Slashdot Mirror
More on the PowerPC 970
functor writes "Ars Technica's Jon Stokes has a treatise up covering the microarchitecture of the high-performance 64-bit PowerPC 970 microprocessor, due to be released by the end of the year, that goes over in detail how this chip is put together, and how we can expect it to perform. This is the follow-up to Stokes' article detailing the PPC 970's design philosophy. 'It appears to hold quite a bit of promise in bolstering Apple's currently almost obsolescent product line, and it appears to have been designed explictly to fulfil Apple's requirements. To say the least, the second half of this year looks to be pretty interesting as Apple's product line promises to become competitive performance-wise with IA-32 and x86-64-based PCs again.''
C'mon! It should be abundantly clear now -- even to Steve -- that nobody else in the universe gives a damn if Macs are the slowest desktops on the planet.
Mac developers are used to heavy lifting to accommodate change. Witness the 680x0->PPC migration (which was incredibly painful), or Mac OS 9->OS X. Adopting a new processor would be a piece of cake at this point.
Take a page from GNU/Linux and the BSD's 1 2 & 3. Target multiple architectures. Let the users decide!
Is this truly the only Earth I can live on?
Lately many things have happened to apple, and if you take a brief look at thir lineup of both computers and gadgets you'll find that they are not dependent on anyone the same way they depended on motorola.
The music industry for iMS, AMD for the chips in the airport base station (and the iPod(?) don't know), Motorola for the non-pro lineup (iMacG4, iBook and the portables until they get 970), etc. etc.
I think Apple will go a long way to make sure they don't get stuck with one provider.
Also I think they are trying to be more competitive pricewise. By having a steady stream of income from selling iPods and songs via iMS, they get more money to develop hardware and software, and we just might get Powermacs970 below the $3k mark.
Be like the twenty-second elephant with heated value in space-Bark!
The PPC 970 will not really make the Macintosh competitive with modern PC's. It will make it competitive with PC's from the beginning of this year, which are not the fastest available any more, and will be even slower when compared to the machines that are available when the PPC 970 ships
"Being competitive" does not equal to 'having more computing power". Look how small is this thingy's power consumption! I guess when 970 ships, we will have similar situation as we have right now. x86 machines will consume enormous amount of power and dissipate enormous amount of heat, what usually results in this nice "quadruple augmented turbofan" sound that accompanies most PC desktops or "not enough battery life even to watch a full DVD" laptops. Not to mention that if you actually put this laptop on the top of your lap, you might get your testicles hard boiled.
And Apple will launch yet another series of slower but cool machines - both in terms of look and heat dissipation. Which actually is pretty much what we have already.
All questions demonstrate ignorance. But those who don't ask remain ignorant. And those who critisize asking questions are doubly ignorant.
First off two points, Slow is relative. In relative terms MAC is dead slow, in real terms, dammit people these are 1ghz *ix laptops and desktops. for most things they are blindingly fast.
That being said, I can see apple working themselves into a corner. Let's say they go to a 970 based MAC in October, and it's 1.8Ghz. Perhaps then a big first jump to a 2.5Ghz machine by early 2004. Let's assume for the sake of argument that MAC is then the quickest on the block... for how long will this last? Apple are still very dependent on ONE single external supplier, being IBM. They're being forced to follow the whims of IBM and their CPU line, when that is not IBM's core business.
With an OS running on x86 architecture, not only do OS authors have the knowledge they're building for a well supported architecture, but there is choice in the market of who makes those chips, AMD or Intel for a start. Not only that, AMD and Intel have desktop CPUs as a MAJOR part of their business. There's a big point I've seen little mention of
I see the only sane option is for MAC to go x86. Everything else seems just a temporary option as long as the world works how it does
I'm sorry, but I don't see anything even approaching obsolete in Apple's product line.
NetInfo connection failed for server 127.0.0.1/local
Unfortunately, Apple FUD'd, claiming that shorter pipelines were inherently faster.
Nothing to see here; Move along.
And yet here we have the last man standing in the "RISC turned hopelessly complex" generation, the Power970. When you look at this things design they threw everything and the kitchen sink in there! Most interesting is that batch parallelism where an instruction for every type of execution unit is queued up and when they're all ready to go they're executed in parallel. It will be interesting to see if that can scale given the latency it introduces, and the likelyhood that you won't always be able to fill every unit.
But.. but.. you have the same command line interfaces. You have fink to install all those other apps. You have X11R6. You have Office et al. I fyou don't wanna deal /w the gui, you can use cli or vice versa.
So.. what are you looking for in terms of productivity?
Speed would be an issue for long compiles, multimedia operations or games, but that's as far as I would go.
-
ping -f 255.255.255.255 # if only
Some video/image editing applications may be able to get a small win out of it, but I don't think it will help a lot, since in general they operate on 8 (single color channel) or 32 (3 color channels+alpha) bit quantities. For that kind of operations, the vector unit shines. You can use the regular integer registers as well, but then you get some overhead because of all the masking that's necessary to keep the separate channels from overflowing into the next one. Of course it's possible (after all, that's all there was before altivec etc) and can be combined with the usage of the vector unit, but I doubt it will deliver a lot of extra performance over a 32 bit processor.
Having extra memory available will help everyone (if only because it can be used as a disk cache if no application needs it), but a 64 bit integer unit is not necessary or even helpful in most cases (except for being able to address said memory). As someone else in this thread already remarked, making a program 64 bit may actually make it slower instead of faster if you do it just for bragging rights or because it seems cool.
Donate free food here
Remember, this is the same company that sells 604e machines for $5,000 in the year 2000. And yes, they are full-on server machines with SCSI, GigE, very nice custom parts, etc, but still, it's not gonna be cheap.
Even if you run Linux on it, Macs will probably be cheaper. Of course, the Linux experience will probably be better on an IBM, and the IBM name might look better to the suits.
Rumor has it that Apple will allow IBM to sell Mac OS X Server with some of its PPC workstations as a part of their ongoing cooperation. So you might get the best of both worlds...
Liberate your mind in two clicks or less.
"If they had to, they could switch to an x86 architecture without batting an eye. It worked pretty well for SGI."
No, they couldn't. Every app would need to be rewritten, right on the heels of the 9 to X transition that isn't even finished yet. Switching to x86 is a complex nightmare that may be Apple's doomsday plan, but it is far from simple.
"it will easily be over 50 watts. At that point, the extra 20 or so watts a P4 consumes hardly seems like a big loss."
LIsten to yourself, you are saying that adding an extra 40% isn't going to have an effect on a laptop battery?
"As a result, the CPU stays cool, and the machine is barely audible from a few feet away."
A few feet away? I can't hear my iBook running while I hold it! Your delusional! Mad I tell you!
JohnnyX
SCSI over IDE
Apple went pretty much all IDE about five years ago.
USB over PCI
Mac's have had PCI slots since the first PowerPC based units became available. In fact, back in those days many PC's still had VLB, and only Pentiums had PCI slots. Further, since they were 100% PCI there was no bottleneck due to legacy support (ISA) Also, USB's importance was such that it replaced SCSI for external, high speed devices...
I don't read or respond to AC posts
As Hannibal (Jon Stokes) notes in the article in question:
"The fact that the Altivec unit was slapped onto the design, leaving some room for improvement in future iterations, leaves no doubt that the 970 achieved its present form under pressure from Apple and that Apple will be rolling out systems based on the new processor. This is the most plausible and reasonable explanation for the way the vector unit looks. If the 970 were solely intended as a Linux desktop platform for IBM, they would've preferred to reduce the 970's die size, power consumption, time-to-market, etc. by just leaving out the Altivec unit altogether, instead of shoehorning it into the design the way they did."
Most Linux variants and apps aren't Altivec-optimized, so there wouldn't be very much incentive for IBM to include the functionality in a Linux-only box given the engineering work involved in doing so. It makes much more sense to do it when you know that you could easily sell hundreds of thousands of these CPUs to another company whose customers are desperately eager for that level of performance, i.e. Apple.
How is calling a processor Post-RISC claiming that it is not RISC? IIRC, his statement was that RISC has grown beyond it's original design philosophy and now includes added complexity that increase performance. What's so bad about evolving to increased complexity anyway?
Moreover, how is this claim anti-Apple? Are they the ONLY company in the world using processors built on Post-RISC design philosophies? Doesn't IBM also use PPC750's in workstations supporting their servers?
So, when's lunch?
Why would it be sooner than we think?
We know apple has been working on this for at least two years.
We know the processors are most likely in production.
We know Apple is making big announcements at WWDC.
Wee know Apple needs to release a new platform soon 'cause anticipation is killing sales
Is there any reason Apple and IBM shouldn't be ready to release?