Couture: Tailoring STT-MRAM for persistent main memory

Mustafa M. Shihab, Jie Zhang, Shuwen Gao, Joseph Callenes-Sloan, Myoungsoo Jung

Research output: Contribution to conferencePaperpeer-review

5 Citations (Scopus)

Abstract

Modern computer systems rely extensively on dynamic random-access memory (DRAM) to bridge the performance gap between on-chip cache and secondary storage. However, continuous process scaling has exposed DRAM to high off-state leakage and excessive power consumption from frequent refresh operations. Spin-transfer torque magnetoresistive RAM (STT-MRAM) is a plausible replacement for DRAM, given its high endurance and near-zero leakage. However, conventional STT-MRAM cannot directly substitute DRAM due to its large cell space area and the high latency and energy costs for writes. In this work, we present Couture – a main memory design using tailored STT-MRAM that can offer a storage density comparable to DRAM and high performance with low-power consumption. In addition, we propose an intelligent data scrubbing method (iScrub) to ensure data integrity with minimum overhead. Our evaluation results show that, equipped with the iScrub policy, our proposed Couture can achieve up to 23% performance improvement, while consuming 18% less energy, on average, compared to a contemporary DRAM.

Original languageEnglish
Publication statusPublished - 2016
Event4th Workshop on Interactions of NVM/Flash with Operating Systems and Workloads, INFLOW 2016, co-located with OSDI 2016 - Savannah, United States
Duration: 2016 Nov 1 → …

Conference

Conference4th Workshop on Interactions of NVM/Flash with Operating Systems and Workloads, INFLOW 2016, co-located with OSDI 2016
CountryUnited States
CitySavannah
Period16/11/1 → …

Bibliographical note

Funding Information:
The authors would like to thank MemRay Corporation for technical support. This research is supported in part by MSIP “ICT Consilience Creative Program” IITP-R0346-16-1008, NRF-2015M3C4A7065645, NRF-2016R1C1B2015312 DOE grant DE-AC02-05CH1123 and MemRay grant (2015-11-1731). M. Jung has an interest in being supported for any engineering or customer sample product on emerging NVM technologies (e.g., PRAM, X-Point, ReRAM, STT-MRAM etc.). The corresponding author is M. Jung.

Publisher Copyright:
© INFLOW 2016 - 4th Workshop on Interactions of NVM/Flash with Operating Systems and Workloads, co-located with OSDI 2016. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Software
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Couture: Tailoring STT-MRAM for persistent main memory'. Together they form a unique fingerprint.

Cite this