Architecting 3D vertical resistive memory for next-generation storage systems

Cong Xu, Pai Yu Chen, Dimin Niu, Yang Zheng, Shimeng Yu, Yuan Xie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Resistive Random Access Memory (ReRAM) has several advantages over current NAND Flash technology, highlighting orders of magnitude lower access latency and higher endurance. Recently proposed 3D vertical cross-point ReRAM (3D-VRAM) architecture is an encouraging development in ReRAM's evolution as a cost-competitive solution, and thus attracts a lot of attention in both industry and academia. In this work, an array-level model to estimate the read/write energy and characterize the vertical access transistor is developed. We use the model to study a range of design trade-offs by tuning the cell-level characteristics and the read/write schemes. The design space exploration addresses several critical issues that are either unique to 3D-VRAM or have substantially different concerns from the 2D cross-point array design. It provides insights on the design optimizations of the array density and access energy, and several important conclusions have been reached. Then we propose multi-directional write driver to mitigate the writer circuitry overhead, and use remote sensing scheme to take full advantage of limited on-die sensing resources. The benefits of these optimizations are evaluated and validated in our macro-Architecture model. With trace-based simulations, system-level comparisons between 3D-VRAM and a wide spectrum of memories are performed in mixed aspects of performance, cost, and energy. The results show that our optimized 3D-VRAM design are better than other contenders for storage memory in both performance and energy.

Original languageEnglish (US)
Title of host publicationIEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages55-62
Number of pages8
Volume2015-January
EditionJanuary
DOIs
StatePublished - Jan 5 2015
Event2014 33rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2014 - San Jose, United States
Duration: Nov 2 2014Nov 6 2014

Other

Other2014 33rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2014
CountryUnited States
CitySan Jose
Period11/2/1411/6/14

Fingerprint

Computer systems
Data storage equipment
Memory architecture
Macros
Costs
Remote sensing
Transistors
Durability
Tuning
RRAM
Industry

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Software

Cite this

Xu, C., Chen, P. Y., Niu, D., Zheng, Y., Yu, S., & Xie, Y. (2015). Architecting 3D vertical resistive memory for next-generation storage systems. In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD (January ed., Vol. 2015-January, pp. 55-62). [7001329] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAD.2014.7001329

Architecting 3D vertical resistive memory for next-generation storage systems. / Xu, Cong; Chen, Pai Yu; Niu, Dimin; Zheng, Yang; Yu, Shimeng; Xie, Yuan.

IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. Vol. 2015-January January. ed. Institute of Electrical and Electronics Engineers Inc., 2015. p. 55-62 7001329.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xu, C, Chen, PY, Niu, D, Zheng, Y, Yu, S & Xie, Y 2015, Architecting 3D vertical resistive memory for next-generation storage systems. in IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. January edn, vol. 2015-January, 7001329, Institute of Electrical and Electronics Engineers Inc., pp. 55-62, 2014 33rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2014, San Jose, United States, 11/2/14. https://doi.org/10.1109/ICCAD.2014.7001329
Xu C, Chen PY, Niu D, Zheng Y, Yu S, Xie Y. Architecting 3D vertical resistive memory for next-generation storage systems. In IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. January ed. Vol. 2015-January. Institute of Electrical and Electronics Engineers Inc. 2015. p. 55-62. 7001329 https://doi.org/10.1109/ICCAD.2014.7001329
Xu, Cong ; Chen, Pai Yu ; Niu, Dimin ; Zheng, Yang ; Yu, Shimeng ; Xie, Yuan. / Architecting 3D vertical resistive memory for next-generation storage systems. IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. Vol. 2015-January January. ed. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 55-62
@inproceedings{a3190bf5922a44759265a1420582b063,
title = "Architecting 3D vertical resistive memory for next-generation storage systems",
abstract = "Resistive Random Access Memory (ReRAM) has several advantages over current NAND Flash technology, highlighting orders of magnitude lower access latency and higher endurance. Recently proposed 3D vertical cross-point ReRAM (3D-VRAM) architecture is an encouraging development in ReRAM's evolution as a cost-competitive solution, and thus attracts a lot of attention in both industry and academia. In this work, an array-level model to estimate the read/write energy and characterize the vertical access transistor is developed. We use the model to study a range of design trade-offs by tuning the cell-level characteristics and the read/write schemes. The design space exploration addresses several critical issues that are either unique to 3D-VRAM or have substantially different concerns from the 2D cross-point array design. It provides insights on the design optimizations of the array density and access energy, and several important conclusions have been reached. Then we propose multi-directional write driver to mitigate the writer circuitry overhead, and use remote sensing scheme to take full advantage of limited on-die sensing resources. The benefits of these optimizations are evaluated and validated in our macro-Architecture model. With trace-based simulations, system-level comparisons between 3D-VRAM and a wide spectrum of memories are performed in mixed aspects of performance, cost, and energy. The results show that our optimized 3D-VRAM design are better than other contenders for storage memory in both performance and energy.",
author = "Cong Xu and Chen, {Pai Yu} and Dimin Niu and Yang Zheng and Shimeng Yu and Yuan Xie",
year = "2015",
month = "1",
day = "5",
doi = "10.1109/ICCAD.2014.7001329",
language = "English (US)",
volume = "2015-January",
pages = "55--62",
booktitle = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
edition = "January",

}

TY - GEN

T1 - Architecting 3D vertical resistive memory for next-generation storage systems

AU - Xu, Cong

AU - Chen, Pai Yu

AU - Niu, Dimin

AU - Zheng, Yang

AU - Yu, Shimeng

AU - Xie, Yuan

PY - 2015/1/5

Y1 - 2015/1/5

N2 - Resistive Random Access Memory (ReRAM) has several advantages over current NAND Flash technology, highlighting orders of magnitude lower access latency and higher endurance. Recently proposed 3D vertical cross-point ReRAM (3D-VRAM) architecture is an encouraging development in ReRAM's evolution as a cost-competitive solution, and thus attracts a lot of attention in both industry and academia. In this work, an array-level model to estimate the read/write energy and characterize the vertical access transistor is developed. We use the model to study a range of design trade-offs by tuning the cell-level characteristics and the read/write schemes. The design space exploration addresses several critical issues that are either unique to 3D-VRAM or have substantially different concerns from the 2D cross-point array design. It provides insights on the design optimizations of the array density and access energy, and several important conclusions have been reached. Then we propose multi-directional write driver to mitigate the writer circuitry overhead, and use remote sensing scheme to take full advantage of limited on-die sensing resources. The benefits of these optimizations are evaluated and validated in our macro-Architecture model. With trace-based simulations, system-level comparisons between 3D-VRAM and a wide spectrum of memories are performed in mixed aspects of performance, cost, and energy. The results show that our optimized 3D-VRAM design are better than other contenders for storage memory in both performance and energy.

AB - Resistive Random Access Memory (ReRAM) has several advantages over current NAND Flash technology, highlighting orders of magnitude lower access latency and higher endurance. Recently proposed 3D vertical cross-point ReRAM (3D-VRAM) architecture is an encouraging development in ReRAM's evolution as a cost-competitive solution, and thus attracts a lot of attention in both industry and academia. In this work, an array-level model to estimate the read/write energy and characterize the vertical access transistor is developed. We use the model to study a range of design trade-offs by tuning the cell-level characteristics and the read/write schemes. The design space exploration addresses several critical issues that are either unique to 3D-VRAM or have substantially different concerns from the 2D cross-point array design. It provides insights on the design optimizations of the array density and access energy, and several important conclusions have been reached. Then we propose multi-directional write driver to mitigate the writer circuitry overhead, and use remote sensing scheme to take full advantage of limited on-die sensing resources. The benefits of these optimizations are evaluated and validated in our macro-Architecture model. With trace-based simulations, system-level comparisons between 3D-VRAM and a wide spectrum of memories are performed in mixed aspects of performance, cost, and energy. The results show that our optimized 3D-VRAM design are better than other contenders for storage memory in both performance and energy.

UR - http://www.scopus.com/inward/record.url?scp=84936858928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936858928&partnerID=8YFLogxK

U2 - 10.1109/ICCAD.2014.7001329

DO - 10.1109/ICCAD.2014.7001329

M3 - Conference contribution

VL - 2015-January

SP - 55

EP - 62

BT - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

PB - Institute of Electrical and Electronics Engineers Inc.

ER -