A WCET-aware parallel programming model for predictability enhanced multi-core architectures
A WCET-aware parallel programming model for predictability enhanced multi-core architectures
复制标题
用于可预测性增强的多核架构的 WCET 感知并行编程模型
DOI：
10.23919/date.2018.8342145
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
J. Becker
中科院分区：
文献类型：
--
作者：
Simon Reder;Leonard Masing;Harald Bucher;Timon D. ter Braak;Timo Stripf;J. Becker
实时应用中对网络物理系统的性能要求越来越高，因此需要迁移到多核处理器系统。然而，商用的多核系统往往不适合实时领域，能够实时的多核编程模型很少。在本文中，我们提出了在欧盟研究项目ARGO内开发的解决方案。通过可预测性增强的基于noc的多/多核架构，我们研究了有助于提高平台和编程模型可预测性的硬件属性。平台和编程模型都由支持wcet的体系结构描述语言（ADL）补充。这在为精确的多核WCET分析算法保留相关细节的同时，实现了一定程度的硬件抽象。目标平台和编程模型被设计成可被多核WCET计算工具静态分析，这是ARGO项目开发的自动化WCET感知软件并行化工具流的一部分。
Increasing performance requirements for cyber-physical systems in real-time applications raise the necessity to migrate to multi-core processor systems. However, commercial of the shelf multi-core systems are often inappropriate for the real-time domain and real-time capable multi-core programming models are rare. In this paper, we present a solution developed within the EU research project ARGO. By means of a predictability-enhanced NoC-based multi-/many-core architecture, we investigate hardware properties that can help to improve the predictability of the platform and the programming model. Both platform and programming model are complemented by a WCET-aware Architecture Description Language (ADL). This enables a certain degree of hardware abstraction while preserving the relevant details for accurate multi-core WCET analysis algorithms. Target platform and programming model are designed to be statically analyzable by multi-core WCET computation tools, that are part of the automated WCET-aware software parallelization tool flow developed in the ARGO project.