Nothing Special   »   [go: up one dir, main page]

skip to main content
research-article

DARE

Published: 01 January 2018 Publication History

Abstract

Power consumption and reliability of memory components are two of the most important hurdles in realizing exascale systems. Dynamic random access memory DRAM scaling projections predict significant performance and power penalty due to the conventional use of pessimistic refresh periods catering for worst-case cell retention times. Recent approaches relax those pessimistic refresh rates only on ``strong'' cells, or build on application-specific error resilience for data placement. However, these approaches cannot reveal the full potential of a relaxed refresh paradigm shift, since they neglect additional application resilience properties related to the inherent functioning of DRAM. In this article, we elevate Refresh-by-Access as a first-class property of application resilience. We develop a complete, non-intrusive system stack, armed with low-cost Data-Access Aware Refresh DARE methods, to facilitate aggressive refresh relaxation and ensure non-disruptive operation on commodity servers. Essentially, our proposed access-aware scheduling of application tasks intelligently amplifies the impact of the implicit refresh of memory accesses, extending the period during which hardware refresh remains disabled, while limiting the number of potential errors, hence their impact on an application's output quality. The stack, implemented on an off-the-shelf server and running a full-fledged Linux OS, captures for the first time the intricate time-dependent system and data interactions in the presence of hardware errors, in contrast to previous architectural simulations approaches of limited detail. Results demonstrate that by applying DARE, it is possible to completely disable hardware refresh, with minor quality loss that ranges from 2% to 18%.

References

[1]
Bergman K, Borkar S, Campbell D . 2008<chapter-title>Exascale computing study: technology challenges in achieving exascale systems</chapter-title>. .
[2]
Bhati I, Chang MT, Chishti Z . 2016 DRAM refresh mechanisms, penalties, and trade-offs. IEEE Transactions on Computers Volume 65 Issue 1: pp.108-–121. <ext-link ext-link-type="uri" xlink:href="http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7070756">http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7070756</ext-link>.
[3]
Bhati I, Chishti Z, Lu SL . 2015 Flexible auto-refresh. ACM SIGARCH Computer Architecture News Volume 43 Issue 3: pp.235-–246. .
[4]
Chippa VK, Chakradhar ST, Roy K . 2013 Analysis and characterization of inherent application resilience for approximate computing. In: Proceedings of the 50th annual design automation conference, DAC '13, New York, NY, USA, 29 May-7 June 2013, pp. pp.113:1-–113:9. New York, NY: ACM. .
[5]
Cui Z, McKee SA, Zha Z . 2014 DTail. In: Proceedings of the 28th ACM international conference on supercomputing-ICS '14, New York, New York, USA, 10-13 June 2014, pp. pp.43-–52. New York, NY: ACM Press. .
[6]
Ghosh M, Lee HHS 2007 Smart refresh: an enhanced memory controller design for reducing energy in conventional and 3d die-stacked DRAMs. In: 40th Annual IEEE/ACM international symposium on microarchitecture MICRO 2007, 1-5 December 2007, pp. pp.134-–145. Chicago, Illinois: IEEE. .
[7]
Giridhar B, Cieslak M, Duggal D . 2013 Exploring DRAM organizations for energy-efficient and resilient exascale memories. In: Proceedings of the international conference on high performance computing, networking, storage and analysis, SC '13, New York, NY, USA, 17-22 November 2013, pp. pp.23:1-–23:12. New York, NY: ACM. .
[8]
Han Y, Wang Y, Li H . 2014 Data-aware DRAM refresh to squeeze the margin of retention time in hybrid memory cube. In: Proceedings of the 2014 IEEE/ACM international conference on computer-aided design, ICCAD '14, Piscataway, NJ, USA, 2-6 November 2014, pp. pp.295-–300. Piscataway, NJ: IEEE Press. .
[9]
Hennessy JL, Patterson DA 2003 Computer Architecture: A Quantitative Approach, 3rd ed.Burlington: Morgan Kaufmann.
[10]
<collab collab-type="author">Intel</collab>2012 Intel xeon processor e5-1600/2400/2600/4600 e5-product family product families datasheet, volume two. .
[11]
<collab collab-type="author">JEDEC</collab>2010 DDR3 Sdram Specification . JEDEC. .
[12]
<collab collab-type="author">JEDEC</collab>2013 DDR4 Sdram Specification . JEDEC. .
[13]
Jung M, Mathew DM, Weis C . 2016a Efficient reliability management in SoCs-an approximate DRAM perspective. In: 2016 21st Asia and South Pacific design automation conference ASP-DAC, Macau, China, 25-28 January 2016, pp. pp.390-–394. IEEE. .
[14]
Jung M, Mathew DM, Weis C . 2016b Invited-approximate computing with partially unreliable dynamic random access memory-approximate DRAM. In: Proceedings of the 53rd annual design automation conference, DAC '16, New York, NY, USA, 5-9 June 2016, pp. pp.100:1-–100:4. New York, NY: ACM. .
[15]
Karakonstantis G, Banerjee N, Roy K 2010 Process-variation resilient and voltage-scalable DCT architecture for robust low-power computing. IEEE Transactions on Very Large Scale Integration VLSI Systems Volume 18 Issue 10: pp.1461-–1470. .
[16]
Kinam Kim K, Jooyoung Lee J 2009 A new investigation of data retention time in truly nanoscaled DRAMs. IEEE Electron Device Letters Volume 30 Issue 8: pp.846-–848. .
[17]
Lin CH, Shen DY, Chen YJ . 2015 Secret. ACM Transactions on Architecture and Code Optimization Volume 12 Issue 2: pp.19:1-–19:24. .
[18]
Liu J, Jaiyen B, Kim Y . 2013 An experimental study of data retention behavior in modern DRAM devices: implications for retention time profiling mechanisms. In: Proceedings of the 40th annual international symposium on computer architecture, ISCA '13, New York, NY, USA, 23-27 June 2013, pp. pp.60-–71. New York, NY: ACM. .
[19]
Liu J, Jaiyen B, Veras R . 2012 RAIDR: retention-aware intelligent DRAM refresh. In: Proceedings of the 39th annual international symposium on computer architecture, ISCA '12, Washington, DC, USA, 9-13 June 2012, pp. pp.1-–12. Washington, DC: IEEE Computer Society. .
[20]
Liu S, Pattabiraman K, Moscibroda T . 2011 Flikker: saving DRAM refresh-power through critical data partitioning. In: Proceedings of the sixteenth international conference on architectural support for programming languages and operating systems, ASPLOS XVI, New York, NY, USA, 5-11 March 2011, pp. pp.213-–224. New York, NY, USA: ACM. .
[21]
Love R 2010 Linux Kernel Development, 3rd ed.Addison-Wesley Professional. .
[22]
Mukundan J, Hunter H, Kim Kh . 2013 Understanding and mitigating refresh overheads in high-density DDR4 DRAM systems. In: Proceedings of the 40th annual international symposium on computer architecture, ISCA '13, NewYork, NY, USA, 23-27 June 2013, pp. pp.48-–59. New York, NY: ACM. .
[23]
Nair PJ, Chou CC, Qureshi MK 2014 Refresh pausing in DRAM memory systems. ACM Transactions on Architecture and Code Optimization Volume 11 Issue 1: pp.1-–26. .
[24]
Nair PJ, Kim DH, Qureshi MK 2013 Archshield: architectural framework for assisting DRAM scaling by tolerating high error rates. In: Proceedings of the 40th annual international symposium on computer architecture, ISCA '13, New York, NY, USA, 23-27 June 2013, pp. pp.72-–83. New York, NY: ACM. .
[25]
Qureshi MK, Kim DH, Khan S . 2015 Avatar: a variable-retention-time vrt aware refresh for DRAM systems. In: Proceedings of the 2015 45th annual IEEE/IFIP international conference on dependable systems and networks, DSN '15, Washington, DC, USA, 22-25 June 2015, pp. pp.427-–437. Washington, DC: IEEE Computer Society. .
[26]
Raha A, Jayakumar H, Sutar S . 2015 Quality-aware data allocation in approximate DRAM? In:2015 international conference on compilers, architecture and synthesis for embedded systems CASES, Amsterdam, Netherlands, 4-9 October 2015, pp. pp.89-–98. Piscataway, NJ, USA: IEEE. .
[27]
Sampson A, Dietl W, Fortuna E . 2011 Enerj: approximate data types for safe and general low-power computation. In: Proceedings of the 32Nd ACM SIGPLAN conference on programming language design and implementation, PLDI '11, New York, NY, USA, 4-8 June 2011, pp. pp.164-–174. New York, NY: ACM. .
[28]
Tang Y, Chowdhury RA, Kuszmaul BC. 2011 The Pochoir stencil compiler. In: Proceedings of the 23rd ACM symposium on parallelism in algorithms and architectures-SPAA '11, San Jose, California, 4-6 June 2011, p. pp.117. ACM. .
[29]
Venkatesan R, Herr S, Rotenberg E 2006 Retention-aware placement in DRAM RAPID: software methods for quasi-non-volatile DRAM. In: The twelfth international symposium on high-performance computer architecture, 2006, Austin, TX, USA, 11-15 February 2006, pp. pp.157-–167. IEEE. .

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image International Journal of High Performance Computing Applications
International Journal of High Performance Computing Applications  Volume 32, Issue 1
1 2018
201 pages

Publisher

Sage Publications, Inc.

United States

Publication History

Published: 01 January 2018

Author Tags

  1. Approximate computing
  2. DRAM
  3. application resilience
  4. operating system
  5. scheduling

Qualifiers

  • Research-article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 0
    Total Downloads
  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024

Other Metrics

Citations

View Options

View options

Get Access

Login options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media