DAPHNE - An automotive benchmark suite for parallel programming models on embedded heterogeneous platforms: work-in-progress

Abstract

Due to the ever-increasing computational demand of automotive applications, and in particular autonomous driving capabilities, the automotive industry and its suppliers are starting to adopt parallel and heterogeneous embedded computing platforms. However, C and C++, the currently dominating programming languages in this industry, do not provide sufficient mechanisms to fully exploit such platforms. As a result, vendors have begun to employ true parallel programming models such as OpenMP, CUDA or OpenCL. In this work, we report on a benchmark suite developed specifically to investigate the applicability of established parallel programming models to automotive workloads on heterogeneous platforms.