- Version 1
- by (unknown)
- Version 2
- by (unknown)
Deletions or items before changed
Additions or items after changed
| 1 | == Scalability Results == | |||
|---|---|---|---|---|
| 2 | === Model Description === | |||
| 3 | ||||
| 4 | These scalability tests were run using !CitcomS 3.2.0 with default configuration. The mesh for these tests is a regional cap with 129x129x129 nodes. Total velocity unknowns is 129^3 x 3 = 6.4 million. The model is run for 11 time steps. The result reported is the total wall clock time. Each node on this cluster has 2 Xeon 5680 series 3.33GHz hex-core processors with a 12MB unified L3 cache and 24GB RAM, for a total of 12 cores per node. The interconnect is QDR !InfiniBand. | |||
| 5 | ||||
| 6 | ||'''Partition'''||'''Total Procs'''||'''Wall Time (sec)'''||'''Speedup'''||'''Scalability'''|| | |||
| 7 | ||1x1x1 ||1 ||47217 ||1.000 ||1.000|| | |||
| 8 | ||1x1x2||2 ||25466 ||1.854 ||0.927|| | |||
| 9 | ||1x1x4 ||4 ||14645 ||3.224 ||0.806|| | |||
| 10 | ||2x2x1 ||4 ||14438 ||3.270 ||0.818|| | |||
| 11 | ||2x2x2 ||8 ||8980 ||5.258 ||0.657|| | |||
| 12 | ||2x2x4 ||16 ||4432 ||10.654 ||0.666|| | |||
| 13 | ||4x4x1 ||16 ||5367 ||8.798 ||0.550|| | |||
| 14 | ||4x4x2 ||32 ||2460 ||19.194 ||0.600|| | |||
| 15 | ||4x4x4 ||64 ||1346 ||35.079 ||0.548|| | |||
| 16 | ||8x8x2 1||28 ||583 ||80.990 ||0.633|| | |||
| 17 | ||8x8x4 ||256 ||337 ||140.110 ||0.547|| | |||
| 18 | ||||
| 19 | - | The input file is available [ |
+ | The input file is available here: [[File(input.sample.zip)]]. It is currently configured for 1x1x1 processors, to do different processor divisions you must change the nprocx, nprocy, and nprocz parameters. You must create a folder named “scratch” in the working directory for the output files. The input file uses the non-Python version of !CitcomS, located at !CitcomS-3.2.0/bin/!CitcomSRegional. |