Towards predictable execution model on ARM-based heterogeneous platforms

Abstract

Many today's real-time applications, such as Advanced Driver Assistant Systems (ADAS), demand both high computing power and safety guarantees. High computing power can be easily delivered by, now ubiquitous, multi-core CPUs or by a heterogeneous system with a multi-core CPU and a parallel accelerator such as a GPU. Reaching the required safety level in such a system is by far more difficult because the commercial-of-the-shelf (COTS) high-performance platforms contain many shared resources (e.g. main memory) with arbiters not designed to provide real-time guarantees. A promising approach to address this problem, known as PRedictable Execution Model (PREM), was introduced by Pellizzoni et al. [1]. We are interested in applying PREM to ARM-based heterogeneous platforms, but so far, all PREM-related work has been done on x86 or PowerPC. In this paper, we introduce several building blocks that are needed for implementing PREM on NVIDIA Tegra X1 platform. We propose a modification of the MemGuard tool to be practically usable on ARM platforms. We also analyse a throttling mechanism of Tegra X1 memory controller, that allows controlling memory bandwidth of non-CPU clients such as the GPU. We show that this mechanism can be used to make the execution time of CPU tasks more predictable.