From PC to Next-Gen Consoles: Largest Performance Gap...

Status
Not open for further replies.
As far as IBM and their relationship with SCE and MS, why does this "leaked internal e-mail" claim

The new Xbox technologies will be based on the latest in IBM's family of state-of-the-art processors;

It is the single largest win for Engineering & Technology Services and a substantial foundry win for our 300 mm facility;

http://www.theinquirer.net/?article=12552

It suggests that MS is a better paying customer than Sony.
 
jvd:
However its not very fair to add in the model 1 and model 2 systems nor model 3 as they are in the hundreds of thousand dollars
They certainly weren't consumer-level, but the boards were actually priced at a few thousand dollars (with a healthy profit margin and only low volume production) and only raised near highs of twenty grand when accounting for those sophisticated deluxe cabinets.
The dc came out and the geforce 1 was already out.
That's just the thing: the DC was actually out much before that, back in late 1998, in the era closer to Voodoo 3 and after Voodoo 2. GeForce 256 launched around late 1999 and early 2000.

Ty:
Did it launch at 199? If so, that wasn't a bad launch price of a console if I recall correctly.
DC released in Japan closer to 30,000 yen which often ends up being the equivalent of the $199 pricetag that the later US launches get. The DC took pricepoints lower than the PS2 at its releases: in the US, for instance, it was $299 PS2 vs $199 DC at their respective launches.
Have to disagree here since, among other things, you're disregarding resolution (PCs were running 800x600 at least for the average game) and DC didn't need to even come close to that.
They're made for different markets of course, but the PowerVR2DC wasn't really matched in capabilities by the Voodoo line (even two Voodoo2s in SLI) or the TNTs either even taking the markets' respective focuses into account.
 
Brimstone said:
As far as IBM and their relationship with SCE and MS, why does this "leaked internal e-mail" claim

It suggests that MS is a better paying customer than Sony.

It suggests nothing of the sort. If you investiagte what it was really saying you'd see that IBM's Engineering & Technology Services (E&TS) other customs are not Sony and Toshiba, but companies and institutions like Lawrence Livermore, the NYSE, Raytheon, the Israel Institute of Technology.

So of course it's going to be the biggest win for that division. What it says compared with the STI investment is nothing at all. What we do know is that IBM built and basically populated the entire STI-Austin complex in the heart of their campus for the project - with them sholdering a large burdon. The team leaders from IBM who worked on the Cell architecture are all eminent and in the highest tier of IBMs community. Who exactly is working on the design of the XCPU again?

What exactly is origional about the XCPU? Even the fact that the win was given to the E&TS division shows that it's more geared toward implimenting a custom IC that uses off-the-shelf technology. Highly unlike STI and their R&D project spanning over half a decade.
 
Vince said:
Brimstone said:
As far as IBM and their relationship with SCE and MS, why does this "leaked internal e-mail" claim

It suggests that MS is a better paying customer than Sony.

It suggests nothing of the sort. If you investiagte what it was really saying you'd see that IBM's Engineering & Technology Services (E&TS) other customs are not Sony and Toshiba, but companies and institutions like Lawrence Livermore, the NYSE, Raytheon, the Israel Institute of Technology.

So of course it's going to be the biggest win for that division. What it says compared with the STI investment is nothing at all. What we do know is that IBM built and basically populated the entire STI-Austin complex in the heart of their campus for the project - with them sholdering a large burdon. The team leaders from IBM who worked on the Cell architecture are all eminent and in the highest tier of IBMs community. Who exactly is working on the design of the XCPU again?

What exactly is origional about the XCPU? Even the fact that the win was given to the E&TS division shows that it's more geared toward implimenting a custom IC that uses off-the-shelf technology. Highly unlike STI and their R&D project spanning over half a decade.


I like how you didn't mention AMD in there. But I guess they are a small fry company.

http://www-1.ibm.com/technology/ourwork/ourclients.shtml

From the front page of the E&TS division.

Turning great ideas into great products takes the right resources. With IBM E&TS, you can have access to those resources on demand.

By leveraging our access to IBM's intellectual property, people, tools and methods, we can help you get to market quicker, operate more cost-effectively, and infuse your products with the kind of advanced technology we've used on highly regarded projects like Blue Gene/L and the Apple G5's PowerPC® processor.

The E&TS group gets access to all of IBM's IP, or at least that how I read it.

I couldn't find the STI CELL page on IBM's site? Was I looking in the wrong places?
 
Brimstone said:
I couldn't find the STI CELL page on IBM's site? Was I looking in the wrong places?

How can you find a page of something that will be officially unveiled in the next year? :rolleyes:

What is different between IBM chips in Xbox2 and PS3 is, the former is used only for other companies (MS et al.) and the latter is used for not only for PS3 but also for IBM's own products and solutions.
 
one said:
Brimstone said:
I couldn't find the STI CELL page on IBM's site? Was I looking in the wrong places?

How can you find a page of something that will be officially unveiled in the next year? :rolleyes:

What is different between IBM chips in Xbox2 and PS3 is, the former is used only for other company (MS) and the latter is used for not only for PS3 but also for IBM's own products and solutions.

I don't understand what your saying .

The xbox2 is using an ibm chip. True the 3 core dual set up may only be used in the xbox2 . But the cores will certianly be used in other products .

Hell since we know nothing so far. What if its based off bluegene . just like the cell is .


Same goes with ati . Ms's chip the r500 may only be used in the xenon but u can bet your but it will find its way to the pc sector as a r600 with modifications. All that ip wont go to waste
 
Brimstone said:
I like how you didn't mention AMD in there. But I guess they are a small fry company.

Ok, that was my fault, but what do they do for AMD?

Brimstone said:
The E&TS group gets access to all of IBM's IP, or at least that how I read it

I think youre totally overestimating this. Lets look at their case studies:

  • A rugged field-maintenance system
    How do you get a state-of-the-art portable maintenance system that's fit for the harshest environments without starting from scratch? Ask us.

    The Technion - Israel Institute of Technology Design Portal
    The VLSI Systems Research Center at the Technion - Israel Institute of Technology wanted to prepare their advanced electrical engineering students for future careers in real-world chip design. So IBM E&TS created the design lab of the future.

    A giant-magnetoresistive (GMR) sensor
    When an industrial automation supplier wanted to simplify its line of sensors, they turned to us for IP and technical know-how that helped them gain a significant cost advantage.

    The IBM pSeries
    When the IBM Systems Group needed help integrating advanced technology to stay ahead in the market, who could they turn to? Why IBM, of course.

    Electromagnetic write head for magnetic tape
    The client had designed a unique electromagnetic head capable of writing skewed servo tracks on magnetic tape, but developing the manufacturing process was a job for IBM.

Maybe it's just me, but they seem more like a a group who takes off the shelf technology and applies it to custom parts.

As for STI, they don't have a join website yet. I imagine they'll do something once the architecture is unveiled but so far they only have this
 
Brimstone wrote:
I like how you didn't mention AMD in there. But I guess they are a small fry company.


And what exactly do they do for AMD?

THey basicly give amd fab tech.

They helped them with soi and 130nm and 90nm. I assume they are going to help them with 65nm and 40nm too .



As for the team working on the xenon chip.

I'm sure this chip will be used in many other things. Perhaps not a dual core or three core dual cpu set up . But single cores will most likely be made from it.

Ibm wouldn't waste resources
 
jvd said:
I don't understand what your saying .

The xbox2 is using an ibm chip. True the 3 core dual set up may only be used in the xbox2 . But the cores will certianly be used in other products .

What I mean is, Cell chips will be almost certainly used in IBM's own server lineups (with new brand name, perhaps), while Xbox2/Mac/Nintendo chips will be for PC/console market.

EDIT:
From the IBM site Vince posted -

IBM strategy with STI cell processor
IBM has an unmatched history and capability of building custom chips and believes the one-size-fits-all model of the PC does not apply in the embedded space; embedded applications will require a flexible architecture, like Cell. Cell also brings together, for the first time, many leading-edge IBM chip technologies and circuit designs developed for its servers.

You know which is which by this statement about the 'one-size-fits-all model of the PC' and the Cell model? 8)
 
They might use the cell chip in thier high end servers and mabye in tablet pcs .

Though bluegene has been done for a long time and we see nothing from it .

Perhaps they will pass on cell or produce them in limit quanitys . I do not know thier plans .

I do know that with ms writing a basic os and a dx version for the xenon cpu . It might find its way into macs and other servers as a side effect of that .


I do get very tired of people hyping cell to high water .
 
jvd said:
I do get very tired of people hyping cell to high water .

I don't hype Cell, only listing what I know about Cell from news media.

For Xbox2, I know nothing other than its 'leaked' spec and the rumor they use Mac G5 for dev platform and its CPU & GPU are by IBM & ATI. But at least from the discovery that IBM is to make Xbox2 CPU, one can estimate the R&D period for Xbox2-specific CPU design is shorter than that of Cell by 1-2 years, because while Cell design started in 1999, it's sure that Microsoft had no plan to move to IBM platform then with Intel + nVidia before 2002.

Granted Microsoft is a software company and Windows is flexible to be recompiled to run on PowerPC, and by using off-the-shelf stable tachnology which is long developed already the length of the period for specific chip design may not matter. But this is not the PC market where x86 still dominates, this is the embedded console market where you can adopt radical design such as PS2 without compatibility to old technology. Today PS2 is seen as less powerful machine than newer Xbox, but if PS2 had had more memory, and if Toshiba had not misestimated future GPU trend in designing GS...?
 
one:
but if PS2 had had more memory, and if Toshiba had not misestimated future GPU trend in designing GS...?
... it would be a different machine.

If DC or GC had been designed for the PS2/Xbox pricepoint...?
 
one said:
jvd said:
Today PS2 is seen as less powerful machine than newer Xbox, but if PS2 had had more memory, and if Toshiba had not misestimated future GPU trend in designing GS...?
Lets have a look at this in 'reality'. Lets look at something 'compareble'

PS2 has 2 general purpose vector units, clocked at 300Hz. Capable of a limited set of 16 bit integer ops and 1 vector dotproduct per cycle. It has looping and primitive generation capabilities.
Xbox has 2 vertex units, clocked at 233Hz. Capable of 1 vector dotproduct per cycle.

Clear win to PS2, lets look closer. Clear high theorical speeds for PS2.

Xbox vertex shader are 6 way SMT. It has 6 threads, that switch automatically when latency would stall the pipes, it also does the homogenous divide and clipping for 'free' (pipeline fixed function).
PS2 rely on manual loop unrolling to hide latency, in many cases the register don't have interlocks so its down to NOP counting. Its LIW make it hard.
Clear win to Xbox this round. Xbox is much easier to program for.

Overall realworld performance, Xbox is faster but then it should be its several years later silicon. PS2 manages to hold it head up VERY well considering how much earlier it was designed and implemented. Its a testiment to the awesome design skills of ST (Sony and Toshiba) that they managed to put so much pure float power in such an early console.

But it also shows a brute-force un-user friendly approach. A good analogy would be modern jets, the early experimental X planes did get to Mach 1 or 2 but modern jets get to a similar speed alot safer.

ATI and NVIDIA have shown how to get good graphics performance relatively easily. Sony have shown pure brute force and good coders can get good graphics performance.
 
don't hype Cell, only listing what I know about Cell from news media.

For Xbox2, I know nothing other than its 'leaked' spec and the rumor they use Mac G5 for dev platform and its CPU & GPU are by IBM & ATI. But at least from the discovery that IBM is to make Xbox2 CPU, one can estimate the R&D period for Xbox2-specific CPU design is shorter than that of Cell by 1-2 years, because while Cell design started in 1999, it's sure that Microsoft had no plan to move to IBM platform then with Intel + nVidia before 2002.

Really ?

Hmm. I would say the g5 development started in at least 1999. So I would say they are equal the same age.

After all a year or two agao ms didn't just go to ibm. Hey make us a chip and ibm went sure. Took out a pen and paper and made a chip.

They used existing ip , existing tech , old design ideas that had been constantly worked on and improved.

Hell. Just because ms decided to go with ati a year ago doesn't mean thast when ati's development on the r500 started.

That chip was in the works regardless of if ms wanted it or not.

The only thing in both counts is whats modified for it .

perhaps the xenon cpu was going to be a single core chip. But ms wanted a 3 core dual chip design. So ibm took a core in production and modified it to work the best it could in that design.

For all we know the chip could have been in the works from 1998 from ibm. Before blue gene even started.

Granted Microsoft is a software company and Windows is flexible to be recompiled to run on PowerPC, and by using off-the-shelf stable tachnology which is long developed already the length of the period for specific chip design may not matter

Microsoft for all its faults is a great software company and they have years of work put into dx versions and the tools for it. What do you think happens when ms turns its might onto the xenon. Your going to get a very good kernal and dev platform for the xenon . I would wager better than ibm and sti could do .



But this is not the PC market where x86 still dominates, this is the embedded console market where you can adopt radical design such as PS2 without compatibility to old technology

Problem is with such a radical design comes problems with devs and programing. Ask any dev what a pain in the ass early development was like on the ps2. Just look at the tights. The horrible jaggies. The half res crap. All of this was becasue of the radical design.

They are just lucky they had a ) the hype b) the price advantage c) the later start over the dreamcast. Because if the dreamcast launched in 1999 when the ps2 did and sega spent as much on it as sony . The ps2 would have had its ass handed to it . THe could have made a faster sh-4 on a smaller process , used a elan tnl chip and a faster neon 250 or even 2 slower ones .

PS2 is seen as less powerful machine than newer Xbox, but if PS2 had had more memory, and if Toshiba had not misestimated future GPU trend in designing GS...?

Right and if a tnt 2 was clocked at 800mhz , had 128 megs of ram instead of 8/16 and was coupled with a 4 ghz cpu it would have been awsome too.

To bad they didn't wait to release it eh



What many people here want to forget is the fact that ibm makes good cpus for a living. Perhaps sony did get a better cpu.... Your forgeting that then there is ati. And its most likely that ms got the better vpu.

I duno about u but i would put my money on a r500 with 3Dc , almost long horn features (if not longhorn features) Hyper z hd , ati's rotated grid fsaa , ati's trilinear filtering optimization , and ati's pipe lines against a cell gpu any day of the week .

Right now we are seeing 16x520mhz vpus from ati. Most users who own them are hitting 600mhz on the core . I have no doubt in my mind that next year ati can't hit 700mhz with a beast like that and if the rumors are true and ms is renting alot of ibms 65nm space... well i can imagine a beast that would put the r420 to shame.

SO i get tired real easily of the cell hype. I've had to deal with it a long time.

Cell is not a some all powerfull tech. Any of the new systems can end up the most powerfull. What matters is what the diffrence is on the screen and in the game play .

That is why my money is on nintendo
 
Devourer said:
http://www.research.ibm.com/people/m/mikeg/

This guy seems involved both in the development of CELL and XBox2 CPU.

Referring to Xbox-next CPU it says: "Contributions to IBM's family of state-of-the-art processors. "

In regard to CELL, instead: "High performance computer architecture".

What's going on here...

The guy involved design of some processor (Power5?).
Then MS has licensed it. Clear and simple.

jvd said:
For all we know the chip could have been in the works from 1998 from ibm. Before blue gene even started.

Is it designed for embedded use? I don't think so.

jvd said:
Microsoft for all its faults is a great software company and they have years of work put into dx versions and the tools for it. What do you think happens when ms turns its might onto the xenon. Your going to get a very good kernal and dev platform for the xenon . I would wager better than ibm and sti could do .

Then, what experience does MS have with embedded real-time OS? I think Sony has far longer experience with it.

jvd said:
Right now we are seeing 16x520mhz vpus from ati. Most users who own them are hitting 600mhz on the core . I have no doubt in my mind that next year ati can't hit 700mhz with a beast like that and if the rumors are true and ms is renting alot of ibms 65nm space... well i can imagine a beast that would put the r420 to shame.

SO i get tired real easily of the cell hype. I've had to deal with it a long time.

Cell is not a some all powerfull tech. Any of the new systems can end up the most powerfull. What matters is what the diffrence is on the screen and in the game play .

Powerful is good, but are we talking about PC or console/embedded? :rolleyes: Mac G5 is equipped with watercooling, BTW.
 
JVD, I think you are bit biased toward ATI, just like Sony fans are toward Sony. You have your reasons for that and there's nothing wrong really. But I think that what you wrote is contradictory.

jvd said:
Problem is with such a radical design comes problems with devs and programing. Ask any dev what a pain in the ass early development was like on the ps2. Just look at the tights. The horrible jaggies. The half res crap. All of this was becasue of the radical design.

They are just lucky they had a ) the hype b) the price advantage c) the later start over the dreamcast. Because if the dreamcast launched in 1999 when the ps2 did and sega spent as much on it as sony . The ps2 would have had its ass handed to it . THe could have made a faster sh-4 on a smaller process , used a elan tnl chip and a faster neon 250 or even 2 slower ones .

Ok, but that is in theory. In reality, Sega, Nintendo and Microsoft had their asses soared badly. Even from a technical POV, PS2 still stands well against much newer hardware like Xbox, even if it is undeniably inferior (how could it be otherwise?). And thinking of the magnitude of the the companies we are talking about, I highly doubt that Sony obtained such results because "they are just lucky". Moreover when PS and Saturn both launched simultaneously, it was the-once-mighty Sega that looked the dwarf of the situation, imho.

jvd said:
PS2 is seen as less powerful machine than newer Xbox, but if PS2 had had more memory, and if Toshiba had not misestimated future GPU trend in designing GS...?

Right and if a tnt 2 was clocked at 800mhz , had 128 megs of ram instead of 8/16 and was coupled with a 4 ghz cpu it would have been awsome too.

To bad they didn't wait to release it eh

What? :oops:
You make fun of his assumptions when a paragraph above you made even bolder ones for Sega? You said they would have kicked Sony in the butt with a super Dreamcast had they waited a year...hence Sony are 'just lucky'. The coherence here sure is striking ;)


jvd said:
What many people here want to forget is the fact that ibm makes good cpus for a living. Perhaps sony did get a better cpu.... Your forgeting that then there is ati. And its most likely that ms got the better vpu.

I duno about u but i would put my money on a r500 with 3Dc , almost long horn features (if not longhorn features) Hyper z hd , ati's rotated grid fsaa , ati's trilinear filtering optimization , and ati's pipe lines against a cell gpu any day of the week .

You doubt of PS3 VPU. And you may be right. We know nothing about it. It could be great, it could be crap. Then again you hype Ati VPU by saying that "its most likely that ms got the better vpu". But if we don't know anything about Sony's VPU, how can you go that far and then criticise Sony's fanboys? So, you basically are annoyed by Cell hype simply because you are hyped by Ati :D



jvd said:
What matters is what the diffrence is on the screen and in the game play .

That is so true and savvy. That's why all this speculation is like a powder keg. It's about to blow up to the face of the loser party. :D

My two cents: In Japan alone Sony can sell a million or more of PS3s just on day one. There's no other consumer electronic device that can move such massive numbers so fast. I think that is Sony's strength and they should capitalize on it by giving their hardcore userbase the most powerful system no matter what, even at high price tags. Microsoft is determined and powerful, and imo it is imperative for Sony not to lose the techlogical leadership, otherwise it could mean trouble.
 
one said:
Powerful is good, but are we talking about PC or console/embedded? :rolleyes: Mac G5 is equipped with watercooling, BTW.

Zallman manages to cool high end P4s with heatpipes alone though.
 
Ok, but that is in theory. In reality, Sega, Nintendo and Microsoft had their asses soared badly. Even from a technical POV, PS2 still stands well against much newer hardware like Xbox, even if it is undeniably inferior (how could it be otherwise?). And thinking of the magnitude of the the companies we are talking about, I highly doubt that Sony obtained such results because "they are just lucky". Moreover when PS and Saturn both launched simultaneously, it was the-once-mighty Sega that looked the dwarf of the situation, imho.

SEGA had NAOMI 2 which is essentially a DC 1.5 that they didn't convert to console form. It's more powerful than PS2 in many ways.
 
Status
Not open for further replies.
Back
Top