PowerPC 970 Running at 2.5 GHz

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."

Comments

Let's see some FAB speed scores

[MarkRH]

Who cares how fast IBM has this running in the lab--let's see how fast those fab lines are running before we get too excited.

you gotta wonder...

[Petrox]

how many people have been holding off (or switching to other platforms) on a new Apple computer purchase for these new chips. I'm sure Apple is chomping at the bit waiting for these chips to be mass produced so that they can get them into Powermacs (and hopefully Powerbooks too), like, yesterday.

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:you gotta wonder...

[BWJones]

how many people have been holding off (or switching to other platforms) on a new Apple computer purchase for these new chips. I'm sure Apple is chomping at the bit waiting for these chips to be mass produced so that they can get them into Powermacs (and hopefully Powerbooks too), like, yesterday.

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.

Comment removed

[account_deleted]

Comment removed based on user account deletion

AltiVec confirmed

[obi]

Interesting: this PR release seems to confirm the planned extensions are in fact, Altivec. I haven't followed it too closely, but I thought this wasn't confirmed yet.

Guess that makes it clear this is Apple's next chip.

wiggy

[DemiKnute]

Whodathunk that one day we'd be reading a story titled "Apple: ..." with an IBM icon? Maybe I'm getting old, but I think it's kinda cool.

Re:?!?!?!1

[binaryDigit]

Funny that you ask. The fact is that it doesn't matter. Remember the so called "mhz myth" well it definitely exists from a marketing standpoint. IBM could have cranked up the clock rate and achieved 0% performance increase and it wouldn't matter to most people. They just say "oh, Apple has a 2.5ghz processor, that's better than 1.8ghz, oooh, aaaah". This is the same battle that AMD fights. They are spending big bucks trying to remind people that just because that P4 is running at 3ghz, it doesn't mean that it is THAT much faster than a 2.2ghz Athlon.

Re:quick question

[TheRaven64]

will laptops be feasible?

These chips are targetted at blades. Blades require:

1. Low power consumption
2. Low heat dissipation

Laptops, on the other hand, require:

1. Low power consumption
2. Low heat dissipation

Draw your own conclusions

Re:More Information

[Anonymous Coward]

One of the most interesting bits of information from the above IBM pages: In addition to its support of new 64-bit solutions, the 970 retains full native support for 32-bit applications. This not only protects 32-bit software investments, but provides these 32-bit applications with the same high-performance levels that it extends to 64-bit uses. This native, nonemulated, 32-bit support is not limited to application code, which runs unmodified. 32-bit operating systems with minor updates can also take advantage of the PowerPC 970's outstanding performance.

No

[Galahad2]

The 2.5GHz number isn't the same as Intel talking about 5GHz P4s. IBM means that they're going to sell 2.5GHz Blade servers. The reason that Intel talks about their insane GHz processors is to impress consumers into buying Intel. People in the market for mid-range Blade servers couldn't care less about what IBM can do in one in a million chips, and they would likely be annoyed if IBM misrepresented it in that way. If IBM can't manufacture the chips in quantity (I'm not aware if they're manufacturing any 970's in mass yet), they will be able to shortly, certanly before the release of the chip.