This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
lammps [2020/02/11 19:05] root |
lammps [2022/02/10 00:14] (current) root |
||
---|---|---|---|
Line 1: | Line 1: | ||
====lammps==== | ====lammps==== | ||
+ | |||
For a reference Intel compilation, | For a reference Intel compilation, | ||
''/ | ''/ | ||
+ | |||
< | < | ||
/ | / | ||
Line 16: | Line 18: | ||
Installed YES: package USER-SMD | Installed YES: package USER-SMD | ||
</ | </ | ||
+ | |||
Makefile is a slight modification of the Lammps-included Makefile.knl. This is compiled on Trestles to be upwards compatible with all systems. For the Phis you would want to include the MIC-AVX512 from the original. | Makefile is a slight modification of the Lammps-included Makefile.knl. This is compiled on Trestles to be upwards compatible with all systems. For the Phis you would want to include the MIC-AVX512 from the original. | ||
+ | |||
< | < | ||
/ | / | ||
Line 41: | Line 45: | ||
> icc -O -o $@ $< | > icc -O -o $@ $< | ||
</ | </ | ||
+ | |||
Best known run configuration on all (non-Phi) systems is with MPI threads=physical cores/2 like so for Pinnacle 32-core: | Best known run configuration on all (non-Phi) systems is with MPI threads=physical cores/2 like so for Pinnacle 32-core: | ||
+ | |||
< | < | ||
module load intel/ | module load intel/ | ||
mpirun -np 16 -genv OMP_NUM_THREADS=2 / | mpirun -np 16 -genv OMP_NUM_THREADS=2 / | ||
</ | </ | ||
+ | |||
Benchmarks across systems for one node are | Benchmarks across systems for one node are | ||
+ | |||
< | < | ||
Razor 16 core, np=8 1:56 | Razor 16 core, np=8 1:56 |