From b97cd78e80faa2d8e8f6aa80c3610365c1c0eb2a Mon Sep 17 00:00:00 2001 From: Axel Kohlmeyer Date: Tue, 16 Jun 2020 21:11:34 -0400 Subject: [PATCH] change input and log files for new example to give consistent results in serial and parallel. the remaining files and logs are updated in PR #2162 --- examples/snap/in.snap.InP.JCPA2020 | 2 +- ....1 => log.15Jun20.snap.InP.JCPA2020.g++.1} | 51 +++++++++--------- ....4 => log.15Jun20.snap.InP.JCPA2020.g++.4} | 53 ++++++++++--------- 3 files changed, 54 insertions(+), 52 deletions(-) rename examples/snap/{log.01Jun20.snap.InP_JCPA2020.g++.1 => log.15Jun20.snap.InP.JCPA2020.g++.1} (72%) rename examples/snap/{log.01Jun20.snap.InP_JCPA2020.g++.4 => log.15Jun20.snap.InP.JCPA2020.g++.4} (71%) diff --git a/examples/snap/in.snap.InP.JCPA2020 b/examples/snap/in.snap.InP.JCPA2020 index dd16301a01..2708ec02fb 100644 --- a/examples/snap/in.snap.InP.JCPA2020 +++ b/examples/snap/in.snap.InP.JCPA2020 @@ -40,7 +40,7 @@ neigh_modify once no every 1 delay 0 check yes # Run MD -velocity all create 300.0 4928459 +velocity all create 300.0 4928459 loop geom fix 1 all nve run ${nsteps} diff --git a/examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.1 b/examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.1 similarity index 72% rename from examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.1 rename to examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.1 index 094e039420..025f4c2abc 100644 --- a/examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.1 +++ b/examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.1 @@ -1,4 +1,5 @@ -LAMMPS (2 Jun 2020) +LAMMPS (15 Jun 2020) + using 1 OpenMP thread(s) per MPI task # Demonstrate SNAP InP potential # Initialize simulation @@ -43,10 +44,10 @@ include InP_JCPA2020.snap # Definition of SNAP+ZBL potential. -variable zblcutinner equal 4 -variable zblcutouter equal 4.2 -variable zblz1 equal 49 -variable zblz2 equal 15 +variable zblcutinner index 4 +variable zblcutouter index 4.2 +variable zblz1 index 49 +variable zblz2 index 15 # Specify hybrid with SNAP and ZBL @@ -90,7 +91,7 @@ neigh_modify once no every 1 delay 0 check yes # Run MD -velocity all create 300.0 4928459 +velocity all create 300.0 4928459 loop geom fix 1 all nve run ${nsteps} run 100 @@ -114,30 +115,30 @@ Neighbor list info ... Per MPI rank memory allocation (min/avg/max) = 6.027 | 6.027 | 6.027 Mbytes Step Temp E_pair E_mol TotEng Press 0 300 -3.4805794 0 -3.4418771 1353.5968 - 10 286.42264 -3.4788274 0 -3.4418767 1586.4881 - 20 250.14148 -3.4741459 0 -3.4418757 2219.0344 - 30 202.52417 -3.4680017 0 -3.4418745 2982.7272 - 40 157.39113 -3.4621782 0 -3.4418735 3631.0936 - 50 126.7004 -3.4582183 0 -3.441873 4053.7725 - 60 117.00722 -3.4569679 0 -3.441873 4204.9542 - 70 127.65968 -3.4583427 0 -3.4418736 4106.3112 - 80 151.50217 -3.4614195 0 -3.4418745 3840.7205 - 90 177.67607 -3.464797 0 -3.4418754 3527.9794 - 100 195.30359 -3.4670717 0 -3.4418761 3300.3795 -Loop time of 18.0803 on 1 procs for 100 steps with 512 atoms + 10 285.84677 -3.4787531 0 -3.4418766 1611.7131 + 20 248.14649 -3.4738884 0 -3.4418756 2312.0308 + 30 198.94136 -3.4675394 0 -3.4418744 3168.1543 + 40 152.74831 -3.4615791 0 -3.4418734 3903.5749 + 50 121.9796 -3.4576091 0 -3.4418728 4387.1254 + 60 113.27555 -3.4564863 0 -3.4418729 4556.3003 + 70 125.68089 -3.4580873 0 -3.4418735 4431.2083 + 80 151.47475 -3.4614159 0 -3.4418745 4107.2369 + 90 179.18708 -3.4649919 0 -3.4418754 3739.5881 + 100 197.50662 -3.4673559 0 -3.441876 3492.7778 +Loop time of 13.3103 on 1 procs for 100 steps with 512 atoms -Performance: 0.239 ns/day, 100.446 hours/ns, 5.531 timesteps/s -99.8% CPU use with 1 MPI tasks x no OpenMP threads +Performance: 0.325 ns/day, 73.946 hours/ns, 7.513 timesteps/s +99.7% CPU use with 1 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 18.078 | 18.078 | 18.078 | 0.0 | 99.99 +Pair | 13.309 | 13.309 | 13.309 | 0.0 | 99.99 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.000979 | 0.000979 | 0.000979 | 0.0 | 0.01 -Output | 0.000243 | 0.000243 | 0.000243 | 0.0 | 0.00 -Modify | 0.000591 | 0.000591 | 0.000591 | 0.0 | 0.00 -Other | | 0.000469 | | | 0.00 +Comm | 0.00068474 | 0.00068474 | 0.00068474 | 0.0 | 0.01 +Output | 0.00020504 | 0.00020504 | 0.00020504 | 0.0 | 0.00 +Modify | 0.0003829 | 0.0003829 | 0.0003829 | 0.0 | 0.00 +Other | | 0.0004075 | | | 0.00 Nlocal: 512 ave 512 max 512 min Histogram: 1 0 0 0 0 0 0 0 0 0 @@ -153,4 +154,4 @@ Ave neighs/atom = 122 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:18 +Total wall time: 0:00:13 diff --git a/examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.4 b/examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.4 similarity index 71% rename from examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.4 rename to examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.4 index 109ed315d2..732ae19f45 100644 --- a/examples/snap/log.01Jun20.snap.InP_JCPA2020.g++.4 +++ b/examples/snap/log.15Jun20.snap.InP.JCPA2020.g++.4 @@ -1,4 +1,5 @@ -LAMMPS (2 Jun 2020) +LAMMPS (15 Jun 2020) + using 1 OpenMP thread(s) per MPI task # Demonstrate SNAP InP potential # Initialize simulation @@ -31,7 +32,7 @@ Created orthogonal box = (0.0 0.0 0.0) to (23.32 23.32 23.32) 1 by 2 by 2 MPI processor grid create_atoms 1 box basis 5 2 basis 6 2 basis 7 2 basis 8 2 Created 512 atoms - create_atoms CPU = 0.001 seconds + create_atoms CPU = 0.000 seconds mass 1 114.76 mass 2 30.98 @@ -43,10 +44,10 @@ include InP_JCPA2020.snap # Definition of SNAP+ZBL potential. -variable zblcutinner equal 4 -variable zblcutouter equal 4.2 -variable zblz1 equal 49 -variable zblz2 equal 15 +variable zblcutinner index 4 +variable zblcutouter index 4.2 +variable zblz1 index 49 +variable zblz2 index 15 # Specify hybrid with SNAP and ZBL @@ -90,7 +91,7 @@ neigh_modify once no every 1 delay 0 check yes # Run MD -velocity all create 300.0 4928459 +velocity all create 300.0 4928459 loop geom fix 1 all nve run ${nsteps} run 100 @@ -114,30 +115,30 @@ Neighbor list info ... Per MPI rank memory allocation (min/avg/max) = 4.587 | 4.587 | 4.587 Mbytes Step Temp E_pair E_mol TotEng Press 0 300 -3.4805794 0 -3.4418771 1353.5968 - 10 286.58246 -3.478848 0 -3.4418767 1582.995 - 20 250.70996 -3.4742192 0 -3.4418757 2207.7507 - 30 203.58199 -3.4681382 0 -3.4418746 2968.5206 - 40 158.84622 -3.462366 0 -3.4418736 3619.0285 - 50 128.30488 -3.4584254 0 -3.4418731 4047.173 - 60 118.40349 -3.4571481 0 -3.4418731 4203.3421 - 70 128.48973 -3.4584499 0 -3.4418737 4109.0296 - 80 151.54241 -3.4614247 0 -3.4418746 3847.4617 - 90 176.92084 -3.4646996 0 -3.4418755 3548.7811 - 100 193.9555 -3.4668978 0 -3.4418761 3342.8083 -Loop time of 4.99339 on 4 procs for 100 steps with 512 atoms + 10 285.84677 -3.4787531 0 -3.4418766 1611.7131 + 20 248.14649 -3.4738884 0 -3.4418756 2312.0308 + 30 198.94136 -3.4675394 0 -3.4418744 3168.1543 + 40 152.74831 -3.4615791 0 -3.4418734 3903.5749 + 50 121.9796 -3.4576091 0 -3.4418728 4387.1254 + 60 113.27555 -3.4564863 0 -3.4418729 4556.3003 + 70 125.68089 -3.4580873 0 -3.4418735 4431.2083 + 80 151.47475 -3.4614159 0 -3.4418745 4107.2369 + 90 179.18708 -3.4649919 0 -3.4418754 3739.5881 + 100 197.50662 -3.4673559 0 -3.441876 3492.7778 +Loop time of 3.73974 on 4 procs for 100 steps with 512 atoms -Performance: 0.865 ns/day, 27.741 hours/ns, 20.026 timesteps/s -99.5% CPU use with 4 MPI tasks x no OpenMP threads +Performance: 1.155 ns/day, 20.776 hours/ns, 26.740 timesteps/s +98.3% CPU use with 4 MPI tasks x 1 OpenMP threads MPI task timing breakdown: Section | min time | avg time | max time |%varavg| %total --------------------------------------------------------------- -Pair | 4.8898 | 4.907 | 4.9329 | 0.8 | 98.27 +Pair | 3.4687 | 3.5182 | 3.5985 | 2.7 | 94.07 Neigh | 0 | 0 | 0 | 0.0 | 0.00 -Comm | 0.058815 | 0.084739 | 0.1019 | 6.1 | 1.70 -Output | 0.000252 | 0.00038775 | 0.000777 | 0.0 | 0.01 -Modify | 0.000262 | 0.00026675 | 0.000272 | 0.0 | 0.01 -Other | | 0.001039 | | | 0.02 +Comm | 0.13897 | 0.21952 | 0.26888 | 10.7 | 5.87 +Output | 0.00018191 | 0.00047094 | 0.0012944 | 0.0 | 0.01 +Modify | 0.00013065 | 0.00013524 | 0.00014186 | 0.0 | 0.00 +Other | | 0.001456 | | | 0.04 Nlocal: 128 ave 128 max 128 min Histogram: 4 0 0 0 0 0 0 0 0 0 @@ -153,4 +154,4 @@ Ave neighs/atom = 122 Neighbor list builds = 0 Dangerous builds = 0 -Total wall time: 0:00:05 +Total wall time: 0:00:03