Exploiting memory allocations in clusterised many‐core architectures. Issue 4 (24th April 2019)

• Record Type: Journal Article
• Authors: Garibotti, Rafael; Ost, Luciano; Butko, Anastasiia; Reis, Ricardo; Gamatié, Abdoulaye; Sassatelli, Gilles
• Is Part Of: IET computers & digital techniques. Volume 13:Issue 4(2019)
• Page Start: 302
• Page End: 311
• Publication Date: 2019-04-24
• Subjects: multiprocessing systems -- resource allocation -- power aware computing -- energy conservation -- distributed shared memory systems -- memory architecture -- storage management -- embedded systems -- mobile computing -- pattern clustering; distributed shared memory allocations -- energy efficiency -- power‐efficiency architectures -- centralised shared memory solution -- many‐core architecture clustering -- embedded systems -- mobile architectures -- distributed shared memory systems -- on‐chip data locality -- memory subsystem; Computers -- Periodicals; Digital electronics -- Periodicals; Computer engineering -- Periodicals; Computer architecture -- Periodicals; Computer organization -- Periodicals; 621.39
• DOI: 10.1049/iet-cdt.2018.5136
• Languages: English
• ISSNs: 1751-8601

Abstract

Abstract : Power‐efficient architectures have become the most important feature required for future embedded systems. Modern designs, like those released on mobile devices, reveal that clusterisation is the way to improve energy efficiency. However, such architectures are still limited by the memory subsystem (i.e. memory latency problems). This work investigates an alternative approach that exploits on‐chip data locality to a large extent, through distributed shared memory systems that permit efficient reuse of on‐chip mapped data in clusterised many‐core architectures. First, this work reviews the current literature on memory allocations and explores the limitations of cluster‐based many‐core architectures. Then, several memory allocations are introduced and benchmarked scalability, performance and energy‐wise against the conventional centralised shared memory solution in order to reveal which memory allocation is the most appropriate for future mobile architectures. The results show that distributed shared memory allocations bring performance gains and opportunities to reduce energy consumption.