Sony und AMD sprechen über PSSR, Pathtracing und mehr PS6-Technik

GamePro

vor 22 Stunden

Wann die PS6 kommt, wird hier zwar leider nicht verraten, aber immerhin sagt Mark Cerny, dass es in ein paar Jahren soweit sein soll. In diesem Tech-Talk geht es aber vor allem um gemeinsame Technologien wie PSSR und Project Amethyst, die die beiden Firmen Sony und AMD gemeinsam vorantreiben.

Kategorie

🎮️

Videospiele

Transkript

Vollständiges Videotranskript anzeigen

00:00Wir haben eine wirkliche sehr gute Gäste mit Sony gearbeitet.

00:03Und ich kann mir nicht mehr jemanden zu überdenken,

00:07als mein guter Freund, Marc Cerny.

00:09Marc, danke für Sie so viel zu kommen.

00:11My pleasure.

00:12Ich habe mich gefragt, Marc,

00:14zu join mir,

00:15zu popfen die Box

00:17und zu geben Sie ein peek

00:18auf die Gaming Breakthroughs

00:19wir haben zusammengearbeitet,

00:21behind-the-scenes.

00:22Ja, wir haben schon viel Zeit, das ist für sicher.

00:23So, heute, es scheint mir zu erzählen,

00:26um die neue Technologien zu entwickeln,

00:28Starting with our collaboration under Project Amethyst

00:31to create the machine learning technologies of the future.

00:34As every gamer knows,

00:36it takes a complex set of system expertise

00:39to get your setup and games

00:41to deliver the highest possible experience.

00:44As we progress together,

00:46the future brings us to real-time physics,

00:49cinematic lighting, efficient asset streaming,

00:52and keeping everything in sync across a CPU and GPU

00:55with super low latency.

00:58Trying to brute force that with raw power alone

01:00just doesn't scale.

01:01That's why we're combining traditional rasterization

01:04with neural acceleration.

01:06And machine learning isn't just a neat trick anymore.

01:09It's become a real tool for developers,

01:12smarter pipelines, cleaner visuals, smoother gameplay,

01:17and more headroom to create the worlds

01:19we want to all get lost in.

01:21And that's what FSR is all about.

01:24FSR and PSR actually come from deep co-engineering

01:27between Sony and AMD.

01:30Co-engineering the neural networks that power both technologies.

01:33And going forward, more and more what you see on screen,

01:37the detail, the fidelity, the atmosphere,

01:41it will be touched or enhanced by ML.

01:43And that means we're not just hitting new technical benchmarks.

01:46We're getting closer to the vision of the artists and creators

01:49behind the games.

01:50And the challenge comes in how we implement these systems.

01:54The neural networks found in technologies like FSR and PSSR

01:58are incredibly demanding on the GPU.

02:00They're both computationally expensive

02:02and require speedy access to large amounts of memory.

02:06The nature of the GPU fights us here.

02:08It's made up of a large number of compute units,

02:11and problems are therefore typically broken up into bite-sized pieces

02:14to enable the individual compute units to tackle them.

02:17And there's a downside to that.

02:19Subdividing a problem can cause inefficiency,

02:22or even force us to give up and find a different approach.

02:25Exactly.

02:27And that challenge got us thinking.

02:29And what came out of it is something we're calling neural arrays.

02:33Here's the idea.

02:34Instead of having a bunch of compute units all working on their own,

02:38we built a way for them to team up,

02:40to actually share data and process things together,

02:43like a single focus AI engine.

02:46Now, we're not linking the entire GPU into one mega unit.

02:50That'll be a cable management nightmare.

02:53But we are connecting CUs with each shader engine

02:56in a smart, efficient way.

02:58And that changes the game for neural rendering.

03:01Bigger ML models, less overhead, more efficiency,

03:05and way more scalability as workloads grow.

03:08Neural arrays will allow us to process a large chunk of the screen in one go.

03:12And the efficiencies that come from that are going to be a game changer

03:16as we begin to develop the next generation of upscaling

03:19and denoising technologies together.

03:21With neural arrays, we're unlocking a whole new level of performance for ML.

03:26Not just faster, but more capable.

03:28That means better FSR, better ray regeneration,

03:32and brand new ML power features we're just starting to imagine.

03:38All working in real time, right on the GPU.

03:41And we're just getting started.

03:43As we look ahead, you also see dedicated innovations that bring cinematic rendering

03:48to an entirely new level.

03:50Another area we've been focusing on has been ray tracing.

03:52When I look at its broad usage on PlayStation 5 for reflections, shadows, and global illumination,

03:58it's difficult to believe that it's been just five years since ray tracing was introduced.

04:03Definitely, Mark.

04:04And now with path tracing becoming more central to real-time graphics,

04:09the demands on GPU just continue to grow.

04:12That's why we've been pushing hard to go beyond the current approach

04:16to help developers bring even more realism and cinematic lighting into their games.

04:21But the challenge is that the current approach has reached its limit.

04:24To perform ray tracing today, a shader program has to juggle two very different responsibilities.

04:30One is ray traversal, digging through complex data structures to locate where the millions of rays

04:36being cast hit the millions of triangles in the scene geometry.

04:40When there are intersections, that same shader program has to also be doing its usual work of

04:46shading the scene, using texture and lighting information and the like.

04:50And we spent the past two years rethinking the entire path tracing pipeline from hardware to software.

04:57Early this year at Computex, we introduced neural radiance caching, a key part of FSR Redstone.

05:05Now, we're building on that with Radiance Cores, a new dedicated hardware block designed for unified light transport.

05:14It handles ray tracing and path tracing in real-time, pushing line performance to the whole new level.

05:20Together, these form a brand new rendering approach for AMD.

05:25Radiance Cores takes full control of ray traversal, one of the most compute-heavy parts of the process.

05:32And that frees up the CPU for geometry and simulation, and lets the GPU focus on what does best, shading and lighting.

05:40The result? A cleaner, faster, and more efficient pipeline built for the next generation of ray-traced games.

05:48There's a significant speed boost that comes from putting the traversal logic in hardware,

05:52and a further boost that comes from having that hardware operate independently from the shader cores.

05:57On top of those performance increases, there's other features in the works too, such as flexible and

06:03efficient data structures for the geometry being ray traced.

06:07Overall, I'm really looking forward to the time when we can get Radiance Cores into the hands of game creators.

06:13And we're excited to see how developers push ray tracing and path tracing even further with these tools.

06:19And here's the thing, whether it's ML or ray tracing, they both hit the same bottleneck.

06:26Current GPU memory bandwidth limitations hinder the seamless adoption of next-gen rendering techniques,

06:32requiring significantly more bandwidth to handle 4K plus textures and ray tracing denoising mass for smooth

06:39asset streaming. And that's where a final piece of news comes in. And yeah, it's a big one.

06:44With current GPUs, including the ones in PlayStation 5 and PlayStation 5 Pro,

06:48we have something called DCC, or Delta Color Compression. It's a strategy that reduces the

06:54memory bandwidth consumed when the GPU is reading or writing certain data, such as textures or render targets.

07:01And what we've built for future GPUs and SoCs take the idea of data compression much further.

07:07We call it universal compression. It's a system that evaluates every piece of data headed to memory,

07:14not just textures, and compresses it whenever possible. Only the essential bytes are sent out,

07:20which dramatically reduces memory bandwidth usage. That means the GPU can deliver more detail,

07:26higher frame rates, and greater efficiency.

07:29Here too, I'm really looking forward to what improvements universal compression will bring,

07:33and to what degree the effective bandwidth of the GPU will exceed its paper spec.

07:39There's a multitude of benefits from this, including lower power consumption,

07:43higher fidelity assets, and perhaps most importantly, the synergies that universal compression

07:49has with neural arrays and radiance cores, as we work to deliver the best possible experiences to gamers.

07:56Overall, it's of course still very early days for these technologies. They only exist in simulation right now,

08:02but the results are quite promising, and I'm really excited about bringing them to a future console

08:07in a few years' time.

08:08We feel the same way, Mark, and we're so excited to bring these innovations to developers across

08:14every gaming platform. Because this isn't just about silicon, it's about empowering the creators and

08:20communities that make gaming what it is. And we're just getting started. As we continue building with

08:26close partners like Sony, everything we're doing is focused on one thing, pushing games forward for all of you.

08:33Gaming has always been at the heart of what we do, and it's never meant more than it does right now.

08:38We're here for the players, the creators, and the communities that make this industry matter,

08:44and everything we're building is for you. Thank you, Mark, so much for taking the time to join me here today.

08:49Thank you, Jack.

08:56Thank you.

09:04Thank you.

09:08Thank you.

09:12Thank you.

Schreibe den ersten Kommentar

Kommentar hinzufügen

Empfohlen