*spin-off* Has The PS3 Been Based On A EE/GS Evolution

[Arwin]

I do think Sony wanted the PS3 out sooner, but particularly the blue laser diode bit was a big issue here if I remember correctly. Though when they discussed the March launch half a year before that, they also indicated that they were considering delaying if they didn't have enough software to back up the launch they'd delay the launch until Holiday. That the diode problem was an issue by this point still though was born out by the small number of units they could bring to the launch.

 

[TheWretched]

I actually think it's the other way around. Sony wanted to come out later, since the PS2 still had enough steam to combat a newcomer known as 360. Sony had to release the PS3 however, as BluRay needed it. Without the PS3, BluRay wouldn't have won the HD wars as it did, as the other players were more capable (as BDROM without BDLive and all simply was only an HD dvd (not HDDVD)), much cheaper, and had MS as a supporter with their 360 too.

I mean, look at what was released in the first year for PS3. There were no meaningful games, beside some exceptions. Until Uncharted 1 came around, it was really bleak. Resistance 1 (US launch) and Motorstorm (European launch) were the only meaningful titles in the beginning. Only much later come August 2007 came some games (Warhawk, Heavenly Sword, Uncharted), that had enough power to sell units.

 

[Akumajou]

I do think Sony wanted the PS3 out sooner, but particularly the blue laser diode bit was a big issue here if I remember correctly. Though when they discussed the March launch half a year before that, they also indicated that they were considering delaying if they didn't have enough software to back up the launch they'd delay the launch until Holiday. That the diode problem was an issue by this point still though was born out by the small number of units they could bring to the launch.

I actually think it's the other way around. Sony wanted to come out later, since the PS2 still had enough steam to combat a newcomer known as 360. Sony had to release the PS3 however, as BluRay needed it. Without the PS3, BluRay wouldn't have won the HD wars as it did, as the other players were more capable (as BDROM without BDLive and all simply was only an HD dvd (not HDDVD)), much cheaper, and had MS as a supporter with their 360 too.

I mean, look at what was released in the first year for PS3. There were no meaningful games, beside some exceptions. Until Uncharted 1 came around, it was really bleak. Resistance 1 (US launch) and Motorstorm (European launch) were the only meaningful titles in the beginning. Only much later come August 2007 came some games (Warhawk, Heavenly Sword, Uncharted), that had enough power to sell units.

I think this is off topic and not to go off further but the purpose of blu ray aside from the obvious is that combined with CellBE and other spirits it would ward off the spectre of pyracy that was eating away at the PS2 game sales and althought there are no hard numbers I remember vividly gameshop customers talking about chipping their PS2 to download and burn games back in 2004 and on... Sony was very much as harsh as they could be back when PSX was being pirated.

Aside from that PS2 BC was included reguardless as a selling feature of you buy the PS3 and you have an extensive back catalogue of PS1 and PS2 games not just the ones you mentioned however online complainers kept voicing the "i wanna play next gen not last gen" as a way to devalue PS3's price and what it literaly offered being too many features that eventually were removed to cut costs and price.

There really were meaningfull games to buy for the PS3 but you gotta realize there were alot of forces at work in evangilizing that the console had nothing or no games while the other did... maybe we should pm each other but rest assured piracy was a major factor, it was definetly a major factor.

 

[liolio]

I'll leave my feelings on Groo out of it...

Anyway I watched part 5 you linked above and part 4 that preceded it; it's an interesting debate no doubt, one that honestly reflects a lot of what is pertinent around here at any given time in a number of threads (hardware vs software, fixed-function vs programmable). I'm not sure that what Andrew was saying spoke directly to what I might be envisioning or reflecting on in terms of a 2nd gen Cell, but from a landmark/benchmark perspective it was interesting to hear his thoughts. Frankly I do hope that the architecture is carried forward, even though my gut feelings are that at the moment, it will be in a B/C form or not at all. I'd love to be wrong, as I think the entire project was a botched effort with the musical chairs going on at Sony at the time - but the vision was sound.

I like the term A.Richard used "unfailed". I would also been interested in seing a Cell v2. The cell has neat advantage it offers a lot of general purpose compute power while offering reasonable power/thermal characteristic.
But there are interesting takes in A.Richard's POV especially in regard to fixed function hardware, which is related to the topic and a discussion I tried (and failed) to start in the "predict next gen" thread. A.Richard when thinking of future gaming architecture seems really concerned about power consumption, he thinks fixed function hardware have neat advantages in this regard (once again it will be interesting to learn more about the 3Ds in this regard). Fixed functions GPUs have disappeared so it's tough to start a discussion on the matter without having perfs/Watt and perfs/mm² figures.

Back to sony if they want to free themselves from PC manufacturers they may consider giving it a go (sounds really unlikely I know). They could continue with the same philosophy that was powering the PS2 general purpose vectors units + fixed hardware for graphics. Updating the Cell in this context could make sense. But does Sony still have the competences to do so on its own?
I'm really iffy about that, I think that Sony as a hardware company would be in a better situation if they used something a bit like I described. They relied too much on other companies competences whether its IBM or Nvidia.

 

[jonabbey]

I still don't see how Sony can do PS4 without a next-gen Cell. They've invested so much in software on PS3, both OS-level and software level. If they can keep compatibility with PS1,2,3 in the next gen, it would seem to be a massive advantage.

Going with Cell would seem to have cost advantages, too. Put a dual-core Cell and a reasonably up-to-date NVidia or ATI chip in there with enough RAM and the BD drive, and Bob's your uncle.

But, I know nothing about the inner workings of American tech companies, let alone Japanese ones..

 

[liolio]

I still don't see how Sony can do PS4 without a next-gen Cell. They've invested so much in software on PS3, both OS-level and software level. If they can keep compatibility with PS1,2,3 in the next gen, it would seem to be a massive advantage.

Going with Cell would seem to have cost advantages, too. Put a dual-core Cell and a reasonably up-to-date NVidia or ATI chip in there with enough RAM and the BD drive, and Bob's your uncle.

But, I know nothing about the inner workings of American tech companies, let alone Japanese ones..

Not that it would make sense but that was not my point, my point is that Sony won't be able to do it it-self. They'll have to pay IBM that this time around will see no point in sharing the effort.
They'll pay for the GPU too. In the end I suspect that the thing won't be better than a commodity part from AMD and the same thing could end true in regard to cost too.

 

[liolio]

I actually think it's the other way around. Sony wanted to come out later, since the PS2 still had enough steam to combat a newcomer known as 360. Sony had to release the PS3 however, as BluRay needed it. Without the PS3, BluRay wouldn't have won the HD wars as it did, as the other players were more capable (as BDROM without BDLive and all simply was only an HD dvd (not HDDVD)), much cheaper, and had MS as a supporter with their 360 too.

I mean, look at what was released in the first year for PS3. There were no meaningful games, beside some exceptions. Until Uncharted 1 came around, it was really bleak. Resistance 1 (US launch) and Motorstorm (European launch) were the only meaningful titles in the beginning. Only much later come August 2007 came some games (Warhawk, Heavenly Sword, Uncharted), that had enough power to sell units.

Completely agreed, even by 2006 the overall environment surrounding the PS3 was a mess from the PSN to the devs tools.

Thats debatable the only time Sony came neck and neck with a direct hardware competitor was with Sega and the Saturn in 94 in Japan and 95 in the US while Jaguar and 3DO had over a yeand start.

2006 falls in line with what Sony was aiming at however yields and software learning curve and most importantly that E3 2005 was set as a place to announce a release date for an unrealistic spring 2006 to please shareholders and press expectations.

Actually Sony may have ship even latter it would not have been much of a problem, more games and mature environment would have helped but the greatest offender for the PS3 at launch was price.

I think its possible for a EE evolution based PS3 but I think that Sony also went after IBM for the chip fabrication capabilities to meet demand hence Cell but for the EE evolution we would have to eliminate IBM and leave Sony and Toshiba to design and fab the chip.

Toshiba would be here for the MIPS CPU right?

for GS evolution I really would not mind seeing something like that since I feel that GS could have used higher frequency and more ram, maybe Sony made an arcade board with a beefed up EE and GS to test scaling, EE and GS where very capable chips but the millions of dollars/yen that it takes to dream up these architectures is staggering, I feel that PS2 would have had to last up to 2008 09 for replacement to give the engineers enough time to design chips for 65nm to 55nm or better yet 40nm, I feel in retrospect that 2005 was too early to start a new generation.

I would not push that far but Sony could have launch 2007 H1 worldwide with a more reasonable pricing, MS head start would have not been much of a problem. On top of using an evolution of and architecture devs was familiar with may have yield better results in the first games and possibly more games (shorten development lifetime).

The other thing is that theoretically engineering sample prototype PS2 board was shown with running software demo in March 1999 so the design had been going for many years, I went back into old magazines, namely pre-US PSX (early 95) launch next generation magazine where Ken Kutaragi was interviewed and quoted that he believed a .250nm chip design would yield 10 million polygons per second

So years later after PS2 and after it was well known that rich kid Microsoft was in the mix in 2001 Cell design and vision was pretty much announced or talked about and the effects of that new era affected the timing of a GS follow up that would have to perform.

So from 2000 to 2005 or 2006 at 90nm engineering process to design a GSE that would still be on a 128bit bus would have to incorporate more cache and better communication to ram and have a sophisticated pipeline evolution I think maybe 64 pipes to GS's 16 and cover full hardware t&L proprietary pixel, vertex shading evolution and incorporate some type of hardware culling or deferred rendering engine.

Indeed DMP pica200 while underpowered give a good idea about what could have been an evolved fixed function pipeline. Things would have been even if as you state the GS.2 would have been designed as tile based deferred renderer.
For vertex I think that the most of the workload could have been handled by EE.2 as in the PS2.

It's really strange that actually Sony gave up on the efforts they put in the PS2 and that may be more relevant in the PSP.
The PSP ship in 2004 on a 90nm process. I tried to find information about dies size and transistors count for the two chips in the PSP without success so far

EDIT
Actually while reading stuff about the PSP I wonder if the very existence of the cell comes from the desire to mix the PS2 Emotion Engine and the PSP Media Engine Co-Processor. A posteriori it was a fucked up idea, both Toshiba and Sony would have been better with an evolved Media engine which would have been more likely to find his way to various devices than the Cell or Toshiba SPURS.
EDIT 2
Does somebody has informations about the state of the PSP hardware?
I've been through pages of google search, I could not find info like die size, process used for PSP Go, die size, etc.

 

[jonabbey]

(continuing a discussion about the use of an Emotion Engine derivative in PS4)

But there is already a MIPS emulator running in the PS3 PPC processor... It would be the contrary: write a PPC emulator in a MIPS 4 Ghz ( for example ) processor...
About MIPS not being evolved since 2003 or less let´s not forget that larrabee was using 1990´s Pentium 1 as general code processor...
IMHO Sony and Toshiba have always made the most poweful per transistor and clock CPUs ( emotion engine had with the two vector units 10 million transistors! ). They only have now to make an easier to program design.

Fair enough. If as you say they go with a Toshiba MIPS/SPU design for PS4, the MIPS cores could surely handle emulating the puny PPU in Cell. And I suppose Toshiba has the rights to the SPU instruction set, so they could create a MIPS/SPU cluster on a chip, but it would still seem that the higher level architectural details of Cell (the bus ring, local store, DMA) would have to be there.

I wonder what benefit Sony might imagine from using MIPS rather than PowerPC in a next-gen CPU? Licensing costs from IBM? A lack of suitable PPC cores with better performance than the PPU?

 

[Fafalada]

could continue with the same philosophy that was powering the PS2 general purpose vectors units + fixed hardware for graphics

Programmability isn't only a function of the instruction set (nor is instruction set by itself a measure of flexibility - see designs like Flipper).
GS can be likened to a true-RISC(back in ancient past when that actually meant REDUCED instruction set), or more concretely (courtesy of archie4oz), an ultra-wide 6502 with a 4MB Register array.
But I disgress, I don't think modern equivalent would mean much(other then sound nice for PR). A 2006 GS equivalent would essentially be a Deffered-Rendering accelerator (super fast at filling attribute buffers and not much else). Which would do just fine paired with Cell or something like it, but one has to ask if it's worth specializing so much when an RSX gives pretty nice results for BOTH forward and deferred rendering even on fundamentally crippled memory interface.

Actually while reading stuff about the PSP I wonder if the very existence of the cell comes from the desire to mix the PS2 Emotion Engine and the PSP Media Engine Co-Processor.

ME is an evolution of IPU, so EE already had one of those. Maybe you're thinking the VFPU, but Cell ISA was a pretty dramatic (and kinda sad) departure from that mindset.

 

[liolio]

I'm late to answer but thanks for this great insight fafalada

For those interested and that don't know much about 6502, here are two links:
http://en.wikipedia.org/wiki/MOS_Technology_6502
http://en.wikipedia.org/wiki/Atari_8-bit_family

Here's one about IPU:
http://en.wikipedia.org/wiki/Digital_image_processing