[Beowulf] FPS memories RE: K Computer built for speed, not use

[Lux, Jim (337C)]

I went and looked up my old friend the APS-120B..
Wow.. we've come a long way since the late 70s..
2 FP ops per cycle on a 6MHz clock.. 12 MFLOPS!
Of course, it was pipelined, so you could set your problem up to really keep the thing going. (at least for FFTs)  I remember canned lookup table for SIN and COS  without needing an instruction. I can't remember if it did stride or bit reversed addressing.  As I recall the architecture was much like the later monolithic Analog Devices ADSP21020... 


Jim Lux


-----Original Message-----
From: beowulf-bounces at beowulf.org [mailto:beowulf-bounces at beowulf.org] On Behalf Of Lux, Jim (337C)
Sent: Wednesday, October 10, 2012 8:16 AM
To: Ivan M; Beowulf Mailing List
Subject: Re: [Beowulf] K Computer built for speed, not use

I could see some sort of computational architecture optimized for matrix math that doesn't necessarily help for non-matrix operations.  For instance, think back to the 70s and Floating Point Systems:  A box you'd hang on your PDP-11 (or other computer) that does FFTs, and only FFTs.  Made life a whole lot easier for applications like CAT scans, but didn't do much for generalized computational problems.

Jim Lux

-----Original Message-----
From: beowulf-bounces at beowulf.org [mailto:beowulf-bounces at beowulf.org] On Behalf Of Ivan M
Sent: Wednesday, October 10, 2012 7:49 AM
To: Beowulf Mailing List
Cc: Gerson Ferreira Junior; Matheus Viana; Daniel de A. M. M. Silvestre; Lucas Rodrigues; Marcel Nogueira d' Eurydice
Subject: [Beowulf] K Computer built for speed, not use

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?

Cheers
_________________________________________
Ivan S.P. Marin, PhD

Postdoctoral Associate
Département de géologie et de génie géologique Pavillon Adrien-Pouliot, local 3744 1065. ave de la Médecine Université Laval Québec (Québec) Canada G1V 0A6
418-656-2131 poste 7246
 ivan.silvestre-paganini-marin.1 at ulaval.ca
_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf