This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
cluster:182 [2019/08/12 17:40] hmeij07 [Gromacs] |
cluster:182 [2019/08/13 12:37] hmeij07 [Gromacs] |
||
---|---|---|---|
Line 81: | Line 81: | ||
| SD | 981, | | SD | 981, | ||
| SS | 1, | | SS | 1, | ||
+ | |||
+ | Forgot run run the 4 GPU P100 scenarios, deh. | ||
As with Amber, it is best to run one job per GPU to achieve max node performance. Depending on problem set performance can be boosted by requesting more MPI threads. In previous tests the P100 in double_double precision mode achieved 2.7 million tau/day, so these results are surprising. The RTX 6000 does a decent job of keeping up with the P100. | As with Amber, it is best to run one job per GPU to achieve max node performance. Depending on problem set performance can be boosted by requesting more MPI threads. In previous tests the P100 in double_double precision mode achieved 2.7 million tau/day, so these results are surprising. The RTX 6000 does a decent job of keeping up with the P100. | ||
Line 88: | Line 90: | ||
==== Gromacs ==== | ==== Gromacs ==== | ||
- | Gromacs was build on each of the nodes locally letting it select the optimal CPU (AVX, SSE) and GPU accelerators. The '' | + | Gromacs was build on each of the nodes locally letting it select the optimal CPU (AVX, SSE) and GPU accelerators. The '' |
Line 96: | Line 98: | ||
| Mixed | | | | | 650| gpu=4, 01-08 | | | Mixed | | | | | 650| gpu=4, 01-08 | | ||
| Mixed | | | | | 733| gpu=4, 01-16 | | | Mixed | | | | | 733| gpu=4, 01-16 | | ||
+ | |||
+ | The T4 is P100's equal in mixed precision performance. Add the wattage factor and you have a favorite. | ||
==== Scripts ==== | ==== Scripts ==== | ||
Line 159: | Line 163: | ||
</ | </ | ||
+ | |||
+ | * Gromacs | ||
+ | |||
+ | < | ||
+ | |||
+ | #!/bin/bash | ||
+ | #SBATCH --nodes=1 | ||
+ | #SBATCH --nodelist=node9 | ||
+ | #SBATCH --job-name=" | ||
+ | #SBATCH --ntasks-per-node=32 | ||
+ | #SBATCH --gres=gpu: | ||
+ | #SBATCH --exclusive | ||
+ | |||
+ | export PATH=$HOME/ | ||
+ | export LD_LIBRARY_PATH=$HOME/ | ||
+ | . $HOME/ | ||
+ | rm -f gpu/??/c* gpu/??/e* gpu/??/s* gpu/??/ | ||
+ | cd gpu | ||
+ | |||
+ | # T4 | ||
+ | #export CUDA_VISIBLE_DEVICES=0123 | ||
+ | |||
+ | mpirun -np 8 gmx_mpi mdrun -maxh 1 -gpu_id 0123 \ | ||
+ | -nsteps 1000000 -multidir 05 06 07 08 \ | ||
+ | -ntmpi 0 -npme 0 -s topol.tpr -ntomp 0 -pin on -nb gpu | ||
+ | |||
+ | </ | ||
+ | |||
+ | And GPU utilization was outstanding. | ||
+ | |||
+ | [heme@login1 gromacs-2018]$ ssh node9 ./ | ||
+ | id, | ||
+ | 0, Tesla T4, 66, 866 MiB, 14213 MiB, 98 %, 9 %\\ | ||
+ | 1, Tesla T4, 67, 866 MiB, 14213 MiB, 98 %, 9 %\\ | ||
+ | 2, Tesla T4, 66, 866 MiB, 14213 MiB, 99 %, 9 %\\ | ||
+ | 3, Tesla T4, 64, 866 MiB, 14213 MiB, 97 %, 9 %\\ | ||
+ | |||
\\ | \\ | ||
**[[cluster: | **[[cluster: |