SCALE-Ahead-Of-Time Compilation of CUDA for AMD GPUs
Spectral Compute, United Kingdom
Proceedings of the 25th International Middleware Conference: Demos, Posters and Doctoral Symposium (Middleware ’24), 2024
@inproceedings{pavlidakis2024scale,
title={SCALE-Ahead-Of-Time Compilation of CUDA for AMD GPUs},
author={Pavlidakis, Manos and Kitching, Chris and Tomlinson, Nicholas and S{o}ndergaard, Michael},
booktitle={Proceedings of the 25th International Middleware Conference Demos, Posters and Doctoral Symposium},
pages={5–6},
year={2024}
}
SCALE is a new solution by Spectral Compute that empowers developers to write code once and deploy it across a range of GPU hardware platforms without modifying the original code. Designed to extend CUDA’s capabilities to AMD GPUs, SCALE maintains CUDA compatibility while introducing novel features that streamline GPU programming. This demo paper presents SCALE’s functionalities and impact, particularly its implications for lowering development costs, enhancing flexibility, and addressing supply chain concerns within the GPU ecosystem.
January 13, 2025 by hgpu
