Predictable Multithreading of Embedded Applications Using PRET-C - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Predictable Multithreading of Embedded Applications Using PRET-C

Abstract

We propose a new language called Precision Timed C (PRET-C), for predictable and lightweight multithreading in C. PRET-C supports synchronous concurrency, preemption, and a high-level construct for logical time. In contrast to existing synchronous languages, PRET-C offers C-based shared memory communications between concurrent threads that is guaranteed to be thread safe. Due to the proposed synchronous semantics, the mapping of logical time to physical time can be achieved much more easily than with plain C, thanks to a Worst Case Reaction Time (WCRT) analyzer (not presented here). Associated to the PRET-C programming language, we present a dedicated target architecture, called ARPRET, which combines a hardware accelerator associated to an existing softcore processor. This allows us to improve the throughput while preserving the predictability. With extensive benchmarking, we then demonstrate that ARPRET not only achieves completely predictable execution of PRET-C programs, but also improves the throughput when compared to the pure software execution of PRET-C. The PRET-C software approach is also significantly more efficient in comparison to two other light-weight concurrent C variants (namely SC and Protothreads), as well as the well-known Esterel synchronous programming language.
Fichier principal
Vignette du fichier
PRETC_MEM10.pdf (333.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00786378 , version 1 (08-02-2013)

Identifiers

Cite

Sidharta Andalam, Partha Roop, Alain Girault. Predictable Multithreading of Embedded Applications Using PRET-C. International Conference on Formal Methods and Models for Codesign, MEMOCODE'10, Jul 2010, Grenoble, France. pp.159-168, ⟨10.1109/MEMCOD.2010.5558636⟩. ⟨hal-00786378⟩
380 View
414 Download

Altmetric

Share

Gmail Facebook X LinkedIn More