Crisis in HPC Discussion - Preston Briggs, Tera Computer

From: preston@tera.com (Preston Briggs)
Newsgroups: comp.parallel
Subject: Re: Crisis in HPC Workshop - Conclusions (Summary)
Date: 9 Oct 1995 15:18:16 GMT
Organization: Tera Computer Company, Seattle, WA
Originator: bigrigg@homer.cs.pitt.edu

P.H.Welch@ukc.ac.uk writes:
--------
   CONCLUSIONS: Crisis in HPC Workshop (11/9/95, UCL)

   o Are users disappointed by their performance with current HPC?
 
     Yes...

   o Is there a problem with the efficiency levels obtained by users
     of MPPs for real applications?
 
     Yes...
 
   o Does efficiency matter - given that absolute performance levels
     and value-for-money are better than the previous generation (vector)
     HPC machines?
 
     Yes...

   o (If there are any "yes" answers to the above) where do the problems lie?
 
     Hardware architecture for MPPs.  Real blame here.  Quoting from
     David May's opening presentation: "Almost all the current parallel
     computers are based on commodity microprocessors without hardware
     assistance for communications or context switching.  With the
     resulting imbalance it is not possible to context switch during
     communications delays and efficiency is severely compromised".
--------
Perfect.

The rest was good too, but it's hard to beat such a wonderfully succinct critique.

Preston Briggs

[Prev] [Next]