This shows you the differences between two versions of the page.
Next revision | Previous revision Next revision Both sides next revision | ||
cluster:167 [2018/06/26 14:36] hmeij07 created |
cluster:167 [2018/06/28 14:16] hmeij07 [CPU vs GPU] |
||
---|---|---|---|
Line 4: | Line 4: | ||
==== CPU vs GPU ==== | ==== CPU vs GPU ==== | ||
- | So the question was raised what does our usage look like between CPU and GPU? I have no idea what the appropriate metrics would be but lets start with comparing the hardware deployed. | + | So the question was raised what does our usage look like between CPU and GPU devices? I have no idea what the appropriate metrics would be but lets start with comparing the hardware deployed. |
- | ^ Metric | + | * Data is period June 1 to June 25, 2018 (job information data ages out) |
- | | How Many | 72 | 24 | cpu all intel, gpu all nvidia | | + | * Maybe build monthly script if this turns out to be usable info |
+ | * That period covers 600 hours of time | ||
+ | * Assume 99% utilization of cpu core or gpu device | ||
+ | * Available Hours is measured per physical CPU core but by GPU device (exclusivity and persistence modes on) | ||
+ | * There is no good/bad metric | ||
+ | * Never collated such data before | ||
+ | * The GPU jobs are detected based on GPU resource reservations (gpu= flag) | ||
+ | |||
+ | |||
+ | ^ Metric ^ CPU ^ Ratio ^ GPU ^ Notes June 2018 ^ | ||
+ | | Device Count | 72 | | ||
+ | | Core Count | 1,192 | 1:54 | 64,300 | physical only | | ||
+ | | Memory | 7,408 | 51:1 | 144 | GB | | ||
+ | | Teraflops | 38 | 1.5:1 | 25 | double precision, floating point, theoretical | | ||
+ | | Job Count | 2,834 | 3:1 | 1,045 | processed jobs irregardless of exit status | | ||
+ | | Avail Hours | 715, | ||
+ | | Job Hours | 221, | ||
+ | | Job Hours % | 31 | 6:1 | 5 | as a percentage of available | | ||
+ | | Avail Hours2 | 561, | ||
+ | | Job Hours2 % | 39 | 8:1 | 5 | more realistic...hp12 rarely used | | ||
+ | |||
+ | 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? | ||
+ | |||
+ | ^ Total Monthly CPU+GPU Hours ^^^^^^^^^^^ | ||
+ | ^Ju17^Aug17^Sep17^Oct17^Nov17^Dec17^Jan18^Feb18^Mar18^Apr18^May18^ | ||
+ | |313, | ||
+ | |||
+ | March is Honors' | ||
+ | |||
+ | ^ Metric ^ CPU ^ Ratio ^ GPU ^ Notes July 2017 ^ | ||
+ | | Device Count | 72 | 4:1 | 20 | cpu all intel, gpu all nvidia | | ||
+ | | Core Count | 1,192 | 1:42 | 50,000 | physical only | | ||
+ | | Memory | 7,408 | 74:1 | 100 | GB | | ||
+ | | Teraflops | 38 | 1.7:1 | 23 | double precision, floating point, theoretical | | ||
+ | | Job Count | 12, | ||
+ | | Avail Hours | 886, | ||
+ | | Job Hours | 260, | ||
+ | | Job Hours % | 30 | 1:1 | 26 | as a percentage of available | | ||
+ | | Avail Hours2 | 696, | ||
+ | | Job Hours2 % | 37 | 1.5:1 | 26 | more realistic...hp12 rarely used | | ||
+ | |||
+ | * 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). | ||
+ | |||
+ | We shall wait for Jul18 metrics. | ||
+ | |||
**[[cluster: | **[[cluster: |