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:167 [2018/06/28 11:33] hmeij07 |
cluster:167 [2018/06/28 14:16] hmeij07 [CPU vs GPU] |
||
---|---|---|---|
Line 10: | Line 10: | ||
* That period covers 600 hours of time | * That period covers 600 hours of time | ||
* Assume 99% utilization of cpu core or gpu device | * Assume 99% utilization of cpu core or gpu device | ||
- | * Available | + | * Available |
* There is no good/bad metric | * There is no good/bad metric | ||
* Never collated such data before | * Never collated such data before | ||
- | * The GPU usage is based on detecting gpu reservations (gpu= flag) | + | * The GPU jobs are detected |
Line 21: | Line 21: | ||
| Memory | 7,408 | 51:1 | 144 | GB | | | Memory | 7,408 | 51:1 | 144 | GB | | ||
| Teraflops | 38 | 1.5:1 | 25 | double precision, floating point, theoretical | | | Teraflops | 38 | 1.5:1 | 25 | double precision, floating point, theoretical | | ||
- | | Job Count | 2,834 | 3:1 | 1,045 | scheduled | + | | Job Count | 2,834 | 3:1 | 1,045 | processed |
- | | Avail Hours | 715, | + | | Avail Hours | 715, |
| Job Hours | 221, | | Job Hours | 221, | ||
- | | Job Hours % | 31 | 6:1 | 5 | as a percentage | | + | | Job Hours % | 31 | 6:1 | 5 | as a percentage |
- | | Avail Hours2 | 561, | + | | Avail Hours2 | 561, |
- | | Job Hours % | 39 | 8:1 | 5 | more realistic...hp12 rarely used in June18| | + | | Job Hours2 |
The logs showing gpu %util confirm the extremely low GPU usage. When concatenating the four gpu %util values into a string, since 01Jan2017, the string ' | The logs showing gpu %util confirm the extremely low GPU usage. When concatenating the four gpu %util values into a string, since 01Jan2017, the string ' | ||
- | So were these 25 days in June 2018 an oddity? | + | So were these 25 days in June 2018 an oddity? |
^ Total Monthly CPU+GPU Hours ^^^^^^^^^^^ | ^ Total Monthly CPU+GPU Hours ^^^^^^^^^^^ | ||
^Ju17^Aug17^Sep17^Oct17^Nov17^Dec17^Jan18^Feb18^Mar18^Apr18^May18^ | ^Ju17^Aug17^Sep17^Oct17^Nov17^Dec17^Jan18^Feb18^Mar18^Apr18^May18^ | ||
|313, | |313, | ||
+ | |||
+ | March is Honors' | ||
^ Metric ^ CPU ^ Ratio ^ GPU ^ Notes July 2017 ^ | ^ Metric ^ CPU ^ Ratio ^ GPU ^ Notes July 2017 ^ | ||
Line 41: | Line 43: | ||
| Memory | 7,408 | 74:1 | 100 | GB | | | Memory | 7,408 | 74:1 | 100 | GB | | ||
| Teraflops | 38 | 1.7:1 | 23 | double precision, floating point, theoretical | | | Teraflops | 38 | 1.7:1 | 23 | double precision, floating point, theoretical | | ||
- | | Job Count | | + | | Job Count | 12, |
| Avail Hours | 886, | | Avail Hours | 886, | ||
- | | Job Hours | 260, | + | | Job Hours | 260, |
- | | Job Hours % | | + | | Job Hours % | 30 |
- | | Avail Hours2 | 696, | + | | Avail Hours2 | 696, |
- | | Job Hours % | | + | | Job Hours2 |
+ | |||
+ | * Some noise in this data with the inability to match start and end of job (~15% of records) | ||
+ | * The assumption that '' | ||
+ | |||
+ | Based on Jul17 we process about 60-70 times more CPU Job Hours than GPU Job Hours, that seems consistent with Jul18. The metric of Job Hours consumed versus Available Hours in %, the picture is probably more like Jul17...30-40% of CPU cycles are consumed and 25% of GPU cycles. | ||
+ | |||
+ | If we take total hours consumed from Usage Report (the 313,303 hours for Jul17) we consume about 45% of available hours (without hp12 in the mix). | ||
- | * Some noise in this data with the inability to match start and end of job (~5% of records) | + | We shall wait for Jul18 metrics. |
- | * The assumption that '' | + | |
- | * | + | |
**[[cluster: | **[[cluster: |