[Beowulf] How Can Microsoft's HPC Server Succeed?

Jim Lux james.p.lux at jpl.nasa.gov
Fri Apr 4 06:29:54 PDT 2008


Quoting Geoff Galitz <geoff at galitz.org>, on Fri 04 Apr 2008 03:19:42 AM PDT:

>
>
>
> Just to be fair... well... maybe not fair... how about Devil's Advocate:
>
> Are any of the MS anti-malware apps more or less difficult to manage than
> their *NIX counterparts?  Network layer firewalls, HIDS, file system
> integrity apps, spam containment and prevention apps and so on?
>
Indeed.

> I don't think anyone expects currently established tools like NAMD (just as
> an example) to ever be ported over to Windows, but if MS can provide great
> development environments and support libraries for a new generation of
> scientists... well... maybe the future is less predictable than we may
> think.  It seems HPC has been swinging away from performance and towards
> ease-of-use for some time, in my opinion.

Why not.. just add more processors to make up for the inefficiency.

That's because performance keeps getting cheaper and labor to use that  
performance more expensive.  Economic forces have always driven this  
way.

Aside from list members and embedded systems coders, how many people  
still program in machine code eschewing an operating system (context  
switch time?) or subroutine calls (all that overhead to remember where  
to go back to, why not just jump).   No, you're willing to accept some  
minor inefficiency (e.g. dynamic memory allocation, etc.) in exchange  
for much higher human productivity.  And, in some cases, thanks to  
extremely smart compiler builders,  the "machine generated code" is  
superior and faster than hand coded versions that do the same thing.


Jim




More information about the Beowulf mailing list