a landscape of the new dark silicon design regime · pdf filea landscape of the new dark...

A Landscape of the New Dark Silicon Design Regime Michael B. Taylor Center for Dark Silicon University of California, San Diego The rise of dark silicon is driving a new class of architectural techniques that “spend” area to “buy” energy efficiency. In this talk we examine two new frameworks employed by computer architects to understand the challenges and opportunities that await us. The first is the utilization wall [3], a simple model that architects use to understand how technology scaling under post-Dennard assumptions will affect hardware design. The second framework is the four horsemen taxonomy [2] that comprises four key approaches that future chip designers will use to attack the dark silicon problem. We describe recent research projects that typify these approaches, including GreenDroid [6], a massively heterogeneous 28 nm processor being developed at UCSD. Finally, we conclude with some directions (and non-directions) that the human brain could offer for refactoring the computational stack for dark silicon [1]. Acknowledgments: This work was partially supported by NSF awards 0846152, 1018850, 0811794 and 1228992, Nokia and AMD gifts, and by C- FAR, one of six centers of STARnet, a Semiconductor Research Corporation program sponsored by MARCO and DARPA. A full paper is available at [1], the four horsemen taxonomy is introduced in [2], the utilization wall in [3], the term ‘dark silicon’ in [4], Dennard scaling in [5], and GreenDroid in [6]. References: [1] M. B. Taylor, “A Landscape of the New Dark Silicon Design Regime”, IEEE Micro, pp. 8-19, Sep/Oct 2013. [2] M. B. Taylor, “ Is Dark Silicon Useful? Harnessing the Four Horseman of the Coming Dark Silicon Apocalypse, DAC 2012. [3] G. Venkatesh et al., “Conservation Cores: Reducing the Energy of Mature Computations,” ASPLOS, March 2010. [4] R. Merritt, “ARM CTO: Power Surge Could Create ‘Dark Silicon’,” EE Times Oct 22, 2009. [5] R.H. Dennard, “Design of Ion-Implanted MOSFET’s with Very Small Physical Dimensions,” IEEE JSSC, 1975. [6] N. Goulding-Hotta et al. GreenDroid: A Mobile Application Processor for a Future of Dark Silicon,” Hot Chips, 2010. 9783981537024/DATE14/©2014 EDAA

Upload: truongquynh

Post on 16-Feb-2018

214 views

Category:

Documents

1 download

Report

Download

Embed Size (px):

TRANSCRIPT

A Landscape of the New Dark Silicon Design Regime

Michael B. Taylor Center for Dark Silicon

University of California, San Diego The rise of dark silicon is driving a new class of architectural techniques that “spend” area to “buy” energy efficiency. In this talk we examine two new frameworks employed by computer architects to understand the challenges and opportunities that await us. The first is the utilization wall [3], a simple model that architects use to understand how technology scaling under post-Dennard assumptions will affect hardware design. The second framework is the four horsemen taxonomy [2] that comprises four key approaches that future chip designers will use to attack the dark silicon problem. We describe recent research projects that typify these approaches, including GreenDroid [6], a massively heterogeneous 28 nm processor being developed at UCSD. Finally, we conclude with some directions (and non-directions) that the human brain could offer for refactoring the computational stack for dark silicon [1]. Acknowledgments: This work was partially supported by NSF awards 0846152, 1018850, 0811794 and 1228992, Nokia and AMD gifts, and by C-FAR, one of six centers of STARnet, a Semiconductor Research Corporation program sponsored by MARCO and DARPA. A full paper is available at [1], the four horsemen taxonomy is introduced in [2], the utilization wall in [3], the term ‘dark silicon’ in [4], Dennard scaling in [5], and GreenDroid in [6]. References: [1] M. B. Taylor, “A Landscape of the New Dark Silicon Design Regime”, IEEE Micro, pp. 8-19, Sep/Oct 2013. [2] M. B. Taylor, “ Is Dark Silicon Useful? Harnessing the Four Horseman of the Coming Dark Silicon Apocalypse, DAC 2012. [3] G. Venkatesh et al., “Conservation Cores: Reducing the Energy of Mature Computations,” ASPLOS, March 2010. [4] R. Merritt, “ARM CTO: Power Surge Could Create ‘Dark Silicon’,” EE Times Oct 22, 2009. [5] R.H. Dennard, “Design of Ion-Implanted MOSFET’s with Very Small Physical Dimensions,” IEEE JSSC, 1975. [6] N. Goulding-Hotta et al. GreenDroid: A Mobile Application Processor for a Future of Dark Silicon,” Hot Chips, 2010. 978-‐3-‐9815370-‐2-‐4/DATE14/©2014 EDAA

Dark Silicon Accelerators for Database Indexing

GREENDROID: AN ARCHITECTURE FOR DARK SILICON AGE · PDF filecontents 1 green technology 2 android platform 3 drawbacks of android 4 utilization wall & dark silicon 5 c-cores 6 greendroid

Dark Silicon Phenomenon

Evidence for Evaporating Dark Matter Particles in Silicon fireballs. …vixra.org/pdf/1407.0001v2.pdf · 2014. 7. 6. · 1 Evidence for Evaporating Dark Matter Particles in Silicon

Dark Silicon and its Implications for Future Processor Design fileDark Silicon and its Implications for Future Processor Design Max Menges 22. December 2015 1/21. Dark Silicon

Towards Dark Silicon Era in FPGAs Using …dsn.ce.sharif.edu/wp-content/uploads/2012/10/HardLogic...Towards Dark Silicon Era in FPGAs Using Complementary Hard Logic Design Ali Ahari

Silicon carbide detectors for sub-GeV dark matter

Dark silicon and the end of multicore scaling

Conservation Cores: Energy-Saving Coprocessors for …users.elis.ugent.be/~brdsutte/lctes2011/lctes_2011_taylor.pdf · This Talk The Dark Silicon Problem How to use Dark Silicon to

DARK SILICON OVERVIEW, ANALYSIS AND FUTURE …rsridhar/cse691/Present15/Jordan_Radice_Dark... · DARK SILICON OVERVIEW, ANALYSIS AND FUTURE WORK Jordan Radice [email protected]

Power Limitations and Dark Silicon Challenge the …hadi/doc/paper/2012-tocs-dark_silicon.pdf11 Power Limitations and Dark Silicon Challenge the Future of Multicore HADI ESMAEILZADEH,

Conservation Cores: Energy-Saving Coprocessors for …brdsutte/lctes2011/lctes_2011_taylor.pdfThis Talk The Dark Silicon Problem How to use Dark Silicon to improve energy efficiency