[Wrf-users] More cores or faster processors?

[Κώστας Μυρωνάκης]

Very good choices both of them.
Very difficult the decision.
I'l try to help.

System     # Cores     # Chips     # Cores Per Chip     Base Copies
Result     Baseline     Published
PowerEdge M620 (Intel Xeon E5-2667 v2, 3.30 GHz)     16     2     8     32
    806     776     Nov-2013
PowerEdge FC630 (Intel Xeon E5-2667 v3, 3.20 GHz)     16     2     8     32
    833     805     Dec-2014
PowerEdge FC630 (Intel Xeon E5-2667 v4, 3.20 GHz)     16     2     8     32
    920     878     Apr-2016

PowerEdge FC430 (Intel Xeon E5-2683 v3, 2.00 GHz)     28     2     14
56     1070     1030     Apr-2015
PowerEdge FC430 (Intel Xeon E5-2683 v4, 2.10 GHz)     32     2     16
64     1340     1280     Apr-2016

Prices

Intel Xeon E5-2667 v4 Introduction date    March 31, 2016 Price at
introduction    $2057
Intel Xeon E5-2667 v3 @ 3.20GHz Last Price Change:  $2110 USD (2016-04-12)

Intel Xeon E5-2683 v4 Introduction date    March 31, 2016 Price at
introduction    $1846
Intel Xeon E5-2683 v3 Last Price Change:  $2136.99 USD (2015-05-18)

First there is no difference in price, of course the price depends from all
the configuration.
We have two choices

Intel Xeon E5-2683 v4, 2.10 GHz Result 1340
Intel Xeon E5-2667 v4, 3.20 GHz Result 920

E5-2683 is 65% faster than E5-2667
The configuration of the test has 2 chips per node
We need 4 nodes for your cluster this is an advance.

Lets see another one

CELSIUS C740, Intel Xeon E5-1650 v3, 3.5 GHz     6     1     6     12
345     333     Jun-2015
CELSIUS C740, Intel Xeon E5-1660 v3, 3.0 GHz     8     1     8     16
425     411     Jun-2015
CELSIUS C740, Intel Xeon E5-1680 v3, 3.2 GHz     8     1     8     16
441     428     Jun-2015

Prices

Intel Xeon E5-1650 v3 @ 3.50GHz  Last Price Change:  $655.63 USD
(2014-11-20)
Intel Xeon E5-1660 v3 @ 3.00GHz Last Price Change:  $1143.99 USD
(2016-02-04)
Intel Xeon E5-1680 v3 @ 3.20GHz Price at introduction    $1723
September 8, 2014

We need 8 nodes for your cluster so E5-1650 v3 give a result 345+345 = 690

E5-2683 v4 is 194% faster than E5-1650 v3

I think E5-2683 is very very good choice.

Efstathios Konstantinos Mironakis
http://www.forecastmaps.eu




2016-05-09 22:48 GMT+03:00 Witcraft, Nick <nick.witcraft at ncdenr.gov>:

> Hi,
>
> We are in the process of building a new cluster, with a total of 8 compute
> nodes. Would it be better to go with a faster processor with less cores, or
> a slower processor with more cores?
> Sample options, very similar price:
> Intel® Xeon® E5-2667 v4 3.2GHz,25M Cache,9.60GT/s QPI,Turbo,HT,8C/16T
> (135W) Max Mem 2400MHz
> Intel® Xeon® E5-2683 v4 2.1GHz,40M Cache,9.60GT/s QPI,Turbo,HT,16C/32T
> (120W) Max Mem 2400MHz
>
> I did look at Q13 of the FAQ ( http://www2.mmm.ucar.edu/wrf/users/FAQ_
> ... ation.html
> <http://www2.mmm.ucar.edu/wrf/users/FAQ_files/FAQ_wrf_installation.html>
> ), but it doesn't really answer this particular question.
>
>
> Thank you,
> Nick Witcraft
> North Carolina DAQ
>
>
>
> Nicholas Witcraft, Meteorologist II
>
> NC DEQ, Division of Air Quality
>
> Planning Section, Attainment Planning Branch
>
> 1641 Mail Service Center
>
> Raleigh, NC 27699-1641
>
> Phone/Fax: 919-707-8484
>
> Email:  Nick.Witcraft at ncdenr.gov
>
> http://www.ncair.org
>
> [image: cid:image001.png at 01D1058E.93ED1C60]
>
> *Email correspondence to and from this address is subject to the*
>
> *North Carolina Public Records Law and may be disclosed to third parties.*
>
>
>
> _______________________________________________
> Wrf-users mailing list
> Wrf-users at ucar.edu
> http://mailman.ucar.edu/mailman/listinfo/wrf-users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ucar.edu/pipermail/wrf-users/attachments/20160510/7f05588a/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 11798 bytes
Desc: not available
Url : http://mailman.ucar.edu/pipermail/wrf-users/attachments/20160510/7f05588a/attachment-0001.png