Damn you consoles!!

Sometimes videos are a lot better than writing technical jargon and trying to make a person see what the technology does.

Watch this video #1 at early evolution of Tessellation in 2010:

Tom Clancy's H.A.W.X. 2 Tessellation On/Off comparison video

http://www.youtube.com/watch?v=bHh8D3AzZaU

Video #2 shows how tessellation works exactly in wireframe:

NVIDIA Endless City Tessellation Demo

http://www.youtube.com/watch?v=sQQpCd_vvGU

This is how a tessellated 3D object would look like in a modern DX11 game like Crysis 3:

A modern graphics card has Geometry engines that are responsible for tessellation. In the past, a graphics card overlaid textures around vertices and the result are simple mountains and walls. To enhance the realism, bump-mapping was added and later this evolved into displacement bump-mapping. However, if you wanted to create an extremely complex environment, everything has to be complex, whether far or up-close and this is simply not efficient/not possible using current tech, etc. With geometry shaders, you can increase complexity on the fly using tessellation. So yes it helps with LOD depending on distance but also expontentially increases the complexity of objects:

The current approach to tessellation still requires that the various iterations of the Dragon are created, the Tessellated and Non-Tessellated form. This means the artist has to do double the work right now. The next iteration of tessellation will move to Adaptive Tessellation where it will happen on the fly and the artist no longer has to create multiple models to account for non-tessellated vs. tessellated characters. It will truly become dynamic/on-the-fly geometry processing of character models and environment. This video highlights Adaptive Tessellation in action:

CryENGINE 3.4.0 - DX11

http://www.youtube.com/watch?v=6KuNw8bjDwc

Even now tessellation already makes objects look more realistic but it's only in its infancy. The artists no longer have to sit there and create a perfectly rounded head or character limbs.  The Geometry shaders in the GPU do it on the fly. But this is pretty GPU intensive, and only parts of the character are tessellated, like shoulders, head and some parts of the arm in Hitman Absolution.

Without tessellation

With tessellation

Global Illumination when combined with ambient occlussion (HDAO) creates more realistic area lights where lights reflect on objects and objects reflect/refract light too, dynamically. In the past, if you blew up a helicopter in COD, someone has to create 100 variations of that explosion and then create lights for them too. With global illumination/dynamic lighting and per-pixel lighting, the way light is reflected onto the gaming environment is calculated in real time. The artist isn't sitting there creating 100 models of a building with different light shadows. 

In case anyone is wondering, both the Samaritan Demo and the new Square Enix demo have all of these technologies incorporated in them at once. 

*** Unfortunately some of this technology is hard to see in these compressed screenshots. Watch the videos I linked instead ***

GPGPU? Sony is copying Nintendo again?

1) Modern uses already exist in games

2) You are relegating GPGPU only to accelerating CPU-related functions but its flexible enough to be used for graphical purpose acceleration that's faster than traidtional means. That brings me to point #3 and the rest of my post:

3) DirectCompute = GPGPU for graphics

For example, to perform tessellation, we need Geometry units/shaders that are dedicated for this task. To shader textures, we have Texture Mapping Units (TMUs). Now imagine creating a GPU that is built from the ground-up so that it can perform a wide variety of tasks - in other words it's flexible enough to have some kind of units that can perform General-Purpose Computing for Graphical Processing. For simplicity, it can just be called a Compute Unit. It's a general purpose unit that can perform some CPU-related functions but because it's so advanced, it can also perform certain graphical functions faster because it can schedule the workload more dynamically with a Dynamic Compute Scheduler. 

GPGPU isn't necessarily using a GPU for physics only (like PhysX of Nvidia). It just means taking a GPU and running general-purpose code, which can be actual graphics effects we already have, but taking it to the next level that is too slow using non-compute units or alternatively minimizing the performance hit of these advanced graphical features compared to older architectures that are less GPGPU focused. What you aren't realizing is modern AMD architecture (Graphics Core Next or GCN) has Stream processors (that's your 2048 in 7970), Texture Units (that's your 128), ROPs (that's your 32), Geometry Engines and Compute Units (32 of those) with a dedicated dynamic scheduler. The first 4 are not really different from other architectures but the Compute Units + Dynamic scheduler is what's driving GPGPU to the next level here.  The dynamic scheduler in a GPGPU-focused architecture can use compute units to perform all kinds of graphical calculations way faster than the traditional architectures. While RV7xx in Wii U can do GPGPU, it's too primitive and most importantly the Compute part is completely unique to HD7000 that wasn't in HD4000-6000 series. If GCN finds its way to PS4/Xbox 720, it could easily be used to accelerate graphics. 

You are saying PC hardware cards since 2007 were ready for GPGPU, but this misses the point that NONE of them can use DirectCompute features well because they lack a proper dedicated dynamic scheduler (this is what issues the work to the compute units to perform general purpose computing via DirectCompute) and dedicated compute units  that schedules the execution of these functions effectively. Since they have no compute units, they can't do DirectCompute and thus are much more inefficient in games. 

You say you expect zero games to use it, but this is already not true as some modern games are already using GPGPU via Compute units/shaders, like Dirt Showdown, Sleeping Dogs, Hitman Absolution, Sniper Elite V2. Instead of using traditional graphics architecture units, modern game engines can accelerate graphics performance using "GPGPU" functionality of Compute units. Right now these are effectively used for Global illumination, dynamic lighting, and contact hardening soft shadows, accelerating ambient occlusion performance, post-processing, depth of field and Anti-aliasing!! Wow, all these should sound familiar to any gamer :) 

"In short this allows all lights in the scene to be truly dynamic lights, rather than just the age old hack of rendering 2D glows. This is achieved by building global lists of all lights in the scene, and then using DirectCompute to produce a culled light list for tiled regions of the screen. During the actual Pixel Shader lighting phase, only the culled light list for a given pixel is processed. This makes it possible to have thousands of dynamic lights in a scene and still achieve playable frame rates."

Source: http://blogs.amd.com/play/2012/07/03/dirt-showdown-amd-benchmark-guide/

Global Illumination Off

Global Illumination ON

No soft shadows

With soft shadows

You can also use Compute function of GPGPU to accelerate High Definition Ambient Occlusion (HDAO) 

HDAO Low quality

HDAO High Quality

Now watch what happens when combine all these graphics effects at once (Global Illiumation + HDAO + soft shadows = all accelerated using GPGPU function of the new Compute units of modern graphics cards). Take old architecture that has poor GPGPU functionality like GTX680 or HD6970 (VLIW-4) and compare it against a more modern architecture like Graphics Core Next that was made from the ground-up for GPGPU and has 28-32 dedicated Compute units:

Notice only HD7000 series can achieve > 30 fps with advanced lighting and older GPU architectures cannot. While you are right that GPGPU cannot solve everything and cannot substitute for some complex calculations where you still need a powerful CPU (AI of NPCs/crowds, real time physics calculations, etc.), you missed an entire aspect of how GPGPU can be used for games -- developers can now use Compute shaders (or compute units if you will) using DirectCompute to accelerate graphicsa effects like lighting and shadows and thus make games more realistic without it being a slideshow.

You can use these general purpose compute shaders to accelerate all kinds of graphics effects in games. 

Depth of Field in Sniper Elite V2

"In photography or cinematography the camera can only focus on one point in distance. All objects in the scene will appear to be more or less blurry depending on their distance to this focus point and the physical characteristics of the lens setup. Since optics (e.g. using a sniper scope or binoculars) is a major game play element in Sniper Elite V2 this effect is simulated by applying a DirectCompute accelerated post process to the image." 

Source: http://blogs.amd.com/play/2012/06/25/sniper-elite-v2-amd-benchmark-guide/

You again end up with much faster performance in a GPGPU-focused architecture that can use DirectCompute well like HD7000 compared to less advanced GPGPU architectures like GTX580/680/HD6970:

There is yet another game that already uses GPGPU via DirectCompute -- Sleeping Dogs.

"Sleeping Dogs uses the HDAO method, which is renowned for the quality and accuracy of its lighting simulation. And in practice, HDAO enables gamers to see shadows in cracks, corners and crevices where the shadows you’d expect in real life would not otherwise appear in a game. However, this renown comes at a price: performance. Thankfully, we were able to mitigate the performance penalty by migrating the lighting computation to DirectCompute, giving the breathtaking compute capabilities of the GCN Architecture a runway to strut its stuff." 

Source: http://reader.mreotech.com/sleeping-dogs-gaming-evolved-and-you-2/

Once again, the performance between GPGPU focused HD7000 series and outdated GPGPU architectures is night and day:

There is another game that uses GPU compute for graphics -- Hitman Absolution.

Real-Time Global Illumination

 "Global illumination, or GI, is a relative newcomer in the world of DirectX® 11 graphics. GI is designed to simulate the way rays of light reflect, not just off of the first object they strike, but each successive object struck by that reflected ray. To achieve this effect, the engine renders a Reflective Shadow Map (RSM) of the scene, taken from the point of view of a light source. Using GPU compute (DirectCompute language), it populates the RSM with a list of angles from which that light can reflect off an object, and then uses the RSM to compute several bounces of that lighting across the objects in a scene. The result is a stunning improvement in the realism of the game’s lighting, which we think contributes quite a lot to a game’s atmosphere.

Global Illumination Disabled

Global Illumination Enabled and accelerated via GPU compute function:

Source: http://blogs.amd.com/play/2012/11/20/hitman-absolution-in-depth/

Hitman Absolution uses Compute units to accelerate global illumination, depth of field and ambient occlusion. And once again, the performance hit is mitigated on a more modern GPGPU architecture compared to outdated architectures. You can see how a $280 GPU with modern GPGPU functions (HD7950) outperforms a $500 GPU without (GTX680)

I think now you see why you CAN use GPGPU for games to make them better looking:

1) Accelerate next generation graphical effects that mitigates the performance hit compared to less advanced GPGPU architectures;

2) GPGPU is not necessarily limited to physics or CPU-related general purpose code, but it can be used for graphical effects specifically (Hence the reason it's called general purpose). While the CPU is best for physics and AI, Compute shaders are WAYYYYYYYYYYYYYYYY faster for accelerating lighting, shadows, ambient occlusion using GPGPU focused architecture.

3) GCN (aka HD7000) is far more suitable for next generaton consoles than any other 2012 GPU. Unfortunately, Wii U uses outdated GPGPU since RV7xx is still VLIW-5, not GCN, which means out of the next gen console it's the most disadvantaged for GPGPU graphical acceleration.

Of course complex physics effects and AI are still best performed on the CPU but in theory you could create a general purpose code specifically for the Compute units if you have 100 million consoles and the development costs are actually worth it.

@BlueFalcon - GREAT post, as usual :)

Though, I think that most of discussion here when GPGPUs are mentioned is whether things like physics and AI will be put on GPU - I recon if they managed to get HSA into MSony consoles it might become reality, but not sure how likely that is.

Haha. Win.

If console gaming kept holding us back, it would not be the hardware alone to blame. That is even unfair to say with what developers of latest game engines like AnvilNext and Square Enix has offered us.

That is really a stupid argument to have in an attempt to say Sony will have a super console.

• PS3 was a dramatic jump from PS2 going from weakest console to arguably the most powerful.
• PS3 was the worst financial home console Sony has ever made.
• PS3 took Sony from two consecutive generations of dominating the home market by over 70% to being in third place with about 25%.
• PS3 is not an approach Sony will want to repeat.

So while its true that Sony has never "marginally" improved the power from one gen to the next, until the PS3 they had also never came close to complete and utter failure and bankruptcy as a company.

Look at their current state... they are financially weak, have a failing portable console, and a marginally successful home console. (along with a lot of other products that are in a wide range of financial circumstances... most not good)

On top of that, they are a Japanese company based on the Yen that is trading horribly to all other currencies right now. Simply put, Sony cannot afford to take massive PS3 level losses on a console again. Therefore, like the Vita that launched with a very small loss, the PS4 will launch with a very small loss. It only makes obvious sense.

They also won't want to put out another $600 console as that proved to be an unwise decision and clearly limited PS3's initial sales. So anyone should expect the PS4 to be around a more normalized price point of ~$400 max.

With those two obvious points in mind, you simply are not going to get a console that is anything more than marginally more powerful than the PS3. Its just not going to happen.

Like the WiiU, it will be more about the newer technologies (stuff in DX11 or similar) and general architecture/services provided than it will be about raw numbers in power.

WiiU is sold at VERY small loss and has a tablet controller for $300 and $350 and basically is on par with current gen otherwise (other than ram which is dirt cheap).  PS4 should be able to have a faster processor, better graphics card (DX11 capable of high resolutions), and at least twice as much ram and still fall safely in the $400 range potentially being profitable or a small loss.  I'm thinking $400 and $450 with an attachment (dongle I believe was rumored) for PS3 BC as an optional peripheral to be purchased separately.  That would still be $150 less for the best model than PS3 was at launch and it will have a lot easier architecture and not have to push a new format this time.  They just need to keep the controller simpler and be the true gamer's console of choice.

This line made me laugh.