I think it was John Romero who said that it is the future of 3D rendered graphics, which is wrong imho.
I think you're thinking of Tim Sweeney.
I think it was John Romero who said that it is the future of 3D rendered graphics, which is wrong imho.
Hmm, Tim Sweeney's more the guy who's been evangelizing software/CPU-driven 3D rendering in the past... He did that as far back as around the time of the original Unreal, and then the topic popped back up a couple times after that. Not heard much about that of late though
Not sure I ever heard Romero talking on the subject though, but of course I could simply have missed it.
Actually I still had not read the link milk gave ( ) but yes.If you're talking about the paper milk linked earlier in this thread the results aren't as impressive as they seem at first glance. All shading was ignored by the paper meaning much of the GTX480 being compared against was idle.
Seems like it's all made to work together as a powerful CPU if a dev choose to use it all for Computing.
Cerny is convinced that in the coming years, developers will want to use the GPU for more than pushing graphics -- and believes he has determined a flexible and powerful solution to giving that to them. "The vision is using the GPU for graphics and compute simultaneously," he said. "Our belief is that by the middle of the PlayStation 4 console lifetime, asynchronous compute is a very large and important part of games technology."
Cerny envisions "a dozen programs running simultaneously on that GPU" -- using it to "perform physics computations, to perform collision calculations, to do ray tracing for audio."
"There are many, many ways to control how the resources within the GPU are allocated between graphics and compute. Of course, what you can do, and what most launch titles will do, is allocate all of the resources to graphics. And that’s perfectly fine, that's great. It's just that the vision is that by the middle of the console lifecycle, that there's a bit more going on with compute."
http://www.gamasutra.com/view/feature/191007/inside_the_playstation_4_with_mark_.php?page=2
Looks like they are going to be throwing more & more compute work at the GPU as time goes by.
Guess you can say the spirit of The Cell lives on, I wonder what some devs will come up with to use the computing power for in a few years.
What is the spirit of the Cell? Heterogenous computing? SIMD? GPGPU?
So while it takes "weeks, not months" to port a game engine from the PC to the PlayStation 4 according to Cerny, down the road, dedicated console developers can grasp the capabilities of the PlayStation 4, customize their technology, and really reap the benefits.
"There are many, many ways to control how the resources within the GPU are allocated between graphics and compute. Of course, what you can do, and what most launch titles will do, is allocate all of the resources to graphics. And that’s perfectly fine, that's great. It's just that the vision is that by the middle of the console lifecycle, that there's a bit more going on with compute."
I was talking about this.
Reminds me of how some devs put the SPE's to good use & made their games shine.
I really don't see how gpgpu thinking is in any way unique to cell and spes. If anything they seem to have abandoned cell for the pc model of heterogeneous processing.
You said "spirit of cell", which would in fact imply cell and SPEs...Where did I say it was unique to cell and spes?
You said "spirit of cell", which would in fact imply cell and SPEs...
Anyway, GPGPU doesn't have to mean software rendering. In fact much of the time it doesn't; anything physics-related like fluids, wind, particles, hair or cloth simulation, which will be a big part of GPGPU going forwards, is obviously not software rendering for example.
"There are many, many ways to control how the resources within the GPU are allocated between graphics and compute. Of course, what you can do, and what most launch titles will do, is allocate all of the resources to graphics. And that’s perfectly fine, that's great. It's just that the vision is that by the middle of the console lifecycle, that there's a bit more going on with compute."
I was talking about quick ports vs using the SPE's/GPGPU for compute to make the best of the game I even quoted this:
& about Software Rendering I know that I wasn't talking about software rendering when I made my new post I was talking about the part about using the GPGPU for computing.
but on that subject we are seeing some software rendering being added to games like Ray-Tracing for reflections & Physically Based Lighting & so on.
Is that ray tracing and physically based lighting using any GPU compute resources to do the rendering or do they rely on the CPU 100%? If it's done on the GPU, regardless if it's graphics rendering or compute I think it should be considered hardware based rendering.
It’s not really software-based because the graphics code is not running in the CPU. GPU got more programmable and CPU-GPU cooperation became cheaper, allowing them to reuse some concepts from PS3 more effectively.
Return to 100% “Software” Rendering
Bypass the OpenGL/DirectX API
Implement a 100% software renderer
Bypass all fixed-function pipeline hardware
Generate image directly
Build & traverse complex data structures
Unlimited possibilities
Could implement this…
On Intel CPU using C/C++
On NVIDIA GPU using CUDA (no DirectX)
I guess that’s why he uses the term “Software” Rendering, instead of simply Software Rendering.