A Case for Near Memory Computation Inside the Smart Memory Cube

  • 3D integration of solid-state memories and logic, as demonstrated by the Hybrid Memory Cube (HMC), offers major opportunities for revisiting near-memory computation and gives new hope to mitigate the power and performance losses caused by the “memory wall”. In this paper we present the first exploration steps towards design of the Smart Memory Cube (SMC), a new Processor-in-Memory (PIM) architecture that enhances the capabilities of the logic-base (LoB) in HMC. An accurate simulation environment has been developed, along with a full featured software stack. All offloading and dynamic overheads caused by the operating system, cache coherence, and memory management are considered, as well. Benchmarking results demonstrate up to 2X performance improvement in comparison with the host SoC, and around 1.5X against a similar host-side accelerator. Moreover, by scaling down the voltage and frequency of PIM’s processor it is possible to reduce energy by around 70% and 55% in comparison with the host and the accelerator, respectively.

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Teilen auf Twitter Suche bei Google Scholar
Verfasserangaben:Erfan Azarkhish, Davide Rossi, Igor Loi, Luca Benini
URN (Permalink):urn:nbn:de:hbz:386-kluedo-43241
Sprache der Veröffentlichung:Englisch
Veröffentlichungsdatum (online):18.03.2016
Jahr der Veröffentlichung:2016
Veröffentlichende Institution:Technische Universität Kaiserslautern
Datum der Publikation (Server):14.03.2016
Freies Schlagwort / Tag:HMC; Near Memory Computation; PIM; Smart Memory Cube
Fachbereiche / Organisatorische Einheiten:Fachbereich Elektrotechnik und Informationstechnik
CCS-Klassifikation (Informatik):B. Hardware / B.3 MEMORY STRUCTURES / B.3.2 Design Styles (D.4.2) / Primary memory
DDC-Sachgruppen:6 Technik, Medizin, angewandte Wissenschaften / 621.3 Elektrontechnik, Elektronik
Sammlungen:International Workshop on Emerging Memory Solutions
Lizenz (Deutsch):Standard gemäß KLUEDO-Leitlinien vom 30.07.2015