PDA

View Full Version : Anand: Next Gen CPU Article (Good Read)


brady
06-29-05, 02:10 PM
Here (http://www.anandtech.com/video/showdoc.aspx?i=2461) is the linky. This was just posted on Anand today. I thought it was a pretty interesting read.

Here is my favorite part: In the end, performance could be better, the consoles aren't what they could have been had the powers at be made some different decisions. While they will bring better quality games to market and will be better than their predecessors, it doesn't look like they will be the end of PC gaming any more than the Xbox and PS2 were when they were launched. The two markets will continue to coexist, with consoles being much easier to deal with, and PCs offering some performance-derived advantages.

With much more powerful CPUs and, in the near future, more powerful GPUs, the PC paired with the right developers should be able to bring about that revolution in game physics and graphics we've been hoping for. Consoles will help accelerate the transition to multithreaded gaming, but it looks like it will take PC developers to bring about real change in things like game physics, AI and other non-visual elements of gaming. :D

LiquidX
06-29-05, 02:24 PM
Did anyone actually need Anand to tell or reasure them of that?

oldsk00l
06-29-05, 02:24 PM
I'm so sick of speculative articles about the 360 and the PS3.

They all consist of "this one might be better than the other" when it boils right down to it, and solely exist for the sake of a headline proclaiming "information".

"Analysts" know precisely DICK, and that's how it always remains.
You'd be better off going to the craps table and having an analyst present to you all the facts about which dice may end up facing up, and it'll all just boil down to "Well, you will definitely end up with a result, whether it's positive or not remains to be seen".

brady
06-29-05, 02:31 PM
I was hoping this would stir things up in the console section a little bit.
You know, so we could do one of these (popcorn) :angel:

kev13dd
06-29-05, 05:19 PM
Hey- I actually like the article

It was an interesting read, even if I don't agree with the hype or the stuff in it 100%. Saying that the 3.2Ghz 3 core IBM processor will only be TWICE as fast as the 733Mhz Intel chip? I think twice might be wayyyyyyyyyyy underestimating the developers ability to pump some juice out of the IBM cores

K

Sammy123
06-29-05, 07:29 PM
"Analysts" know precisely DICK, and that's how it always remains.
You'd be better off going to the craps table and having an analyst present to you all the facts about which dice may end up facing up, and it'll all just boil down to "Well, you will definitely end up with a result, whether it's positive or not remains to be seen".

Analysts?

The most ironic bit of it all is that according to developers, if either manufacturer had decided to use an Athlon 64 or a Pentium D in their next-gen console, they would be significantly ahead of the competition in terms of CPU performance."

Third, when a manufacturer is talking about peak floating point performance there are a few things that they aren't taking into account. Being able to process billions of operations per second depends on actually being able to have that many floating point operations to work on. That means that you have to have enough bandwidth to keep the FPUs fed, no mispredicted branches, no cache misses and the right structure of code to make sure that all of the FPUs can be fed at all times so they can execute at their peak rates. We already know that's not the case as game developers have already told us that the Xenon CPU isn't even in the same realm of performance as the Pentium 4 or Athlon 64. Not to mention that the requirements for hitting peak theoretical performance are always ridiculous; caches are only so big and thus there will come a time where a request to main memory is needed, and you can expect that request to be fulfilled in a few hundred clock cycles, where no floating point operations will be happening at all.

The Cell processor is no different; given that its PPE is identical to one of the PowerPC cores in Xenon, it must derive its floating point performance superiority from its array of SPEs. So what's the issue with 218 GFLOPs number (2 TFLOPs for the whole system)? Well, from what we've heard, game developers are finding that they can't use the SPEs for a lot of tasks. So in the end, it doesn't matter what peak theoretical performance of Cell's SPE array is, if those SPEs aren't being used all the time.


For all the marketing hype Sony and Microsoft insisted concerning their respective IBM CPU's, the reality of the matter shows quite a different story.

Karma
06-30-05, 05:43 AM
All you fanboys might listen up: Anand apparently hit the nail on the head with the insider info from developers under NDA. MS is now investigating Anands insider and he's decided/been asked to pull the article.

Lesson: If Microsoft doesn't care, they don't track down your sources.

brady
06-30-05, 06:15 AM
All you fanboys might listen up: Anand apparently hit the nail on the head with the insider info from developers under NDA. MS is now investigating Anands insider and he's decided/been asked to pull the article.

Lesson: If Microsoft doesn't care, they don't track down your sources.

:eek: run anand!

LiquidX
06-30-05, 08:15 AM
Analysts?

The most ironic bit of it all is that according to developers, if either manufacturer had decided to use an Athlon 64 or a Pentium D in their next-gen console, they would be significantly ahead of the competition in terms of CPU performance."

Third, when a manufacturer is talking about peak floating point performance there are a few things that they aren't taking into account. Being able to process billions of operations per second depends on actually being able to have that many floating point operations to work on. That means that you have to have enough bandwidth to keep the FPUs fed, no mispredicted branches, no cache misses and the right structure of code to make sure that all of the FPUs can be fed at all times so they can execute at their peak rates. We already know that's not the case as game developers have already told us that the Xenon CPU isn't even in the same realm of performance as the Pentium 4 or Athlon 64. Not to mention that the requirements for hitting peak theoretical performance are always ridiculous; caches are only so big and thus there will come a time where a request to main memory is needed, and you can expect that request to be fulfilled in a few hundred clock cycles, where no floating point operations will be happening at all.

The Cell processor is no different; given that its PPE is identical to one of the PowerPC cores in Xenon, it must derive its floating point performance superiority from its array of SPEs. So what's the issue with 218 GFLOPs number (2 TFLOPs for the whole system)? Well, from what we've heard, game developers are finding that they can't use the SPEs for a lot of tasks. So in the end, it doesn't matter what peak theoretical performance of Cell's SPE array is, if those SPEs aren't being used all the time.


For all the marketing hype Sony and Microsoft insisted concerning their respective IBM CPU's, the reality of the matter shows quite a different story.

I never fully understood why all three companies went out of there way for a custom CPU's instead of using a Intel or AMD on the market or soon to be on the market. I thought it was so there hardware could not be emulated and a game from say PS2 could not be played on the XBox and the reverse...no?

brady
06-30-05, 09:10 AM
If I remember correctly, the reason neither sony nor M$ will be using Intel or AMD chips is because they (AMD & Intel) were not willing to allow the console makers to have rights to produce their cpus. Additionally, It seemed that there were other factors to which neither AMD or Intel were willing to agree to, which Sony & M$ demanded.

Anyone else recall reading that?

|MaguS|
06-30-05, 09:14 AM
No, Sony has been developing Cell for a long time. They claim its because it is made specifically for certain operations. Its not suppose to compete with AMD/Intel since those are General CPUs.

DEaD_IRiS
06-30-05, 01:54 PM
Wow, I think anand took this article down. I went back to reference something in it today and it was missing from their front page so I came here to try the linky and whoosh it was gone. Interesting article though, I wonder if they got pressured? Seems to be what MS and Sony do best. :)

Ninjaman09
06-30-05, 02:18 PM
I'm sure much of the information they had was obtained through a broken NDA. Microsoft and/or Sony probably got this article taken down real fast.

oldsk00l
06-30-05, 03:17 PM
I still believe it's conjecture until finalized hardware has been produced.

As much as we'd all like to believe that an AMD CPU would spank the hell out of a Xenon array of CPU's or a Cell I still don't draw conclusions until we have hardware that's final spec. At that point, I'll believe with a grain of salt sure. Given though, that all we have are underpowered samples, it is CONJECTURE even from developers.