The demand for heterogeneous architectures continues to rise, driven by the exponential growth in generative AI and accelerated computing. Workloads are being spread across new and diverse hardware, such as GPUs, NPUs, and AI accelerators, allowing both traditional algorithms and new neural networks to run much faster than was previously possible. The challenge we face is in ensuring that there is a standards based way to target hardware with multiple types of processors from different vendors. The UXL Foundation is at the heart of making this a reality with a core set of projects that are standards-based and open source, but we still need to do more.
This session brings together experts from the hardware and software community to talk about the strengths of open standards and open-source software, and how everyone wins when we collaborate towards the same goals.