Does Cell Have Any Other Advantages Over XCPU Other Than FLOPS?
- Thread starter Alpha_Spartan
- Start date
MrSingh said:According to sources within Toshiba and SCEJ, the decision to use an Nvidia solution came at the 11th hour. Just be happy Sony didn't choose the Toshiba GPU (or a PowerVR solution).
Hey, I'm happy to have you link to that - I'm sure you'll find it easy enough to do since you've got the sources.
I remember it well. That thread on RSX did cover every single point!xbdestroya said:
MrSingh : I'd love to see that info which perhaps could end the speculation once and for all as to the nature of the nVidia contract. Though it shouldn't really be posted here. Could you start another thread, or dig up an old RSX thread, with the link please.
Panajev2001a
Veteran
MrSingh said:According to sources within Toshiba and SCEJ, the decision to use an Nvidia solution came at the 11th hour. Just be happy Sony didn't choose the Toshiba GPU (or a PowerVR solution
Do not tell me they had a moment in which PowerVR was being considered ? Not that I would have hated it (hehe
), just that it seems so weird for soem reason (from Dreamcast to PLAYSTATION 3... curious they would be launching their second "come-back" product with a console again .I have accepted that RSX is basically G70 + FlexIO + minor optimizations + some caches re-working + clock-speed bump, it is more than fine: G70 is a good GPU with full DirectX 9.0c support and plenty of speed, it comes with nVIDIA development tools and drivers as well as nVIDIA 3rd party relations connections with major PC developers.
Gubbi, here's the thread: RSX Thread
It starts at post #103, then #109, and then basically every post on from there for several pages. There's no way to bump that thread since in the end it was locked, but if you are interested in it I'd read the whole thing through from that point I indicated.
Shifty's right though, indeed for further debate a new thread should be started, as I was really enjoying the Cell back-and-forth here and would hate for us to derail this thread further with an RSX sideshow.
It starts at post #103, then #109, and then basically every post on from there for several pages. There's no way to bump that thread since in the end it was locked, but if you are interested in it I'd read the whole thing through from that point I indicated.
Shifty's right though, indeed for further debate a new thread should be started, as I was really enjoying the Cell back-and-forth here and would hate for us to derail this thread further with an RSX sideshow.
HAHAHA boys!!! Don't chew what you can't swallow!!!
Huh? doesn't that make Chewing Gum kinda redundant?london-boy said:
Shifty Geezer said:
You don't swallow chewing gum?
Goodness, no! I stick it on the underside of classroom tables and bus-seats like any well-behaved law-abiding citizen.
Guilty Bystander
Newcomer
Considering Next Gen games will be made with Floating Points throughout the entire pipe it does matter and matters a hole ****ing lot.
With the PC Flop/s might not have mattered before and still doesn't but that's because in Flop/s terms the PC just sucks.
An Amd 64 X2 4800+ for example can only do 12GFlop/s at best while the Xenon in the 360 can do 115GFlop/s and the Cell can even do 218GFlop/s which are huge differences obviously.
That's the reason why the Next Gen console don't need PPU's cause their extreme CPU power takes care they can do loads of character animations, complex physics, loads of players, advanced A.I. etc.
And for anyone out there saying it doesn't matter console will do more Flop/s.
It will SOON, real SOON!!!
Guilty Bystander said:
Uhm excuse me?? What entire pipe? We're not talking GPU's here.
Scary.
scificube said:
No problem - it's just annoying when people post bold statements - it can be forgiven if there is no public reference material ( apart from presentations, which are often easy to misrepresent )
This is the architecture book for the cell broadband engine. In here it talks about SPU interupts - both from external causes ( via signal notification registers ) and internal ( by decrementor counter )
http://www-306.ibm.com/chips/techlib/techlib.nsf/techdocs/1AEEE1270EA2776387257060006E61BA
arjan de lumens
Veteran
Would you care to point out exactly where this document (page number please) says that one SPU can pass an interrupt to another one? Having read through that document, I have found no hint whatsoever that the capability is actually present. You can hand an interrupt from the PPE to an SPU, you can hand an interrupt from the SPU to the PPE, there seems to be a mechanism for passing interrupts back and forth between PPEs (in a hypothetihical multi-PPE cell), but I couldn't find any mechanism whatsoever for passing an interrupt from one SPU to another.Crazyace said: