LL-PCM: Low-latency phase change memory architecture

Nam Sung Kim, Choungki Song, Woo Young Cho, Jian Huang, Myoungsoo Jung

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

Abstract

PCM is a promising non-volatile memory technology, as it can offer a unique trade-off between density and latency compared with DRAM and flash memory. Albeit PCM is much faster than flash memory, it is still notably slower than DRAM, which can significantly degrade system performance. In this paper, we analyze a PCM implementation in depth, and identify the primary cause of PCM's long latency, i.e., a long interconnect (high resistance/capacitance) path between a cell and a sense-amp/writedriver. This in turn requires (1) a very large charge pump consuming: ∼20% of PCM chip space, ∼50% of latency of write operations, and ∼2× more power than a write operation itself; and (2) a large current sense-amp with long time to pre-charge the interconnect path. Then, we propose Low-Latency PCM (LLPCM) architecture. Our analysis shows that LL-PCM can give 119% higher performance and consume 43% lower memory energy than PCM for memory-intensive applications. LL-PCM is only ∼1% larger than PCM, as the cost of reducing the resistance/capacitance of the interconnect path is negated by its 4.1× smaller charge pump.

Original languageEnglish (US)
Title of host publicationProceedings of the 56th Annual Design Automation Conference 2019, DAC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450367257
DOIs
StatePublished - Jun 2 2019
Event56th Annual Design Automation Conference, DAC 2019 - Las Vegas, United States
Duration: Jun 2 2019Jun 6 2019

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

Conference

Conference56th Annual Design Automation Conference, DAC 2019
CountryUnited States
CityLas Vegas
Period6/2/196/6/19

Fingerprint

Phase change memory
Memory architecture
Pulse code modulation
Phase Change
Latency
Interconnect
Flash Memory
Charge
Capacitance
Path
Pump
Flash memory
Dynamic random access storage
System Performance
Chip
Data storage equipment
High Performance
Trade-offs
Architecture
Pumps

Keywords

  • DRAM
  • Heterogeneous memory system
  • PCM

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Modeling and Simulation

Cite this

Kim, N. S., Song, C., Cho, W. Y., Huang, J., & Jung, M. (2019). LL-PCM: Low-latency phase change memory architecture. In Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019 [a14] (Proceedings - Design Automation Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3316781.3317853

LL-PCM : Low-latency phase change memory architecture. / Kim, Nam Sung; Song, Choungki; Cho, Woo Young; Huang, Jian; Jung, Myoungsoo.

Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. a14 (Proceedings - Design Automation Conference).

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

Kim, NS, Song, C, Cho, WY, Huang, J & Jung, M 2019, LL-PCM: Low-latency phase change memory architecture. in Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019., a14, Proceedings - Design Automation Conference, Institute of Electrical and Electronics Engineers Inc., 56th Annual Design Automation Conference, DAC 2019, Las Vegas, United States, 6/2/19. https://doi.org/10.1145/3316781.3317853
Kim NS, Song C, Cho WY, Huang J, Jung M. LL-PCM: Low-latency phase change memory architecture. In Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. a14. (Proceedings - Design Automation Conference). https://doi.org/10.1145/3316781.3317853
Kim, Nam Sung ; Song, Choungki ; Cho, Woo Young ; Huang, Jian ; Jung, Myoungsoo. / LL-PCM : Low-latency phase change memory architecture. Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - Design Automation Conference).
@inproceedings{b7c78e9217b24a8dbaecb3ebe684f2c5,
title = "LL-PCM: Low-latency phase change memory architecture",
abstract = "PCM is a promising non-volatile memory technology, as it can offer a unique trade-off between density and latency compared with DRAM and flash memory. Albeit PCM is much faster than flash memory, it is still notably slower than DRAM, which can significantly degrade system performance. In this paper, we analyze a PCM implementation in depth, and identify the primary cause of PCM's long latency, i.e., a long interconnect (high resistance/capacitance) path between a cell and a sense-amp/writedriver. This in turn requires (1) a very large charge pump consuming: ∼20{\%} of PCM chip space, ∼50{\%} of latency of write operations, and ∼2× more power than a write operation itself; and (2) a large current sense-amp with long time to pre-charge the interconnect path. Then, we propose Low-Latency PCM (LLPCM) architecture. Our analysis shows that LL-PCM can give 119{\%} higher performance and consume 43{\%} lower memory energy than PCM for memory-intensive applications. LL-PCM is only ∼1{\%} larger than PCM, as the cost of reducing the resistance/capacitance of the interconnect path is negated by its 4.1× smaller charge pump.",
keywords = "DRAM, Heterogeneous memory system, PCM",
author = "Kim, {Nam Sung} and Choungki Song and Cho, {Woo Young} and Jian Huang and Myoungsoo Jung",
year = "2019",
month = "6",
day = "2",
doi = "10.1145/3316781.3317853",
language = "English (US)",
series = "Proceedings - Design Automation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019",
address = "United States",

}

TY - GEN

T1 - LL-PCM

T2 - Low-latency phase change memory architecture

AU - Kim, Nam Sung

AU - Song, Choungki

AU - Cho, Woo Young

AU - Huang, Jian

AU - Jung, Myoungsoo

PY - 2019/6/2

Y1 - 2019/6/2

N2 - PCM is a promising non-volatile memory technology, as it can offer a unique trade-off between density and latency compared with DRAM and flash memory. Albeit PCM is much faster than flash memory, it is still notably slower than DRAM, which can significantly degrade system performance. In this paper, we analyze a PCM implementation in depth, and identify the primary cause of PCM's long latency, i.e., a long interconnect (high resistance/capacitance) path between a cell and a sense-amp/writedriver. This in turn requires (1) a very large charge pump consuming: ∼20% of PCM chip space, ∼50% of latency of write operations, and ∼2× more power than a write operation itself; and (2) a large current sense-amp with long time to pre-charge the interconnect path. Then, we propose Low-Latency PCM (LLPCM) architecture. Our analysis shows that LL-PCM can give 119% higher performance and consume 43% lower memory energy than PCM for memory-intensive applications. LL-PCM is only ∼1% larger than PCM, as the cost of reducing the resistance/capacitance of the interconnect path is negated by its 4.1× smaller charge pump.

AB - PCM is a promising non-volatile memory technology, as it can offer a unique trade-off between density and latency compared with DRAM and flash memory. Albeit PCM is much faster than flash memory, it is still notably slower than DRAM, which can significantly degrade system performance. In this paper, we analyze a PCM implementation in depth, and identify the primary cause of PCM's long latency, i.e., a long interconnect (high resistance/capacitance) path between a cell and a sense-amp/writedriver. This in turn requires (1) a very large charge pump consuming: ∼20% of PCM chip space, ∼50% of latency of write operations, and ∼2× more power than a write operation itself; and (2) a large current sense-amp with long time to pre-charge the interconnect path. Then, we propose Low-Latency PCM (LLPCM) architecture. Our analysis shows that LL-PCM can give 119% higher performance and consume 43% lower memory energy than PCM for memory-intensive applications. LL-PCM is only ∼1% larger than PCM, as the cost of reducing the resistance/capacitance of the interconnect path is negated by its 4.1× smaller charge pump.

KW - DRAM

KW - Heterogeneous memory system

KW - PCM

UR - http://www.scopus.com/inward/record.url?scp=85067816456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067816456&partnerID=8YFLogxK

U2 - 10.1145/3316781.3317853

DO - 10.1145/3316781.3317853

M3 - Conference contribution

AN - SCOPUS:85067816456

T3 - Proceedings - Design Automation Conference

BT - Proceedings of the 56th Annual Design Automation Conference 2019, DAC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -