Cell and RSX : their relationship.

[PC-Engine]

Simply put, SONY was too ambitious with their original CELL CPU goal of 1TFLOPS + CELL GPU for a 2006 release so instead of 1TFLOPS they got 215GFLOPS for the CPU and ditched the CELL GPU which together wasn't good enough to compete with Xbox 360.

 

[Shifty Geezer]

By 'Cell based GPU' I mean Sony's solution for a GPU, such as whacking another 2 or 3 Cells in there, and not a specific GPU structured around Cell.

 

[PC-Engine]

The use of a PC GPU in PS3 is pretty ironic considering Vince kept pushing the idea of a non-PC centric architecture.

 

[London Geezer]

The use of a PC GPU in PS3 is pretty ironic considering Vince kept pushing the idea of a non-PC centric architecture.

Well Vince is not Sony.

 

[nAo]

Simply put, SONY was too ambitious with their original CELL CPU goal of 1TFLOPS + CELL GPU for a 2006 release so instead of 1TFLOPS they got 215GFLOPS for the CPU and ditched the CELL GPU which together wasn't good enough to compete with Xbox 360.

How do you know they aimed for a CELL GPU?

 

[mckmas8808]

Simply put, SONY was too ambitious with their original CELL CPU goal of 1TFLOPS + CELL GPU for a 2006 release so instead of 1TFLOPS they got 215GFLOPS for the CPU and ditched the CELL GPU which together wasn't good enough to compete with Xbox 360.

Is being too ambitious a bad thing? I think it was great that Ken and company wanted a processor to obtain a teraflop of data.

 

[London Geezer]

Simply put, SONY was too ambitious with their original CELL CPU goal of 1TFLOPS + CELL GPU for a 2006 release so instead of 1TFLOPS they got 215GFLOPS for the CPU and ditched the CELL GPU which together wasn't good enough to compete with Xbox 360.

Is being too ambitious a bad thing? I think it was great that Ken and company wanted a processor to obtain a teraflop of data.

Well it seems they got it, it's just not Cell... errr... Seems everyone can have a 1TFlop system now anyway so i don't think anyone's very worried.

 

[PC-Engine]

Simply put, SONY was too ambitious with their original CELL CPU goal of 1TFLOPS + CELL GPU for a 2006 release so instead of 1TFLOPS they got 215GFLOPS for the CPU and ditched the CELL GPU which together wasn't good enough to compete with Xbox 360.

How do you know they aimed for a CELL GPU?

According to the patents. The patents for the 1TFLOPS CELL is exactly what SONY wanted but couldn't get on a single chip according to those PS3 history stories posted. If PS3's CELL goal was directly from the patent then the GPU probably was taken from the CELL based GPU patent.

Oh btw london-boy, SONY didn't achieve 1TFLOPS, they achieved 215GFLOPS.

If Xbox 360 didn't turn out to be as powerful as it is, SONY would've probably stayed with the CELL based GPU.

 

[London Geezer]

Oh btw london-boy, SONY didn't achieve 1TFLOPS, they achieved 215GFLOPS.

I was joking, they have a 1.8TFlop chip don't they, it's just not Cell... errr.... Like MS have a 900GFlop chip...

 

[nAo]

According to the patents.

Too bad a CELL based GPU patent has never existed, and there's no patent that talks about a CELL based GPU (there is just a pic with some SPEs attached to a pixel engine that could mean anything, that's all)
In fact everything we know for sure from papers and interviews is that CELL was not designed to address problems such as pixel shading or rasterizing.

 

[PC-Engine]

According to the patents.

Too bad a CELL based GPU patent has never existed, and there's no patent that talks about a CELL based GPU (there is just a pic with some SPEs attached to a pixel engine that could mean anything, that's all)
In fact everything we know for sure from papers and interviews is that CELL was not designed to address problems such as pixel shading or rasterizing.

Pretty selective memory you got there. One word....VISUALIZER......

 

[nAo]

Pretty selective memory you got there. One word....VISUALIZER......

OH god, since I was the first to found that stuff maybe I remember better than you.
There was no word about 'visualizer' to be CELL based..there was no word about visualizer at all, it was just a name (and in some other patent it's called REALIZER).
How do you know it was CELL based? Link please

 

[PC-Engine]

Pretty selective memory you got there. One word....VISUALIZER......

OH god, since I was the first to found that stuff maybe I remember better than you.
There was no word about 'visualizer' to be CELL based..there was no word about visualizer at all, it was just a name (and in some other patent it's called REALIZER).
How do you know it was CELL based? Link please

1TFLOP by '05 could be integrated graphics level(cheap ass eMachines caliber) for GPUs though, they aren't far off from that number now.

of course... the famous NVFLOPS...

Fact is I do not believe the Rendering core will be as simple as you perceive it... fact is the GPU will be programmable ( you have seen the patent and you know we have 64 Integer Units and 64 FP Units in the Visualizer in addition to the 4 Pixel Engines and the Image Cache )...

Fact is, you are basically saying "well if they had a basically purely software Rasterizer and T&L engine 1 TFLOPS would be e-machines level"...

Of course if you took the current GS even and counted the number of flops for the set-up engine and you rated in a MIPS scale the power of all the rest of the GS's rendering pipeline ( integer pipeline ) you would obtain a very high number... GeForce FX is already over 250 GFLOPS isn't it ?

So, in 1999 they had ready a machine that kicked the living crap of high end PCs in RAW performance and npw in 2005 they ship a console that is as powerfule as a 2005 e-machine ?

 

[nAo]

PC-Engine..are you kidding? I asked you for a proof of your statements, is a personal opinion (even by my dear friend Pana) a proof of what?
You cited patents..well..let us see those patents that are about a CELL based GPU.

 

[PC-Engine]

PC-Engine..are you kidding? I asked you for a proof of your statements, is a personal opinion (even by my dear friend Pana) a proof of what?
You cited patents..well..let us see those patents that are about a CELL based GPU.

I'm citing the same patent Panajev is citing.

I don't believe he is making stuff up.

 

[nAo]

I'm citing the same patent Panajev is citing.

So you're not even able to do your homework alone.
Why don't you link the patent Panajev is talking about?
It would be funny to look at it and to not found anything related to your CELL GPU erotic fantasies.

 

[PC-Engine]

I'm citing the same patent Panajev is citing.

So you're not even able to do your homework alone.
Why don't you link the patent Panajev is talking about?
It would be funny to look at it and to not found anything related to your CELL GPU erotic fantasies.

Why would I need to find it? The point is I remember it very well and everyone back then was talking about it and it is based on the CELL concept that's enough evidence for me. The patent isn't even in that particular thread so I don't really know which thread it was posted in.

 

[London Geezer]

If my memory serves me right, Pana only ever explained how a Cell GPU would work, he never spoke out of factual information or having read patents. His point was that a Cell GPU could exist and went out of his way to explain to everyone how it could be done.

Never have i seen information from Sony about a Cell GPU. Only words about a "hybrid Cell Nvidia GPU thing". No patents.

 

[Neeyik]

Some vague Visualizer patents or patent claims or the possibility of them, at least!

http://gauss.ffii.org/PatentView/EP1370968
http://www.freepatentsonline.com/6526491.html
Another link

On the other hand, a processor may comprise the structure of visualizer (VS) 505. As shown in FIG. 5, VS 505 comprises PU 512, DMAC 514 and four APUs, namely, APU 516, APU 518, APU 520 and APU 522. The space within the chip package normally occupied by the other four APUs of a PE is occupied in this case by pixel engine 508, image cache 510 and cathode ray tube controller (CRTC) 504.

 

[nAo]

Why would I need to find it? The point is I remember it very well and everyone back then was talking about it and it is based on the CELL concept that's enough evidence for me. The patent isn't even in that particular thread so I don't really know which thread it was posted in.

Oh well..since everyone believes something..that something should be true!
LOL, thanks for proving my point.