A New Machine Learning Development Offering from AMD: ROCm 6.0
AMD has announced the expansion of its machine learning (ML) development offerings with the introduction of AMD ROCm 6.0. This expansion builds upon the previously announced support for the AMD Radeon RX 7900 XT, XTX, and Radeon PRO W7900 GPUs and PyTorch integration. Some important improvements include better support for GPUs, which lets the AI research and machine learning engineering communities use the Radeon PRO W7800 and Radeon RX 7900 GRE GPUs for development. This makes more desktop graphics cards available at a wider range of price points and performance levels.
AMD’s Enhanced Machine Learning Stack
On the software side, AMD’s solution stack now includes support for ONNX Runtime, an intermediary machine learning framework that allows users to perform inference on a wider range of source data using local AMD hardware. Additionally, AMD introduces support for the INT8 data type through MIGraphX, AMD’s graph inference engine, complementing existing data types like FP32 and FP16. With ROCm 6.0, AMD continues to support the PyTorch framework by introducing mixed precision capabilities (FP32/FP16) in ML training workflows.
AMD is making it possible for AI researchers and engineers to use a wider range of Radeon hardware at a wider range of price points and performance levels. However, AMD’s ROCm platform does not support AMD’s Radeon RX 7800 XT or RX 7700 XT, though this may change with future versions of ROCm.
AMD ROCm 6.0 Enhancements: Future Radeon GPU Support
In addition to hardware support, AMD ROCm 6.0 features support for ONNX Runtime, an open standard for machine learning algorithms and software tools that allow developers to easily convert AI models to new frameworks. This support allows AI researchers and developers to utilize a wider range of source data.
In the future, AMD hopes to see AMD’s RX 7800 XT support ROCm, further expanding the Radeon GPU options available to developers. If AMD’s 16GB RX 7900 GRE can support ROCm, there is no reason why AMD’s 16GB RX 7800 XT shouldn’t.
