AMD Touts Ryzen AI Platform for AI Development
AMD is hard at work enhancing the software support for using its GPUs to power generative AI applications.
And as reported by Wccftech, the chip maker has also confirmed its next-gen MI400 accelerators, even as it mulls a potentially slower MI300 variant designed for Chinese markets to comply with US trade policies.
While AMD GPUs such as its Instinct Mi250X GPU provides almost five times faster performance than Nvidia’s A100 GPU for double precision HPC applications, it has lagged in supporting software developers.
Ryzen AI
Specifically, AMD is behind when it comes to broad support for common data science libraries, as well as for generative AI applications.
On its part, Nvidia has multiple specialized versions of common libraries such as PyTorch to easily utilize its GPU for much faster data science and AI processing.
To address this, AMD in May unveiled its Ryzen AI Software Platform for public testing. Ryzen AI will provide developers with the tools they need to add AI to existing applications, as well as to create all-new programs that take advantage of this nascent field in new ways.
Later this year, AMD promised it will release additional toolchains, libraries, and guides for easier AI development.
AMD says this is part of its strategy to simplify AI at every level, from training models to locally deploying them on Ryzen AI-powered systems. Support for Generative AI models is also planned.
Support for new operators running on the IPU and quantization support for ONNX, PyTorch, and TensorFlow models will be added this summer.
“AMD's goal for the Ryzen AI Software Platform is to shrink the gap between hardware debut and end-user software availability to the greatest extent possible, allowing programmers and end-users to see the benefits of AI processing even at this relatively nascent stage of development,” wrote AMD’s Joel Hruska.
“The interim release this summer and the expanded functionality AMD will provide later this year will speed the development of an AI ecosystem and bring the benefits of this new type of processing to developers.”
The full Ryzen AI Software Platform is expected to launch later this year.
Paul Mah is the editor of DSAITrends. A former system administrator, programmer, and IT lecturer, he enjoys writing both code and prose. You can reach him at [email protected].
Image credit: iStockphoto/Sundry Photography
