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 [2018/06/26 14:45] hmeij07 [CPU vs GPU] |
cluster:167 [2018/06/26 18:27] 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 ^ CPU ^ GPU ^ Notes ^ | + | * Data is period June 1 to June 25, 2018 (job information data ages out) |
- | | Device Count | 72 | 24 | cpu all intel, gpu all nvidia | | + | * Maybe build monthly script if this turns out to be usable info |
- | | Core Count | 1,712 | 64,300 | physical | + | * That period covers 600 hours of time |
+ | * Assume 99% utilization of cpu core or gpu device | ||
+ | * Available time is measured per cpu core but by gpu device | ||
+ | * There is no good/bad metric | ||
+ | * Never collated such data before | ||
+ | * The GPU usage is based on detecting gpu reservations (gpu= flag) | ||
+ | * | ||
+ | |||
+ | ^ Metric ^ CPU ^ Ratio ^ GPU ^ Notes ^ | ||
+ | | Device Count | 72 | | ||
+ | | Core Count | 1,192 | | ||
+ | | Memory | 7,408 | 51:1 | 144 | GB | | ||
+ | | Teraflops | 38 | 1.5:1 | 25 | double precision, floating point, theoretical | | ||
+ | | Avail Hours | 715, | ||
+ | | Job Count | 2,834 | 3:1 | 1,045 | scheduled jobs irregardless of exit status | | ||
+ | | Job Hours | 221, | ||
+ | | Avail Hrs Util% | 31 | 6:1 | 5 | weeping... | | ||
+ | | Avail Hours2 | 561, | ||
+ | | Avail Hrs2 Util% | 39 | 8:1 | 5 | more realistic... | ||
**[[cluster: | **[[cluster: |