Ideas: Expand computational capabilities (power and/ or number of computers), increase efficiency of code, streamline workflows, etc.
Purpose of page
Write down concerns, ideas, and efforts as understood by Chemistry IT so research group members can review and correct.
Request from group: Buy a server to process multiple Matlab calculation simultaneously
Outstanding questions:
- Windows or Linux? Past testing by researchers have yielded faster processing on servers running Linux than Windows. Some researchers only comfortable working within Windows.
- If Windows, how will user accounts and access work? How many simultaneously? Per user or shared accounts? How manage contention, if desired?
- Coordinate monthly (or every 3 months) shutdown periods to ensure baseline patching and OS, file-share and hardware checking.
- Any value in Dual 10-Gigabit Ethernet?
Server spec suggestions and costs
| Criteria | Current deskop's specs | ~4 * desktop specs is minumum proposed server | Cost increase if go up about a level | Borrowed Dell's specs | Notes |
|---|---|---|---|---|---|
Cores, hyper-threading (HT) | 4 cores (one processor) No HT i5-6500, 3.20 GHz | 16 cores (Two, 8 cores each) HT-capable Each: Xeon Silver 4110 | $xx: 16 cores => 20 cores $xx: 16 cores = 24 cores See chart below for even more cores, at slowest (cheapest) speeds. | 16 cores (Two, 8 cores each) HT-capable Each: Xeon E5-2620v4 | Q: Testing performance difference between using HT and not using HT? |
| Storage, all SSD | 500 GB | 2 TB | $800: 2 TB => 3TB $1,700: 2TB = 3.8 TB | SSD (size n/a, at 400GB) | If Windows, buy $xx software on server (free clients) to enable moving large amounts of data to server more speedily. Large amounts of data not needed to be stored on server, nor moved from server (simply deleted after processing). |
| RAM | 32 GB | 128 GB | $xx: 128 GB => 256 GB? | 32 GB | |
| Other | Need: UPS ($xxx) Option: Redundant power supply unit $xxx) | n/a | |||
| Approx. cost | ~$900? | ~$xxx | n/a | $xxx |
Core prices snap-shot
Prices taken 12/22/2017
This chart of estimated marginal costs is a sub-set of options pulled from <https://www.thinkmate.com/system/rax-xs4-21s1-sh>, focusing on SLOWEST procs to reduce costs. Other, more expensive-per-proc options available.
Price compared to 8-core Xeon Silver 4110 for TWO processors Can go with ONE pr | Processor (all Xeon) | Actual core count EACH processor Multiply by 2 since 2 procs. All HT-capable | Other specs |
|---|---|---|---|
| $0 (base-line, for comparison) | Silver 4110 | 8-core | 2.10GHz 11.00MB Cache (85W) |
| +460 | Silver 4114 | 10-core | 2.20GHz 13.75MB Cache (85W) |
| +600 | Silver 4116 | 12-core | 2.10GHz 16.50MB Cache (85W) |
| +814 | Gold 5115 | 10-core | 2.40GHz 13.75MB Cache (85W) |
| +980 (delay) | Gold 5118 | 12-core | 2.30GHz 16.50MB Cache (105W) |
| +1,640 | Gold 6130 | 16-core | 2.10GHz 22.00MB Cache (125W) |
| +2,530 | Gold 6138 | 20-core | 2.00GHz 27.50MB Cache (125W) |
| +3,780 | Gold 6152 | 22-core | 2.10GHz 30.25MB Cache (140W) |
| +3,280 (delay) | Platinum 8153 | 16-core | 2.00GHz 22.00MB Cache (125W) |
| +5,080 | Platinum 8160 | 24-core | 2.10GHz 33.00MB Cache (150W) |
| +6,780 | Platinum 8164 | 26-core | 2.10GHz 35.75MB Cache (165W) |
| +8,330 | Platinum 8170 | 26-core | 2.10GHz 35.75MB Cache (165W) |
| +9,880 | Platinum 8176 | 28-core | 2.10GHz 38.50MB Cache (165W) |
Status
10/5/17: Oliver met with Mahdi <mh2356> and Kushal <ks2285>. Action steps to have Peng review and refine:
(1) Group: Decide if worth having (select?) Matlab code reviewed by experts at CAC, focused primarily to increase efficiency. Secondary outcomes include:
- May result in the ability to run older code on current version of Matlab, expanding where code could run on non-group computers.
- May result in clarifying computational bottlenecks so the best fitted computational hardware is purchased. What does one prioritize when faced with choice to invest in: better processors, number of processors, number of cores per processors, bus speeds, SSD drives, and/ or RAM?
- May result in a confirmation whether or not problem lends itself to parallelization. If so, can increase efficiency with the right hardware and expands the locations to efficiently run the code (RedCloud, etc.).
(2) Oliver: Have group test their code on test server in 248, initially by-passing using the network to get the data to the server.
- Time comparisons of both single runs and simultaneous runs. Does the server reduce computational time for a single job, as compared to current workstations? To what degree does the server's performance drop as more jobs are added? Again, compare to current workstations.
(3) Oliver: Optimize getting data to test server in 248 via the network.
Other thoughs from Oliver:
- Confirm if any campus computing is a good fit for the group: CISER, RedCloud (likely only if code can be and is parallelized), David Botsh's cluster(?), others?
- Group may benefit from optimizing workflow at various workstations.