Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| tcr_sri003 [2020/12/17 09:47] – tmatejuk | tcr_sri003 [2023/08/01 01:08] (current) – external edit 127.0.0.1 | ||
|---|---|---|---|
| Line 106: | Line 106: | ||
| T2=`date +%s` | T2=`date +%s` | ||
| echo -e "stop ${T2}\t start ${T1}\t ${SLURM_NNODES}" | echo -e "stop ${T2}\t start ${T1}\t ${SLURM_NNODES}" | ||
| - | |||
| - | |||
| - | FIXME | ||
| - | |||
| - | FIXME | ||
| - | |||
| - | FIXME | ||
| - | |||
| - | FIXME | ||
| - | |||
| - | FIXME | ||
| ==== performance tests ==== | ==== performance tests ==== | ||
| - | Bellow results show time of computation in function of used resources (computation scalability) for a specific computational task done with '' | + | Bellow results show time of computation in function of used resources (computation scalability) for a specific computational task '' |
| Assigning a larger amount of computing nodes does not always lead to a (efficient) reduction in computing time (wall-time of the job). To find the most appropriate number of nodes for a specific type of job, it is essential to run one's own benchmarks. In general, parallel <color # | Assigning a larger amount of computing nodes does not always lead to a (efficient) reduction in computing time (wall-time of the job). To find the most appropriate number of nodes for a specific type of job, it is essential to run one's own benchmarks. In general, parallel <color # | ||
| - | Bellow results should be consider as results of this specific computational task on this specific hardware (TCR cluster) and not overall benchmark for Quantum Espresso | + | Bellow results should be consider as results of this specific computational task on this specific hardware (TCR cluster) and not overall benchmark for LAMMPS |
| - | {{ tcr: | ||
| ^nodes ^min [s] ^avg [s] ^median [s] ^max [s] ^efficiency [%] ^ | ^nodes ^min [s] ^avg [s] ^median [s] ^max [s] ^efficiency [%] ^ | ||
| - | |1 |1862 |2065.75 |2126 |2149 |<color # | + | |1 |349 |351.67 |349 |357 |<color # |
| - | |2 |1105 |1192.75 |1157.5 |1351 |<color # | + | |2 |206 |209.33 |207 |215 |<color # |
| - | |3 |763 |770 |768.5 |780 |<color #22b14c>81.35%</ | + | |3 |156 |156.33 |156 |157 |<color #22b14c>74.57%</ |
| - | |4 |798 |1026.25 |868.5 |1570 |58.33%| | + | |4 |128 |128.67 |129 |129 |68.16%| |
| - | |5 |571 |589.75 |574 |640 |65.22%| | + | |5 |121 |121.33 |121 |122 |57.69%| |
| - | |6 |488 |536 |525.5 |605 |63.59%| | + | |6 |111 |111 |111 |111 |52.40%| |
| - | |7 |372 |502.25 |414.5 |808 |<color # | + | |7 |92 |93 |93 |94 |54.19%| |
| - | |8 |375 |489.75 |408.5 |767 |62.07%| | + | |8 |88 |88.67 |89 |89 |49.57%| |
| - | |9 |324 |403.75 |346.5 |598 |63.85%| | + | |9 |83 |84 |84 |85 |46.72%| |
| - | |10 |327 |456.25 |465.5 |567 |56.94%| | + | |
| - | |12 |285 |429.4 |375 |609 |54.44%| | + | |
| - | |16 |228 |274.25 |281.5 |306 |51.04%| | + | |
| - | + | ||
| - | + | ||
| *) values (min, avg, median, max, efficiency) do not include failed runs \\ | *) values (min, avg, median, max, efficiency) do not include failed runs \\ | ||
| + | *) results are from 3 runs \\ | ||
| *) efficiency as '' | *) efficiency as '' | ||
| - | example source) https:// | + | ==== other ==== |
| + | above desciption uses default settings and do not include any extra LAMMPS packages that you may require. More about LAMMPS' | ||
| + | |||
| + | *) [[https:// | ||