A dynamic partial reconfigurable system with combined task allocation method to improve the reliability of FPGA. (April 2018)

• Record Type: Journal Article
• Authors: Wang, Guohua; Liu, Song; Sun, Jiangtao
• Is Part Of: Microelectronics and reliability. Volume 83(2018)
• Page Start: 14
• Page End: 24
• Publication Date: 2018-04
• Subjects: Resource management -- Reliability -- Task allocating -- Task acceptance ratio -- Dynamic partial reconfigurable system; Electronic apparatus and appliances -- Reliability -- Periodicals; Miniature electronic equipment -- Periodicals; Appareils électroniques -- Fiabilité -- Périodiques; Équipement électronique miniaturisé -- Périodiques; Electronic apparatus and appliances -- Reliability; Miniature electronic equipment; Periodicals; 621.3815
• DOI: 10.1016/j.microrel.2018.02.005
• Languages: English
• ISSNs: 0026-2714

Abstract

Abstract: Currently most FPGAs use SRAM-based technology, which are susceptible to faults from external electromagnetic radiation or produced by long-time internal overload operation. The dynamic partial reconfigurable (DPR) system, as an emerging technology, provides a promising way to solve this problem by reallocating the tasks in damaged resource areas to non-faulty regions at runtime. Based on such idea, an infrastructure for coordinately executing specialized hardware tasks on a reconfigurable FPGA is presented to achieve the flexibility for tolerating the occurring faults at runtime. Moreover, a method named MER-3D-Contact that combines the maximum empty rectangles (MER) technique with the adjacency heuristic is proposed to allocate tasks in the dynamical partial reconfiguration system for higher resource utilization, higher task acceptance ratio and lower fragmentation ratio. At last, experiments are carried out to evaluate the performance of the proposed system, results show that the proposed system can make the highest improvement 36% without damaged areas and the highest improvement 58% with damaged resources in terms of task acceptance ratio. Thus, the proposed system is expected a wide application in the field of more reliable FPGAs. Highlights: An infrastructure for executing tasks on a reconfigurable FPGA is able to achieve the flexibility for tolerating faults. A task allocation method is proposed for lower fragmentation ratio, higher resource utilization and task acceptance ratio. Experiments are carried out and results indicate the high performance of the system in terms of task acceptance ratio.