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

Forums - Sony Discussion - Why Sony should also use a Cell Processor for PS5 (x86+Cell coprocessor)

Ruler said:

So every console generation has a major bottleneck, last generation it was the memory, this gen its the CPU limiting many games from achieving 60fps or causing framedrops in general.

I think Sony shouldnt just focus on getting a stronger CPU and GPU but also getting the PS3s Cell processor into the next PS5 along stronger hardware in general.

Why?

 

1st Power

Despite what people say the Cell Processor was a beast for its time, if you look at exclusives like Uncharted 2 or the Last of Us, they look a generation above other games during their times. Or even way before that when some developers really tried you had Namco Releasing Ridge Racer 7 running on Native 1080p, while on Xbox the same game engine and with same tracks could only reach 720p in Ridge Racer 6, thats like twice the resolution on PS3.

And its not only fanboy talk in the system wars, the data proves that the Cell Broadband Engine running in 3.2Ghz is fact stronger the current PS4 jaguar CPU running at 1.6 Ghz, below some examples by developers 

 

 

I think Sony should go for a CPU by AMD like the Ryzen but also with a Cell processor so it can be used for certain graphic effect or physics based effects to save performance on the CPU side. Especially annoying Alpha effect causing framerate drops and the likes of that. Yes the Cell is complicated as whole, but only if you try to run an entire game on it.

And keep in mind that on PS3 you had only 1 PPEs and 6 SPEs for devoloping games for, 1 other were used for the OS and another was scraped in order to save money on production. So on PS5 you could have 1 3.2 Ghz PPE core and 8 SPES for pure game development.

 

2nd cost

Sony owns the Cell processor, its already developed. Why shouldnt they just add it in to give the PS5 some extra power? A Cell processor and 256mb XDR DRAM combined have cost less than 50$ in 2009.

The cost could be even lower today and it would give much more XDR DRAM which is the fastest ram on the market. And Sony is known for going unique architecture, even with the PS4 they added an extra ARM processor running parts of the OS in the background. I also dont think its good put all your eggs into one basket and let AMD decide everything.

 

3rd BC 

Having a Cell processor and XDR DRAM inside the PS5 would give the console full BC for PS3 games. The PS3 GPU could easily be emulated or rendered by the PS5 graphicscard. So full PS4 and PS3 BC would be the result for PS5.

 

So looking at this i would aim PS5 to have

-An 8 core Ryzen CPU with over 3Ghz

-A Cell CPU with 8 SPEs, with 3.2Ghz

- An AMD or Nvidia GPU with with over 11 Teraflops

- 12GB GDDR 5 RAM

- and 1GB XDR2 DRAM

- full PS4 Pro, PS3 BC

With a 500$ price tag and a late 2019 or and early 2020 release


Totally off-topic but I'm interested on the source of your avatar.



Around the Network
torok said:

IBM was clearly intending it for HPC. But it failed badly due to lack of performance against GPUs and terribly bad dev tools. Sony had this weird plan about home electronics, that I really never understood. If you want to pack a punch on electronics, just use an ARM SoC. In their defense, Cell was developed before the smartphone arms race made ARM SoCs improve dramatically fast.

I believe around 05-06 ARM was largely still sub-200MHz single core and it was roughly at this time that Intel introduced it's Core architecture, so the multicore processors weren't really that common at the time. Technically the Cell could produce high performance per cost, as the SPE's could eventually be dirt cheap to manufacture, opposed to multi-PPE core processors.

I don't know if it was because of bad dev tools, as it was the processor that required you to know when an SPE was doing nothing.



Ei Kiinasti.

Eikä Japanisti.

Vaan pannaan jalalla koreasti.

 

Nintendo games sell only on Nintendo system.

Go back to an unusual design that's powerful. There's something about seeing wondrous visuals and not knowing what's under the hood. Plus is ps4 becomes even more popular people will naturally buy ps5. I know Sony made a mistake doing that last time but I think its worth it.... Will guarantee many more exclusives etc



...not much time to post anymore, used to be awesome on here really good fond memories from VGchartz...

PSN: Skeeuk - XBL: SkeeUK - PC: Skeeuk

really miss the VGCHARTZ of 2008 - 2013...

Skeeuk said:
Go back to an unusual design that's powerful. There's something about seeing wondrous visuals and not knowing what's under the hood. Plus is ps4 becomes even more popular people will naturally buy ps5. I know Sony made a mistake doing that last time but I think its worth it.... Will guarantee many more exclusives etc

Did people naturally bought PS3 due to the popular PS2 and the unusual powerful design? Was the PS3 very profitable because of the unusual powerful design? Did it get much more exclusives than the Xbox 360 or the Wii?



Sorry but first party and 3rd party devs became well adapted to the cell, and were happy with what they could achieve with it. They had taken their time to get adjusted to it so it would have been no issues developing for cell on the ps4/5. Had their been no issues at the start i am sure they would have stuck with cell, considering how much money and time went into research and development. It would have been in the ps4 and ps5. They could have sold the ps4 at 450, 499. the ps3 was released at 499 to 599. Sony isn't concerned about the microsoft competition. They know they have it won always. The xbox 360 had a year head start and was a $ 100 cheaper and ps3 still won. so no issues there. An advanced cell on ps4/ps5 would be a better console.



Around the Network

Ps3 got plenty more acclaimed exclusives than the xbox 360. And a greater variety of games. Remember it got released 1 year after the xbox 360 and was much dearer, it still outsold it in the end by a few million, and the AAA games kept coming right to the end, unlike xbox. 



KratosLives said:
Sorry but first party and 3rd party devs became well adapted to the cell, and were happy with what they could achieve with it. They had taken their time to get adjusted to it so it would have been no issues developing for cell on the ps4/5. Had their been no issues at the start i am sure they would have stuck with cell, considering how much money and time went into research and development. It would have been in the ps4 and ps5. They could have sold the ps4 at 450, 499. the ps3 was released at 499 to 599. Sony isn't concerned about the microsoft competition. They know they have it won always. The xbox 360 had a year head start and was a $ 100 cheaper and ps3 still won. so no issues there. An advanced cell on ps4/ps5 would be a better console.

Why would it be a better console if it had an "advanced CELL"?



Please can someone lock this stupid thread?!



Errorist76 said:
Please can someone lock this stupid thread?!

Don't ruin my entertainment please.

I am hoping Ruler replies eventually. Although I think he has abandoned this thread now anyway.



--::{PC Gaming Master Race}::--

bdbdbd said:

I believe around 05-06 ARM was largely still sub-200MHz single core and it was roughly at this time that Intel introduced it's Core architecture, so the multicore processors weren't really that common at the time. Technically the Cell could produce high performance per cost, as the SPE's could eventually be dirt cheap to manufacture, opposed to multi-PPE core processors.

I don't know if it was because of bad dev tools, as it was the processor that required you to know when an SPE was doing nothing.

Yes, ARM SoCs were jokes at the time. They only had to power feature phones. Smartphones made them jump in performance quickly, stabilizing after reaching limits imposed by physics. But nowadays, they pack quite a punch.

I remember it was extremely hard to debug stuff on the SPEs. Comparing with CUDA, that has great tools, good docs and helps a lot to deal with the quirks of GPU programming, it's hard to get dev support. Intel is facing this issue now trying to push the Xeon Phi, specially now that tons of libraries support CUDA. But you're correct when pointing that the difficulties were not only on the tools, but also on the weird design of the architecture. It doesn't matter if its ingenuous if it takes way more time to develop something for it.