AP1000+ (Re: xCPU)

Petr Snajdr snajdr na pvt.net
Úterý Říjen 22 10:23:19 CEST 1996


Jakub Jelinek wrote:
>
> > Co je to AP1000+  Multicomputer ? Nevim   proc mam tento projekt spojen
> > se SPARC Linuxem.
> > Pry "full" konfigurace muze obsahova neco pres 1000 CPU ? Jak tedy
> > souvisi se Sparc Linuxem ?
> To je podle vseho nejaky Fujitsu experiment, obsahujici mnoho SuperSPARCu.
> Na rozdil od sun4c/4m/4d atd. architektur napriklad nema PROM, etc. Cast
> zdrojaku SparcLinuxu je sdilena s AP1000, ale cast se ve zdrojacich ocividne
> nenachazi... Pry existuje AP3000 zalozene na UltraSparcich, ktere by mel
> take podobnym zpusobem podporovat UltraLinux.
> 

ted jsem narazil na na jejich HomePage.Tak me npada znaji-li mensi
jednotkunez MB.
8-))

viz.

About the AP1000+ 

 The AP1000+ is a distributed memory multi-computer. Its built by
Fujitsu and
 is in a similar class to the CM5 and T3D systems common in parallel
 supercomputer labs. It is based around 50MHz SuperSparc cpus, but has
 custom networking and disk controller systems. Our current system is
the
 minimum configuration of 16 cpus each with 16MB of ram. We will be
 upgrading this within a month or so to 32 cpus with 64MB of ram each
and
 128GB of (distributed) disk. A "full" configuration would have 1024
cpus each
 with 64MB of ram, but would be very expensive :-) 


                          The CPUs are connected using two main networks
(plus a status net). The Bnet
                          is a broadcast network and runs at around
50MB/sec. This is also the network
                          used to talk to the front end processor (a
sparc 10 running SunOS connected via
                          a Sbus interface) 

                          The Tnet is a 2D torus network which runs at
around 25MB/sec, and has very
                          low latency (around 10us). The network is
wormhole routed in hardware, so
                          hops cost very little. 


We also have a single FDDI board designed and built locally by Paul
Mackerras. Its currently connected to cell
8, and is on a ring that includes the major high performance computers
on campus. 

We still have our "AP1000" system, which has 128 Sparc1+ cpus, but as
its doesn't have any MMUs its pretty
useless for linux. 


BTW:Docela by me zajimalo proc SparcLinux na SUNEch  a ne neco jineho ?
(zbyva asi jen Solaris :))) (?)

--
  S pozdravem
     Petr Snajdr


Další informace o konferenci Linux