AMD may get across the CUDA moat
hpcwire.com
AMD may get across the CUDA moat
1–10 of 312 posts
Re: AMD may get across the CUDA moat
#2Yup, thank the hobbyists. Pytorch is allowing other hardware. Stable diffusion working on m chips, intel arc, and Amd.
Now what I'd like to see is real benchmarks for compute power. Might even get a few startups to compete in this new area.
Re: AMD may get across the CUDA moat
#3>There is also a version of PyTorch that uses AMD ROCm, an open-source software stack for AMD GPU programming. Crossing the CUDA moat for AMD GPUs may be as easy as using PyTorch.
Unfortunately since the AMD firmware doesn't reliably do what it's supposed to those ROCm calls often don't either. That's if your AMD card is even still supported by ROCm: the AMD RX 580 I bought in 2021 (the great GPU shortage) had it's ROCm support dropped in 2022 (4 years support total).
The only reliable interface in my experience has been via opencl.
Re: AMD may get across the CUDA moat
#4Yup, thank the hobbyists. Pytorch is allowing other hardware. Stable diffusion working on m chips, intel arc, and Amd. Now what I'd like to see is real benchmarks for compute power. Might even get a few startups to compete in this new area.
Re: startups, Geohotz raised a few million for this already. https://tinygrad.org/
Re: AMD may get across the CUDA moat
#5>There is also a version of PyTorch that uses AMD ROCm, an open-source software stack for AMD GPU programming. Crossing the CUDA moat for AMD GPUs may be as easy as using PyTorch. Unfortunately since the AMD firmware doesn't reliably do what it's supposed to those ROCm calls often don't either. That's if your AMD card is even still supported by ROCm: the AMD RX 580 I bought in 2021 (the great GPU shortage) had it's R…
has opencl actually improved enough to be competitive?
Re: AMD may get across the CUDA moat
#6And the question for most that remains once AMD catches up: will the duopoly result in lower prices to a reasonable level for hobbyists or bootstrapped startups, or will AMD just gouge like NVidia?
Re: AMD may get across the CUDA moat
#7And the question for most that remains once AMD catches up: will the duopoly result in lower prices to a reasonable level for hobbyists or bootstrapped startups, or will AMD just gouge like NVidia?
A simplistic economic take would suggest that the competition would result in lower prices, but given two players in the market who knows.
Re: AMD may get across the CUDA moat
#8>There is also a version of PyTorch that uses AMD ROCm, an open-source software stack for AMD GPU programming. Crossing the CUDA moat for AMD GPUs may be as easy as using PyTorch. Unfortunately since the AMD firmware doesn't reliably do what it's supposed to those ROCm calls often don't either. That's if your AMD card is even still supported by ROCm: the AMD RX 580 I bought in 2021 (the great GPU shortage) had it's R…
Do you mean OpenCL using Rusticl or something else? And what DL framework, if any?
Re: AMD may get across the CUDA moat
#9>There is also a version of PyTorch that uses AMD ROCm, an open-source software stack for AMD GPU programming. Crossing the CUDA moat for AMD GPUs may be as easy as using PyTorch. Unfortunately since the AMD firmware doesn't reliably do what it's supposed to those ROCm calls often don't either. That's if your AMD card is even still supported by ROCm: the AMD RX 580 I bought in 2021 (the great GPU shortage) had it's R…
Do you mean OpenCL using Rusticl or something else? And what DL framework, if any?
I should clarify that I mean for human person uses. Not commercial or institutional. But, clBLAST via llama.cpp for LLM currently. Or far in the past just pure opencl for things with AMD cards.
Re: AMD may get across the CUDA moat
#10They are just too late even if they catch up. Until they make a leap like they did with ryzen nothing will happen.