Power5
<a href="http://news.com.com/2100-1001-984808.html?tag=fd_top" target="_blank">Power5 article from news.com</a>
"Power5 will be able to perform four times the work of the existing Power4 processor"
"unlike Power4, Power5 will be designed not only for high-end servers but also for lower-end systems."
Coming in 2004 to a Mac near you <img src="graemlins/cancer.gif" border="0" alt="[cancer]" />
"Power5 will be able to perform four times the work of the existing Power4 processor"
"unlike Power4, Power5 will be designed not only for high-end servers but also for lower-end systems."
Coming in 2004 to a Mac near you <img src="graemlins/cancer.gif" border="0" alt="[cancer]" />
Comments
[ 02-17-2003: Message edited by: Mr. Macintosh ]</p>
it would render the wintel industry completely useless
i think when something that powerful is available...and apple is for the masses...3 percent worldwide marketshare is definitly a large market...it gets cheaper and cheaper...
it would cause incredible impact...
Very interesting..this Power5. IBM is going to push Linux in a big way. Mac users might as well reap the rewards where we can.
<strong>The thing is does the Power5 have a SIMD unit or do we care. Should Apple eventually migrate Xserve products to Power5, Powermacs to be PPC 970/980 and consumer lineups G4 for the forseeable future.
Very interesting..this Power5. IBM is going to push Linux in a big way. Mac users might as well reap the rewards where we can.</strong><hr></blockquote>
Here's a great article on the Power5 which should answer most questions, the freaky news is this chip makes the 970 look like a stop gap (Maybe Apple made the right decision giving up on Moto's G5, and instead, throwing it's lot in with IBM's future road map)
<a href="http://www.infoworld.com/article/03/02/04/HNibmroad_1.html" target="_blank">Power5 Article</a>
<strong>The thing is does the Power5 have a SIMD unit or do we care.
</strong><hr></blockquote>
If it doesn't, I would think IBM could add altivec to it just like they did with the modified power4 chip.
<strong>BTW, what happened to the previous POWER5 thread? I presumed that the mods deleted it, in the grip of either a fit of pique, a brain fart, or both.</strong><hr></blockquote>
I can only surmise that it fell off the default page view for Future Hardware.
<hr></blockquote>
<a href="http://www.macedition.com/nmr/nmr_20030122.php" target="_blank">From The Gay Blade </a>
Drool <img src="graemlins/cancer.gif" border="0" alt="[cancer]" />
However Intel isn't <a href="http://www.xbitlabs.com/news/story.html?id=1045279519" target="_blank">standing still </a>
The next couple of years will be interesting.
<strong>
I can only surmise that it fell off the default page view for Future Hardware.</strong><hr></blockquote>
Nah ... I think infopop started something funny, I stuck a post in it that mysteriously showed up in between two earlier posts, and then next morning, the thread was completely missing, not even in page 2 or 3.
Anyway, the Power5 is back at the top where it should be ...
<strong>
Nah ... I think infopop started something funny, I stuck a post in it that mysteriously showed up in between two earlier posts, and then next morning, the thread was completely missing, not even in page 2 or 3.
Anyway, the Power5 is back at the top where it should be ...</strong><hr></blockquote>
That's right, I looked back a couple of pages too. Given Amorph's cry of innocence, I'll put it down to an attack by cyber-ninjas from the House of Intel.
Toasty, I totally agree that this news gives us ample room for some rather unfamiliar feelings, namely a warm and fuzzy sense of impending hardware superiority. That is, that feeling I'm getting is either that or last night's curry....
If we read the linkage carefully, we see that the IBM spokesthing speaks of some "dramatic" improvements over the old POWER4. Does a four-fold improvement over 2 years rate as "dramatic"? Maybe. But I'm hopeful that it's a broad hint that Big Blue have a trick or two up their sleeve, perhaps some Cell-inspired easy-peasy lego-style scalability....
Come to think of it, it might be last night's curry doing the talking. Disregard everything I've said.
It didn't seem too clear whether a single core would be 4x faster than a single POWER4 core, or if the chip's overall net performance (including multi-core, multi-threading) would be 4x. Either way it sounds like those things will be real brutes. My guess is that now that IBM has a VMX implementation they'll probably keep it -- it sort of fits with their "FastPath" ideas.
I also agree that IBM will likely make a "mini me" version of the power 5 for the 9X0 family. The Power 5 is likely too costly for the desktop and low end server market.
A while back I heard something about the Power5 being a 4 core processor with hyperthreading. Is it just another dual core then?
"unlike Power4, Power5 will be designed not only for high-end servers but also for lower-end systems."
Coming in 2004 to a Mac near you
<hr></blockquote>
POWER5. Sounds like IBM is opening a whole can of whoop-ass on Intel.
Moto G5 vs IBM 'G5'. With the latter, IBM buys a credible partner and a road map. Good for business. And that's a Good Thing TM.
Gurgle. (Future hardware lust...)
Lemon Bon Bon
XBits Reports :
Prescott CPUs will feature 800MHz Quad Pumped Bus, 1MB of L2 cache and the Hyper-Threading II technology in addition to new set of instructions known as PNI ? Prescott New Instructions. Apparently, the Prescott chips will live through 2004 and will be discontinued only in 2005. Implementation of 1066MHz Quad Pumped Bus and new Prescott ?B? core to support the new PSB in early 2005. Tejas should come to the market in late 2004 or early 2005 and feature another set of new instructions (TNI, Tejas New Instuctions) as well as new Hyper-Threading technology. Tejas chips will be shrunk to 65nm technology in late 2005 or early 2006 and receive 2MB of L2 cache and 1200MHz Quad Pumped Bus in addition to higher core-clock.
Prescott Tejas
Prescott 3.20GHz (800MHz QPB)
Prescott 3.40GHz (800MHz QPB)
Prescott 3.60GHz (800MHz QPB)
Prescott 3.80GHz (800MHz QPB)
Prescott 4.00GHz (800MHz QPB)
Prescott 4.20GHz (800MHz QPB)
Prescott 4.40GHz (800MHz QPB)
Prescott 4.60GHz (800MHz QPB)
Prescott 4.80GHz (800MHz QPB)
Prescott 4.80GHz (1066MHz QPB)
Prescott 5.00GHz (800MHz QPB)
Prescott 5.06GHz (1066MHz QPB)
Prescott 5.33GHz (1066MHz QPB)
Tejas 5.33GHz (L2=1MB, 1066MHz QPB)
Tejas 5.60GHz (L2=1MB, 1066MHz QPB)
Tejas 5.86GHz (L2=1MB, 1066MHz QPB)
Tejas 6.00GHz (L2=2MB, 1200MHz QPB)
Tejas 6.13GHz (L2=1MB, 1066MHz QPB)
Tejas 6.30GHz (L2=2MB, 1200MHz QPB)
Tejas 6.60GHz (L2=2MB, 1200MHz QPB)
Tejas 6.90GHz (L2=2MB, 1200MHz QPB)
Tejas 7.20GHz (L2=2MB, 1200MHz QPB)
<hr></blockquote>
And Apple will need to do SOMETHING in the next year. Shipping 1 gig processors against Intel's 2004/5 roadmap will look increasingly embarrassing. Hey, we may even have got over 2 gig by then...
Lemon Bon Bon
[ 02-18-2003: Message edited by: Lemon Bon Bon ]</p>
In any event, competition between IBM and Intel doesn't really scare me. I think neither side will run away from the other. Ultimately, consumers on both sides will benefit...
Apple better run off some Quad-970s pretty goddamn fast! Power5 seems like a good move to me! :eek: