By using this site, you agree to our Privacy Policy and our Terms of Use. Close

@ NJ5

No, it's not. It's much more powerful for certain applications (for example, embarassingly parallel problems which games are not). It's less powerful or equally powerful for some other applications (for example, an application which can't take advantage of more than two threads and which needs double-precision floating-point arithmetic; the Xenon would beat it there).


Modern games are excellently suited for multi-threaded processing, there are so many different things going on in games that are well suited to be split across many different processing units. Far more so than for other kinds of programs.

While I don't think we've yet seen PS3's power peak, I don't think we'll see fantastic advances (even if we do it will be in very few games).


Why?

Once you have an advanced game engine, why wouldn't it be possible to create many different games based on the same game engine?

If the Cell was fundamentally more powerful, it would be significantly better for every single application you could throw at it. At least that's my notion of "fundamentally more powerful".


It is. Even if handling a double precision format. (Although half and single precision formats make much more sense)

Issues mainly relate to breaking down game engines into separate pieces of code and manually optimising your code to some extend.



Naughty Dog: "At Naughty Dog, we're pretty sure we should be able to see leaps between games on the PS3 that are even bigger than they were on the PS2."

PS3 vs 360 sales