http://www.osnews.com/story/16134/Sun_Fujitsu_Promise_Sparc_Speed_Surge Exploring the Future of Computing en-us Copyright 2001-2009, David Adams adam+nospam@osnews.com Thu, 09 Jul 2009 20:29:02 GMT http://www.osnews.com/images/osnews.gif http://www.osnews.com http://osnews.com/thread?170768 http://osnews.com/thread?170768 At least they didn't killed the sparc line as originaly announced. I'm gland that there still exist non x86 architetures, so I can still build stronger Fw machines.

Ludo
--
http://perso.hirlimann.net/~ludo/blog/ Wed, 11 Oct 2006 15:37:00 GMT donotreply@osnews.com (!dev!null) Comments http://osnews.com/thread?170817 http://osnews.com/thread?170817 They made some nice comparisons about how the Sparc64 VI is a huge improvement over the Sparc64 V but how does it compare to the UltraSparc IV+? I work in a shop that has UltraSparc servers and I would like to know what kind of performance boost the new generation of chips will give me.

On a related note, I SO want to play with the Niagra II chips. Eight threads per core, 5x increase on floating point, 1.4x increase on integer, etc. What's not to like? Wed, 11 Oct 2006 17:19:00 GMT donotreply@osnews.com (kiz01) Comments http://osnews.com/thread?170839 http://osnews.com/thread?170839 I've been waiting for Niagra II, I love the original but with the advent of the second version, I don't believe I'll need to maintain a single x86 machine!

I am really liking the direction Sun has been heading and continues to move towards. If they keep this up, the company may yet have it's day in the "Sun" again. Wed, 11 Oct 2006 18:03:00 GMT donotreply@osnews.com (ormandj) Comments http://osnews.com/thread?170949 http://osnews.com/thread?170949 Sparc64 leaves UltraSPARC in the dust. They are true OOO cores with both better IPC and higher clockspeed than Sun's UltraSPARC chips.

I don't know whether the system interconnect is any good, though. Wed, 11 Oct 2006 21:53:00 GMT donotreply@osnews.com (rayiner) Comments http://osnews.com/thread?171051 http://osnews.com/thread?171051 Well, the TPC benchmarks demonstrate its performance pretty good - one assumes that database benchmarks are going to be bandwidth and latency sensitive.

I'd say that Sun will be using their own interconnect, with the SPARC VI sitting ontop; its their CPU that is crap, not the processor itself.

Edit: Mind you, IIRC, Sun is a member of Hypertransport consortium, so I'm assuming that when Hypertransport surpasses Suns own technology, they're going to use it - IIRC, Hypertransport 3.0 looks *really* good on paper, that would be a great combo; SPARC IV + Hypertransport 3.0.Edited 2006-10-12 07:47 Thu, 12 Oct 2006 07:43:00 GMT donotreply@osnews.com (kaiwai) Comments http://osnews.com/thread?171057 http://osnews.com/thread?171057 I'd say that Sun will be using their own interconnect, with the SPARC VI sitting ontop; its their CPU that is crap, not the processor itself.

I thought both Sun and Fujitsu will co-marketing the Sparc64 VI in the APL systems developed by Fujitsu. The only difference probably will be the badges and possibly the colour of the plastic. Thu, 12 Oct 2006 09:03:00 GMT donotreply@osnews.com (drdoug) Comments