Performance and power-efficient design of dense non-volatile cache in CMPs

Amin Jadidi, Mohammad Arjomand, Mahmut T. Kandemir, Chita R. Das

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we present a novel cache design based on Multi-Level Cell Spin-Transfer Torque RAM (MLC STT-RAM) that can dynamically adjust the set capacity and associativity to efficiently use the full potential of MLC STT-RAM technology. We exploit the asymmetric nature of the MLC storage scheme to build cache lines featuring heterogeneous performances, that is, half of the cache lines are read-friendly, while the other half are write-friendly. Furthermore, we propose to opportunistically deactivate cache ways in underutilized sets to convert MLC to Single-Level Cell (SLC) mode, which features overall better performance and lifetime. Our ultimate goal is to build a cache architecture that combines the capacity advantages of MLC and performance/energy advantages of SLC. Our experimental evaluations show an average improvement of 43 percent in total numbers of conflict misses, 27 percent in memory access latency, 12 percent in system performance, and 26 percent in L3 access energy, with a slight degradation in lifetime (about 7 percent) compared to an SLC cache.

Original languageEnglish (US)
Pages (from-to)1054-1061
Number of pages8
JournalIEEE Transactions on Computers
Volume67
Issue number7
DOIs
StatePublished - Jul 1 2018

Fingerprint

Random access storage
Cache
Torque
Percent
Cell
Data storage equipment
Degradation
Lifetime
Associativity
Line
Energy
Experimental Evaluation
Convert
Latency
Design
System Performance

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computational Theory and Mathematics

Cite this

@article{6074fefca3854fb0b285bcfd05c8be8a,
title = "Performance and power-efficient design of dense non-volatile cache in CMPs",
abstract = "In this paper, we present a novel cache design based on Multi-Level Cell Spin-Transfer Torque RAM (MLC STT-RAM) that can dynamically adjust the set capacity and associativity to efficiently use the full potential of MLC STT-RAM technology. We exploit the asymmetric nature of the MLC storage scheme to build cache lines featuring heterogeneous performances, that is, half of the cache lines are read-friendly, while the other half are write-friendly. Furthermore, we propose to opportunistically deactivate cache ways in underutilized sets to convert MLC to Single-Level Cell (SLC) mode, which features overall better performance and lifetime. Our ultimate goal is to build a cache architecture that combines the capacity advantages of MLC and performance/energy advantages of SLC. Our experimental evaluations show an average improvement of 43 percent in total numbers of conflict misses, 27 percent in memory access latency, 12 percent in system performance, and 26 percent in L3 access energy, with a slight degradation in lifetime (about 7 percent) compared to an SLC cache.",
author = "Amin Jadidi and Mohammad Arjomand and Kandemir, {Mahmut T.} and Das, {Chita R.}",
year = "2018",
month = "7",
day = "1",
doi = "10.1109/TC.2018.2796067",
language = "English (US)",
volume = "67",
pages = "1054--1061",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "7",

}

Performance and power-efficient design of dense non-volatile cache in CMPs. / Jadidi, Amin; Arjomand, Mohammad; Kandemir, Mahmut T.; Das, Chita R.

In: IEEE Transactions on Computers, Vol. 67, No. 7, 01.07.2018, p. 1054-1061.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Performance and power-efficient design of dense non-volatile cache in CMPs

AU - Jadidi, Amin

AU - Arjomand, Mohammad

AU - Kandemir, Mahmut T.

AU - Das, Chita R.

PY - 2018/7/1

Y1 - 2018/7/1

N2 - In this paper, we present a novel cache design based on Multi-Level Cell Spin-Transfer Torque RAM (MLC STT-RAM) that can dynamically adjust the set capacity and associativity to efficiently use the full potential of MLC STT-RAM technology. We exploit the asymmetric nature of the MLC storage scheme to build cache lines featuring heterogeneous performances, that is, half of the cache lines are read-friendly, while the other half are write-friendly. Furthermore, we propose to opportunistically deactivate cache ways in underutilized sets to convert MLC to Single-Level Cell (SLC) mode, which features overall better performance and lifetime. Our ultimate goal is to build a cache architecture that combines the capacity advantages of MLC and performance/energy advantages of SLC. Our experimental evaluations show an average improvement of 43 percent in total numbers of conflict misses, 27 percent in memory access latency, 12 percent in system performance, and 26 percent in L3 access energy, with a slight degradation in lifetime (about 7 percent) compared to an SLC cache.

AB - In this paper, we present a novel cache design based on Multi-Level Cell Spin-Transfer Torque RAM (MLC STT-RAM) that can dynamically adjust the set capacity and associativity to efficiently use the full potential of MLC STT-RAM technology. We exploit the asymmetric nature of the MLC storage scheme to build cache lines featuring heterogeneous performances, that is, half of the cache lines are read-friendly, while the other half are write-friendly. Furthermore, we propose to opportunistically deactivate cache ways in underutilized sets to convert MLC to Single-Level Cell (SLC) mode, which features overall better performance and lifetime. Our ultimate goal is to build a cache architecture that combines the capacity advantages of MLC and performance/energy advantages of SLC. Our experimental evaluations show an average improvement of 43 percent in total numbers of conflict misses, 27 percent in memory access latency, 12 percent in system performance, and 26 percent in L3 access energy, with a slight degradation in lifetime (about 7 percent) compared to an SLC cache.

UR - http://www.scopus.com/inward/record.url?scp=85040930970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040930970&partnerID=8YFLogxK

U2 - 10.1109/TC.2018.2796067

DO - 10.1109/TC.2018.2796067

M3 - Article

AN - SCOPUS:85040930970

VL - 67

SP - 1054

EP - 1061

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 7

ER -