Intel Conroe: From a Console's Perspective

basanti

Banned
Conroe is Intel's next generation architecture just like Cell is the next generation of IBM/Sony PPC Architecture. How would the performances compare if say Xbox 360 had a next generation Intel Conroe (single or triple core) vs a PS3 Next generation PPC Cell Processor. Would it make much of a difference over PPC Tri-core processor? Anyone have some knowledge of this new intel architecture?
 
It would be better.

The just released benches show it easily besting a A64 by 20-50%, as I imagine you know.
 
Don't forget that MS wants to own the IP of the hardware inside it's consoles, so an Intel-based Conroe chip is out of the question.
 
Karma Police said:
Don't forget that MS wants to own the IP of the hardware inside it's consoles, so an Intel-based Conroe chip is out of the question.

true but anything can change in 5 years
 
who cares this won't be in any of the next-gen consoles. and by the time next-next generation consoles are here (2011?) there will be even newer stuff that blows this stuff away.
 
It would be better.

The just released benches show it easily besting a A64 by 20-50%, as I imagine you know.


Pfff... the Cell slamdunk owns a 2,7GHz G5 more than 50 times in powerhungry applications (and that's 1 SPE with the PPC).
Cell is the most powerfull CPU out there why do you think engineers, developers etc. think it's a Revolutionairy CPU?
 
Guilty Bystander said:
Pfff... the Cell slamdunk owns a 2,7GHz G5 more than 50 times in powerhungry applications (and that's 1 SPE with the PPC).
Cell is the most powerfull CPU out there why do you think engineers, developers etc. think it's a Revolutionairy CPU?

For certain types of applications, I agree, CELL has revolutionary performance. For general computing purposes, it may fall short.
 
Karma Police said:
Don't forget that MS wants to own the IP of the hardware inside it's consoles
I'd bet real money they don't own the IP of either xenos or xenon, except betting is illegal where I live, so I have to settle with just speculating. :p

There's no reason to believe they own this IP, and every reason to believe they do not. For starters, if they did, IBM and ATi would have just pissed away a large chunk of their research and development efforts. So... Not really gonna happen, I say.

Besides, a dual-core conroe is way too large and costly to make a console CPU out of. It would own on integer calculations, but FP would suck as usual when it comes to x86, particulary as clockspeed would be much less than the current xenon CPU. And a triple-core version would be friggin huge, and draw a lot of power as well.
 
Guden Oden said:
There's no reason to believe they own this IP, and every reason to believe they do not. For starters, if they did, IBM and ATi would have just pissed away a large chunk of their research and development efforts. So... Not really gonna happen, I say.

I'm pretty sure it was part of the deal..
 
Guden Oden said:
I'd bet real money they don't own the IP of either xenos or xenon, except betting is illegal where I live, so I have to settle with just speculating. :p

There's no reason to believe they own this IP, and every reason to believe they do not. For starters, if they did, IBM and ATi would have just pissed away a large chunk of their research and development efforts. So... Not really gonna happen, I say.

Why not? It has been said many times that they do own the IP for both chips, which allows them to later on shrink them, which is always a good thing. It's not like they can't afford it anyway.
 
Guden Oden said:
I'd bet real money they don't own the IP of either xenos or xenon, except betting is illegal where I live, so I have to settle with just speculating. :p

There's no reason to believe they own this IP, and every reason to believe they do not. For starters, if they did, IBM and ATi would have just pissed away a large chunk of their research and development efforts. So... Not really gonna happen, I say.

ATI and IBM were hired to develop specific SOCs for MS. MS owns the designs for these SOCs, they can do with them what they want, including integrating them on a single piece of Si in the future.

Cheers
 
Xbox.com: Damn, where was I during the fire testing portion? Anyway Jeff, let's move on to the cost-saving. How exactly are we saving money on Xbox 360?

JR: Two main ways. We have multiple suppliers for each part of Xbox 360. If you only have one supplier, you have less price negotiation leverage. Multiple suppliers keep the prices competitive. The other thing is that this time we own the IP on the chips. So we can make them at our own foundries.

http://www.xbox.com/en-US/hardware/xbox360/xbox360theguts.htm

Edit - searched for some other stuff we've been discussing (on the 360 subject) earlier on this forum. This is a good read too: http://blogs.mercurynews.com/aei/2005/08/a_walk_through_.html
 
Last edited by a moderator:
Jeezus Christ the hardware sites are hard up for news, this much fuss about a tradeshow demonstration.

As for what it does for the comparison between Xbox360/PS3 and PC desktop hardware, not a whole lot ... PC processors get incrementally faster, big whoop they always do that. Shifting the performance by a couple 10s of percentage points is not going to shift the balance that much.
 
Guden Oden said:
I'd bet real money they don't own the IP of either xenos or xenon, except betting is illegal where I live, so I have to settle with just speculating. :p

There's no reason to believe they own this IP, and every reason to believe they do not. For starters, if they did, IBM and ATi would have just pissed away a large chunk of their research and development efforts. So... Not really gonna happen, I say.

Darnit, pipo, looks like you beat me to it!
 
pipo said:
I'm pretty sure it was part of the deal..

They may own the rights to that particular implementation of those chips and have the ability to fab it wherever they please (including getting it shrunk or whatever), but I doubt they could do any suing if IBM or ATI decided to use modified versions of those elsewhere -- who knows though.

I think the whole "owning the IP" is a bit overplayed -- they likely didn't need to own the entire IP (which would be sort of impossible on the CPU side, as its still a power core, which is very much in IBMs control still) to get the benefits they needed (having more control over it -- getting it fabbed and shrunk wherever and whenever they please).

I'm sure MS got themselves a good deal (surely better than the deals they had with Xbox1), but I have my doubts that IBM/ATI really gave up anything. It just isn't really necessary for either side.
 
Bobbler said:
They may own the rights to that particular implementation of those chips and have the ability to fab it wherever they please (including getting it shrunk or whatever), but I doubt they could do any suing if IBM or ATI decided to use modified versions of those elsewhere -- who knows though..
That's exactly it -- they basically own the configuration of Xenon, I'd assume the same is true for Xenos. Many components in Xenon are patented by IBM or even used in other IBM products. MS owns the right to that specific configuration/blueprint.
 
I dunno about the floating point sucking. If Conroe can do single cycle SSE across the board that sounds awfully efficient. I wonder how that would compare to Xenon. A64 is more efficient than P4 which was more efficient than K7 for SSE, so I don't know how AMD64 compares to Conroe's SSE implementation.

Xenon gets direct attention of code optimization on a totally different level than PC CPUs though. And Xenon would suck as a general purpose chip too with its simplistic architecture and limited cache.
 
Back
Top