Re: New itaniums out at 2.5x perform gain


Bill Todd wrote:
bob@xxxxxxxxxxxxxxx wrote:
http://www.informationweek.com/news/showArticle.jhtml?articleID=190500823

Ah, me - even an article that starts by bending over backward to try to
make Itanic look good has a lot of difficulty doing so these days - at
least if it doesn't play somewhat fast and loose with its wording.

Examples:

"Say this for Intel-after five years of [initially negligible and later
only] modest sales and [dramatically] scaled-down ambitions, it's not
[at least not yet] giving up on Itanium [at least not publicly]."
(bracketed clarifications added)

"The chips deliver more than twice the database performance of
previous-generation Itaniums [at the *chip* level, though only slightly
more *per-core* performance despite years of new development, 5x as much
L2 cache and 1.33x as much L3 cache, and significant core enhancements
like multi-threading: the rest comes from having two cores on the
chip], and draw 2.5 times less electric power [if you nimbly and
ever-so-tacitly switch the subject from the *chip* to *per-core* power:
the per-chip power is only moderately reduced]"

You are right, but it does really depend on whether you want to look at
the differences on a per core, per socket, per box, or per dollar
basis.

Montecito does draw less per socket than Mad9M. The Mad9M is rated at
130Watts, while the Montecito is rated at 104Watts. That is 26% less
wattage on a per socket basis. Which is significant if you are buying
based on a core count, since the same number of CPUs draw 40% the
power.

At the box level, the new Montecito SuperDome is shown on the SPEC site
as being able to achieve a SPECint_rate2000 base of 2367 with 128 CPUs
/ 64 sockets (Jul 2006), vs 1108 for the 64/64 for the Mad9M Superdome
(Jan 2005) and 1063 for the 64/32 IBM P5 595 (Oct 2004).

"But..." it then continues, and actually isn't all that biased thereafter.

- bill

.

Relevant Pages

  • Re: Intel hammer another nail in Itanium coffin
    ... >> Is AMD using Processor in this case to mean socket or core? ... > Bill Todd wrote: ... populated with either Opteron 248 single-core chips or Opteron 275 ...
    (comp.os.vms)
  • Re: Big IA64 test coming in a few months
    ... > recent discussion about Montecito Itanium: ... Except, of course that it *won't* be double per core, as further exploration ... 9M to 1.6 GHz rather than the target 1.7 GHz, which is kind of ironic given ... a Montecito core won't offer nearly twice the ...
    (comp.os.vms)
  • Re: Curly soon to be out of a job
    ... In the first stage the 2,560 Dual-Core Itanium-2 processors (Montecito) are to ... > fastest Madison at the time of my posting above clocked at 1.6 GHz IIRC ... David Mulvihill (part of the Foxton ... > not clear about whether that was per core or per socket. ...
    (comp.os.vms)
  • Re: Intel releases 64bit Xeon
    ... speed improvements in going from Madison to Montecito is relatively minor ... Rob - something you're not very good at. ... > core was around for a long time and sped up many times. ... So a POWER5 CPU should out-perform a Montecito CPU by a *greater* ...
    (comp.os.vms)
  • Re: HP should....
    ... >>Not unless Intel stops aggressively developing Itanic, ... > cores on one chip with necessary support infrastructure around the 2 ... While the general design of the Montecito core dates right back to ...
    (comp.os.vms)