On 16 Jan 2004 09:10:35 -0800, AM2forever.TakeThisOut@hotmail.com (AM2forever)
wrote:
>quote:
>"Just to remind you before you jump saying how they suxxor, TXB was
>the first place to break out the news of Xbox 2 using IBM CPU, months
>before it was officially announced."
>
>http://www.teamxbox.com/news.php?id=5327
>
>
>
>quote:
>--------------------------------------------------------------------------------
>Today we can confirm that the Xbox 2 CPU will also be built using a
>65-nanometer manufacturing process.
>
>
>"It'll be built on a 65-nanometer process," a source confirmed to
>TeamXbox. "IBM has already taped out experimental samples at its East
>Fishkill fab but it will take between 12 to 18 months for them to
>deliver commercial parts. Anyway, they're way ahead of Intel."
Not to say that they're wrong, but I'll believe that one when I see
it. 65-nm parts by early to mid 2005 when they've only JUST started
shipping 90nm parts? It could happen, but I for one don't expect any
65nm parts from ANYONE until late 2005/early 2006.
For their part though, IBM does seem to be more or less on track with
Intel for their 90nm parts. Both companies are shipping to OEMs now
with availability to the public expected in February.
>And the truth is, when it comes to microprocessors, IBM has been
>pulling off one success after the other. It was the first company to
>deliver a 64-bit processor for the desktop, the PowerPC 970 found in
Ahh, that infamous "first 64-bit desktop processor". I still love how
a single processor Opteron system with a plain old PCI bus and AGP
graphics was a "workstation" machine while a dual-processor Powermac
G5 with PCI-X was a "desktop" machine.
When in the Steve Jobs Reality Distortion Field, they certainly had
the first 64-bit desktop processors. In the real world though, they
did not. Hell, Sun, SGI and others have been selling desktop machines
with 64-bit chips for years.
>Apple's Power Mac G5 and, contrary to what most analysts predicted, it
>is the first company to deliver a 90nm microprocessor: the second
>generation PowerPC 970 found inside the new Xserve G5 that will also
>power the second revision of the G5. With this updated PowerPC 970,
>IBM delivers a 90nm processor before Intel's Prescott.
Again, they only delivered them first when you're inside the Steve
Jobs Reality Distortion Field. Go price out an Xserve, estimated
shipping time is 6-8 weeks. Actual availability to customers is going
to be mid to late February, or about the same time that you can walk
into your favorite computer store and pick up a new P4 "Prescott"
system.
>"With the new 90nm manufacturing process, IBM broke the 2 Ghz barrier.
Uhh, and that's impressive how exactly? Intel broke the 3GHz barrier
with 130nm manufacturing process!
>The 65-nanometer technology will allow them to break the 3 Ghz barrier
>for sure and get closer to the 5 Ghz mark," our source further
>clarified and was quick to add, "However, this is not just about clock
>speed. The more important thing here is what this baby and its
>specialized cores can do in a single clock cycle."
Actually it's about both. How much performance-per-clock and the
clock speed give you the real and true performance, which is what
people actually care about. Performance per dollar and/or performance
per watt are the only things that really count. The PPC 970 does fine
here, but it's hardly running away with the title in either case.
Performance, price and power consumption are all well within the same
ballpark for the PPC 970, the AMD Athlon64/Opteron and the Intel
P4/Xeon.
In any case, the 65nm part of this story doesn't seem at all out of
the question. The system is probably not going to be shipping until
2006, so by then a 65nm part seems quite reasonable. The dual-core
idea seems a bit odd though. Currently most games are not effectively
multithreaded, and if your game is not multithreaded it really isn't
going to make much use of the second core. I had almost expected the
next-generation in the PPC 9xx line would use multiple cores and/or
SMT (or perhaps both, the Power5 is expected to do both and the next
PPC 9xx is expected to be a stripped-down version of the Power5 much
like the PPC 970 is a stripped-down Power4). I can see this being
quite useful for the Mac crowd, but for the XBox and games, I dunno.
Even the Playstation3 with it's "cell" processor doesn't really need
multithreaded code, since it's multiple processing units are something
different altogether.
Who knows though, maybe we will see a big push to make multithreaded
games in the next couple of years. Intel already provides some
incentive to do this now by including SMT ("hyperthreading" in
Intel-speak) on their P4.
-------------
Tony Hill
hilla <underscore> 20 <at> yahoo <dot> ca<!-- ~MESSAGE_AFTER~ -->
FAQ
Profile
Private Messages
Log in
