By using this site, you agree to our Privacy Policy and our Terms of Use. Close
SvennoJ on 13 September 2013
Edit Thread
Zappykins said:
Adinnieken said:
 

Actually, 32MB divided up into 4 - 8MB blocks means you can have two processes reading and two writing to the memory at once.  If they're smart, no, they won't think of it as a single 32MB block.  More importantly, I think the API will make using it approrpiately easy.

A patent was awarded yesterday on how Microsoft is doing coherent memory, the patent dealt with the API or at least the images I looked at did, and it's clear that they are working to ensure developers have to do as little work as possible to take advantage of hardware features.

Sony didn't do anything with an audio chip, they don't have one.  They have a video encoder and that is for the DVR function.

Taking small tasks away from the CPU and GPU frees up processing cycles for the CPU and GPU.  The very reason you use separate processors. 

And thank you for posting such intelligent remarks as "He seems full of crap."  Your assutute, educated observations not with standing, he actually makes some reasonable, rational points.

I think the PS4 has at least one or two audio chips from reports.  However, there are also reports of Sony telling developers to use the GPU for audio. Other reports say that is for non gaming products, which would be fine.  If it's actually for games, then whoops, Houston, we have a problem.

I could see them avoiding co-processors as they wouldn't want to duplicate the same problems with the Cell and PS3.  Which would make it more of a PC with the video encoder.  

I need to go look up that coherent memory patent.  It sounds fascinating and will fulfill one of Microsoft's goals to make games even easier to develop.  I know they say they have been working on this since 2010, but really, right after they put out the Xbox 360 they up development on DirectX 10, which in many ways in my opinion, a beginning prototype test drive for the Xbox One. 

That audio FUD again. Sony said that down the road the GPU can be used for other things, like ray-casting, during downtime between frames, to show how flexible the GPU is. They didn't tell developers that they have to do their sound processing on the GPU at all.

http://www.eurogamer.net/articles/digitalfoundry-face-to-face-with-mark-cerny
Now when I say that many people say, "but we want the best possible graphics". It turns out that they're not incompatible. If you look at how the GPU and its various sub-components are utilised throughout the frame, there are many portions throughout the frame - for example during the rendering of opaque shadowmaps - that the bulk of the GPU is unused. And so if you're doing compute for collision detection, physics or ray-casting for audio during those times you're not really affecting the graphics. You're utilising portions of the GPU that at that instant are otherwise under-utilised. And if you look through the frame you can see that depending on what phase it is, what portion is really available to use for compute.


http://blog.games.com/2013/07/23/sony-explains-how-developers-will-unlock-full-potential-ps4/

Cerny describes how the PS4 will be ready for the future and claims that the full power of the next-gen console will increase as the years go by. He explains what will happen when the PS4 launches as well as what will occur several years down the road.

The interview did get technical, though, so we've devised a list on what was discussed:

  • At the beginning of the PS4 cycle, most games will not unlock the PS4′s full potential.
  • Earlier PS4 Games will use "straight forward" features of the console, like its visual power and bandwidth.
  • Later on, the GPU will be used for many other objectives besides processing graphics
  • The GPU can do things like "physics, simulation, collision detecting or ray casting for audio or the like."
  • The extra stuff will not make the visuals worse.
  • "Some of these phases [within a frame of animation on-screen] don't really use all of the various modules within the GPU."
  • When there is free space on the GPU modules, it will have room for other tasks.
  • It will "improve the quality of your world's simulation without decreasing the quality of your graphics."


And this is what Sony said in April

http://techreport.com/news/24725/ps4-architect-discusses-console-custom-amd-processor
Cerny says the PS4's custom silicon incorporates not only the CPU and GPU, but also a "large number of other units." The chip has a dedicated audio unit to perform processing for voice chat and multiple audio streams. It also has a hardware block designed explicitly for zlib decompression. The main processor is backed by a secondary chip that enables an ultra-low-power mode for background downloading. In that mode, the CPU and GPU shut down, leaving only the auxiliary chip, system memory, networking, and storage active.

A 256-bit interface links the console's processor to its shared memory pool. According to Cerny, Sony considered a 128-bit implementation paired with on-chip eDRAM but deemed that solution too complex for developers to exploit. Sony has also taken steps to make it easier for developers to use the graphics component for general-purpose computing tasks.

secret sauce!