SUn/Intel slides have Nehalem performance projections

jokerman · **Joined:** Wed Aug 22, 2007 9:24 am **Posts:** 36

removed broken link

TacoBell · **Joined:** Fri Aug 17, 2007 2:55 pm **Posts:** 369

jokerman wrote:

http://at.sun.com/sunnews/events/2008/jan/sun_intel_breakfast/pdf/Sun_Intel_Road%20Show_Austria.pdf

also has AMD Shanghai projections ... Intel expects a pretty decent fight from Shanghai.

In FP it looks relatively competitive but if the Integer performance is even close to what is realized this would be very bad news for Shanghai, with Nehalem having a 40% lead (looks like about 2 for SH versus 2.85ish for Nehalem).

Wouter Tinus · **Joined:** Wed Sep 26, 2007 11:11 pm **Posts:** 38

Working the numbers for Nehalem I get about 164/167 for SPECint/fp_rate_base2006 (assuming two socket configurations, which seems to fit with the relative numbers).

Current top of the line Harpertown is at 121/80.4, while the (now invalidated) 2.5 GHz Barcelona submissions were 102/86.3. It looks like Intel/Sun are expecting a 2.8 GHz Shanghai to come in at about 122/126.

Edit: switched int/fp for Barcelona. Also those are peak numbers, not base.

GeorgeOu · **Joined:** Sun Sep 30, 2007 12:27 am **Posts:** 10

I posted a link to here on my blog.
http://blogs.zdnet.com/Ou/?p=1025

I ran some numbers of my own and I had to make some adjustments to the numbers since I don't know what Intel's reference point is. The following are the adjusted numbers I came up with.

I estimated 176/163 for Nehalem on SPECint/SPECfp rate base 2006.
I estimate 123/121 for Shanghai 2.8 SPECint/SPECfp rate base 2006.

JamesG · **Joined:** Mon Feb 25, 2008 7:22 am **Posts:** 3

The slides are down, anyone got a mirror or can put one up please? Thanks.

The_Wolf_Who_Cried_Boy · **Joined:** Sun Sep 30, 2007 11:01 am **Posts:** 22

This was the interesting one.

JamesG · **Joined:** Mon Feb 25, 2008 7:22 am **Posts:** 3

Thanks wolf, but I was interested specifically in something I saw on the inq, they say the 2 core, 4 core and 8 core are coming "in late" and that's it, is there a date in the slides? Specifically I want to know about the 8 core desktop/enthusiast chips.

The_Wolf_Who_Cried_Boy · **Joined:** Sun Sep 30, 2007 11:01 am **Posts:** 22

Makes you wonder why companies bother "pulling" leaked documents. Once the horse has bolted as they say...

mocad_tom · **Joined:** Fri Sep 07, 2007 8:41 am **Posts:** 23

JamesG wrote:

Thanks wolf, but I was interested specifically in something I saw on the inq, they say the 2 core, 4 core and 8 core are coming "in late" and that's it, is there a date in the slides? Specifically I want to know about the 8 core desktop/enthusiast chips.

Hiroshige Goto says:
Bloomfield/Lynnfield Nehalem-EP (Native Quad-Core) Q3 08
Dunnington (Native Hexa-Core for old FSB) Q3 08
Nehalem-EX Beckton (Native-Eight-Core-Nehalem) H2 09

http://pc.watch.impress.co.jp/docs/2007 ... gai394.htm

Dunnington only for MP-Boards (4 Sockets)
Nehalem-EP is for Single- and Dual-Socket-Configurations.
There is no Beckton planned for DP-Boards or Desktop, big Server-Iron only.

JamesG · **Joined:** Mon Feb 25, 2008 7:22 am **Posts:** 3

The_Wolf_Who_Cried_Boy wrote:

Makes you wonder why companies bother "pulling" leaked documents. Once the horse has bolted as they say...

Hehe, yep. Thanks, but you were right, nothing much else of interest in there and no dates for nehalem, not sure what the inq was talking about. oh well.

Aceshardware

SUn/Intel slides have Nehalem performance projections

Who is online