Brook Auto: High-Level Certification-Friendly Programming for GPU-powered Automotive Systems

摘要

Modern automotive systems require increased performance to implement Advanced Driving Assistance Systems (ADAS). GPU-powered platforms are promising candidates for such computational tasks, however current low-level programming models challenge the accelerator software certification process, while they limit the hardware selection to a fraction of the available platforms. In this paper we present Brook Auto, a high-level programming language for automotive GPU systems which removes these limitations. We describe the challenges and solutions we faced in its implementation, as well as a complete evaluation in terms of performance and productivity, which shows the effectiveness of our method.