Ah but you missed this bit:
"If you look at the ONLY real metric that matters "Wallclock time to
solution" then things aren't quite so bad."
;-)
/\
\/
|\oss Walker
| HPC Consultant and Staff Scientist |
| San Diego Supercomputer Center |
| Tel: +1 858 822 0854 | EMail:- ross.rosswalker.co.uk |
|
http://www.rosswalker.co.uk <
http://www.rosswalker.co.uk/> | PGP Key
available on request |
Note: Electronic Mail is not secure, has no guarantee of delivery, may not
be read every day, and should not be used for urgent or sensitive issues.
_____
From: owner-amber.scripps.edu [mailto:owner-amber.scripps.edu] On Behalf Of
Yong Duan
Sent: Thursday, February 22, 2007 14:25
To: amber.scripps.edu
Subject: RE: AMBER: Sander slower on 16 processors than 8
What Ross was saying was that we all should go back to the "good-old" days
to use 100MHz PII with Gigabit Ethernet. That way, the scaling will be
dramatically better and we will all feel happier. Of course, the bosses
aren't going to be too happy .... :)
Cheers!
yong
-----Original Message-----
From: owner-amber.scripps.edu [mailto:owner-amber.scripps.edu] On Behalf Of
Ross Walker
Sent: Thursday, February 22, 2007 2:15 PM
To: amber.scripps.edu
Subject: RE: AMBER: Sander slower on 16 processors than 8
Dear Steve,
To understand what you are seeing a takes a deeper understanding of the
concept of a cluster. Just remember "all clusters are not created equal".
-----------------------------------------------------------------------
The AMBER Mail Reflector
To post, send mail to amber.scripps.edu
To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
Received on Sun Feb 25 2007 - 06:07:25 PST
