PowerPC 970 Running at 2.5 GHz 719
kuwan writes "IBM has just released a press release that indicates they have the new PowerPC 970 running at 1.8 to 2.5 GHz making it 'the fastest PowerPC so far.' IBM's original estimates were to have the chip running at 1.4 to 1.8 GHz at introduction, so this is very good news for those of us hoping Apple will use this as their next-generation chip."
Let's see some FAB speed scores (Score:5, Insightful)
drool ...imagine dual pro Macs :) (Score:3, Insightful)
I just hope apple doesnt go back to using single chip on their high end systems...its ok if they do use one chip for say the iMac, *book line but the Power Macs should stay with dual if they end up using this chip.
Oh and the obligatory, karma whoring
"Imagine a Beowulf of these!!!!"
Anyone else notice... (Score:2, Insightful)
If Apple uses this, it will just be the same prob. (Score:3, Insightful)
you gotta wonder... (Score:5, Insightful)
The POWERLite series (which is basically what the 970 is) is a great alternative to x86 for Apple for quite a few years ahead. Not only does IBM have an incentive to keep producing these chips at ever-greater clock speeds (something that Motorola with the G4 doesn't seem to have a great deal of interest in doing) because IBM actually uses these in their Blade servers, but it sets up a nice roadmap for successive generations of chips (the POWER5 is just around the corner, with a Power5Lite a la PowerPC 980 coming shortly thereafter? Such a chip is probably only a year and a half off and, running MacOSX, would rocksock).
Yum.
Re:Turtle races! (Score:1, Insightful)
Comment removed (Score:5, Insightful)
AltiVec confirmed (Score:5, Insightful)
Guess that makes it clear this is Apple's next chip.
Re:Help (Score:3, Insightful)
interesting from a historical perspective, it's not
that relevant these days as a benchmark point.
A dual G4 running OS X is a whole 'nuther animal.
Implications? (Score:3, Insightful)
wiggy (Score:5, Insightful)
Re:?!?!?!1 (Score:5, Insightful)
Re:If Apple uses this, it will just be the same pr (Score:4, Insightful)
Re:PowerPC, IBM, and DRM (Score:3, Insightful)
"Install them on Intel servers?" I think you're a bit confused here. The PowerPC chips are used instead of Intel chips, not WITH them. At any rate, IBM only uses the PowerPC on their low end. They use PowerIII, RS64, Power4 on their mid-high end stuff. The announcment was about their blade server, blade servers typically use lower end processors that don't run as hot because of the dense packaging.
Is PowerPC going to implement Palladium and DRM
Typically the only thing that a processor lends to the DRM equation is a unique serial number. I don't know if they support it or not. Wouldn't surprise me however if they did as this scheme is very popular on higher end systems to do software licensing.
If so, then this is good. If all computers become hard-wired with DRM as well as Windows, then I could conceivably still assemble my own system with commodity hardware, a PowerPC chip, and run a Linux PowerPC distro on it.
You will not likely be able to assemble a "commodity" box using a PPC. You'd have to either dig up an Apple mobo or an IBM mobo. Possible to do, but far from bopping down to Fry's and grabing the latest VIA PPC mobo and chip.
Re:quick question (Score:5, Insightful)
will laptops be feasible?
These chips are targetted at blades. Blades require:
Laptops, on the other hand, require:
Draw your own conclusions
Re:More Information (Score:4, Insightful)
I'm sick of you Mac haters (Score:3, Insightful)
You think they suck because they base their computer and OS designs on what their customers want, unlike MS which designs its own ideas and forces them on its customers (HTML email, VBS, ASP and now the new IE5, with it's different rendering of web pages and 96dpi images) because, being the market leader (due to great marketing, not great design), people have no choice.
You think Apple hardware sucks because it uses parts compatible with PC's, despite the fact that Apple hardware components have (for the most part) always been designed by other manufacturers, merely this time they have selected less unique hardware, because this is what their customers wanted and Apple customers are willing to spend extra for this.
You all think Apple sucks because they build computers up to a quality, not down to a price. They suck especially because they took the bold step of designing harware that simple, straightforward and attractive to alot of people (iMac), and in great defiance of the PC market, sells very well. More insulting are the PC owners who discovered their friends' iMacs ran faster.
Oh, and you think Apple sucks most of all because it forces PC owners to realise that they are MS and Intel lemmings - in no control of the chipset's and OS'es they use, as what they do is controlled by both these companies. If it weren't for Apple, AMD and others, everyone, with the exception of companies that can afford expensive un*x workstations, would be complete slaves to MS and Intel.
This is like saying Mercedes Benz sucks because they design innovative cars who's designs influenced car designs for many decades.
Maybe Apple should apologise for shattering people's ideas of what a computer should be.
Join my Slashdot clan! [slashdot.org]
Re:May Apple ISNT dead??? (Score:2, Insightful)
Isn't Apple going to suffer the same problem that the industry has where people's systems are good enough for the apps they are using? Consider that Apple seems to be targetting the end-user arena, are users gonna care if they can run Itunes in 1 second instead of 4?
How many people are choosing PC over MAC based on top-end speed?
I would suspect that price is the biggest determining factor for most users. The addition of $x,000 for that big of a speed jump will not intice many new "switchers".
Not that I am predicting the end of Apple but this news should be taken in context.
Illustrator could use more speed (Score:1, Insightful)
I have a first-gen PowerBook G4 (500 MHz), and with each OS update, it just gets faster and faster.
I think Adobe just needs to spend a little more time optimizing Illustrator. Even with no filters and few objects, it's one of the slowest applications I have.
I'm a developer, too. When you take the time to profile and optimize some code, well, 500 MHz really is a lot of power. I think Illustrator could be really snappy if they work on it just a little more.
Re:Help (Score:4, Insightful)
Your Mac is broken.
Re:you gotta wonder... (Score:5, Insightful)
Well, for scientific users the debate about which platform to use has *significantly* been mitigated by the presence of a true UNIX with OS X allowing for the easy porting and running of code already written for other *nix distros. I personally have replaced three machines including an older Mac, a Windows box and an SGI with a single dual G4 with a sweet Cinema Display.
Now, could I use more power? Absolutely. Code that is optimized for Altivec is screaming fast. Faster than just about any other platform I have used in fact. However, code not optimized for Altivec gets whomped on by the Wintel platform right now and I would like to see some of the delta in performance go away.
All of that said, OS X is one impressive OS. The best OS out there for the general audience and for a number of specialized audiences as well. It can only get better and is awaiting fast CPU's with fast bus speeds.
I suppose it also might be argued that OS X has matured faster as a result of the lagging performance of the G4 chips in that Apple has had to optimize lots of code to get things running fast, whereas Microsoft tends to rely on fast boxes to get through code bloat. Just look at Safari vs. IE as an example of this.
Re:Help (Score:0, Insightful)
I had a similar experience back in 1995. Heh. Seriously, I had a 486 33 with 8 meg of RAM running Windows 95. At school we had a Mac, 16 meg of RAM, 75 mhz. (I think it was PowerPC, but I will let you all know right now I am not Mac Literate.) My school had and I each had similar HP inkjet printers. However, when it came to print artwork, it took over half an hour to get it to finish spooling and printing at school on the Mac. At home, my 486 responded REALLY fast in comparison, my images were printed within 5 minutes.
Macs really suck, don't they? At twice the clock speed and RAM, they should have stomped my piddly PC, right? It'd be easy to make that assumption, but no. The problem wasn't with the machine, it wasn't a fair test.
The program I used for the artwork was called 'Photostyler'. Imagine Photoshop with no layers support and virtually no features. We were using Photoshop on the Mac, which needed a LOT more RAM to to the most basic operation. It wasn't bloated, but more sophisticated. Also, the Mac at school had LOTS and LOTS of fonts installed on it, which we think were cached by the machine, forcing it to swap. My Windows 95 box was a lot more direct to doing what I wanted to do.
Now I will fault Apple for one thing, they had this insistence on loading EVERYTHING into RAM and storing it there even if it's not being used. Got a plugin for Photoshop? No problem, we'll load it in case you need it. I could sort of understand that today when RAM is abundant, but geez why would you do this when you're working on print-level graphics and you're starting point is only 16 megs?!
In any case, the point of my post isn't to bash Apple. Just the opposite really. You really can't compare it that way.
You assume too much about PC speed (Score:3, Insightful)
You know what, a year ago I would have agreed with you but now I'm not so sure. The prices for the top end chips are very high. I'm not so sure that AMD and Intel are currently going to continue their breakneck R&D budgets into the next year. I suspect you will see a dip or a flat spot in the new PC tech for the next 12 months to let them recoup some of the bazillions that have been invested into fabs and development. In that time frame prices will drop on the higher speeds - but the introduction of even faster chips will slow until new architectures become viable/microsoft gets their head out of their ass. Wouldn't it be ironic if Intel got screwed because Microsoft couldn't get Windows XP stable on a new architecture? The reverse situtation happening to apple, now?
PC speed has become less important
*shrug* I have a Apple Powerbook 1Ghz that I use for everything except games. It's fine, zippy, etc. Games I use my PC for. I don't know of any hardcore apple gamers. Apple's focus on notebooks is partially because of this - their powermacs are suffering, but there isn't anything they can do about that right now. In much the same vein, I have a openBSD box, two linux boxes, and a QNX box all running 3-4 year old motherboards and processors fine.
I don't think Apple needs to get involved. The extra time spent making their software better NOW will make it even faster when the new machines come out.
Pick the right tool for the job, duh. Mac isn't the right tool for a FPS or flight sim game monster. It kicks some serious ass as a unixy workstation-to-go, though. Their developer tools are excellent, and free. etcetcetc.
No (Score:4, Insightful)
The constantly moving fencepost horizon (Score:3, Insightful)
To my half thought-through way of seeing things, this is a strong argument for coming up with a product roadmap, even if such things are half-truths in the end. Apple is so secretive about everything that it's impossible to know if something like this -- or something else entirely! -- is going to come out in a month or a year or ever, and consumers like me are perfectly willing to wait. And wait. And apparently, wait indefinitely. Clearing up some of that uncertainty would certainly make me more eager to buy new gear...
</wibbling>
Re:Let's see some FAB speed scores (specs here) (Score:3, Insightful)
He has a valid point. It would be fair to compair it to the best chips out now. I don't care what AMD + rating it has or what MHZ Intel has it running, just the best chips out. It would also be good to see how the best sparc chip, Xeon, (whatever SGI uses), etc compared.
I realize that this is just ONE benchmark and a lot goes in to a system, but it would still be interesting to see.
Re:Hmmm (Score:3, Insightful)
I'm not saying this is always the case; there are very nicely engineered PC's and Macs that aren't as nice as they could be. But Apple products are perceived as being premium products and are generally priced accordingly... and lots of people are willing to pay. Keeping that in mind, I doubt if Apple will ever really get into a PC price war. They'll keep doing just fine in the upper price scales, and with a better profit margin to boot.
Re:Any takers? (Score:3, Insightful)
Re:Let's see some FAB speed scores (Score:2, Insightful)
I would expect pretty lean lead times, given the current market conditions (eg cannot afford Vaporware) and given their reputation.
Re:Let's see some FAB speed scores (Score:5, Insightful)
Re:on a kinda related note... (Score:2, Insightful)
umm.. (Score:3, Insightful)
For anyone who has been paying attention to Apple and IBM and the PowerPC 970 the article didn't NEED to mention Apple. It has been an open and obvoius secret that this chip was developed by IBM specifically for Apple - The presense of Altivec (which is largely useless on a server) is proof enough of that even without the coy public statements (and a few explicit slip-ups despite the standard policy of "we never comment on unannounced products" ).
Yeah, Apple hopes to use this some day, but it'll be a long time coming.
They will be using it the moment IBM can produce them in sufficient quantites.
Someone resection this to strictly IBM rather than an Apple > IBM article.
Despite the article itself having nothing to do with Apple it IS of interest to Apple users because it reveals that the chip everyone knows will replace the G4 is reaching speeds up to 2.5 GHz when it had previously been reported to be between 1.4 - 1.8 GHz.
Re:Let's see some FAB speed scores (Score:5, Insightful)
Nostradamus should have won a Pulitzer.
Re:Let's see some FAB speed scores (Score:4, Insightful)
> Here's the (condensed) deal with the MHz myth:
[ long explaination snipped... ]
I like my description better
MHz is like RPM. Pretend you have 2 engines pulling a heavy load. One is at a high RPM, but with a few cylinders (Pentium 4), and the other at low RPM, but lots of cylinders (Athlon XP). Both can pull the load effectively the same, but watch out when the one with more cylinders gets its RPM up.
It's not completely accurate, but then again, its an anology to illustrate the point.
Cheers
Itanium 2 peaks @ 1 GHz and costs over $3000 (Score:4, Insightful)
For all your Wintel idiots out there who know nothing other than GHz, PPC 970 is a super efficient 64 bit server grade RISC processor with the G4 style Altivec engine, and will blow away your P4, Xeon and Itanium. I home Apple will make a PowerBook with one of these.
According to benchmarks by Intel and HP, the floating point performance of Itanium 2 @ 1 GHz is about 50% faster than P4 @ 3.06 GHz, so clock rate clearly doesn't equal to performance.
In other news, out of 4.5 million servers shipped in 2002, only 3500 were Itanium. In contrast, Apple apparently had already sold approximately 8000 Xserves 6 or 7 months after it was launched in May 2002 - not too shaby for a new product.
Re:Let's see some FAB speed scores (specs here) (Score:3, Insightful)
Re:Reality check (Score:3, Insightful)
Don't tell that to all the folks in the scientific and bio fields doing number crunching on G4s.
Reliable information.... (Score:1, Insightful)
- Comparing DDR RAM to RAMBUS
- Comparing a GF4 with a (professional) Quadro workstation card
- Considering 1.8 GHz P4 Xeons as "top" CPUs
Well... need I say more...?
Re:If Apple uses this, it will just be the same pr (Score:3, Insightful)
I don't know what you mean by 50% (like, compared to what?), but some applications definitely benefit from SMP. 2 1GHz chips will perform almost as well as 1 2GHz chip for some of these things. In that case, I would say the (unacheivable ideal) for 2-way SMP is 50% speed-up. Time goes from 2 minutes to (just over) 1 minute, for example. Of course, going from 1Ghz to 2Ghz chip for the same application will probably give you somewhat less than a 50% speed up. Hence my confustion at your comment.
I find desktop SMP systems nice not only for the parallel apps I run, but also because the general responsiveness of the system seems to be better on average under load.
I haven't done rendering in a while, but SMP systems seem like they would help there. They definitely help in compiling, in my experience. Don't know about games.
YMMV
Re:Let's see some FAB speed scores (specs here) (Score:5, Insightful)
Since this is a 64 bit chip though, wouldn't the proper comparison be with the 64 bit Itanium series?
Re:?!?!?!1 (Score:3, Insightful)
Then again the max shipping speed on the Itanium 2 (Intel's fastest 64 bit chip) is 1Ghz.
I think the days of selling computers based on Mhz just drew to a close.
Re:Totally overpriced. (Score:3, Insightful)
First, I'd estimate the value of the skills needed to assemble that pile of gear into a working computer at several thousand dollars.
That is, you have a valuable skill that allows you to assemble a desktop computer for far less than the average human.
Your comparison only goes to show how much both of those above companies are gouging their customers.
The customers of those two companies generally do not have the skill to assemble your pile of lowest-cost components.
And don't even get me started on the nightmare that befalls you when one of the 10 different suppliers you've chosen delivers an incompatible or broken part.
You clearly don't value your time.
I could spend 5 minutes ordering a new Mac or Dell online. Odds are good it would work perfectly on arrival, and all software would be installed and configured.
Or I could order PC components from 10 different suppliers, getting the best deals. Then I'd wait 8 weeks for the slowest shipment to arive. Then I'd spend at least 2 hours assembling it. Odds are definately not good that everything works on the first try. If something goes wrong, or was poorly documented, it might take 5 hours. And if something is truely broken, another 2 hours on the phone, and a few more hours dealing with shipping stuff back. And when the hardware is finally all working, then I get to install software!
I don't describe this out of ignorance. I bet my experiences building computers are pretty similar to those of most people here. It's just not worth it unless you're time is free.
MHZ? What about FLOPS? (Score:3, Insightful)
Re:Wrong. (Score:2, Insightful)