[Beowulf] Power calculations , double precision, ECC and power of APU's

[Joe Landman]

On 03/19/2013 06:24 PM, Geoffrey Jacobs wrote:
> On 03/19/2013 05:12 PM, Joe Landman wrote:
>> +10 (on the caring about things other than DP, and even SP). There's a
>> fairly large cross section of people whose simulation, codes, etc.
>> have to deal with other-than-*P performance issues. Instruction
>> graduation rate, IO and network bandwidth ... all of these things
>> matter for a large and growing segment of the HPC community. I've
>> argued many times that basing the "fastest supercomputer" metric off a
>> parallel LU decomposition manages to miss an ever larger segment of
>> the HPC community, for whom that metric is not useful.
> The MDGRAPE systems, for one.

Yup.

>
> Your concern (or your clients) arises mainly from a public relations /
> funding perspective?

Not really ... most of our customers are not in the 
government/university space, so top500 is of next to no relevance for 
them for PR/funding or attracting faculty candidates.  Its marginal 
utility comes from answering CEOs questions about where a particular 
system might sit on the list, and that is, at best, passing interest.  
They need ways to articulate scale of performance to their boards, whom 
may or may not have heard of "the worlds fastest computer" without 
having adequate context to understand the metric.  The people updating 
their board need that context, and a rough guess as to how the scale 
maps, but they also can easily articulate that not all scales are 
relevant to their needs.

-- 
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics, Inc.
email: landman at scalableinformatics.com
web  : http://scalableinformatics.com
        http://scalableinformatics.com/sicluster
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615