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:189 [2020/01/11 17:47] hmeij07 |
cluster:189 [2020/01/11 18:09] hmeij07 [Funding Policy] |
||
---|---|---|---|
Line 7: | Line 7: | ||
In 2006, 4 Wesleyan qfaculty members approached ITS with a proposal to centrally manage a whigh performance computing center (HPCC) seeding the effort with an NSF grant (about $190K). ITS offered 0.5 FTE for a dedicated " | In 2006, 4 Wesleyan qfaculty members approached ITS with a proposal to centrally manage a whigh performance computing center (HPCC) seeding the effort with an NSF grant (about $190K). ITS offered 0.5 FTE for a dedicated " | ||
+ | |||
+ | The Advisory Group meets with the user base yearly in reading week of the Spring semester (early May) before everybody scatters for the summer. At this meeting the hpcadmin reviews the past year, previews the coming year and users are contributing feedback on progress and problems. | ||
==== Structure ==== | ==== Structure ==== | ||
Line 20: | Line 22: | ||
Several months later a pattern emerged. | Several months later a pattern emerged. | ||
+ | In order for the HPC user base to raise $15K annually, CPU and GPU hourly usage was deployed. A dictionary is maintained listing PIs and their members (students majors, lab students, grads, phd candidates, collaborators, | ||
+ | Here is 2019's queue usage [[cluster: | ||
- | funding policy | + | Contribution Scheme for 01 July 2019 onwards\\ |
- | priority access policy | + | Hours (K) - Rate ($/CPU Hour)\\ |
- | + | * 0-5 = Free | |
- | user base stats, annual meeting, spring reading week | + | * >5-25 = 0.03 |
- | 2019 queue usage stats link | + | * >25-125 = 0.006 |
- | adv group details, administrative | + | * >125-625 = 0.0012 |
- | hpcc stats cpu cores, gpus, mem, hdd (rough) link to guide | + | * > |
- | latest deployment: nvidia | + | * >3125 = 0.000048 |
- | + | A cpu usage of 3,125,000 hours/year would cost $ 2,400.00 \\ | |
- | Add funding model scheme 2016 2019 | + | A gpu hour of usage is 3x the cpu hourly rate.\\ |
- | 3x gpu vs cpu. | + | |
- | Script preempts nodes every 2 hours. | + | |
+ | We currently have about 1,450 physical cpu cores, 60 gpus, 520 gb of gpu memory and 8,560 gb cpu memory provided by about 120 compute nodes and login nodes. Scratch spaces are provide local to compute nodes (2-5 tb) or over the network via NFS (55 tb). Home directories are under quota (10 tb) but these will disappear in the future with the TrueNAS/ZFS appliance (190 tb, 475 tb effective assuming a compression rate of 2.5x). a guide can be found here [[cluster: | ||