News AMD to Expand ROCm Support to Pro and Consumer RDNA 3 GPUs This Fall

[Admin]

AMD has sensed a growing demand for AI and LLM computing acceleration and will thus add ROCm support to new RDNA 3 workstation and consumer GPUs this fall.

AMD to Expand ROCm Support to Pro and Consumer RDNA 3 GPUs This Fall : Read more

 

[digitalgriffin]

I made this response a couple months back. The fact CUDA couldn't be easily mapped on consumer AMD GPUs was a nightmare. And AI uses CUDA.

Will this create another GPU shortage? Only if CUDA ports are successful to consumer hardware.

 

[bit_user]

I made this response a couple months back. The fact CUDA couldn't be easily mapped on consumer AMD GPUs was a nightmare. And AI uses CUDA.

Not necessarily. AI developers are using frameworks like PyTorch and TensorFlow. Sure, some use custom layers written using CUDA, but the more popular models will tend to have all their needs catered for by the layers that already ship with these frameworks.

Also, AMD has their CUDA clone, called HIP. They have tools which help you convert your CUDA code to HIP. So, existing CUDA users do have a migration path. Intel did something similar, except they're using SYCL (an open standard - more credit to them!).

 

[bit_user]

What bothers me about this is all the APU users with GCN that are being left out in the cold.

And I get that AMD needs to focus on its new products, but if they really wanted to help sell off their backlog of RDNA2 inventory, they'd also add official support for all of those cards.

 

[digitalgriffin]

Not necessarily. AI developers are using frameworks like PyTorch and TensorFlow. Sure, some use custom layers written using CUDA, but the more popular models will tend to have all their needs catered for by the layers that already ship with these frameworks.

Also, AMD has their CUDA clone, called HIP. They have tools which help you convert your CUDA code to HIP. So, existing CUDA users do have a migration path. Intel did something similar, except they're using SYCL (an open standard - more credit to them!).

CUDA has a stranglehold on AI. Trust me on this. A number of the biggest libraries use it's underpinnings.

It is possible to port over with some mods using HIP (as you said) But it was a pain in the duckass. I'm hoping more will work on it now that AMD is opening ROCm up to the comsumer GPU space.

 

[bit_user]

CUDA has a stranglehold on AI. Trust me on this. A number of the biggest libraries use it's underpinnings.

Yes, the popular deep learning frameworks all have cudnn backends, but they also have backends for other hardware.

Nvidia's biggest advantage is its performance, followed by their level of software support. Given how expensive they are and how scarce they've become, even those advantages are no longer enough to keep their competitors shut out of the market.

It is possible to port over with some mods using HIP (as you said) But it was a pain in the duckass. I'm hoping more will work on it now that AMD is opening ROCm up to the comsumer GPU space.

It's not only a 2-horse race!