Scaling of VASP
HSE06 hybrid calculations
Test benchmark case: VASP 5.4.1, gamma only (except of GPU is vasp_std)
ENCUT = 600.00 eV (ENAUG = 1200.00 eV)
PRECFOCK=Fast
| NAME | budapest2 | uv2 | debrecen2 | szeged | fast |
|---|---|---|---|---|---|
| Perf. per Node (1/s) | 120.25 | 615.78 | 543.88 | 131.23 | 83.08 |
| Perf. per Core (1/s) | 6.01 | 6.41 | 181.29 | 2.73 | 6.92 |
| Total Perf. (1/s) 0 | 0.84 | 0.62 | 2.18 | 0.52 | 0.33 |
| time (s) | 1188 | 1624 | 460 | 1905 | 3009 |
| NCORE | 5 | 1 | 1 | 6 | 1 |
| Total Cores | 140 | 96 | 12 | 192 | 48 |
| Node count | 7 | 1 | 4 | 4 | 4 |
| MPI per Node | 20 | 96 | 3 | 48 | 12 |
| mkl_threads | 1 | 1 | 1 | 1 | 1 |
| VASPcore | 140 | 96 | 12 | 192 | 48 |
| IALGO | DAV | DAV | DAV | DAV | DAV |
| CPU | E5-2680V2 | E5-4610 | Nvidia K20x | Opteron 6174 | E5-2620 |
| Wattage (W) | 115 | 115 | 235 | 115 | 115 |
| count per Node | 2 | 8 | 3 | 4 | 8 |
| suplement (W) | 50 | 50 | 150 | 75 | 50 |
| perNode (W) | 280 | 970 | 855 | 535 | 970 |
| total (W) | 1960 | 970 | 3420 | 2140 | 3880 |
| efficiency (1/W) | 429 | 635 | 636 | 245 | 86 |
Notes: - There is one MPI thread per pysical GPU. There are 3 GPU's per node in debrecen2. As well as there is no gamma only VASP version available, the performance would be even higher.
- AMD Opteron 6174 is considerably slower than recent intel CPU's. They have only 1/2 of the speed of an intel core. It is best to use NCORE = 6 flag. This will group the six cores of the real cpu dies. Opteron 6174 actually two six core cpu's inside the same chassis. Thus at szeged's nodes there are 8 hexa core cpu's, totaling 48 cores.
- On intel cpu's NCORE > 1 is important when more than 100 MPI threads. A value 2 might be enough to restore the linear scaling and avoid the bandwidth limitations.