tx258/lammps-gran-kokkos
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@12042 f3b2605a-c512-4ea7-a41b-209d697bcdaa

Browse Source
This commit is contained in:
sjplimp
2014-05-29 22:52:10 +00:00
parent 3cfef73208
commit 30361f0dfa
11 changed files with 542 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/README
View File

@ -73,6 +73,7 @@ gpu: use of the GPU package for GPU acceleration
hugoniostat: Hugoniostat shock dynamics hugoniostat: Hugoniostat shock dynamics
indent: spherical indenter into a 2d solid indent: spherical indenter into a 2d solid
kim: use of potentials in Knowledge Base for Interatomic Models (KIM) kim: use of potentials in Knowledge Base for Interatomic Models (KIM)
kokkos: use of the KOKKOS package for multi-threading and GPU acceleration
meam: MEAM test for SiC and shear (same as shear examples) meam: MEAM test for SiC and shear (same as shear examples)
melt: rapid melt of 3d LJ system melt: rapid melt of 3d LJ system
micelle: self-assembly of small lipid-like molecules into 2d bilayers micelle: self-assembly of small lipid-like molecules into 2d bilayers

35
examples/gpu/README Normal file
View File

@ -0,0 +1,35 @@
These are input scripts designed for use with the GPU package.
To run them, you must first build LAMMPS with the GPU package
installed, following the steps explained in Section 2.3 of
doc/Section_start.html and lib/gpu/README. An overview of building
and running LAMMPS with the GPU package is given in Section 5.6 of
doc/Section_accelerate.html. Note that you can choose the precision
at which computations are performed on the GPU in the build process.
Note that lines such as this in each of the input scripts:
package gpu force/neigh 0 1 1
are set for running on a compute node with 2 GPUs. If you
have a single GPU, you should comment out the line, since
the default is 1 GPU per compute node.
The scripts can be run in the usual manner:
lmp_g++ < in.gpu.melt.2.5
lmp_g++ < in.gpu.melt.5.0
lmp_g++ < in.gpu.phosphate
lmp_g++ < in.gpu.rhodo
mpirun -np 4 lmp_g++ < in.gpu.melt.2.5
mpirun -np 4 lmp_g++ < in.gpu.melt.5.0
mpirun -np 4 lmp_g++ < in.gpu.phosphate
mpirun -np 4 lmp_g++ < in.gpu.rhodo
The first set of commmands will run a single MPI task using a single
GPU (even if you have 2 GPUs).
The second set of commands will run 4 MPI tasks, with 2 MPI tasks per
GPU (if you have 2 GPUs), or 4 MPI tasks per GPU (if you have a single
GPU).

42
examples/kokkos/README Normal file
View File

@ -0,0 +1,42 @@
The in.kokkos input script is a copy of the bench/in.lj script,
but can be run with the KOKKOS package,
To run it, you must first build LAMMPS with the KOKKOS package
installed, following the steps explained in Section 2.3.4 of
doc/Section_start.html. An overview of building and running LAMMPS
with the KOKKOS package, for different compute-node hardware on your
machine, is given in Section 5.8 of doc/Section_accelerate.html.
The example log files included in this directory are for a desktop box
with dual hex-core CPUs and 2 GPUs.
Two executables were built in the following manner:
make yes-kokkos
make g++ OMP=yes -> lmp_cpu
make cuda CUDA=yes -> lmp_cuda
Then the following runs were made. The "->" means that the run
produced log.lammps which was then copied to the named log file.
* MPI-only runs
lmp_cpu -k off < in.kokkos -> log.kokkos.date.mpionly.1
mpirun -np 4 lmp_cpu -k off < in.kokkos -> log.kokkos.date.mpionly.4
* OpenMP threaded runs on CPUs only
lmp_cpu -k on t 1 -sf kk < in.kokkos.half -> log.kokkos.date.cpu.1
lmp_cpu -k on t 4 -sf kk < in.kokkos -> log.kokkos.date.cpu.4
Note that in.kokkos.half was use for one of the runs, which uses the
package command to force the use of half neighbor lists which are
faster when running on just 1 thread.
* GPU runs on 1 or 2 GPUs
lmp_cuda -k on t 6 -sf kk < in.kokkos -> log.kokkos.date.gpu.1
mpirun -np 2 lmp_cuda -k on t 6 -sf kk < in.kokkos -> log.kokkos.date.gpu.2
Note that this is a very small problem (32K atoms) to run
on 1 or 2 GPUs.

30
examples/kokkos/in.kokkos Normal file
View File

@ -0,0 +1,30 @@
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable yy equal 20*$y
variable zz equal 20*$z
units lj
atom_style atomic
lattice fcc 0.8442
region box block 0 ${xx} 0 ${yy} 0 ${zz}
create_box 1 box
create_atoms 1 box
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100

32
examples/kokkos/in.kokkos.half Normal file
View File

@ -0,0 +1,32 @@
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable yy equal 20*$y
variable zz equal 20*$z
package kokkos neigh half
units lj
atom_style atomic
lattice fcc 0.8442
region box block 0 ${xx} 0 ${yy} 0 ${zz}
create_box 1 box
create_atoms 1 box
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100

68
examples/kokkos/log.kokkos.1Feb14.cpu.1 Normal file
View File

@ -0,0 +1,68 @@
LAMMPS (27 May 2014)
KOKKOS mode is enabled (../lammps.cpp:468)
using 1 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
package kokkos neigh half
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 1 by 1 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 7.79551 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 2.29105 on 1 procs (1 MPI x 1 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 1.82425 (79.6249)
Neigh time (%) = 0.338632 (14.7806)
Comm time (%) = 0.0366232 (1.59853)
Outpt time (%) = 0.000144005 (0.00628553)
Other time (%) = 0.0914049 (3.98965)
Nlocal: 32000 ave 32000 max 32000 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 19657 ave 19657 max 19657 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 1.20283e+06 ave 1.20283e+06 max 1.20283e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 1202833
Ave neighs/atom = 37.5885
Neighbor list builds = 5
Dangerous builds = 0

68
examples/kokkos/log.kokkos.1Feb14.cpu.4 Normal file
View File

@ -0,0 +1,68 @@
LAMMPS (27 May 2014)
KOKKOS mode is enabled (../lammps.cpp:468)
using 4 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 1 by 1 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 13.2888 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 0.983697 on 4 procs (1 MPI x 4 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 0.767155 (77.9869)
Neigh time (%) = 0.14734 (14.9782)
Comm time (%) = 0.041466 (4.21532)
Outpt time (%) = 0.000172138 (0.0174991)
Other time (%) = 0.0275636 (2.80204)
Nlocal: 32000 ave 32000 max 32000 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 19657 ave 19657 max 19657 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 0 ave 0 max 0 min
Histogram: 1 0 0 0 0 0 0 0 0 0
FullNghs: 2.40567e+06 ave 2.40567e+06 max 2.40567e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 2405666
Ave neighs/atom = 75.1771
Neighbor list builds = 5
Dangerous builds = 0

68
examples/kokkos/log.kokkos.1Feb14.gpu.1 Normal file
View File

@ -0,0 +1,68 @@
LAMMPS (27 May 2014)
KOKKOS mode is enabled (../lammps.cpp:468)
using 6 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 1 by 1 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 16.9509 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 0.57192 on 6 procs (1 MPI x 6 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 0.205416 (35.917)
Neigh time (%) = 0.112468 (19.665)
Comm time (%) = 0.174223 (30.4629)
Outpt time (%) = 0.000159025 (0.0278055)
Other time (%) = 0.0796535 (13.9274)
Nlocal: 32000 ave 32000 max 32000 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 19657 ave 19657 max 19657 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 0 ave 0 max 0 min
Histogram: 1 0 0 0 0 0 0 0 0 0
FullNghs: 2.40567e+06 ave 2.40567e+06 max 2.40567e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 2405666
Ave neighs/atom = 75.1771
Neighbor list builds = 5
Dangerous builds = 0

68
examples/kokkos/log.kokkos.1Feb14.gpu.2 Normal file
View File

@ -0,0 +1,68 @@
LAMMPS (27 May 2014)
KOKKOS mode is enabled (../lammps.cpp:468)
using 6 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 1 by 2 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 8.95027 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 0.689608 on 12 procs (2 MPI x 6 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 0.210953 (30.5903)
Neigh time (%) = 0.122991 (17.8349)
Comm time (%) = 0.25264 (36.6353)
Outpt time (%) = 0.000259042 (0.0375636)
Other time (%) = 0.102765 (14.9019)
Nlocal: 16000 ave 16001 max 15999 min
Histogram: 1 0 0 0 0 0 0 0 0 1
Nghost: 13632.5 ave 13635 max 13630 min
Histogram: 1 0 0 0 0 0 0 0 0 1
Neighs: 0 ave 0 max 0 min
Histogram: 2 0 0 0 0 0 0 0 0 0
FullNghs: 1.20283e+06 ave 1.20347e+06 max 1.2022e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 1
Total # of neighbors = 2405666
Ave neighs/atom = 75.1771
Neighbor list builds = 5
Dangerous builds = 0

65
examples/kokkos/log.kokkos.1Feb14.mpionly.1 Normal file
View File

@ -0,0 +1,65 @@
LAMMPS (27 May 2014)
using 1 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 1 by 1 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 8.21387 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 2.57975 on 1 procs (1 MPI x 1 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 2.20959 (85.6512)
Neigh time (%) = 0.269136 (10.4326)
Comm time (%) = 0.0252256 (0.977833)
Outpt time (%) = 0.000126123 (0.00488898)
Other time (%) = 0.0756752 (2.93343)
Nlocal: 32000 ave 32000 max 32000 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 19657 ave 19657 max 19657 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 1.20283e+06 ave 1.20283e+06 max 1.20283e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 1202833
Ave neighs/atom = 37.5885
Neighbor list builds = 5
Dangerous builds = 0

65
examples/kokkos/log.kokkos.1Feb14.mpionly.4 Normal file
View File

@ -0,0 +1,65 @@
LAMMPS (27 May 2014)
using 1 OpenMP thread(s) per MPI task
# 3d Lennard-Jones melt
variable x index 1
variable y index 1
variable z index 1
variable xx equal 20*$x
variable xx equal 20*1
variable yy equal 20*$y
variable yy equal 20*1
variable zz equal 20*$z
variable zz equal 20*1
units lj
atom_style atomic
lattice fcc 0.8442
Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
region box block 0 ${xx} 0 ${yy} 0 ${zz}
region box block 0 20 0 ${yy} 0 ${zz}
region box block 0 20 0 20 0 ${zz}
region box block 0 20 0 20 0 20
create_box 1 box
Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
1 by 2 by 2 MPI processor grid
create_atoms 1 box
Created 32000 atoms
mass 1 1.0
velocity all create 1.44 87287 loop geom
pair_style lj/cut 2.5
pair_coeff 1 1 1.0 1.0 2.5
neighbor 0.3 bin
neigh_modify delay 0 every 20 check no
fix 1 all nve
run 100
Memory usage per processor = 4.09506 Mbytes
Step Temp E_pair E_mol TotEng Press
0 1.44 -6.7733681 0 -4.6134356 -5.0197073
100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
Loop time of 0.709072 on 4 procs (4 MPI x 1 OpenMP) for 100 steps with 32000 atoms
Pair time (%) = 0.574495 (81.0206)
Neigh time (%) = 0.0709588 (10.0073)
Comm time (%) = 0.0474771 (6.69567)
Outpt time (%) = 6.62804e-05 (0.00934748)
Other time (%) = 0.0160753 (2.26708)
Nlocal: 8000 ave 8037 max 7964 min
Histogram: 2 0 0 0 0 0 0 0 1 1
Nghost: 9007.5 ave 9050 max 8968 min
Histogram: 1 1 0 0 0 0 0 1 0 1
Neighs: 300708 ave 305113 max 297203 min
Histogram: 1 0 0 1 1 0 0 0 0 1
Total # of neighbors = 1202833
Ave neighs/atom = 37.5885
Neighbor list builds = 5
Dangerous builds = 0