HoloDust said:
Well, maybe this - not really the same thing, but I liked Charlie's thoughts on the matter - though it's totally different topic (why he thinks Xeon Phi will destroy GPGPU market): "The talent pools that can write decent GPGPU code is both small and shallow, plus the people that can do it well are few and far between. Worse yet, they are expensive, very very expensive, and they know it. The normal GPGPU coding process involves hiring people for way more than you want to spend, then paying them copious amounts to climb a steep and always changing learning curve. The end result usually ends up with mediocre code that more often than not misses the vendor’s promises by an order of magnitude. More often than not, the projects don’t come close to their goals if they don’t outright fail. This is why the software stack is of deadly importance. If a top GPGPU coder makes $150K or so, lets just round up to $200K with benefits, toys, and incentives, that is a lot of money. To develop a code base with a team of ten coders over a year will cost lots and lots of money, usually dwarfing the cost of the hardware. The safe route is to use vanilla x86 servers, coders that are familiar with them, and proven tools to do the job." http://semiaccurate.com/2012/11/13/what-will-intel-xeon-phi-do-to-the-gpgpu-market/ Honestly, I would love to see Intel coming back with another Larrabee in high end GPU market - than, it would be quite possible to take things like "we'll run that on GPU" with ease. |
Except, most of those problems don't exist to the same extent with the Wii U that they do with PC development ...
First off, even open source physics engines are using cross platform GPU programming languages (OpenCL) to handle physics on the GPU. Here is a video of the bullet physics engine running on the GPU:
On top of that, the Open Dynamics Engine has OpenCL solvers and it could be argued that the "proof of concept" of running it on the GPU is completed; and it is likely that within a year a couple developers could have it ready for production environments.
Then there is the "steep and always changing learning curve" ... which is a problem because you have multiple hardware manufacturers with very different ways of doing things and the hardware is changing rapidly with how something is best handled on one generation of card being very different on the next generation of card. With static hardware like a game console you have 5+ years of stability to learn and improve what you're doing.
Now, to be clear, I wouldn't expect a physics simulation as large as the one in the video to be in many Wii U games; but even a simulation with 5% as many objects (1600 obects at the same time) is probably adequate for the vast majority of games out there.
