AMD to Support NVIDIA’s CUDA Technology?
Bill Dally (Image credit: NVIDIA)
Bill Dally, the Chief Technology Officer at NVIDIA, has hinted that AMD will probably support CUDA applications, when he talked about GPGPU at a recent conference, according to Techradar.
Bill Dally stated: “In the future you’ll be able to run C with CUDA extensions on a broader range of platforms, so I don’t think that will be a fundamental limitation.” Though Dally didn’t name AMD outright, he said: “I am familiar with some projects that are underway to enable CUDA on other platforms.”
Dally indicated that the Brook programming language that AMD’s Stream is using has “a large number of limitations”. He believed CUDA provides “hundreds of applications”, while “there are just a handful of things at AMD’s corresponding website for GPU computing”.
Dally was also unconcerned about people buying AMD GPUs instead of NVIDIA GPUs if they supported CUDA.
“We don’t care whether they [GPGPU apps] are restricted to running on our GPUs or on a broader range of platforms,” said Dally. “We produce the best GPUs that there are, so given a fair competitive environment, people will choose our GPUs.”
June 30th, 2009 at 5:04 pm
This is highly unlikely especially with OpenCL around. What is known is that Nvidia have been working on for a while now on a CPU compiler for cuda, which will run cuda code on multi core cpus efficiently. This will give CUDA another definite edge over OpenCL since a code that was developed once will run well whether the machine it runs on has a Nvidia gpu or just a strong cpu. Of course on the GPU the performance you get will still be much higher.