orthogonal box = (0 0 0) to (10 10 10) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 300 atoms + +velocity all set 0.0 0.0 0.0 mom no + +pair_style zero 1.0 +pair_coeff * * + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +kspace_style scafacos fmm 1.0e-3 +kspace_modify scafacos tolerance energy_rel +kspace_modify scafacos fmm_tuning 1 +ScaFaCoS setting fmm inhomogen tuning ... + +timestep 0.005 + +thermo_style custom step atoms cpu temp pe ke etotal ecoul press + +run_style verlet + +#dump simple all custom 1000 id x y z vx vy vz +#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass +#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass +#dump_modify dmpvtk pad 7 + +thermo 10 +run 100 +Setting up ScaFaCoS with solver fmm ... +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 10 10 10 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 3.333 | 3.333 | 3.333 Mbytes +Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press + 0 300 0 0 0.49646402 0 0.49646402 0 0.016548801 + 10 300 0.01548481 0.015455672 0.47336221 0.023106229 0.49646844 0 0.020399986 + 20 300 0.031042576 0.062291145 0.40334518 0.093125262 0.49647044 0 0.032069892 + 30 300 0.044115782 0.14310262 0.28254543 0.21393842 0.49648385 0 0.052205865 + 40 300 0.059348583 0.52932294 0.089676201 0.79133779 0.88101399 0 0.16125676 + 50 300 0.071757555 1.1962334 -0.082794531 1.788369 1.7055744 0 0.35491397 + 60 300 0.088143587 1.3927481 -0.37659486 2.0821585 1.7055636 0 0.40387853 + 70 300 0.099860907 1.7068337 -0.84572368 2.5517165 1.7059928 0 0.4821525 + 80 300 0.11159992 15.509932 -3.369527 23.187348 19.817821 0 4.5251521 + 90 300 0.12841201 42.26862 -2.0785273 63.191586 61.113059 0 12.569033 + 100 300 0.14122367 41.459415 -0.88546313 61.981825 61.096362 0 12.36685 +Loop time of 0.141343 on 4 procs for 100 steps with 300 atoms + +Performance: 305639.349 tau/day, 707.498 timesteps/s +94.8% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 2.5988e-05 | 2.9087e-05 | 3.2663e-05 | 0.0 | 0.02 +Kspace | 0.13587 | 0.13743 | 0.13808 | 0.2 | 97.23 +Neigh | 0.00041199 | 0.00057679 | 0.00076771 | 0.0 | 0.41 +Comm | 0.001039 | 0.0015332 | 0.0029936 | 2.2 | 1.08 +Output | 0.00017786 | 0.00044322 | 0.0012352 | 0.0 | 0.31 +Modify | 0.00017333 | 0.00018805 | 0.00020623 | 0.0 | 0.13 +Other | | 0.001146 | | | 0.81 + +Nlocal: 75 ave 80 max 71 min +Histogram: 2 0 0 0 0 0 0 1 0 1 +Nghost: 282.5 ave 290 max 275 min +Histogram: 1 0 1 0 0 0 0 0 1 1 +Neighs: 615.25 ave 970 max 292 min +Histogram: 1 1 0 0 0 0 0 1 0 1 + +Total # of neighbors = 2461 +Ave neighs/atom = 8.20333 +Neighbor list builds = 15 +Dangerous builds = 0 +Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.1 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.1 similarity index 64% rename from examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.1 index f47f24edee..10c2fa166b 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.1 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task units lj @@ -52,31 +51,31 @@ Neighbor list info ... Per MPI rank memory allocation (min/avg/max) = 3.34 | 3.34 | 3.34 Mbytes Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press 0 300 0 0 0.49683273 0 0.49683273 0 0.016561091 - 10 300 0.071435928 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 - 20 300 0.14302707 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 - 30 300 0.21480989 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 - 40 300 0.28638172 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 - 50 300 0.35810781 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 - 60 300 0.42993116 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 - 70 300 0.50181961 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 - 80 300 0.57404566 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 - 90 300 0.64724708 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 - 100 300 0.72128963 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 -Loop time of 0.721302 on 1 procs for 100 steps with 300 atoms + 10 300 0.028267145 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 + 20 300 0.056742668 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 + 30 300 0.085426331 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 + 40 300 0.11415625 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 + 50 300 0.14363861 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 + 60 300 0.17313194 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 + 70 300 0.20299363 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 + 80 300 0.23256087 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 + 90 300 0.26286936 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 + 100 300 0.29372239 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 +Loop time of 0.293738 on 1 procs for 100 steps with 300 atoms -Performance: 59891.733 tau/day, 138.638 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 147070.013 tau/day, 340.440 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 8.893e-05 | 8.893e-05 | 8.893e-05 | 0.0 | 0.01 -Kspace | 0.71502 | 0.71502 | 0.71502 | 0.0 | 99.13 -Neigh | 0.0035415 | 0.0035415 | 0.0035415 | 0.0 | 0.49 -Comm | 0.001024 | 0.001024 | 0.001024 | 0.0 | 0.14 -Output | 0.00015044 | 0.00015044 | 0.00015044 | 0.0 | 0.02 -Modify | 0.0010409 | 0.0010409 | 0.0010409 | 0.0 | 0.14 -Other | | 0.0004385 | | | 0.06 +Pair | 4.3869e-05 | 4.3869e-05 | 4.3869e-05 | 0.0 | 0.01 +Kspace | 0.29081 | 0.29081 | 0.29081 | 0.0 | 99.00 +Neigh | 0.0019989 | 0.0019989 | 0.0019989 | 0.0 | 0.68 +Comm | 0.0003159 | 0.0003159 | 0.0003159 | 0.0 | 0.11 +Output | 0.00016809 | 0.00016809 | 0.00016809 | 0.0 | 0.06 +Modify | 0.00021863 | 0.00021863 | 0.00021863 | 0.0 | 0.07 +Other | | 0.0001831 | | | 0.06 Nlocal: 300 ave 300 max 300 min Histogram: 1 0 0 0 0 0 0 0 0 0 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.4 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.4 similarity index 64% rename from examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.4 index d5a07e0324..aa828ed159 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.cw.g++.p2nfft.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p2nfft.g++.4 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task units lj @@ -52,31 +51,31 @@ Neighbor list info ... Per MPI rank memory allocation (min/avg/max) = 3.333 | 3.333 | 3.333 Mbytes Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press 0 300 0 0 0.49683273 0 0.49683273 0 0.016561091 - 10 300 0.02743125 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 - 20 300 0.05494833 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 - 30 300 0.082517862 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 - 40 300 0.11015558 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 - 50 300 0.13790298 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 - 60 300 0.1660006 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 - 70 300 0.1937964 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 - 80 300 0.22181106 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 - 90 300 0.25105524 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 - 100 300 0.28086019 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 -Loop time of 0.280875 on 4 procs for 100 steps with 300 atoms + 10 300 0.013789177 0.015479312 0.47369009 0.023141571 0.49683166 0 0.020417984 + 20 300 0.025422812 0.062386358 0.40356181 0.093267605 0.49682941 0 0.032105581 + 30 300 0.039611578 0.14331637 0.2825636 0.21425798 0.49682157 0 0.052270382 + 40 300 0.051841736 0.53041843 0.089505208 0.79297556 0.88248077 0 0.16157862 + 50 300 0.07456398 1.1948397 -0.083317439 1.7862853 1.7029679 0 0.35447982 + 60 300 0.087505341 1.3915614 -0.37745551 2.0803842 1.7029287 0 0.40349499 + 70 300 0.10280418 1.7061978 -0.84746071 2.5507657 1.703305 0 0.48190445 + 80 300 0.1173315 20.692093 -3.32971 30.93468 27.60497 0 6.0759456 + 90 300 0.13260174 48.999403 -2.1632167 73.254107 71.090891 0 14.578714 + 100 300 0.14577007 51.199785 -0.81127924 76.543678 75.732399 0 15.281693 +Loop time of 0.145873 on 4 procs for 100 steps with 300 atoms -Performance: 153805.254 tau/day, 356.031 timesteps/s -99.7% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 296148.120 tau/day, 685.528 timesteps/s +92.8% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 5.6744e-05 | 6.0022e-05 | 6.4135e-05 | 0.0 | 0.02 -Kspace | 0.27651 | 0.27682 | 0.27714 | 0.0 | 98.56 -Neigh | 0.00079465 | 0.001082 | 0.0014107 | 0.8 | 0.39 -Comm | 0.0019372 | 0.002014 | 0.0020835 | 0.1 | 0.72 -Output | 0.00018406 | 0.00019914 | 0.00023413 | 0.0 | 0.07 -Modify | 0.0002749 | 0.00028563 | 0.00029325 | 0.0 | 0.10 -Other | | 0.0004173 | | | 0.15 +Pair | 2.3842e-05 | 2.5034e-05 | 2.7657e-05 | 0.0 | 0.02 +Kspace | 0.14221 | 0.14239 | 0.14264 | 0.0 | 97.61 +Neigh | 0.00041676 | 0.0005784 | 0.00076866 | 0.0 | 0.40 +Comm | 0.0013564 | 0.0014941 | 0.0016375 | 0.3 | 1.02 +Output | 0.00017166 | 0.00033867 | 0.00083518 | 0.0 | 0.23 +Modify | 0.00012016 | 0.00012261 | 0.0001266 | 0.0 | 0.08 +Other | | 0.0009243 | | | 0.63 Nlocal: 75 ave 81 max 69 min Histogram: 1 0 0 0 1 1 0 0 0 1 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.1 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.1 new file mode 100644 index 0000000000..9410529284 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.1 @@ -0,0 +1,92 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task + +units lj +atom_style charge + +read_data data.cloud_wall + orthogonal box = (0 0 0) to (10 10 10) + 1 by 1 by 1 MPI processor grid + reading atoms ... + 300 atoms + +velocity all set 0.0 0.0 0.0 mom no + +pair_style zero 1.0 +pair_coeff * * + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve +kspace_style scafacos p3m 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 + +thermo_style custom step atoms cpu temp pe ke etotal ecoul press + +run_style verlet + +#dump simple all custom 1000 id x y z vx vy vz +#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass +#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass +#dump_modify dmpvtk pad 7 + +thermo 10 +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 10 10 10 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 3.34 | 3.34 | 3.34 Mbytes +Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press + 0 300 0 0 0.49619864 0 0.49619864 0 0 + 10 300 0.018853664 0.015458704 0.47310664 0.023110763 0.4962174 0 0.0046221526 + 20 300 0.037713289 0.062303961 0.40312435 0.093144421 0.49626877 0 0.018628884 + 30 300 0.055995226 0.14313464 0.28239193 0.21398628 0.49637821 0 0.042797257 + 40 300 0.074442625 0.53306643 0.089950137 0.79693431 0.88688444 0 0.15938686 + 50 300 0.093066454 1.1925037 -0.08272797 1.7827931 1.7000651 0 0.35655861 + 60 300 0.11158967 1.3890617 -0.37645444 2.0766472 1.7001927 0 0.41532944 + 70 300 0.1300416 1.7033725 -0.84587122 2.5465418 1.7006706 0 0.50930837 + 80 300 0.14844203 15.906218 -3.3586154 23.779796 20.421181 0 4.7559592 + 90 300 0.1676445 42.749883 -2.2769116 63.911076 61.634164 0 12.782215 + 100 300 0.1866703 42.25523 -0.84978755 63.171569 62.321782 0 12.634314 +Loop time of 0.186683 on 1 procs for 100 steps with 300 atoms + +Performance: 231408.103 tau/day, 535.667 timesteps/s +99.5% CPU use with 1 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 2.7657e-05 | 2.7657e-05 | 2.7657e-05 | 0.0 | 0.01 +Kspace | 0.18368 | 0.18368 | 0.18368 | 0.0 | 98.39 +Neigh | 0.0020967 | 0.0020967 | 0.0020967 | 0.0 | 1.12 +Comm | 0.00027132 | 0.00027132 | 0.00027132 | 0.0 | 0.15 +Output | 0.00013709 | 0.00013709 | 0.00013709 | 0.0 | 0.07 +Modify | 0.0002718 | 0.0002718 | 0.0002718 | 0.0 | 0.15 +Other | | 0.0001974 | | | 0.11 + +Nlocal: 300 ave 300 max 300 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 374 ave 374 max 374 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 2478 ave 2478 max 2478 min +Histogram: 1 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 2478 +Ave neighs/atom = 8.26 +Neighbor list builds = 15 +Dangerous builds = 0 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.4 new file mode 100644 index 0000000000..2dc5c07b2b --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.cw.p3m.g++.4 @@ -0,0 +1,92 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task + +units lj +atom_style charge + +read_data data.cloud_wall + orthogonal box = (0 0 0) to (10 10 10) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 300 atoms + +velocity all set 0.0 0.0 0.0 mom no + +pair_style zero 1.0 +pair_coeff * * + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve +kspace_style scafacos p3m 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 + +thermo_style custom step atoms cpu temp pe ke etotal ecoul press + +run_style verlet + +#dump simple all custom 1000 id x y z vx vy vz +#dump dmp all custom 1000 part.dump id mol x y z vx vy vz fx fy fz q mass +#dump dmpvtk all vtk 1000 vtk/part_*.vtk id mol x y z vx vy vz fx fy fz q mass +#dump_modify dmpvtk pad 7 + +thermo 10 +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 10 10 10 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 3.333 | 3.333 | 3.333 Mbytes +Step Atoms CPU Temp PotEng KinEng TotEng E_coul Press + 0 300 0 0 0.49601855 0 0.49601855 0 0 + 10 300 0.0080001354 0.015443077 0.47292202 0.0230874 0.49600942 0 0.00461748 + 20 300 0.018443823 0.062241297 0.40294626 0.093050739 0.495997 0 0.018610148 + 30 300 0.029161692 0.14299426 0.28226416 0.21377642 0.49604058 0 0.042755283 + 40 300 0.037320137 0.53371718 0.089969593 0.79790718 0.88787677 0 0.15958144 + 50 300 0.045557499 1.195874 -0.082570725 1.7878316 1.7052608 0 0.35756631 + 60 300 0.054044962 1.3923357 -0.37594466 2.0815419 1.7055972 0 0.41630838 + 70 300 0.064656734 1.7063617 -0.84481819 2.5510108 1.7061926 0 0.51020216 + 80 300 0.073246241 13.884845 -3.3804644 20.757843 17.377379 0 4.1515687 + 90 300 0.081598997 40.561354 -2.1801816 60.639224 58.459042 0 12.127845 + 100 300 0.092384577 39.972453 -0.95590215 59.758818 58.802916 0 11.951764 +Loop time of 0.0924569 on 4 procs for 100 steps with 300 atoms + +Performance: 467244.853 tau/day, 1081.585 timesteps/s +96.2% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 1.812e-05 | 1.955e-05 | 2.1935e-05 | 0.0 | 0.02 +Kspace | 0.087202 | 0.087385 | 0.087595 | 0.1 | 94.51 +Neigh | 0.00039053 | 0.00056016 | 0.00074887 | 0.0 | 0.61 +Comm | 0.00095391 | 0.001252 | 0.001538 | 0.6 | 1.35 +Output | 0.00015235 | 0.00026172 | 0.00058818 | 0.0 | 0.28 +Modify | 9.7275e-05 | 0.00010461 | 0.00011683 | 0.0 | 0.11 +Other | | 0.002874 | | | 3.11 + +Nlocal: 75 ave 81 max 70 min +Histogram: 2 0 0 0 0 0 0 1 0 1 +Nghost: 284 ave 290 max 277 min +Histogram: 1 0 0 1 0 0 0 1 0 1 +Neighs: 619.25 ave 986 max 285 min +Histogram: 1 1 0 0 0 0 0 1 0 1 + +Total # of neighbors = 2477 +Ave neighs/atom = 8.25667 +Neighbor list builds = 15 +Dangerous builds = 0 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.1 b/examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.1 similarity index 79% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.1 index 13212ede0c..e6cd7c506f 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.1 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 1 by 1 MPI processor grid 4096 atoms - Time spent = 0.000498772 secs + Time spent = 0.000287294 secs velocity all create 1.5 49893 @@ -47,6 +46,7 @@ thermo 10 run 100 Setting up ScaFaCoS with solver ewald ... +WARNING: Virial computation for Ewald not available (src/USER-SCAFACOS/scafacos.cpp:107) Neighbor list info ... update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 @@ -72,21 +72,21 @@ Step Temp E_pair E_mol TotEng Press 80 1.5033218 -1.7524875 0 0.50194458 12.023638 90 1.5108306 -1.7637462 0 0.50194636 12.083694 100 1.5292479 -1.7913449 0 0.50196695 12.230996 -Loop time of 1121.22 on 1 procs for 100 steps with 4096 atoms +Loop time of 427.03 on 1 procs for 100 steps with 4096 atoms -Performance: 38.530 tau/day, 0.089 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 101.164 tau/day, 0.234 timesteps/s +99.9% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.0015197 | 0.0015197 | 0.0015197 | 0.0 | 0.00 -Kspace | 1121.2 | 1121.2 | 1121.2 | 0.0 |100.00 +Pair | 0.0003655 | 0.0003655 | 0.0003655 | 0.0 | 0.00 +Kspace | 427.02 | 427.02 | 427.02 | 0.0 |100.00 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.013699 | 0.013699 | 0.013699 | 0.0 | 0.00 -Output | 0.00038314 | 0.00038314 | 0.00038314 | 0.0 | 0.00 -Modify | 0.011126 | 0.011126 | 0.011126 | 0.0 | 0.00 -Other | | 0.00418 | | | 0.00 +Comm | 0.0047293 | 0.0047293 | 0.0047293 | 0.0 | 0.00 +Output | 0.00025916 | 0.00025916 | 0.00025916 | 0.0 | 0.00 +Modify | 0.0029993 | 0.0029993 | 0.0029993 | 0.0 | 0.00 +Other | | 0.00181 | | | 0.00 Nlocal: 4096 ave 4096 max 4096 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -99,4 +99,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:18:57 +Total wall time: 0:07:10 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.4 b/examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.4 similarity index 76% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.4 index 26c1953afa..39e0387491 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.ewald.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.ewald.g++.4 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 2 by 2 MPI processor grid 4096 atoms - Time spent = 0.000261068 secs + Time spent = 0.000125408 secs velocity all create 1.5 49893 @@ -47,6 +46,7 @@ thermo 10 run 100 Setting up ScaFaCoS with solver ewald ... +WARNING: Virial computation for Ewald not available (src/USER-SCAFACOS/scafacos.cpp:107) Neighbor list info ... update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 @@ -61,32 +61,32 @@ Neighbor list info ... bin: standard Per MPI rank memory allocation (min/avg/max) = 4.008 | 4.008 | 4.008 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -1.7475938 0 0.50185691 -nan - 10 1.500011 -1.747529 0 0.50193816 -nan - 20 1.5000023 -1.7475152 0 0.50193898 -nan - 30 1.4999308 -1.747404 0 0.50194285 -nan - 40 1.4997722 -1.7471622 0 0.50194686 -nan - 50 1.4995835 -1.746878 0 0.50194808 -nan - 60 1.4996054 -1.7469114 0 0.50194749 -nan - 70 1.5004341 -1.7481558 0 0.50194592 -nan - 80 1.5033218 -1.7524875 0 0.50194458 -nan - 90 1.5108306 -1.7637462 0 0.50194636 -nan - 100 1.5292479 -1.7913449 0 0.50196695 -nan -Loop time of 295.996 on 4 procs for 100 steps with 4096 atoms + 0 1.5 -1.7475938 0 0.50185691 11.99707 + 10 1.500011 -1.747529 0 0.50193816 11.997158 + 20 1.5000023 -1.7475152 0 0.50193898 11.997089 + 30 1.4999308 -1.747404 0 0.50194285 11.996517 + 40 1.4997722 -1.7471622 0 0.50194686 11.995248 + 50 1.4995835 -1.746878 0 0.50194808 11.993739 + 60 1.4996054 -1.7469114 0 0.50194749 11.993914 + 70 1.5004341 -1.7481558 0 0.50194592 12.000543 + 80 1.5033218 -1.7524875 0 0.50194458 12.023638 + 90 1.5108306 -1.7637462 0 0.50194636 12.083694 + 100 1.5292479 -1.7913449 0 0.50196695 12.230996 +Loop time of 113.519 on 4 procs for 100 steps with 4096 atoms -Performance: 145.948 tau/day, 0.338 timesteps/s -99.9% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 380.555 tau/day, 0.881 timesteps/s +98.8% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00071096 | 0.00071985 | 0.00072813 | 0.0 | 0.00 -Kspace | 295.98 | 295.98 | 295.98 | 0.0 | 99.99 +Pair | 0.00022793 | 0.00023127 | 0.00023508 | 0.0 | 0.00 +Kspace | 113.51 | 113.51 | 113.51 | 0.0 | 99.99 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.013666 | 0.013736 | 0.013795 | 0.0 | 0.00 -Output | 0.00023484 | 0.00025135 | 0.00029254 | 0.0 | 0.00 -Modify | 0.0029099 | 0.002973 | 0.0030224 | 0.1 | 0.00 -Other | | 0.001821 | | | 0.00 +Comm | 0.0084581 | 0.0085486 | 0.0086188 | 0.1 | 0.01 +Output | 0.00019598 | 0.00046694 | 0.0012727 | 0.0 | 0.00 +Modify | 0.0016849 | 0.0017331 | 0.0017881 | 0.1 | 0.00 +Other | | 0.002307 | | | 0.00 Nlocal: 1024 ave 1024 max 1024 min Histogram: 4 0 0 0 0 0 0 0 0 0 @@ -99,4 +99,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:05:02 +Total wall time: 0:01:54 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.1 b/examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.1 similarity index 79% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.1 index 598585ae95..b9ae654659 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.1 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 1 by 1 MPI processor grid 4096 atoms - Time spent = 0.000518799 secs + Time spent = 0.000326395 secs velocity all create 1.5 49893 @@ -72,21 +71,21 @@ Step Temp E_pair E_mol TotEng Press 80 1.5032684 -1.7524625 0 0.50188958 10.465466 90 1.5107749 -1.763714 0 0.50189507 10.515502 100 1.52919 -1.791306 0 0.50191895 10.638261 -Loop time of 34.7058 on 1 procs for 100 steps with 4096 atoms +Loop time of 9.55733 on 1 procs for 100 steps with 4096 atoms -Performance: 1244.749 tau/day, 2.881 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 4520.093 tau/day, 10.463 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.0015228 | 0.0015228 | 0.0015228 | 0.0 | 0.00 -Kspace | 34.675 | 34.675 | 34.675 | 0.0 | 99.91 +Pair | 0.0003767 | 0.0003767 | 0.0003767 | 0.0 | 0.00 +Kspace | 9.5472 | 9.5472 | 9.5472 | 0.0 | 99.89 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.013741 | 0.013741 | 0.013741 | 0.0 | 0.04 -Output | 0.00041246 | 0.00041246 | 0.00041246 | 0.0 | 0.00 -Modify | 0.01107 | 0.01107 | 0.01107 | 0.0 | 0.03 -Other | | 0.004232 | | | 0.01 +Comm | 0.0047688 | 0.0047688 | 0.0047688 | 0.0 | 0.05 +Output | 0.00027132 | 0.00027132 | 0.00027132 | 0.0 | 0.00 +Modify | 0.0029824 | 0.0029824 | 0.0029824 | 0.0 | 0.03 +Other | | 0.001692 | | | 0.02 Nlocal: 4096 ave 4096 max 4096 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -99,4 +98,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:35 +Total wall time: 0:00:10 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.4 b/examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.4 similarity index 79% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.4 index 27fdfcedcb..7ee8d3d068 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.fmm.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.fmm.g++.4 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 2 by 2 MPI processor grid 4096 atoms - Time spent = 0.000270367 secs + Time spent = 0.00015521 secs velocity all create 1.5 49893 @@ -72,21 +71,21 @@ Step Temp E_pair E_mol TotEng Press 80 1.5032684 -1.7524625 0 0.50188958 10.465466 90 1.5107749 -1.763714 0 0.50189507 10.515502 100 1.52919 -1.791306 0 0.50191895 10.638261 -Loop time of 10.0781 on 4 procs for 100 steps with 4096 atoms +Loop time of 3.05974 on 4 procs for 100 steps with 4096 atoms -Performance: 4286.533 tau/day, 9.923 timesteps/s -99.9% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 14118.863 tau/day, 32.683 timesteps/s +98.6% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00071096 | 0.00073177 | 0.00075269 | 0.0 | 0.01 -Kspace | 10.056 | 10.057 | 10.057 | 0.0 | 99.79 +Pair | 0.00021482 | 0.0002175 | 0.00022054 | 0.0 | 0.01 +Kspace | 3.0468 | 3.0468 | 3.0468 | 0.0 | 99.58 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.01492 | 0.015036 | 0.015207 | 0.1 | 0.15 -Output | 0.00036311 | 0.00039428 | 0.00046515 | 0.0 | 0.00 -Modify | 0.002944 | 0.0030704 | 0.0033708 | 0.3 | 0.03 -Other | | 0.002214 | | | 0.02 +Comm | 0.0081758 | 0.0082486 | 0.0083146 | 0.1 | 0.27 +Output | 0.00019073 | 0.00049388 | 0.0013943 | 0.0 | 0.02 +Modify | 0.001507 | 0.0015851 | 0.0017498 | 0.2 | 0.05 +Other | | 0.002385 | | | 0.08 Nlocal: 1024 ave 1024 max 1024 min Histogram: 4 0 0 0 0 0 0 0 0 0 @@ -99,4 +98,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:11 +Total wall time: 0:00:04 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.g++.1 b/examples/USER/scafacos/log.27Nov18.scafacos.g++.1 new file mode 100644 index 0000000000..6b36f0ba91 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.g++.1 @@ -0,0 +1,102 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Point dipoles in a 2d box + +units lj +atom_style charge + +read_data data.NaCl + orthogonal box = (0 0 0) to (1 1 1) + 1 by 1 by 1 MPI processor grid + reading atoms ... + 8 atoms + +replicate 8 8 8 + orthogonal box = (0 0 0) to (8 8 8) + 1 by 1 by 1 MPI processor grid + 4096 atoms + Time spent = 0.000253677 secs + +velocity all create 1.5 49893 + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + +# LAMMPS computes pairwise and long-range Coulombics + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +# Scafacos computes entire long-range Coulombics +# use dummy pair style to perform atom sorting + +pair_style zero 1.0 +pair_coeff * * + +#fix 2 all scafacos p3m tolerance field 0.001 + +kspace_style scafacos p3m 0.001 +#kspace_style scafacos tolerance field + +timestep 0.005 +thermo 10 + +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 8 8 8 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 5.813 | 5.813 | 5.813 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 1.5 -1.7475752 0 0.5018755 11.99707 + 10 1.5000018 -1.7475779 0 0.50187548 11.997085 + 20 1.4999833 -1.7475525 0 0.5018731 11.996936 + 30 1.4999006 -1.7474414 0 0.5018603 11.996276 + 40 1.49973 -1.7471989 0 0.50184695 11.994911 + 50 1.4995292 -1.7469064 0 0.50183822 11.993305 + 60 1.49954 -1.7469273 0 0.50183355 11.993391 + 70 1.5003599 -1.7481583 0 0.50183215 11.999949 + 80 1.5032409 -1.752478 0 0.50183276 12.022991 + 90 1.5107445 -1.7637257 0 0.50183781 12.083005 + 100 1.5291568 -1.7913136 0 0.50186158 12.230268 +Loop time of 2.98552 on 1 procs for 100 steps with 4096 atoms + +Performance: 14469.821 tau/day, 33.495 timesteps/s +98.7% CPU use with 1 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 0.0003686 | 0.0003686 | 0.0003686 | 0.0 | 0.01 +Kspace | 2.9749 | 2.9749 | 2.9749 | 0.0 | 99.65 +Neigh | 0 | 0 | 0 | 0.0 | 0.00 +Comm | 0.0049963 | 0.0049963 | 0.0049963 | 0.0 | 0.17 +Output | 0.00027728 | 0.00027728 | 0.00027728 | 0.0 | 0.01 +Modify | 0.0031269 | 0.0031269 | 0.0031269 | 0.0 | 0.10 +Other | | 0.001828 | | | 0.06 + +Nlocal: 4096 ave 4096 max 4096 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 9728 ave 9728 max 9728 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 524288 ave 524288 max 524288 min +Histogram: 1 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 524288 +Ave neighs/atom = 128 +Neighbor list builds = 0 +Dangerous builds = 0 +Total wall time: 0:00:03 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.g++.4 new file mode 100644 index 0000000000..23f55fc5a6 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.g++.4 @@ -0,0 +1,102 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Point dipoles in a 2d box + +units lj +atom_style charge + +read_data data.NaCl + orthogonal box = (0 0 0) to (1 1 1) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 8 atoms + +replicate 8 8 8 + orthogonal box = (0 0 0) to (8 8 8) + 1 by 2 by 2 MPI processor grid + 4096 atoms + Time spent = 0.00012064 secs + +velocity all create 1.5 49893 + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + +# LAMMPS computes pairwise and long-range Coulombics + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +# Scafacos computes entire long-range Coulombics +# use dummy pair style to perform atom sorting + +pair_style zero 1.0 +pair_coeff * * + +#fix 2 all scafacos p3m tolerance field 0.001 + +kspace_style scafacos p3m 0.001 +#kspace_style scafacos tolerance field + +timestep 0.005 +thermo 10 + +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 8 8 8 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 4.008 | 4.008 | 4.008 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 1.5 -1.7475814 0 0.50186926 11.99707 + 10 1.5000019 -1.7475841 0 0.50186935 11.997085 + 20 1.4999837 -1.747556 0 0.50187017 11.99694 + 30 1.4999022 -1.7474323 0 0.50187181 11.996288 + 40 1.4997327 -1.7471824 0 0.50186744 11.994932 + 50 1.4995318 -1.7468908 0 0.50185778 11.993326 + 60 1.499542 -1.7469166 0 0.5018472 11.993407 + 70 1.5003608 -1.7481509 0 0.50184084 11.999956 + 80 1.5032406 -1.7524717 0 0.5018387 12.022989 + 90 1.5107432 -1.7637208 0 0.5018408 12.082995 + 100 1.5291549 -1.7913103 0 0.50186206 12.230252 +Loop time of 1.04979 on 4 procs for 100 steps with 4096 atoms + +Performance: 41150.904 tau/day, 95.257 timesteps/s +96.5% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 0.00021386 | 0.00022691 | 0.00023532 | 0.0 | 0.02 +Kspace | 1.0351 | 1.0353 | 1.0354 | 0.0 | 98.61 +Neigh | 0 | 0 | 0 | 0.0 | 0.00 +Comm | 0.0092776 | 0.0094286 | 0.0095558 | 0.1 | 0.90 +Output | 0.00019121 | 0.00050998 | 0.0014408 | 0.0 | 0.05 +Modify | 0.0019102 | 0.0019451 | 0.0019991 | 0.1 | 0.19 +Other | | 0.002431 | | | 0.23 + +Nlocal: 1024 ave 1024 max 1024 min +Histogram: 4 0 0 0 0 0 0 0 0 0 +Nghost: 5120 ave 5120 max 5120 min +Histogram: 4 0 0 0 0 0 0 0 0 0 +Neighs: 131072 ave 131072 max 131072 min +Histogram: 4 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 524288 +Ave neighs/atom = 128 +Neighbor list builds = 0 +Dangerous builds = 0 +Total wall time: 0:00:01 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.1 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.1 similarity index 69% rename from examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.1 index b0a47e4f98..2d3ca0d588 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.1 @@ -1,13 +1,12 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box units lj atom_style charge -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) 1 by 1 by 1 MPI processor grid reading atoms ... 1000 atoms @@ -45,51 +44,51 @@ Neighbor list info ... max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2 ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 + binsize = 1, bins = 103 103 103 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair zero, 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) = 10.3 | 10.3 | 10.3 Mbytes +Per MPI rank memory allocation (min/avg/max) = 10.44 | 10.44 | 10.44 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777512 0 272.51604 0.17462195 - 5 286.36222 -4.382053 0 424.73173 0.26918926 - 6 481.42206 -4.3095567 0 717.1014 0.45274088 - 7 488.59167 -3.8685194 0 728.2861 0.45956866 - 8 497.85287 -3.0417966 0 742.99073 0.46838116 - 9 499.61615 -3.419003 0 745.2558 0.46983345 - 10 502.63684 -2.8360961 0 750.36521 0.47280809 - 11 504.4846 -2.7628105 0 753.20736 0.47462793 - 12 506.54485 -2.8460356 0 756.21142 0.47651441 - 13 508.27211 -2.730935 0 758.91482 0.47813752 - 14 510.57045 -2.6094877 0 762.48033 0.48031431 - 15 513.14798 -2.7150827 0 766.23717 0.48275229 - 16 515.78124 -2.3961811 0 770.50201 0.48526333 - 17 515.70265 -2.2982683 0 770.48215 0.48526617 - 18 515.7081 -2.1515983 0 770.63699 0.48530393 - 19 515.74906 -2.0581436 0 770.79182 0.48530977 - 20 515.70883 -1.8922577 0 770.89742 0.48527105 -Loop time of 0.465839 on 1 procs for 20 steps with 1000 atoms + 0 1.5 -0.62417787 0 1.6235721 0.0015226607 + 1 18.780041 -10.770002 0 17.371889 0.01623671 + 2 65.289192 -11.084705 0 86.751149 0.058612772 + 3 121.92987 -7.0625759 0 175.64933 0.11076005 + 4 185.78164 -5.8777512 0 272.51604 0.16958509 + 5 286.36222 -4.382053 0 424.73173 0.26142467 + 6 481.42206 -4.3095567 0 717.1014 0.43968187 + 7 488.59167 -3.8685194 0 728.2861 0.4463127 + 8 497.85287 -3.0417966 0 742.99073 0.45487101 + 9 499.61615 -3.419003 0 745.2558 0.45628141 + 10 502.63684 -2.8360961 0 750.36521 0.45917024 + 11 504.4846 -2.7628105 0 753.20736 0.46093759 + 12 506.54485 -2.8460356 0 756.21142 0.46276966 + 13 508.27211 -2.730935 0 758.91482 0.46434596 + 14 510.57045 -2.6094877 0 762.48033 0.46645996 + 15 513.14798 -2.7150827 0 766.23717 0.46882762 + 16 515.78124 -2.3961811 0 770.50201 0.47126623 + 17 515.70265 -2.2982683 0 770.48215 0.47126898 + 18 515.7081 -2.1515983 0 770.63699 0.47130565 + 19 515.74906 -2.0581436 0 770.79182 0.47131132 + 20 515.70883 -1.8922577 0 770.89742 0.47127372 +Loop time of 0.139386 on 1 procs for 20 steps with 1000 atoms -Performance: 18547.165 tau/day, 42.933 timesteps/s -99.9% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 61985.954 tau/day, 143.486 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00021982 | 0.00021982 | 0.00021982 | 0.0 | 0.05 -Kspace | 0.3218 | 0.3218 | 0.3218 | 0.0 | 69.08 -Neigh | 0.14249 | 0.14249 | 0.14249 | 0.0 | 30.59 -Comm | 0.00014853 | 0.00014853 | 0.00014853 | 0.0 | 0.03 -Output | 0.00026131 | 0.00026131 | 0.00026131 | 0.0 | 0.06 -Modify | 0.00055146 | 0.00055146 | 0.00055146 | 0.0 | 0.12 -Other | | 0.0003715 | | | 0.08 +Pair | 5.4359e-05 | 5.4359e-05 | 5.4359e-05 | 0.0 | 0.04 +Kspace | 0.1018 | 0.1018 | 0.1018 | 0.0 | 73.03 +Neigh | 0.037074 | 0.037074 | 0.037074 | 0.0 | 26.60 +Comm | 4.6492e-05 | 4.6492e-05 | 4.6492e-05 | 0.0 | 0.03 +Output | 0.00016332 | 0.00016332 | 0.00016332 | 0.0 | 0.12 +Modify | 0.000139 | 0.000139 | 0.000139 | 0.0 | 0.10 +Other | | 0.0001132 | | | 0.08 Nlocal: 1000 ave 1000 max 1000 min Histogram: 1 0 0 0 0 0 0 0 0 0 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.4 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.4 similarity index 64% rename from examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.4 index 1235c0a3cd..085958d351 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.direct.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.direct.g++.4 @@ -1,13 +1,12 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box units lj atom_style charge -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) 1 by 2 by 2 MPI processor grid reading atoms ... 1000 atoms @@ -45,58 +44,58 @@ Neighbor list info ... max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2 ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 + binsize = 1, bins = 103 103 103 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair zero, 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) = 4.837 | 5.123 | 5.6 Mbytes +Per MPI rank memory allocation (min/avg/max) = 4.882 | 5.463 | 7.161 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777512 0 272.51604 0.17462195 - 5 286.36222 -4.382053 0 424.73173 0.26918926 - 6 481.42206 -4.3095567 0 717.1014 0.45274088 - 7 488.59167 -3.8685194 0 728.2861 0.45956866 - 8 497.85287 -3.0417966 0 742.99073 0.46838116 - 9 499.61615 -3.419003 0 745.2558 0.46983345 - 10 502.63684 -2.8360961 0 750.36521 0.47280809 - 11 504.4846 -2.7628105 0 753.20736 0.47462793 - 12 506.54485 -2.8460356 0 756.21142 0.47651441 - 13 508.27211 -2.730935 0 758.91482 0.47813752 - 14 510.57045 -2.6094877 0 762.48033 0.48031431 - 15 513.14798 -2.7150827 0 766.23717 0.48275229 - 16 515.78124 -2.3961811 0 770.50201 0.48526333 - 17 515.70265 -2.2982683 0 770.48215 0.48526617 - 18 515.7081 -2.1515983 0 770.63699 0.48530393 - 19 515.74906 -2.0581436 0 770.79182 0.48530977 - 20 515.70883 -1.8922577 0 770.89742 0.48527105 -Loop time of 0.161335 on 4 procs for 20 steps with 1000 atoms + 0 1.5 -0.62417787 0 1.6235721 0.0015226607 + 1 18.780041 -10.770002 0 17.371889 0.01623671 + 2 65.289192 -11.084705 0 86.751149 0.058612772 + 3 121.92987 -7.0625759 0 175.64933 0.11076005 + 4 185.78164 -5.8777512 0 272.51604 0.16958509 + 5 286.36222 -4.382053 0 424.73173 0.26142467 + 6 481.42206 -4.3095567 0 717.1014 0.43968187 + 7 488.59167 -3.8685194 0 728.2861 0.4463127 + 8 497.85287 -3.0417966 0 742.99073 0.45487101 + 9 499.61615 -3.419003 0 745.2558 0.45628141 + 10 502.63684 -2.8360961 0 750.36521 0.45917024 + 11 504.4846 -2.7628105 0 753.20736 0.46093759 + 12 506.54485 -2.8460356 0 756.21142 0.46276966 + 13 508.27211 -2.730935 0 758.91482 0.46434596 + 14 510.57045 -2.6094877 0 762.48033 0.46645996 + 15 513.14798 -2.7150827 0 766.23717 0.46882762 + 16 515.78124 -2.3961811 0 770.50201 0.47126623 + 17 515.70265 -2.2982683 0 770.48215 0.47126898 + 18 515.7081 -2.1515983 0 770.63699 0.47130565 + 19 515.74906 -2.0581436 0 770.79182 0.47131132 + 20 515.70883 -1.8922577 0 770.89742 0.47127372 +Loop time of 0.100977 on 4 procs for 20 steps with 1000 atoms -Performance: 53553.228 tau/day, 123.966 timesteps/s -99.5% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 85564.440 tau/day, 198.066 timesteps/s +95.2% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00022721 | 0.00023353 | 0.000247 | 0.0 | 0.14 -Kspace | 0.10295 | 0.11808 | 0.13377 | 3.5 | 73.19 -Neigh | 0.023849 | 0.039717 | 0.055031 | 6.1 | 24.62 -Comm | 0.0023148 | 0.0025774 | 0.0028391 | 0.4 | 1.60 -Output | 0.00029063 | 0.00038403 | 0.00050664 | 0.0 | 0.24 -Modify | 0.00015664 | 0.00015944 | 0.00016165 | 0.0 | 0.10 -Other | | 0.0001805 | | | 0.11 +Pair | 5.1975e-05 | 5.3406e-05 | 5.4836e-05 | 0.0 | 0.05 +Kspace | 0.07448 | 0.084484 | 0.08939 | 2.0 | 83.67 +Neigh | 0.006777 | 0.012519 | 0.023358 | 5.7 | 12.40 +Comm | 0.0011938 | 0.0020879 | 0.0029798 | 1.8 | 2.07 +Output | 0.00024247 | 0.00065064 | 0.0016594 | 0.0 | 0.64 +Modify | 1.812e-05 | 5.3406e-05 | 0.00014162 | 0.0 | 0.05 +Other | | 0.001127 | | | 1.12 -Nlocal: 250 ave 259 max 238 min -Histogram: 1 0 0 1 0 0 0 0 0 2 -Nghost: 672.25 ave 683 max 663 min -Histogram: 2 0 0 0 0 0 0 0 1 1 -Neighs: 61954.2 ave 97157 max 25016 min -Histogram: 1 0 0 1 0 0 1 0 0 1 +Nlocal: 250 ave 518 max 78 min +Histogram: 1 0 1 1 0 0 0 0 0 1 +Nghost: 659 ave 791 max 430 min +Histogram: 1 0 0 0 0 0 0 1 1 1 +Neighs: 61954.2 ave 115962 max 19730 min +Histogram: 1 0 1 0 0 1 0 0 0 1 Total # of neighbors = 247817 Ave neighs/atom = 247.817 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.1 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.1 similarity index 65% rename from examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.1 index 4bef247e26..94ac525119 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.1 @@ -1,13 +1,12 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box units lj atom_style charge -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) 1 by 1 by 1 MPI processor grid reading atoms ... 1000 atoms @@ -49,51 +48,51 @@ Neighbor list info ... max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2 ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 + binsize = 1, bins = 103 103 103 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair zero, 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) = 10.3 | 10.3 | 10.3 Mbytes +Per MPI rank memory allocation (min/avg/max) = 10.44 | 10.44 | 10.44 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417141 0 1.6235786 0.0015676581 - 1 18.780412 -10.770009 0 17.372438 0.016719188 - 2 65.294131 -11.084501 0 86.758754 0.06035827 - 3 121.92555 -7.0612033 0 175.64423 0.1140457 - 4 185.71165 -5.8781334 0 272.41077 0.17455524 - 5 286.28339 -4.3800108 0 424.61565 0.26911306 - 6 481.28097 -4.3052012 0 716.89433 0.45262045 - 7 487.26022 -3.8672741 0 726.29216 0.45830216 - 8 493.65478 -3.0242687 0 736.71742 0.46443761 - 9 495.66203 -3.4336343 0 739.31592 0.46613014 - 10 498.41831 -2.8837072 0 743.99613 0.46887706 - 11 499.20944 -2.7724783 0 745.29287 0.46966875 - 12 500.97345 -2.8281484 0 747.88057 0.47126462 - 13 507.46412 -2.7752775 0 757.65971 0.47728761 - 14 525.35729 -2.5749814 0 784.67292 0.49422171 - 15 563.9578 -2.9982381 0 842.09253 0.53043696 - 16 645.47602 -2.5519203 0 964.69389 0.60730795 - 17 647.09276 -2.2568468 0 967.41166 0.60891914 - 18 647.12596 -2.2791003 0 967.43915 0.60900309 - 19 647.24862 -2.2495226 0 967.65253 0.60908339 - 20 647.51175 -2.0239179 0 968.27244 0.60932598 -Loop time of 0.797289 on 1 procs for 20 steps with 1000 atoms + 0 1.5 -0.62417141 0 1.6235786 0.00152244 + 1 18.780412 -10.770009 0 17.372438 0.016236934 + 2 65.294131 -11.084501 0 86.758754 0.058617275 + 3 121.92555 -7.0612033 0 175.64423 0.11075612 + 4 185.71165 -5.8781334 0 272.41077 0.16952031 + 5 286.28339 -4.3800108 0 424.61565 0.26135067 + 6 481.28097 -4.3052012 0 716.89433 0.43956491 + 7 487.26022 -3.8672741 0 726.29216 0.44508273 + 8 493.65478 -3.0242687 0 736.71742 0.45104121 + 9 495.66203 -3.4336343 0 739.31592 0.45268492 + 10 498.41831 -2.8837072 0 743.99613 0.4553526 + 11 499.20944 -2.7724783 0 745.29287 0.45612146 + 12 500.97345 -2.8281484 0 747.88057 0.4576713 + 13 507.46412 -2.7752775 0 757.65971 0.46352056 + 14 525.35729 -2.5749814 0 784.67292 0.47996621 + 15 563.9578 -2.9982381 0 842.09253 0.51513685 + 16 645.47602 -2.5519203 0 964.69389 0.58979054 + 17 647.09276 -2.2568468 0 967.41166 0.59135526 + 18 647.12596 -2.2791003 0 967.43915 0.59143679 + 19 647.24862 -2.2495226 0 967.65253 0.59151478 + 20 647.51175 -2.0239179 0 968.27244 0.59175037 +Loop time of 0.345449 on 1 procs for 20 steps with 1000 atoms -Performance: 10836.721 tau/day, 25.085 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 25010.947 tau/day, 57.896 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00022364 | 0.00022364 | 0.00022364 | 0.0 | 0.03 -Kspace | 0.6524 | 0.6524 | 0.6524 | 0.0 | 81.83 -Neigh | 0.14312 | 0.14312 | 0.14312 | 0.0 | 17.95 -Comm | 0.00020337 | 0.00020337 | 0.00020337 | 0.0 | 0.03 -Output | 0.00036621 | 0.00036621 | 0.00036621 | 0.0 | 0.05 -Modify | 0.00058126 | 0.00058126 | 0.00058126 | 0.0 | 0.07 -Other | | 0.0003934 | | | 0.05 +Pair | 6.485e-05 | 6.485e-05 | 6.485e-05 | 0.0 | 0.02 +Kspace | 0.30702 | 0.30702 | 0.30702 | 0.0 | 88.88 +Neigh | 0.037661 | 0.037661 | 0.037661 | 0.0 | 10.90 +Comm | 5.4598e-05 | 5.4598e-05 | 5.4598e-05 | 0.0 | 0.02 +Output | 0.00032878 | 0.00032878 | 0.00032878 | 0.0 | 0.10 +Modify | 0.00016141 | 0.00016141 | 0.00016141 | 0.0 | 0.05 +Other | | 0.0001564 | | | 0.05 Nlocal: 1000 ave 1000 max 1000 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -106,4 +105,4 @@ Total # of neighbors = 244342 Ave neighs/atom = 244.342 Neighbor list builds = 19 Dangerous builds = 18 -Total wall time: 0:00:01 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.4 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.4 similarity index 60% rename from examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.4 index e3f5bf44c9..79137934ab 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.fmm.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.fmm.g++.4 @@ -1,13 +1,12 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box units lj atom_style charge -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) 1 by 2 by 2 MPI processor grid reading atoms ... 1000 atoms @@ -49,58 +48,58 @@ Neighbor list info ... max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2 ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 + binsize = 1, bins = 103 103 103 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair zero, 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) = 4.837 | 5.123 | 5.6 Mbytes +Per MPI rank memory allocation (min/avg/max) = 4.882 | 5.463 | 7.161 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417141 0 1.6235786 0.0015676581 - 1 18.780412 -10.770009 0 17.372438 0.016719188 - 2 65.294131 -11.084501 0 86.758754 0.06035827 - 3 121.92555 -7.0612033 0 175.64423 0.1140457 - 4 185.71165 -5.8781334 0 272.41077 0.17455524 - 5 286.28339 -4.3800108 0 424.61565 0.26911306 - 6 481.28097 -4.3052012 0 716.89433 0.45262045 - 7 487.26022 -3.8672741 0 726.29216 0.45830216 - 8 493.65478 -3.0242687 0 736.71742 0.46443761 - 9 495.66203 -3.4336343 0 739.31592 0.46613014 - 10 498.41831 -2.8837072 0 743.99613 0.46887706 - 11 499.20944 -2.7724783 0 745.29287 0.46966875 - 12 500.97345 -2.8281484 0 747.88057 0.47126462 - 13 507.46412 -2.7752775 0 757.65971 0.47728761 - 14 525.35729 -2.5749814 0 784.67292 0.49422171 - 15 563.9578 -2.9982381 0 842.09253 0.53043696 - 16 645.47602 -2.5519203 0 964.69389 0.60730795 - 17 647.09276 -2.2568468 0 967.41166 0.60891914 - 18 647.12596 -2.2791003 0 967.43915 0.60900309 - 19 647.24862 -2.2495226 0 967.65253 0.60908339 - 20 647.51175 -2.0239179 0 968.27244 0.60932598 -Loop time of 0.666895 on 4 procs for 20 steps with 1000 atoms + 0 1.5 -0.62417141 0 1.6235786 0.00152244 + 1 18.780412 -10.770009 0 17.372438 0.016236934 + 2 65.294131 -11.084501 0 86.758754 0.058617275 + 3 121.92555 -7.0612033 0 175.64423 0.11075612 + 4 185.71165 -5.8781334 0 272.41077 0.16952031 + 5 286.28339 -4.3800108 0 424.61565 0.26135067 + 6 481.28097 -4.3052012 0 716.89433 0.43956491 + 7 487.26022 -3.8672741 0 726.29216 0.44508273 + 8 493.65478 -3.0242687 0 736.71742 0.45104121 + 9 495.66203 -3.4336343 0 739.31592 0.45268492 + 10 498.41831 -2.8837072 0 743.99613 0.4553526 + 11 499.20944 -2.7724783 0 745.29287 0.45612146 + 12 500.97345 -2.8281484 0 747.88057 0.4576713 + 13 507.46412 -2.7752775 0 757.65971 0.46352056 + 14 525.35729 -2.5749814 0 784.67292 0.47996621 + 15 563.9578 -2.9982381 0 842.09253 0.51513685 + 16 645.47602 -2.5519203 0 964.69389 0.58979054 + 17 647.09276 -2.2568468 0 967.41166 0.59135526 + 18 647.12596 -2.2791003 0 967.43915 0.59143679 + 19 647.24862 -2.2495226 0 967.65253 0.59151478 + 20 647.51175 -2.0239179 0 968.27244 0.59175037 +Loop time of 0.357618 on 4 procs for 20 steps with 1000 atoms -Performance: 12955.555 tau/day, 29.990 timesteps/s -99.5% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 24159.843 tau/day, 55.926 timesteps/s +96.2% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.0002284 | 0.00024879 | 0.00025725 | 0.0 | 0.04 -Kspace | 0.6085 | 0.62278 | 0.6386 | 1.6 | 93.38 -Neigh | 0.023998 | 0.040044 | 0.054552 | 6.2 | 6.00 -Comm | 0.0025489 | 0.0028656 | 0.0031898 | 0.4 | 0.43 -Output | 0.0004077 | 0.00053912 | 0.00071406 | 0.0 | 0.08 -Modify | 0.00017953 | 0.00018525 | 0.00020218 | 0.0 | 0.03 -Other | | 0.0002366 | | | 0.04 +Pair | 5.9605e-05 | 6.2883e-05 | 6.8426e-05 | 0.0 | 0.02 +Kspace | 0.32759 | 0.3385 | 0.34421 | 1.1 | 94.65 +Neigh | 0.0090706 | 0.014676 | 0.025457 | 5.3 | 4.10 +Comm | 0.0013905 | 0.0015741 | 0.0017447 | 0.3 | 0.44 +Output | 0.00034785 | 0.00099462 | 0.0026579 | 0.0 | 0.28 +Modify | 5.2929e-05 | 8.3923e-05 | 0.00015783 | 0.0 | 0.02 +Other | | 0.001731 | | | 0.48 -Nlocal: 250 ave 259 max 240 min -Histogram: 1 0 0 0 0 2 0 0 0 1 -Nghost: 668.75 ave 679 max 657 min -Histogram: 1 0 0 0 0 1 1 0 0 1 -Neighs: 61085.5 ave 95363 max 24964 min -Histogram: 1 0 0 1 0 0 0 1 0 1 +Nlocal: 250 ave 512 max 84 min +Histogram: 1 0 2 0 0 0 0 0 0 1 +Nghost: 655.75 ave 784 max 433 min +Histogram: 1 0 0 0 0 0 0 1 1 1 +Neighs: 61085.5 ave 111012 max 21779 min +Histogram: 1 0 1 0 0 1 0 0 0 1 Total # of neighbors = 244342 Ave neighs/atom = 244.342 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.1 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.1 similarity index 52% rename from examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.1 index f8a85c6c6b..9fa1677017 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.hsph.g++.p2nfft.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.1 @@ -1,13 +1,12 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box units lj atom_style charge -read_data data.hammersley_shphere - orthogonal box = (-50.5 -50.5 -50.5) to (51.5 51.5 51.5) +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) 1 by 1 by 1 MPI processor grid reading atoms ... 1000 atoms @@ -47,51 +46,51 @@ Neighbor list info ... max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 2 ghost atom cutoff = 2 - binsize = 1, bins = 102 102 102 + binsize = 1, bins = 103 103 103 1 neighbor lists, perpetual/occasional/extra = 1 0 0 (1) pair zero, 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) = 10.3 | 10.3 | 10.3 Mbytes +Per MPI rank memory allocation (min/avg/max) = 10.44 | 10.44 | 10.44 Mbytes Step Temp E_pair E_mol TotEng Press - 0 1.5 -0.62417787 0 1.6235721 0.0015678854 - 1 18.780041 -10.770002 0 17.371889 0.016718957 - 2 65.289192 -11.084705 0 86.751149 0.060353634 - 3 121.92987 -7.0625759 0 175.64933 0.11404974 - 4 185.78164 -5.8777511 0 272.51603 0.17462194 - 5 286.36221 -4.3820531 0 424.73172 0.26918925 - 6 481.42203 -4.3095567 0 717.10136 0.45274086 - 7 488.59165 -3.8685193 0 728.28607 0.45956865 - 8 497.85288 -3.0417938 0 742.99075 0.46838117 - 9 499.61619 -3.4190063 0 745.25585 0.46983349 - 10 502.63691 -2.8360951 0 750.36531 0.47280815 - 11 504.4847 -2.7628089 0 753.20751 0.47462802 - 12 506.54494 -2.8460319 0 756.21157 0.4765145 - 13 508.2722 -2.7309328 0 758.91497 0.47813761 - 14 510.57053 -2.6094792 0 762.48045 0.48031438 - 15 513.14804 -2.7150819 0 766.23726 0.48275234 - 16 515.78127 -2.3961749 0 770.50206 0.48526336 - 17 515.70267 -2.2982581 0 770.48219 0.48526619 - 18 515.70813 -2.1516075 0 770.63702 0.48530395 - 19 515.74908 -2.0581483 0 770.79185 0.48530979 - 20 515.70881 -1.892235 0 770.89742 0.48527104 -Loop time of 1.06008 on 1 procs for 20 steps with 1000 atoms + 0 1.5 -0.62417787 0 1.6235721 0.0015226607 + 1 18.780041 -10.770002 0 17.371889 0.01623671 + 2 65.289192 -11.084705 0 86.751149 0.058612772 + 3 121.92987 -7.0625759 0 175.64933 0.11076005 + 4 185.78164 -5.8777511 0 272.51603 0.16958509 + 5 286.36221 -4.3820531 0 424.73172 0.26142466 + 6 481.42203 -4.3095567 0 717.10136 0.43968184 + 7 488.59165 -3.8685193 0 728.28608 0.44631269 + 8 497.85288 -3.0417938 0 742.99075 0.45487102 + 9 499.61619 -3.4190062 0 745.25585 0.45628145 + 10 502.63691 -2.8360951 0 750.36531 0.45917031 + 11 504.4847 -2.762809 0 753.20751 0.46093768 + 12 506.54494 -2.846032 0 756.21156 0.46276975 + 13 508.2722 -2.7309328 0 758.91496 0.46434604 + 14 510.57052 -2.6094795 0 762.48045 0.46646002 + 15 513.14804 -2.715082 0 766.23725 0.46882767 + 16 515.78127 -2.396175 0 770.50206 0.47126626 + 17 515.70267 -2.2982584 0 770.48219 0.47126901 + 18 515.70813 -2.1516073 0 770.63702 0.47130567 + 19 515.74908 -2.0581482 0 770.79185 0.47131134 + 20 515.70881 -1.8922354 0 770.89742 0.47127371 +Loop time of 0.313936 on 1 procs for 20 steps with 1000 atoms -Performance: 8150.306 tau/day, 18.866 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 27521.533 tau/day, 63.707 timesteps/s +99.9% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00022078 | 0.00022078 | 0.00022078 | 0.0 | 0.02 -Kspace | 0.91611 | 0.91611 | 0.91611 | 0.0 | 86.42 -Neigh | 0.14232 | 0.14232 | 0.14232 | 0.0 | 13.43 -Comm | 0.00015092 | 0.00015092 | 0.00015092 | 0.0 | 0.01 -Output | 0.00033736 | 0.00033736 | 0.00033736 | 0.0 | 0.03 -Modify | 0.00056243 | 0.00056243 | 0.00056243 | 0.0 | 0.05 -Other | | 0.0003803 | | | 0.04 +Pair | 5.7697e-05 | 5.7697e-05 | 5.7697e-05 | 0.0 | 0.02 +Kspace | 0.27613 | 0.27613 | 0.27613 | 0.0 | 87.96 +Neigh | 0.037193 | 0.037193 | 0.037193 | 0.0 | 11.85 +Comm | 4.9591e-05 | 4.9591e-05 | 4.9591e-05 | 0.0 | 0.02 +Output | 0.00022483 | 0.00022483 | 0.00022483 | 0.0 | 0.07 +Modify | 0.00014615 | 0.00014615 | 0.00014615 | 0.0 | 0.05 +Other | | 0.0001338 | | | 0.04 Nlocal: 1000 ave 1000 max 1000 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -104,4 +103,4 @@ Total # of neighbors = 247817 Ave neighs/atom = 247.817 Neighbor list builds = 19 Dangerous builds = 18 -Total wall time: 0:00:01 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.4 new file mode 100644 index 0000000000..a41a3d9685 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.hsph.p2nfft.g++.4 @@ -0,0 +1,106 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Point dipoles in a 2d box + +units lj +atom_style charge + +read_data data.hammersley_sphere + orthogonal box = (-51.5 -51.5 -51.5) to (51.5 51.5 51.5) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 1000 atoms +change_box all boundary f f f + +velocity all create 1.5 49893 + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + +# LAMMPS computes pairwise and long-range Coulombics + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +# Scafacos computes entire long-range Coulombics +# use dummy pair style to perform atom sorting + +pair_style zero 1.0 +pair_coeff * * + +#fix 2 all scafacos p3m tolerance field 0.001 + +kspace_style scafacos p2nfft 0.001 +kspace_modify scafacos tolerance potential + +timestep 0.005 +thermo 1 + +run 20 +Setting up ScaFaCoS with solver p2nfft ... +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 103 103 103 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 4.882 | 5.463 | 7.161 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 1.5 -0.62417787 0 1.6235721 0.0015226607 + 1 18.780041 -10.770002 0 17.371889 0.01623671 + 2 65.289192 -11.084705 0 86.751149 0.058612772 + 3 121.92987 -7.0625759 0 175.64933 0.11076005 + 4 185.78164 -5.8777511 0 272.51603 0.16958509 + 5 286.36221 -4.3820531 0 424.73172 0.26142466 + 6 481.42203 -4.3095567 0 717.10136 0.43968184 + 7 488.59165 -3.8685193 0 728.28608 0.44631269 + 8 497.85288 -3.0417938 0 742.99075 0.45487102 + 9 499.61619 -3.4190062 0 745.25585 0.45628145 + 10 502.63691 -2.8360951 0 750.36531 0.45917031 + 11 504.4847 -2.762809 0 753.20751 0.46093768 + 12 506.54494 -2.846032 0 756.21156 0.46276975 + 13 508.2722 -2.7309328 0 758.91496 0.46434604 + 14 510.57052 -2.6094795 0 762.48045 0.46646002 + 15 513.14804 -2.715082 0 766.23725 0.46882767 + 16 515.78127 -2.396175 0 770.50206 0.47126626 + 17 515.70267 -2.2982584 0 770.48219 0.47126901 + 18 515.70813 -2.1516073 0 770.63702 0.47130567 + 19 515.74908 -2.0581482 0 770.79185 0.47131134 + 20 515.70881 -1.8922354 0 770.89742 0.47127371 +Loop time of 0.283172 on 4 procs for 20 steps with 1000 atoms + +Performance: 30511.451 tau/day, 70.628 timesteps/s +94.8% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 5.8413e-05 | 6.2227e-05 | 6.8665e-05 | 0.0 | 0.02 +Kspace | 0.2548 | 0.26559 | 0.27139 | 1.2 | 93.79 +Neigh | 0.0083673 | 0.014062 | 0.024744 | 5.3 | 4.97 +Comm | 0.0013778 | 0.0014804 | 0.0015941 | 0.2 | 0.52 +Output | 0.00029898 | 0.00072974 | 0.0017858 | 0.0 | 0.26 +Modify | 3.6001e-05 | 6.3002e-05 | 0.00013065 | 0.0 | 0.02 +Other | | 0.001181 | | | 0.42 + +Nlocal: 250 ave 518 max 78 min +Histogram: 1 0 1 1 0 0 0 0 0 1 +Nghost: 659 ave 791 max 430 min +Histogram: 1 0 0 0 0 0 0 1 1 1 +Neighs: 61954.2 ave 115962 max 19730 min +Histogram: 1 0 1 0 0 1 0 0 0 1 + +Total # of neighbors = 247817 +Ave neighs/atom = 247.817 +Neighbor list builds = 19 +Dangerous builds = 18 +Total wall time: 0:00:00 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.1 b/examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.1 similarity index 80% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.1 rename to examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.1 index 1876a0e52b..2993de6329 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.1 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.1 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 1 by 1 MPI processor grid 4096 atoms - Time spent = 0.00049448 secs + Time spent = 0.000288725 secs velocity all create 1.5 49893 @@ -72,21 +71,21 @@ Step Temp E_pair E_mol TotEng Press 80 1.5033149 -1.7524495 0 0.50197233 10.46585 90 1.5108219 -1.7637095 0 0.50197005 10.515883 100 1.529239 -1.7913105 0 0.501988 10.638649 -Loop time of 18.1113 on 1 procs for 100 steps with 4096 atoms +Loop time of 7.17417 on 1 procs for 100 steps with 4096 atoms -Performance: 2385.257 tau/day, 5.521 timesteps/s -100.0% CPU use with 1 MPI tasks x 1 OpenMP threads +Performance: 6021.602 tau/day, 13.939 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.0014985 | 0.0014985 | 0.0014985 | 0.0 | 0.01 -Kspace | 18.079 | 18.079 | 18.079 | 0.0 | 99.82 +Pair | 0.00037169 | 0.00037169 | 0.00037169 | 0.0 | 0.01 +Kspace | 7.1639 | 7.1639 | 7.1639 | 0.0 | 99.86 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.014229 | 0.014229 | 0.014229 | 0.0 | 0.08 -Output | 0.0004642 | 0.0004642 | 0.0004642 | 0.0 | 0.00 -Modify | 0.011227 | 0.011227 | 0.011227 | 0.0 | 0.06 -Other | | 0.004455 | | | 0.02 +Comm | 0.0048451 | 0.0048451 | 0.0048451 | 0.0 | 0.07 +Output | 0.00030565 | 0.00030565 | 0.00030565 | 0.0 | 0.00 +Modify | 0.0029933 | 0.0029933 | 0.0029933 | 0.0 | 0.04 +Other | | 0.001761 | | | 0.02 Nlocal: 4096 ave 4096 max 4096 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -99,4 +98,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:21 +Total wall time: 0:00:07 diff --git a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.4 b/examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.4 similarity index 79% rename from examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.4 rename to examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.4 index bf4494df8b..19db90d822 100644 --- a/examples/USER/scafacos/log.08Aug18.scafacos.g++.p2nfft.4 +++ b/examples/USER/scafacos/log.27Nov18.scafacos.p2nfft.g++.4 @@ -1,5 +1,4 @@ -LAMMPS (2 Aug 2018) -OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:87) +LAMMPS (27 Nov 2018) using 1 OpenMP thread(s) per MPI task # Point dipoles in a 2d box @@ -16,7 +15,7 @@ replicate 8 8 8 orthogonal box = (0 0 0) to (8 8 8) 1 by 2 by 2 MPI processor grid 4096 atoms - Time spent = 0.000260592 secs + Time spent = 0.000186443 secs velocity all create 1.5 49893 @@ -72,21 +71,21 @@ Step Temp E_pair E_mol TotEng Press 80 1.5033149 -1.7524495 0 0.50197233 10.46585 90 1.5108219 -1.7637095 0 0.50197005 10.515883 100 1.529239 -1.7913105 0 0.501988 10.638649 -Loop time of 5.09997 on 4 procs for 100 steps with 4096 atoms +Loop time of 2.28914 on 4 procs for 100 steps with 4096 atoms -Performance: 8470.643 tau/day, 19.608 timesteps/s -99.8% CPU use with 4 MPI tasks x 1 OpenMP threads +Performance: 18871.750 tau/day, 43.685 timesteps/s +98.4% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.00069928 | 0.00071001 | 0.00073647 | 0.0 | 0.01 -Kspace | 5.0795 | 5.0796 | 5.0797 | 0.0 | 99.60 +Pair | 0.00019193 | 0.00020188 | 0.00020981 | 0.0 | 0.01 +Kspace | 2.2771 | 2.2771 | 2.2772 | 0.0 | 99.48 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.014101 | 0.014216 | 0.014331 | 0.1 | 0.28 -Output | 0.00030541 | 0.00033581 | 0.00039625 | 0.0 | 0.01 -Modify | 0.0030217 | 0.0030621 | 0.0030868 | 0.0 | 0.06 -Other | | 0.002036 | | | 0.04 +Comm | 0.0075378 | 0.007587 | 0.0076075 | 0.0 | 0.33 +Output | 0.00019574 | 0.00051248 | 0.0014374 | 0.0 | 0.02 +Modify | 0.0014074 | 0.0014608 | 0.0014906 | 0.1 | 0.06 +Other | | 0.002247 | | | 0.10 Nlocal: 1024 ave 1024 max 1024 min Histogram: 4 0 0 0 0 0 0 0 0 0 @@ -99,4 +98,4 @@ Total # of neighbors = 524288 Ave neighs/atom = 128 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:05 +Total wall time: 0:00:02 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.1 b/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.1 new file mode 100644 index 0000000000..92e85e072e --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.1 @@ -0,0 +1,102 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Point dipoles in a 2d box + +units lj +atom_style charge + +read_data data.NaCl + orthogonal box = (0 0 0) to (1 1 1) + 1 by 1 by 1 MPI processor grid + reading atoms ... + 8 atoms + +replicate 8 8 8 + orthogonal box = (0 0 0) to (8 8 8) + 1 by 1 by 1 MPI processor grid + 4096 atoms + Time spent = 0.000295162 secs + +velocity all create 1.5 49893 + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + +# LAMMPS computes pairwise and long-range Coulombics + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +# Scafacos computes entire long-range Coulombics +# use dummy pair style to perform atom sorting + +pair_style zero 1.0 +pair_coeff * * + +#fix 2 all scafacos p3m tolerance field 0.001 + +kspace_style scafacos p3m 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 +thermo 10 + +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 8 8 8 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 5.813 | 5.813 | 5.813 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 1.5 -1.7475754 0 0.5018753 11.99707 + 10 1.5000018 -1.7475781 0 0.50187528 11.997085 + 20 1.4999833 -1.7475525 0 0.50187314 11.996937 + 30 1.4999008 -1.7474408 0 0.50186112 11.996277 + 40 1.4997303 -1.7471984 0 0.5018478 11.994913 + 50 1.4995294 -1.7469059 0 0.50183901 11.993306 + 60 1.4995402 -1.7469269 0 0.50183416 11.993392 + 70 1.50036 -1.7481582 0 0.50183238 11.99995 + 80 1.5032409 -1.7524778 0 0.50183303 12.022991 + 90 1.5107445 -1.7637255 0 0.50183801 12.083005 + 100 1.5291568 -1.7913136 0 0.50186158 12.230268 +Loop time of 2.98343 on 1 procs for 100 steps with 4096 atoms + +Performance: 14479.957 tau/day, 33.518 timesteps/s +99.8% CPU use with 1 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 0.00035572 | 0.00035572 | 0.00035572 | 0.0 | 0.01 +Kspace | 2.9729 | 2.9729 | 2.9729 | 0.0 | 99.65 +Neigh | 0 | 0 | 0 | 0.0 | 0.00 +Comm | 0.005022 | 0.005022 | 0.005022 | 0.0 | 0.17 +Output | 0.00027037 | 0.00027037 | 0.00027037 | 0.0 | 0.01 +Modify | 0.003046 | 0.003046 | 0.003046 | 0.0 | 0.10 +Other | | 0.00182 | | | 0.06 + +Nlocal: 4096 ave 4096 max 4096 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 9728 ave 9728 max 9728 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 524288 ave 524288 max 524288 min +Histogram: 1 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 524288 +Ave neighs/atom = 128 +Neighbor list builds = 0 +Dangerous builds = 0 +Total wall time: 0:00:03 diff --git a/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.4 b/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.4 new file mode 100644 index 0000000000..18199eca16 --- /dev/null +++ b/examples/USER/scafacos/log.27Nov18.scafacos.p3m.g++.4 @@ -0,0 +1,102 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Point dipoles in a 2d box + +units lj +atom_style charge + +read_data data.NaCl + orthogonal box = (0 0 0) to (1 1 1) + 1 by 2 by 2 MPI processor grid + reading atoms ... + 8 atoms + +replicate 8 8 8 + orthogonal box = (0 0 0) to (8 8 8) + 1 by 2 by 2 MPI processor grid + 4096 atoms + Time spent = 0.000118017 secs + +velocity all create 1.5 49893 + +neighbor 1.0 bin +neigh_modify delay 0 + +fix 1 all nve + +# LAMMPS computes pairwise and long-range Coulombics + +#pair_style coul/long 3.0 +#pair_coeff * * +#kspace_style pppm 1.0e-3 + +# Scafacos computes entire long-range Coulombics +# use dummy pair style to perform atom sorting + +pair_style zero 1.0 +pair_coeff * * + +#fix 2 all scafacos p3m tolerance field 0.001 + +kspace_style scafacos p3m 0.001 +kspace_modify scafacos tolerance field + +timestep 0.005 +thermo 10 + +run 100 +Setting up ScaFaCoS with solver p3m ... +WARNING: Virial computation for P3M not available (src/USER-SCAFACOS/scafacos.cpp:104) +Neighbor list info ... + update every 1 steps, delay 0 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 2 + ghost atom cutoff = 2 + binsize = 1, bins = 8 8 8 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair zero, 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) = 4.008 | 4.008 | 4.008 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 1.5 -1.7475797 0 0.50187096 11.99707 + 10 1.5000019 -1.7475825 0 0.50187094 11.997085 + 20 1.4999837 -1.7475551 0 0.50187104 11.99694 + 30 1.4999024 -1.7474348 0 0.50186949 11.996289 + 40 1.4997328 -1.747187 0 0.50186299 11.994934 + 50 1.499532 -1.7468958 0 0.50185295 11.993327 + 60 1.4995421 -1.74692 0 0.50184401 11.993408 + 70 1.5003611 -1.7481536 0 0.5018387 11.999959 + 80 1.5032412 -1.7524745 0 0.50183679 12.022994 + 90 1.510744 -1.763723 0 0.50183979 12.083002 + 100 1.5291558 -1.7913123 0 0.5018614 12.23026 +Loop time of 1.10005 on 4 procs for 100 steps with 4096 atoms + +Performance: 39271.030 tau/day, 90.905 timesteps/s +96.4% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 0.0002172 | 0.00022924 | 0.0002377 | 0.0 | 0.02 +Kspace | 1.0848 | 1.0849 | 1.085 | 0.0 | 98.62 +Neigh | 0 | 0 | 0 | 0.0 | 0.00 +Comm | 0.010176 | 0.01062 | 0.01088 | 0.3 | 0.97 +Output | 0.00019169 | 0.0003345 | 0.00075459 | 0.0 | 0.03 +Modify | 0.001878 | 0.0018976 | 0.0019398 | 0.1 | 0.17 +Other | | 0.002097 | | | 0.19 + +Nlocal: 1024 ave 1024 max 1024 min +Histogram: 4 0 0 0 0 0 0 0 0 0 +Nghost: 5120 ave 5120 max 5120 min +Histogram: 4 0 0 0 0 0 0 0 0 0 +Neighs: 131072 ave 131072 max 131072 min +Histogram: 4 0 0 0 0 0 0 0 0 0 + +Total # of neighbors = 524288 +Ave neighs/atom = 128 +Neighbor list builds = 0 +Dangerous builds = 0 +Total wall time: 0:00:01