This looks like a pretty decent review. It was pretty difficult to read
around all the advertising, though. (I don't recall Tom's Hardware
being that heavy on ads, but I haven't visited there in quite some time.)
Anyway, the review was very PC- (ie., desktop-) centric. And worse, it
wasn't clear to me whether or not *any* of the benchmarks were actually
multithreaded. (This was made more unclear by the difficulty I had
reading around the ads -- I eventually stopped trying.) As I recall,
dhrystones and whetstones are single threaded, and I would expect the
same with video rendering and audio compression benchmarks, although
there's no reason they *have* to be single-threaded. I supect that most
or all of these tests were effectively comparing one "core" in a
dual-core processor against a single-core processor. Under these
conditions, the chip vendor or motherboard designer (or maybe the
benchmarker) would really have to mess up to get any result other than
"almost identical".
I can't say I really agree with the analysis or conclusions either,
except with in the narrow desktop-centric assumptions of the study.
True, if you're running a laptop computer with Windows-XP and using
MS-Word (or maybe Access), you *should* go with the cheaper solution
(two single-core chips), since almost nothing you do is actually going
to use the second CPU anyway. Yet.
But most readers of this list (I presume) are more interested in
database servers than desktops. In this space, the cost of the hardware
is often irrelevant (and a $500 delta between single- and dual-core
processors is *completely* irrelevant) compared to the cost of Oracle
database licenses. You can easily find yourself paying $175,000 to
license EE and a few options on a dual-processor box that *might* cost
$15,000.
So, the question remains, are server-class systems built on multi-core
processors comparable in speed to systems built with single-core CPUs?
Or more to the point, are they more than half as fast, since the
database licenses now cost only half as much? (On x86 architectures,
that is.)
I haven't looked yet, but answers to this might be found at
www.spec.org. You won't see as much prose there as at Tom's Hardware,
but you won't see any ads, either. ;-) Anyway, if the answers aren't
there yet, they should be soon.
Just my two cents' worth...
Cheers, -- Mark
Allen, Brandon wrote:
Just found this one on google - looks like a pretty good study:
http://www.tomshardware.com/2005/11/07/single/page13.html
-----Original Message----- From: oracle-l-bounce@xxxxxxxxxxxxx [mailto:oracle-l-bounce@xxxxxxxxxxxxx]On Behalf Of dba1 mcc Sent: Tuesday, December 20, 2005 3:42 PM To: RROGERS@xxxxxxxxxxxxx; Oracle-L@xxxxxxxxxxxxx Subject: Re: Oracle pricing changes
Anyone have document compare performance between dual-core and two CPU?
Thanks.
--- Ron Rogers <RROGERS@xxxxxxxxxxxxx> wrote:
List,http://news.zdnet.com/2100-9597_22-6002050.html?tag=nl.e589
Just got this email news about Oracle changing it's
pricing on muti-core chip sets.
Thought you might be interested. Our office is
looking at the MS prices and now I have newer info
on Oracle. News appeared at the right time as we are installing
SQLServer and the duhmgt wants to convert Oracle to
it.
Ron
The information transmitted is intended solely for the individual or entity to which it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of or taking action in reliance upon this information by persons or entities other than the intended recipient is prohibited. If you have received this email in error please contact the sender and delete the material from any computer.
-- //www.freelists.org/webpage/oracle-l
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com --
//www.freelists.org/webpage/oracle-l
Privileged/Confidential Information may be contained in this message or attachments hereto. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. Opinions, conclusions and other information in this message that do not relate to the official business of this company shall be understood as neither given nor endorsed by it.
-- //www.freelists.org/webpage/oracle-l
-- //www.freelists.org/webpage/oracle-l
