From 4b8c6d40e2e857330eaafe6d825e9df29e234780 Mon Sep 17 00:00:00 2001 From: Axel Kohlmeyer Date: Thu, 29 Nov 2018 15:15:14 -0500 Subject: [PATCH] update log files for qeq and rdf-adf examples --- examples/qeq/ffield.reax.cho | 0 ....buck.g++.1 => log.27Nov18.qeq.buck.g++.1} | 62 +++--- ....buck.g++.4 => log.27Nov18.qeq.buck.g++.4} | 62 +++--- ...eaxc.g++.1 => log.27Nov18.qeq.reaxc.g++.1} | 35 +-- ...eaxc.g++.4 => log.27Nov18.qeq.reaxc.g++.4} | 35 +-- ...2018.spce.g++.2 => log.27Nov18.spce.g++.1} | 131 +++++------ examples/rdf-adf/log.27Nov18.spce.g++.4 | 203 ++++++++++++++++++ 7 files changed, 389 insertions(+), 139 deletions(-) mode change 100755 => 100644 examples/qeq/ffield.reax.cho rename examples/qeq/{log.5Oct16.qeq.buck.g++.1 => log.27Nov18.qeq.buck.g++.1} (60%) rename examples/qeq/{log.5Oct16.qeq.buck.g++.4 => log.27Nov18.qeq.buck.g++.4} (57%) rename examples/qeq/{log.5Oct16.qeq.reaxc.g++.1 => log.27Nov18.qeq.reaxc.g++.1} (76%) rename examples/qeq/{log.5Oct16.qeq.reaxc.g++.4 => log.27Nov18.qeq.reaxc.g++.4} (76%) rename examples/rdf-adf/{log.10Oct2018.spce.g++.2 => log.27Nov18.spce.g++.1} (52%) create mode 100644 examples/rdf-adf/log.27Nov18.spce.g++.4 diff --git a/examples/qeq/ffield.reax.cho b/examples/qeq/ffield.reax.cho old mode 100755 new mode 100644 diff --git a/examples/qeq/log.5Oct16.qeq.buck.g++.1 b/examples/qeq/log.27Nov18.qeq.buck.g++.1 similarity index 60% rename from examples/qeq/log.5Oct16.qeq.buck.g++.1 rename to examples/qeq/log.27Nov18.qeq.buck.g++.1 index 2dbd6674ae..4d5225ccc3 100644 --- a/examples/qeq/log.5Oct16.qeq.buck.g++.1 +++ b/examples/qeq/log.27Nov18.qeq.buck.g++.1 @@ -1,4 +1,5 @@ -LAMMPS (5 Oct 2016) +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task # This example demonstrates the use of various fix qeq variants with # that defines and uses charges, in this case pair_style buck/coul/long @@ -14,6 +15,7 @@ replicate 2 2 2 orthogonal box = (0 0 0) to (50.3166 50.3166 56.0405) 1 by 1 by 1 MPI processor grid 9600 atoms + Time spent = 0.00114894 secs pair_style buck/coul/long 12.0 pair_coeff 2 2 1388.77 .3623188 175.0 @@ -50,47 +52,57 @@ fix 2 all qeq/fire 1 10 1.0e-4 100 param.qeq2 run 100 Ewald initialization ... -WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:316) + using 12-bit tables for long-range coulomb (src/kspace.cpp:321) G vector (1/distance) = 0.305064 estimated absolute RMS force accuracy = 2.07629e-05 estimated relative force accuracy = 1.44191e-06 KSpace vectors: actual max1d max3d = 13556 20 34460 kxmax kymax kzmax = 18 18 20 Neighbor list info ... - 2 neighbor list requests update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 13 ghost atom cutoff = 13 - binsize = 6.5 -> bins = 8 8 9 -Memory usage per processor = 110.875 Mbytes + binsize = 6.5, bins = 8 8 9 + 2 neighbor lists, perpetual/occasional/extra = 2 0 0 + (1) pair buck/coul/long, perpetual + attributes: half, newton on + pair build: half/bin/atomonly/newton + stencil: half/bin/3d/newton + bin: standard + (2) fix qeq/fire, perpetual, copy from (1) + attributes: half, newton on + pair build: copy + stencil: none + bin: none +Per MPI rank memory allocation (min/avg/max) = 134 | 134 | 134 Mbytes Step PotEng c_q1 c_q2 v_qtot S/CPU 0 -27457.219 0.85227886 -0.42613943 -2.1827873e-10 0 - 10 -27626.057 0.85486228 -0.42743114 -2.0372681e-10 0.64960264 - 20 -27975.085 0.85968531 -0.42984266 -8.8220986e-11 0.55300005 - 30 -28552.628 0.86755661 -0.4337783 1.4142643e-10 0.52434987 - 40 -29133.643 0.87426387 -0.43713193 1.6871127e-10 0.52326849 - 50 -29697.011 0.8794039 -0.43970195 1.2460077e-10 0.52083626 - 60 -30342.001 0.88478594 -0.44239297 -4.3655746e-11 0.52824882 - 70 -31081.138 0.8906973 -0.44534865 -4.7293724e-11 0.56010601 - 80 -31792.732 0.89506635 -0.44753317 -3.774403e-11 0.60040973 - 90 -32424.749 0.89714841 -0.44857421 -1.0004442e-10 0.57758717 - 100 -32998.353 0.89755721 -0.44877861 -1.0231815e-10 0.59560798 -Loop time of 178.401 on 1 procs for 100 steps with 9600 atoms + 10 -27626.057 0.85486228 -0.42743114 -2.0372681e-10 0.64313877 + 20 -27975.085 0.85968531 -0.42984266 -1.036824e-10 0.55119179 + 30 -28552.628 0.86755661 -0.4337783 1.3051249e-10 0.53160643 + 40 -29133.643 0.87426387 -0.43713193 1.1368684e-10 0.53075341 + 50 -29697.011 0.8794039 -0.43970195 1.200533e-10 0.52358127 + 60 -30342.001 0.88478594 -0.44239297 6.002665e-11 0.5366762 + 70 -31081.138 0.8906973 -0.44534865 -4.7293724e-11 0.55904546 + 80 -31792.732 0.89506635 -0.44753317 -4.3200998e-11 0.59606079 + 90 -32424.749 0.89714841 -0.44857421 -1.1596057e-10 0.58047419 + 100 -32998.353 0.89755721 -0.44877861 -1.0231815e-10 0.59444001 +Loop time of 177.79 on 1 procs for 100 steps with 9600 atoms -Performance: 0.005 ns/day, 4955.597 hours/ns, 0.561 timesteps/s -99.9% CPU use with 1 MPI tasks x no OpenMP threads +Performance: 0.005 ns/day, 4938.612 hours/ns, 0.562 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 | 15.042 | 15.042 | 15.042 | 0.0 | 8.43 -Kspace | 98.245 | 98.245 | 98.245 | 0.0 | 55.07 +Pair | 11.518 | 11.518 | 11.518 | 0.0 | 6.48 +Kspace | 107.37 | 107.37 | 107.37 | 0.0 | 60.39 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.019511 | 0.019511 | 0.019511 | 0.0 | 0.01 -Output | 0.0020375 | 0.0020375 | 0.0020375 | 0.0 | 0.00 -Modify | 65.083 | 65.083 | 65.083 | 0.0 | 36.48 -Other | | 0.009152 | | | 0.01 +Comm | 0.019721 | 0.019721 | 0.019721 | 0.0 | 0.01 +Output | 0.002218 | 0.002218 | 0.002218 | 0.0 | 0.00 +Modify | 58.869 | 58.869 | 58.869 | 0.0 | 33.11 +Other | | 0.007197 | | | 0.00 Nlocal: 9600 ave 9600 max 9600 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -103,4 +115,4 @@ Total # of neighbors = 2940800 Ave neighs/atom = 306.333 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:03:02 +Total wall time: 0:03:01 diff --git a/examples/qeq/log.5Oct16.qeq.buck.g++.4 b/examples/qeq/log.27Nov18.qeq.buck.g++.4 similarity index 57% rename from examples/qeq/log.5Oct16.qeq.buck.g++.4 rename to examples/qeq/log.27Nov18.qeq.buck.g++.4 index 0f628740bd..947c3caeaf 100644 --- a/examples/qeq/log.5Oct16.qeq.buck.g++.4 +++ b/examples/qeq/log.27Nov18.qeq.buck.g++.4 @@ -1,4 +1,5 @@ -LAMMPS (5 Oct 2016) +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task # This example demonstrates the use of various fix qeq variants with # that defines and uses charges, in this case pair_style buck/coul/long @@ -14,6 +15,7 @@ replicate 2 2 2 orthogonal box = (0 0 0) to (50.3166 50.3166 56.0405) 1 by 2 by 2 MPI processor grid 9600 atoms + Time spent = 0.000675201 secs pair_style buck/coul/long 12.0 pair_coeff 2 2 1388.77 .3623188 175.0 @@ -50,47 +52,57 @@ fix 2 all qeq/fire 1 10 1.0e-4 100 param.qeq2 run 100 Ewald initialization ... -WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:316) + using 12-bit tables for long-range coulomb (src/kspace.cpp:321) G vector (1/distance) = 0.305064 estimated absolute RMS force accuracy = 2.07629e-05 estimated relative force accuracy = 1.44191e-06 KSpace vectors: actual max1d max3d = 13556 20 34460 kxmax kymax kzmax = 18 18 20 Neighbor list info ... - 2 neighbor list requests update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 13 ghost atom cutoff = 13 - binsize = 6.5 -> bins = 8 8 9 -Memory usage per processor = 46.867 Mbytes + binsize = 6.5, bins = 8 8 9 + 2 neighbor lists, perpetual/occasional/extra = 2 0 0 + (1) pair buck/coul/long, perpetual + attributes: half, newton on + pair build: half/bin/atomonly/newton + stencil: half/bin/3d/newton + bin: standard + (2) fix qeq/fire, perpetual, copy from (1) + attributes: half, newton on + pair build: copy + stencil: none + bin: none +Per MPI rank memory allocation (min/avg/max) = 53.06 | 53.13 | 53.21 Mbytes Step PotEng c_q1 c_q2 v_qtot S/CPU 0 -27457.215 0.85227886 -0.42613943 2.1373125e-11 0 - 10 -27626.057 0.85486228 -0.42743114 3.0468073e-11 2.561772 - 20 -27975.085 0.85968531 -0.42984266 9.777068e-11 2.1470405 - 30 -28552.627 0.86755661 -0.4337783 1.2823875e-10 2.0585052 - 40 -29133.643 0.87426387 -0.43713193 1.5506885e-10 2.0319632 - 50 -29697.01 0.8794039 -0.43970195 2.1873348e-10 2.0350244 - 60 -30342 0.88478594 -0.44239297 1.891749e-10 2.0793976 - 70 -31081.139 0.89069733 -0.44534866 1.4688339e-10 2.1759002 - 80 -31792.732 0.89506635 -0.44753317 1.4142643e-10 2.3320978 - 90 -32424.752 0.89714841 -0.44857421 9.9134922e-11 2.2673305 - 100 -32998.353 0.89755721 -0.44877861 1.5097612e-10 2.3389389 -Loop time of 45.6331 on 4 procs for 100 steps with 9600 atoms + 10 -27626.057 0.85486228 -0.42743114 3.0468073e-11 2.4245312 + 20 -27975.085 0.85968531 -0.42984266 1.0095391e-10 2.0185316 + 30 -28552.627 0.86755661 -0.4337783 1.3096724e-10 1.9605335 + 40 -29133.643 0.87426387 -0.43713193 1.5279511e-10 1.9624139 + 50 -29697.01 0.8794039 -0.43970195 1.6461854e-10 1.8113263 + 60 -30342 0.88478594 -0.44239297 1.7826096e-10 1.9537722 + 70 -31081.139 0.89069733 -0.44534866 1.4733814e-10 2.058406 + 80 -31792.732 0.89506635 -0.44753317 1.3824319e-10 2.2160813 + 90 -32424.752 0.89714841 -0.44857421 1.2914825e-10 2.0952145 + 100 -32998.353 0.89755721 -0.44877861 1.4824764e-10 2.1292486 +Loop time of 48.7541 on 4 procs for 100 steps with 9600 atoms -Performance: 0.019 ns/day, 1267.586 hours/ns, 2.191 timesteps/s -99.9% CPU use with 4 MPI tasks x no OpenMP threads +Performance: 0.018 ns/day, 1354.281 hours/ns, 2.051 timesteps/s +97.4% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 3.8297 | 3.8983 | 3.938 | 2.1 | 8.54 -Kspace | 24.434 | 24.579 | 24.78 | 2.9 | 53.86 +Pair | 2.9747 | 3.0315 | 3.0758 | 2.1 | 6.22 +Kspace | 27.873 | 28.264 | 28.63 | 5.3 | 57.97 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.078239 | 0.31795 | 0.53069 | 30.8 | 0.70 -Output | 0.00097322 | 0.0010365 | 0.0011294 | 0.2 | 0.00 -Modify | 16.831 | 16.832 | 16.832 | 0.0 | 36.88 -Other | | 0.005259 | | | 0.01 +Comm | 0.53835 | 0.8523 | 1.2286 | 28.2 | 1.75 +Output | 0.0012984 | 0.001591 | 0.0024178 | 1.2 | 0.00 +Modify | 16.58 | 16.59 | 16.601 | 0.3 | 34.03 +Other | | 0.01409 | | | 0.03 Nlocal: 2400 ave 2400 max 2400 min Histogram: 4 0 0 0 0 0 0 0 0 0 @@ -103,4 +115,4 @@ Total # of neighbors = 2940800 Ave neighs/atom = 306.333 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:46 +Total wall time: 0:00:49 diff --git a/examples/qeq/log.5Oct16.qeq.reaxc.g++.1 b/examples/qeq/log.27Nov18.qeq.reaxc.g++.1 similarity index 76% rename from examples/qeq/log.5Oct16.qeq.reaxc.g++.1 rename to examples/qeq/log.27Nov18.qeq.reaxc.g++.1 index 493b4b62d8..c88acc39f2 100644 --- a/examples/qeq/log.5Oct16.qeq.reaxc.g++.1 +++ b/examples/qeq/log.27Nov18.qeq.reaxc.g++.1 @@ -1,4 +1,5 @@ -LAMMPS (5 Oct 2016) +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task # This example demonstrates the use of various fix qeq variants with pair reax/c # You can comment in/out various versions below # @@ -54,13 +55,23 @@ timestep 0.25 run 10 Neighbor list info ... - 2 neighbor list requests update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 11 ghost atom cutoff = 11 - binsize = 5.5 -> bins = 5 5 5 -Memory usage per processor = 15.8004 Mbytes + binsize = 5.5, bins = 5 5 5 + 2 neighbor lists, perpetual/occasional/extra = 2 0 0 + (1) pair reax/c, perpetual + attributes: half, newton off, ghost + pair build: half/bin/newtoff/ghost + stencil: half/ghost/bin/3d/newtoff + bin: standard + (2) fix qeq/reax, perpetual, copy from (1) + attributes: half, newton off, ghost + pair build: copy + stencil: none + bin: none +Per MPI rank memory allocation (min/avg/max) = 16.65 | 16.65 | 16.65 Mbytes Step PotEng c_q1 c_q2 c_q3 v_qtot 0 -10226.557 0.095634063 -0.15658793 -0.091167279 4.4408921e-16 1 -10225.799 0.095649584 -0.1566219 -0.091171371 7.1054274e-15 @@ -73,20 +84,20 @@ Step PotEng c_q1 c_q2 c_q3 v_qtot 8 -10194.646 0.095767243 -0.15689184 -0.091186932 -2.4424907e-15 9 -10190.016 0.095760528 -0.15687664 -0.091185782 -4.4408921e-16 10 -10186.168 0.095748006 -0.15684815 -0.09118383 1.110223e-15 -Loop time of 0.0398569 on 1 procs for 10 steps with 105 atoms +Loop time of 0.0322483 on 1 procs for 10 steps with 105 atoms -Performance: 5.419 ns/day, 4.429 hours/ns, 250.898 timesteps/s -100.3% CPU use with 1 MPI tasks x no OpenMP threads +Performance: 6.698 ns/day, 3.583 hours/ns, 310.094 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 | 0.034917 | 0.034917 | 0.034917 | 0.0 | 87.61 +Pair | 0.026229 | 0.026229 | 0.026229 | 0.0 | 81.34 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 3.2663e-05 | 3.2663e-05 | 3.2663e-05 | 0.0 | 0.08 -Output | 0.00016952 | 0.00016952 | 0.00016952 | 0.0 | 0.43 -Modify | 0.0047123 | 0.0047123 | 0.0047123 | 0.0 | 11.82 -Other | | 2.527e-05 | | | 0.06 +Comm | 5.2214e-05 | 5.2214e-05 | 5.2214e-05 | 0.0 | 0.16 +Output | 0.00027299 | 0.00027299 | 0.00027299 | 0.0 | 0.85 +Modify | 0.0056667 | 0.0056667 | 0.0056667 | 0.0 | 17.57 +Other | | 2.694e-05 | | | 0.08 Nlocal: 105 ave 105 max 105 min Histogram: 1 0 0 0 0 0 0 0 0 0 diff --git a/examples/qeq/log.5Oct16.qeq.reaxc.g++.4 b/examples/qeq/log.27Nov18.qeq.reaxc.g++.4 similarity index 76% rename from examples/qeq/log.5Oct16.qeq.reaxc.g++.4 rename to examples/qeq/log.27Nov18.qeq.reaxc.g++.4 index 834c8170c8..c54a99577e 100644 --- a/examples/qeq/log.5Oct16.qeq.reaxc.g++.4 +++ b/examples/qeq/log.27Nov18.qeq.reaxc.g++.4 @@ -1,4 +1,5 @@ -LAMMPS (5 Oct 2016) +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task # This example demonstrates the use of various fix qeq variants with pair reax/c # You can comment in/out various versions below # @@ -54,13 +55,23 @@ timestep 0.25 run 10 Neighbor list info ... - 2 neighbor list requests update every 1 steps, delay 0 steps, check yes max neighbors/atom: 2000, page size: 100000 master list distance cutoff = 11 ghost atom cutoff = 11 - binsize = 5.5 -> bins = 5 5 5 -Memory usage per processor = 11.6046 Mbytes + binsize = 5.5, bins = 5 5 5 + 2 neighbor lists, perpetual/occasional/extra = 2 0 0 + (1) pair reax/c, perpetual + attributes: half, newton off, ghost + pair build: half/bin/newtoff/ghost + stencil: half/ghost/bin/3d/newtoff + bin: standard + (2) fix qeq/reax, perpetual, copy from (1) + attributes: half, newton off, ghost + pair build: copy + stencil: none + bin: none +Per MPI rank memory allocation (min/avg/max) = 10.83 | 11.69 | 12.52 Mbytes Step PotEng c_q1 c_q2 c_q3 v_qtot 0 -10226.557 0.095633919 -0.15658765 -0.091167194 1.7763568e-15 1 -10225.799 0.0956503 -0.15662357 -0.09117143 2.8865799e-15 @@ -73,20 +84,20 @@ Step PotEng c_q1 c_q2 c_q3 v_qtot 8 -10194.646 0.095766449 -0.15689014 -0.091186673 -4.4408921e-16 9 -10190.016 0.095761078 -0.15687818 -0.09118551 -4.4408921e-16 10 -10186.168 0.095747223 -0.15684634 -0.091183742 0 -Loop time of 0.0217528 on 4 procs for 10 steps with 105 atoms +Loop time of 0.0185181 on 4 procs for 10 steps with 105 atoms -Performance: 9.930 ns/day, 2.417 hours/ns, 459.710 timesteps/s -93.1% CPU use with 4 MPI tasks x no OpenMP threads +Performance: 11.664 ns/day, 2.058 hours/ns, 540.011 timesteps/s +92.5% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 0.012203 | 0.014022 | 0.015427 | 1.0 | 64.46 +Pair | 0.0097179 | 0.01078 | 0.012052 | 0.8 | 58.21 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.00011754 | 0.0015323 | 0.0033445 | 3.0 | 7.04 -Output | 0.00041366 | 0.00044626 | 0.00048447 | 0.1 | 2.05 -Modify | 0.0056725 | 0.0056758 | 0.0056815 | 0.0 | 26.09 -Other | | 7.629e-05 | | | 0.35 +Comm | 0.00041604 | 0.0017492 | 0.0028496 | 2.1 | 9.45 +Output | 0.00041103 | 0.00046283 | 0.00051498 | 0.0 | 2.50 +Modify | 0.0051849 | 0.0052357 | 0.0052917 | 0.1 | 28.27 +Other | | 0.0002902 | | | 1.57 Nlocal: 26.25 ave 35 max 15 min Histogram: 1 0 0 1 0 0 0 0 0 2 diff --git a/examples/rdf-adf/log.10Oct2018.spce.g++.2 b/examples/rdf-adf/log.27Nov18.spce.g++.1 similarity index 52% rename from examples/rdf-adf/log.10Oct2018.spce.g++.2 rename to examples/rdf-adf/log.27Nov18.spce.g++.1 index d19e69a031..70adb9d1c5 100644 --- a/examples/rdf-adf/log.10Oct2018.spce.g++.2 +++ b/examples/rdf-adf/log.27Nov18.spce.g++.1 @@ -1,12 +1,13 @@ -LAMMPS (10 Oct 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 +# Liquid water RDFs and ADFs (~12 O-O-O/atom, ~1 O-H...O/atom) + units real atom_style full read_data data.spce orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736) - 1 by 2 by 1 MPI processor grid + 1 by 1 by 1 MPI processor grid reading atoms ... 4500 atoms scanning bonds ... @@ -65,7 +66,7 @@ PPPM initialization ... estimated absolute RMS force accuracy = 0.000394674 estimated relative force accuracy = 1.18855e-06 using double precision FFTs - 3d grid and FFT values/proc = 59643 32000 + 3d grid and FFT values/proc = 103823 64000 Neighbor list info ... update every 1 steps, delay 2 steps, check yes max neighbors/atom: 2000, page size: 100000 @@ -78,39 +79,39 @@ Neighbor list info ... pair build: half/bin/newton stencil: half/bin/3d/newton bin: standard -Per MPI rank memory allocation (min/avg/max) = 25.06 | 25.25 | 25.44 Mbytes +Per MPI rank memory allocation (min/avg/max) = 35.36 | 35.36 | 35.36 Mbytes Step Temp E_pair E_mol TotEng Press 0 300 -16692.369 0 -14010.534 -112.83562 - 100 283.44729 -17008.717 0 -14474.854 -162.06374 - 200 298.75279 -16765.544 0 -14094.858 428.79127 - 300 296.6501 -16589.155 0 -13937.267 547.40768 - 400 303.83151 -16625.028 0 -13908.942 237.9775 - 500 298.01615 -16717.015 0 -14052.915 230.7095 -Loop time of 21.4041 on 2 procs for 500 steps with 4500 atoms + 100 283.44729 -17008.717 0 -14474.854 -162.06378 + 200 298.75279 -16765.543 0 -14094.858 428.7917 + 300 296.65014 -16589.155 0 -13937.267 547.40796 + 400 303.82963 -16625.011 0 -13908.942 237.93694 + 500 298.00057 -16716.887 0 -14052.926 231.55014 +Loop time of 38.2796 on 1 procs for 500 steps with 4500 atoms -Performance: 4.037 ns/day, 5.946 hours/ns, 23.360 timesteps/s -94.8% CPU use with 2 MPI tasks x 1 OpenMP threads +Performance: 2.257 ns/day, 10.633 hours/ns, 13.062 timesteps/s +99.2% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 14.892 | 15.034 | 15.176 | 3.7 | 70.24 -Bond | 0.00056624 | 0.00059342 | 0.0006206 | 0.0 | 0.00 -Kspace | 3.987 | 4.1321 | 4.2773 | 7.1 | 19.31 -Neigh | 1.7494 | 1.7496 | 1.7497 | 0.0 | 8.17 -Comm | 0.20554 | 0.20637 | 0.2072 | 0.2 | 0.96 -Output | 0.00015688 | 0.00036144 | 0.00056601 | 0.0 | 0.00 -Modify | 0.25707 | 0.2606 | 0.26413 | 0.7 | 1.22 -Other | | 0.02059 | | | 0.10 +Pair | 28.428 | 28.428 | 28.428 | 0.0 | 74.26 +Bond | 0.00056672 | 0.00056672 | 0.00056672 | 0.0 | 0.00 +Kspace | 5.3161 | 5.3161 | 5.3161 | 0.0 | 13.89 +Neigh | 4.1185 | 4.1185 | 4.1185 | 0.0 | 10.76 +Comm | 0.12788 | 0.12788 | 0.12788 | 0.0 | 0.33 +Output | 0.00021887 | 0.00021887 | 0.00021887 | 0.0 | 0.00 +Modify | 0.26748 | 0.26748 | 0.26748 | 0.0 | 0.70 +Other | | 0.02102 | | | 0.05 -Nlocal: 2250 ave 2258 max 2242 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 16319 ave 16381 max 16257 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 1.30073e+06 ave 1.32386e+06 max 1.2776e+06 min -Histogram: 1 0 0 0 0 0 0 0 0 1 +Nlocal: 4500 ave 4500 max 4500 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 21248 ave 21248 max 21248 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 2.60146e+06 ave 2.60146e+06 max 2.60146e+06 min +Histogram: 1 0 0 0 0 0 0 0 0 0 -Total # of neighbors = 2601457 +Total # of neighbors = 2601459 Ave neighs/atom = 578.102 Ave special neighs/atom = 2 Neighbor list builds = 45 @@ -119,7 +120,7 @@ Dangerous builds = 0 reset_timestep 0 compute gofr all rdf 100 1 1 2 2 1 2 # O-O, H-H, O-H -compute gofa all adf 45 1 1 1 2.0 3.5 2.0 3.5 1 2 1 0.0 1.2 1.5 2.5 +compute gofa all adf 45 1 1 1 2.0 3.5 2.0 3.5 2 1 1 0.0 1.2 1.5 2.5 # O-O-O, O-H...O fix rdf all ave/time 100 10 1000 c_gofr[*] file spce-rdf.dat mode vector fix adf all ave/time 10 100 1000 c_gofa[*] file spce-adf.dat mode vector @@ -132,7 +133,7 @@ PPPM initialization ... estimated absolute RMS force accuracy = 0.000394674 estimated relative force accuracy = 1.18855e-06 using double precision FFTs - 3d grid and FFT values/proc = 59643 32000 + 3d grid and FFT values/proc = 103823 64000 Neighbor list info ... update every 1 steps, delay 2 steps, check yes max neighbors/atom: 2000, page size: 100000 @@ -155,48 +156,48 @@ Neighbor list info ... pair build: full/bin stencil: full/bin/3d bin: standard -Per MPI rank memory allocation (min/avg/max) = 26.78 | 26.78 | 26.78 Mbytes +Per MPI rank memory allocation (min/avg/max) = 36.67 | 36.67 | 36.67 Mbytes Step Temp E_pair E_mol TotEng Press - 0 298.01615 -16717.015 0 -14052.915 230.81371 - 100 307.1766 -16759.33 0 -14013.341 454.2771 - 200 298.94628 -16674.186 0 -14001.771 114.20846 - 300 293.13091 -16581.542 0 -13961.113 272.85574 - 400 294.47017 -16556.872 0 -13924.471 180.3252 - 500 305.57174 -16647.976 0 -13916.333 -444.14856 - 600 302.53992 -16670.304 0 -13965.764 114.82353 - 700 306.56761 -16616.508 0 -13875.962 534.02537 - 800 299.06297 -16644.133 0 -13970.675 83.643063 - 900 301.15522 -16674.021 0 -13981.859 325.04538 - 1000 298.14963 -16701.663 0 -14036.369 356.0601 -Loop time of 53.3181 on 2 procs for 1000 steps with 4500 atoms + 0 298.00057 -16716.887 0 -14052.926 231.6595 + 100 307.31045 -16761.022 0 -14013.835 449.26027 + 200 299.52847 -16679.165 0 -14001.546 148.44719 + 300 293.68499 -16583.548 0 -13958.166 140.79069 + 400 306.76266 -16658.573 0 -13916.284 481.26934 + 500 294.75648 -16640.446 0 -14005.485 585.05479 + 600 303.19282 -16629.985 0 -13919.608 328.23667 + 700 300.28233 -16590.155 0 -13905.797 -176.71076 + 800 292.36899 -16620.826 0 -14007.208 -194.83408 + 900 304.92802 -16633.331 0 -13907.443 479.49808 + 1000 300.64529 -16598.233 0 -13910.63 904.96137 +Loop time of 107.579 on 1 procs for 1000 steps with 4500 atoms -Performance: 3.241 ns/day, 7.405 hours/ns, 18.755 timesteps/s -97.3% CPU use with 2 MPI tasks x 1 OpenMP threads +Performance: 1.606 ns/day, 14.942 hours/ns, 9.295 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 | 28.831 | 29.365 | 29.899 | 9.9 | 55.07 -Bond | 0.00097084 | 0.0010794 | 0.001188 | 0.3 | 0.00 -Kspace | 7.3086 | 7.8356 | 8.3626 | 18.8 | 14.70 -Neigh | 3.7241 | 3.7245 | 3.7248 | 0.0 | 6.99 -Comm | 0.32839 | 0.33495 | 0.34151 | 1.1 | 0.63 -Output | 0.00043344 | 0.0015392 | 0.002645 | 2.8 | 0.00 -Modify | 12.013 | 12.014 | 12.015 | 0.0 | 22.53 -Other | | 0.04153 | | | 0.08 +Pair | 58.928 | 58.928 | 58.928 | 0.0 | 54.78 +Bond | 0.0012271 | 0.0012271 | 0.0012271 | 0.0 | 0.00 +Kspace | 10.698 | 10.698 | 10.698 | 0.0 | 9.94 +Neigh | 8.7649 | 8.7649 | 8.7649 | 0.0 | 8.15 +Comm | 0.2608 | 0.2608 | 0.2608 | 0.0 | 0.24 +Output | 0.00043702 | 0.00043702 | 0.00043702 | 0.0 | 0.00 +Modify | 28.883 | 28.883 | 28.883 | 0.0 | 26.85 +Other | | 0.04301 | | | 0.04 -Nlocal: 2250 ave 2251 max 2249 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Nghost: 16300 ave 16358 max 16242 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -Neighs: 1.301e+06 ave 1.31594e+06 max 1.28606e+06 min -Histogram: 1 0 0 0 0 0 0 0 0 1 -FullNghs: 2.602e+06 ave 2.60923e+06 max 2.59476e+06 min -Histogram: 1 0 0 0 0 0 0 0 0 1 +Nlocal: 4500 ave 4500 max 4500 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Nghost: 21275 ave 21275 max 21275 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +Neighs: 2.60217e+06 ave 2.60217e+06 max 2.60217e+06 min +Histogram: 1 0 0 0 0 0 0 0 0 0 +FullNghs: 5.20478e+06 ave 5.20478e+06 max 5.20478e+06 min +Histogram: 1 0 0 0 0 0 0 0 0 0 -Total # of neighbors = 5203998 -Ave neighs/atom = 1156.44 +Total # of neighbors = 5204784 +Ave neighs/atom = 1156.62 Ave special neighs/atom = 2 -Neighbor list builds = 93 +Neighbor list builds = 94 Dangerous builds = 0 -Total wall time: 0:01:14 +Total wall time: 0:02:26 diff --git a/examples/rdf-adf/log.27Nov18.spce.g++.4 b/examples/rdf-adf/log.27Nov18.spce.g++.4 new file mode 100644 index 0000000000..4fa0369e19 --- /dev/null +++ b/examples/rdf-adf/log.27Nov18.spce.g++.4 @@ -0,0 +1,203 @@ +LAMMPS (27 Nov 2018) + using 1 OpenMP thread(s) per MPI task +# Liquid water RDFs and ADFs (~12 O-O-O/atom, ~1 O-H...O/atom) + +units real +atom_style full + +read_data data.spce + orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736) + 2 by 2 by 1 MPI processor grid + reading atoms ... + 4500 atoms + scanning bonds ... + 2 = max bonds/atom + scanning angles ... + 1 = max angles/atom + reading bonds ... + 3000 bonds + reading angles ... + 1500 angles + 2 = max # of 1-2 neighbors + 1 = max # of 1-3 neighbors + 1 = max # of 1-4 neighbors + 2 = max # of special neighbors + +pair_style lj/cut/coul/long 12.0 12.0 +pair_coeff * * 0.0 1.0 +pair_coeff 1 1 0.15535 3.166 +kspace_style pppm 1.0e-6 + +bond_style harmonic +angle_style harmonic +dihedral_style none +improper_style none + +bond_coeff 1 1000.00 1.000 +angle_coeff 1 100.0 109.47 + +# need to set bond/angle inclusion to > 0.0 +# so that intramolecular pairs are included in neighbor lists (required for second ADF) +special_bonds lj/coul 1.0e-100 1.0e-100 1.0 + 2 = max # of 1-2 neighbors + 1 = max # of 1-3 neighbors + 2 = max # of special neighbors + +neighbor 2.0 bin +timestep 2.0 +neigh_modify every 1 delay 2 check yes + +fix 1 all shake 0.0001 20 0 b 1 a 1 + 0 = # of size 2 clusters + 0 = # of size 3 clusters + 0 = # of size 4 clusters + 1500 = # of frozen angles +fix 2 all nvt temp 300.0 300.0 100.0 + +velocity all create 300.0 6244325 + +thermo 100 +run 500 +PPPM initialization ... + using 12-bit tables for long-range coulomb (src/kspace.cpp:321) + G vector (1/distance) = 0.279652 + grid = 40 40 40 + stencil order = 5 + estimated absolute RMS force accuracy = 0.000394674 + estimated relative force accuracy = 1.18855e-06 + using double precision FFTs + 3d grid and FFT values/proc = 34263 16000 +Neighbor list info ... + update every 1 steps, delay 2 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 14 + ghost atom cutoff = 14 + binsize = 7, bins = 6 6 6 + 1 neighbor lists, perpetual/occasional/extra = 1 0 0 + (1) pair lj/cut/coul/long, perpetual + attributes: half, newton on + pair build: half/bin/newton + stencil: half/bin/3d/newton + bin: standard +Per MPI rank memory allocation (min/avg/max) = 13.1 | 13.1 | 13.1 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 300 -16692.369 0 -14010.534 -112.83562 + 100 283.44729 -17008.717 0 -14474.854 -162.06378 + 200 298.75279 -16765.543 0 -14094.858 428.79175 + 300 296.65013 -16589.155 0 -13937.267 547.40809 + 400 303.82993 -16625.014 0 -13908.942 237.957 + 500 298.00206 -16716.893 0 -14052.919 231.33112 +Loop time of 12.5516 on 4 procs for 500 steps with 4500 atoms + +Performance: 6.884 ns/day, 3.487 hours/ns, 39.836 timesteps/s +94.9% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 7.739 | 7.9051 | 8.2663 | 7.5 | 62.98 +Bond | 0.00061631 | 0.00064486 | 0.00070524 | 0.0 | 0.01 +Kspace | 2.7001 | 3.0573 | 3.2239 | 11.9 | 24.36 +Neigh | 1.1736 | 1.174 | 1.1743 | 0.0 | 9.35 +Comm | 0.18222 | 0.1869 | 0.19248 | 0.8 | 1.49 +Output | 0.00017595 | 0.00032246 | 0.00076079 | 0.0 | 0.00 +Modify | 0.20354 | 0.20467 | 0.20652 | 0.2 | 1.63 +Other | | 0.02259 | | | 0.18 + +Nlocal: 1125 ave 1132 max 1114 min +Histogram: 1 0 0 0 0 0 1 1 0 1 +Nghost: 12241 ave 12298 max 12196 min +Histogram: 2 0 0 0 0 0 0 1 0 1 +Neighs: 650366 ave 671163 max 631441 min +Histogram: 1 0 0 1 0 1 0 0 0 1 + +Total # of neighbors = 2601464 +Ave neighs/atom = 578.103 +Ave special neighs/atom = 2 +Neighbor list builds = 45 +Dangerous builds = 0 + +reset_timestep 0 + +compute gofr all rdf 100 1 1 2 2 1 2 # O-O, H-H, O-H +compute gofa all adf 45 1 1 1 2.0 3.5 2.0 3.5 2 1 1 0.0 1.2 1.5 2.5 # O-O-O, O-H...O +fix rdf all ave/time 100 10 1000 c_gofr[*] file spce-rdf.dat mode vector +fix adf all ave/time 10 100 1000 c_gofa[*] file spce-adf.dat mode vector + +run 1000 +PPPM initialization ... + using 12-bit tables for long-range coulomb (src/kspace.cpp:321) + G vector (1/distance) = 0.279652 + grid = 40 40 40 + stencil order = 5 + estimated absolute RMS force accuracy = 0.000394674 + estimated relative force accuracy = 1.18855e-06 + using double precision FFTs + 3d grid and FFT values/proc = 34263 16000 +Neighbor list info ... + update every 1 steps, delay 2 steps, check yes + max neighbors/atom: 2000, page size: 100000 + master list distance cutoff = 14 + ghost atom cutoff = 14 + binsize = 7, bins = 6 6 6 + 3 neighbor lists, perpetual/occasional/extra = 1 2 0 + (1) pair lj/cut/coul/long, perpetual + attributes: half, newton on + pair build: half/bin/newton + stencil: half/bin/3d/newton + bin: standard + (2) compute rdf, occasional, copy from (1) + attributes: half, newton on + pair build: copy + stencil: none + bin: none + (3) compute adf, occasional + attributes: full, newton on + pair build: full/bin + stencil: full/bin/3d + bin: standard +Per MPI rank memory allocation (min/avg/max) = 13.96 | 13.96 | 13.96 Mbytes +Step Temp E_pair E_mol TotEng Press + 0 298.00206 -16716.893 0 -14052.919 231.44272 + 100 307.28155 -16760.647 0 -14013.72 452.38436 + 200 299.05168 -16674.695 0 -14001.338 177.44237 + 300 292.7564 -16573.946 0 -13956.865 122.27796 + 400 299.2644 -16578.318 0 -13903.059 482.03304 + 500 296.04028 -16623.179 0 -13976.742 89.968145 + 600 300.30911 -16664.206 0 -13979.608 132.70079 + 700 292.39517 -16703.749 0 -14089.897 825.267 + 800 298.75851 -16661.684 0 -13990.948 468.68671 + 900 301.55689 -16644.846 0 -13949.093 -72.16965 + 1000 298.2852 -16682.077 0 -14015.572 0.69725342 +Loop time of 32.3106 on 4 procs for 1000 steps with 4500 atoms + +Performance: 5.348 ns/day, 4.488 hours/ns, 30.950 timesteps/s +96.8% CPU use with 4 MPI tasks x 1 OpenMP threads + +MPI task timing breakdown: +Section | min time | avg time | max time |%varavg| %total +--------------------------------------------------------------- +Pair | 15.647 | 15.876 | 16.119 | 4.3 | 49.13 +Bond | 0.0011718 | 0.0012704 | 0.001348 | 0.2 | 0.00 +Kspace | 5.286 | 5.5364 | 5.7729 | 7.5 | 17.13 +Neigh | 2.3892 | 2.3962 | 2.3991 | 0.3 | 7.42 +Comm | 0.34641 | 0.35514 | 0.35988 | 0.9 | 1.10 +Output | 0.00047851 | 0.00069892 | 0.0013568 | 0.0 | 0.00 +Modify | 8.0882 | 8.0963 | 8.1047 | 0.3 | 25.06 +Other | | 0.04887 | | | 0.15 + +Nlocal: 1125 ave 1137 max 1114 min +Histogram: 1 1 0 0 0 0 0 1 0 1 +Nghost: 12206.2 ave 12239 max 12169 min +Histogram: 1 0 1 0 0 0 0 0 1 1 +Neighs: 650464 ave 655962 max 641444 min +Histogram: 1 0 0 0 0 0 0 2 0 1 +FullNghs: 1.30095e+06 ave 1.31925e+06 max 1.28413e+06 min +Histogram: 1 0 1 0 0 0 1 0 0 1 + +Total # of neighbors = 5203786 +Ave neighs/atom = 1156.4 +Ave special neighs/atom = 2 +Neighbor list builds = 94 +Dangerous builds = 0 +Total wall time: 0:00:45