[Beowulf] K Computer built for speed, not use

[Prentice Bisbal]

On 10/10/2012 10:49 AM, Ivan M wrote:
> http://www.sciencemag.org/content/338/6103/26.full?rss=1
>
> "Japan's K computer made headlines in June 2011 as the world's fastest
> supercomputer and again last November when it became the first
> computer to top 10 petaflops—or 10 quadrillion calculations per
> second—solving a benchmark mathematical problem. (...) And now, after
> a year of testing and software development, as the $1.4 billion K
> computer is put to work on real-world problems, some scientific users
> say it was too narrowly built for speed."
>
> Interesting claim. What kind of architecture structure would benefit
> Linpack and would hinder real-world applications?
>

One that has lousy I/O performance is one example. Another would be one 
that takes a lot of memory, especially on a per-node basis (ie, there's 
only so far you can decompose the data across nodes). I'm no expert on 
Linpack, but I don't think it is a memory-intensive benchmark.

--
Prentice