Transcript ppt - SEAS
ESE534 Computer Organization Day 6: February 12, 2014 Energy, Power, Reliability 1 Penn ESE534 Spring2014 -- Mehta & DeHon Today • Energy tradeoffs • Voltage limits and leakage • Variations • [more of the gory transistor equations…] 2 Penn ESE534 Spring2014 -- Mehta & DeHon At Issue • Many now argue energy will be the ultimate scaling limit – (not lithography, costs, …) • Proliferation of portable and handheld devices – …battery size and life biggest issues • Cooling, energy costs may dominate cost of electronics – Even server room applications 3 Penn ESE534 Spring2014 -- Mehta & DeHon Preclass 1 • 1GHz case – Voltage? – Energy per Operation? – Power required for 2 processors? • 2GHz case – Voltage? – Energy per Operation? – Power required for 1 processor? 4 Penn ESE534 Spring2014 -- Mehta & DeHon Preclass 1 Lesson • What does Preclass 1 result tell us? 5 Penn ESE534 Spring2014 -- Mehta & DeHon Energy and Delay 1 2 E CV 2 tgd=Q/I=(CV)/I Id,sat=(mCOX/2)(W/L)(Vgs-VTH 2 ) 6 Penn ESE534 Spring2014 -- Mehta & DeHon Energy/Delay Tradeoff • EV2 • tgd1/V 1 2 E CV 2 tgd=(CV)/I Id,sat (Vgs-VTH)2 • We can trade speed for energy • E×(tgd)2 constant Martin et al. Power-Aware Computing, Kluwer 2001 http://caltechcstr.library.caltech.edu/308/ 7 Penn ESE534 Spring2014 -- Mehta & DeHon Area/Time Tradeoff • Also have Area-Time tradeoffs – HW2 spatial vs temporal multipliers – See more next week • Compensate slowdown with additional parallelism • …trade Area for Energy Architectural Option 8 Penn ESE534 Spring2014 -- Mehta & DeHon Question • By how much can we reduce energy? • What limits us? 9 Penn ESE534 Spring2014 -- Mehta & DeHon Challenge: Power 10 Penn ESE534 Spring2014 -- Mehta & DeHon Origin of Power Challenge • Limited capacity to remove heat – ~100W/cm2 force air – 1-10W/cm2 ambient • Transistors per chip grow at Moore’s Law rate = (1/F)2 • Energy/transistor must decrease at this rate to keep constant power density • P/tr CV2f • E/tr CV2 – …but V scaling more slowly than F 11 Penn ESE534 Spring2014 -- Mehta & DeHon ITRS Vdd Scaling: More slowly than F 12 Penn ESE534 Spring2014 -- Mehta & DeHon ITRS CV2 Scaling: More slowly than (1/F)2 13 Penn ESE534 Spring2014 -- Mehta & DeHon Origin of Power Challenge • Transistors per chip grow at Moore’s Law rate = (1/F)2 • Energy/transistor must decrease at this rate to keep constant • E/tr CV2 14 Penn ESE534 Spring2014 -- Mehta & DeHon Historical Power Scaling [Horowitz et al. / IEDM 2005] Penn ESE534 Spring2014 -- Mehta & DeHon 15 Microprocessor Power Density Watts The Future of Computing Performance: Game Over or Next Level? National Academy Press, 2011 16 Penn ESE534 Spring2014 -- Mehta & DeHon http://www.nap.edu/catalog.php?record_id=12980 Intel Power Density 17 Penn ESE534 Spring2014 -- Mehta & DeHon Impact Power Limits Integration Density Limit Constant Power Limit 45nm 32nm 22nm 16nm 11nm Source: Carter/Intel 18 Penn ESE534 Spring2014 -- Mehta & DeHon 18 Impact • Power density is limiting scaling – Can already place more transistors on a chip than we can afford to turn on! • Power is potential challenge/limiter for all future chips. – Only turn on small percentage of transistors? – Operate those transistors as much slower frequency? – Find a way to drop Vdd? 19 Penn ESE534 Spring2014 -- Mehta & DeHon How far can we reduce Vdd? 20 Penn ESE534 Spring2014 -- Mehta & DeHon Limits • Ability to turn off the transistor • Parameter Variations • Noise (not covered today) 21 Penn ESE534 Spring2014 -- Mehta & DeHon MOSFET Conduction From: http://en.wikipedia.org/wiki/File:IvsV_mosfet.png Penn ESE534 Spring2014 -- Mehta & DeHon 22 Transistor Conduction • Three regions – Subthreshold (Vgs<VTH) – Linear (Vgs>VTH) and (Vds < (Vgs-VTH)) – Saturation (Vgs>VTH) and (Vds > (Vgs-VTH)) 23 Penn ESE534 Spring2014 -- Mehta & DeHon Saturation Region • (Vgs>VTH) • (Vds > (Vgs-VTH)) Ids,sat=(mCOX/2)(W/L)(Vgs-VTH 2 ) 24 Penn ESE534 Spring2014 -- Mehta & DeHon Linear Region • (Vgs>VTH) • (Vds < (Vgs-VTH)) Ids,lin=(mCOX)(W/L)((Vgs-VTH)Vds-(Vds)2/2) 25 Penn ESE534 Spring2014 -- Mehta & DeHon Subthreshold Region • (Vgs<VTH) V V / S I I 10 gs TH sub VT S (ln( 10 )) kT / q [Frank, IBM J. R&D v46n2/3p235] 26 Penn ESE534 Spring2014 -- Mehta & DeHon Operating a Transistor • Concerned about Ion and Ioff • Ion drive (saturation) current for charging – Determines speed: Tgd = CV/I • Ioff leakage current – Determines leakage power/energy: • Pleak = V×Ileak • Eleak = V×Ileak×Tcycle 27 Penn ESE534 Spring2014 -- Mehta & DeHon Leakage • To avoid leakage want Ioff very small • Switch V from Vdd to 0 • Vgs in off state is 0 (Vgs<VTH) V V / S I I 10 gs TH sub VT V / S TH off VT I I 10 28 Penn ESE534 Spring2014 -- Mehta & DeHon Leakage V / S TH off VT I I 10 • • • • S90mV for single gate S70mV for double gate For lowest leakage, want S small, VTH large 4 orders of magnitude IVT/IoffVTH>280mV Leakage limits VTH in turn limits Vdd 29 Penn ESE534 Spring2014 -- Mehta & DeHon How maximize Ion/Ioff ? • Maximize Ion/Ioff – for given Vdd ? EswCV2 • Get to pick VTH, Vdd Id,sat=(mCOX/2)(W/L)(Vgs-VTH 2 ) Id,lin=(mCOX)(W/L)(Vgs-VTH)Vds-(Vds)2/2 V V / S I I 10 gs TH sub VT Penn ESE534 Spring2014 -- Mehta & DeHon 30 Preclass 2 • E = Esw + Eleak • Eleak = V×Ileak×Tcycle • EswCV2 V V / S I I 10 gs TH sub VT • Ichip-leak = Ndevices ×Itr-leak 31 Penn ESE534 Spring2014 -- Mehta & DeHon Preclass 2 • Eleak(V) ? • Tcycle(V)? 32 Penn ESE534 Spring2014 -- Mehta & DeHon In Class • Assign calculations – SIMD – each student computes for a different Voltage • Collect results on board • Group: Identify minimum energy point and discuss 33 Penn ESE534 Spring2014 -- Mehta & DeHon Graph for In Class 35 Penn ESE534 Spring2014 -- Mehta & DeHon Impact • Subthreshold slope prevents us from scaling voltage down arbitrarily. • Induces a minimum operating energy. 36 Penn ESE534 Spring2014 -- Mehta & DeHon Challenge: Variation 37 Penn ESE534 Spring2014 -- Mehta & DeHon Statistical Dopant Count and Placement 38 Penn ESE534 Spring2014 -- Mehta & DeHon [Bernstein et al, IBM JRD 2006] Vth Variability @ 65nm 39 Penn ESE534 Spring2014 -- Mehta & DeHon [Bernstein et al, IBM JRD 2006] Variation • Fewer dopants, atoms increasing Variation • How do we deal with variation? % variation in VTH (From ITRS prediction) 40 Penn ESE534 Spring2014 -- Mehta & DeHon 40 Impact of Variation? • Higher VTH? – Not drive as strongly slower – Id,sat (Vgs-VTH)2 • Lower VTH? – Not turn off as well leaks more V / S TH off VT I I 10 41 Penn ESE534 Spring2014 -- Mehta & DeHon Variation • Margin for expected variation • Must assume VTH can be any value in range Ion,min=Ion(Vth,max) Probability Distribution Id,sat (Vgs-VTH)2 Vgs = Vdd VTH 42 Penn ESE534 Spring2014 -- Mehta & DeHon Margining • Must raise Vdd to increase drive strength • Increase energy Ion,min=Ion(Vth,max) Probability Distribution Id,sat (Vgs-VTH)2 Vgs = Vdd VTH 43 Penn ESE534 Spring2014 -- Mehta & DeHon Variation • Increasing variation forces higher voltages – On top of our leakage limits 44 Penn ESE534 Spring2014 -- Mehta & DeHon 44 • Margins growing due to increasing variation Probability Distribution Variations Old New Delay • Margined value may be worse than older technology? 45 Penn ESE534 Spring2014 -- Mehta & DeHon End of Energy Scaling? Black nominal Grey with variation [Bol et al., IEEE TR VLSI Sys 17(10):1508—1519]46 Penn ESE534 Spring2014 -- Mehta & DeHon Chips Growing • Larger chips (billions of transistors) sample further out on distribution curve From: http://en.wikipedia.org/wiki/File:Standard_deviation_diagram.svg 47 Penn ESE534 Spring2014 -- Mehta & DeHon Big Ideas • Can trade time for energy – … area for energy • Variation and leakage limit voltage scaling • Power major limiter going forward – Can put more transistors on a chip than can switch • Continued scaling demands – Deal with noisier components • High variation • … other noise sources 48 Penn ESE534 Spring2014 -- Mehta & DeHon Admin • Homework 2 due Tonight • Reading for Monday on web • Homework 3 due next Wednesday 49 Penn ESE534 Spring2014 -- Mehta & DeHon