EnerJApproximate Data Typesfor Safe and GeneralLow-Power ComputationAdrian SampsonWerner DietlEmily FortunaDanushen GnanapragasamLuis CezeDan Grossman

sa paPLDI 2011University of Washington

photo: Apple, Inc.

photo: Robert Scoble (CC BY 2.0)

photo: Rob Van De Pavert (CC BY-NC-SA 2.0)

EnerJ:Save energyusing programmer controlsover execution correctness.

Perfect correctness is not required

information retrieval

machine learning

sensory data

scientific computing

physical simulation

games

augmented reality

computer vision

Anant Agarwal, Martin Rinard, Stelios Sidiroglou, Sasa Misailovic, and Henry Hoffmann. Using code perforation to improve performance, reduce energy consumption, and respond to failures. Technical report, MIT, 2009.

[1]

B.E.S. Akgul, L.N. Chakrapani, P. Korkmaz, and K.V. Palem. Probabilistic CMOS technology: A survey and future directions. In IFIP Intl. Conference on VLSI, 2006.

[2]

M. de Kruijf and K. Sankaralingam. Exploring the synergy of emerging workloads and silicon reliability trends. In SELSE, 2009.

[3]

Larkhoon Leem, Hyungmin Cho, Jason Bau, Quinn A. Jacobson, and Subhasish Mitra. ERSA: Error resilient system architecture for probabilistic applications. In DATE, 2010.

[4]

Xuanhua Li and Donald Yeung. Exploiting soft computing for increased fault tolerance. In ASGI, 2006.

[5]

Song Liu, Karthik Pattabiraman, Thomas Moscibroda, and Benjamin G. Zorn. Flicker: Saving refresh-power in mobile devices through critical data partitioning. Technical Report MSR-TR-2009-138, Microsoft Research, 2009.

[6]

Sriram Narayanan, John Sartori, Rakesh Kumar, and Douglas L. Jones. Scalable stochastic processors. In DATE, 2010.

[7]

Vicky Wong and Mark Horowitz. Soft error resilience of probabilistic inference applications. In SELSE, 2006.

[8]

StorageAND

NOR

NAND

Logic Algorithms

λ

EnerJ

FlikkerASPLOS 2011

Kinds of imprecision

RelaxISCA 2010

GreenPLDI 2010

GeneralityA range of approximation strategiessupported with a single abstraction.

Critical Non-Critical

error-sensitive error-resilient

references

jump targets

JPEG header

pixel data

neuron weights

audio samples

video frames

Critical Non-Critical

error-sensitive error-resilient

✓✗

references

jump targets

JPEG header

pixel data

neuron weights

audio samples

video frames

SafetySeparate critical and non-criticalprogram components.

GeneralityA range of approximation strategiessupported with a single abstraction.

Java language extensionusing type annotations

Proposed approximate hardware

Potential energy savingsin existing Java programs

Java language extensionusing type annotations

Proposed approximate hardware

Potential energy savingsin existing Java programs

Java language extensionusing type annotations

Type qualifiers: @Approx @Precise&

Endorsement

Operator overloading

Prevention of implicit flows

Objects: qualifier polymorphism

✓✗

int a = ...;

int p = ...;

@Approx

@Precise

p = a;

a = p;

Type qualifiers

endorse( )✓✗

int a = expensiveCalc();

int p;

@Approx

@Precise

p = a;

Endorsement: escape hatch

quickChecksum(p);

output(p);

int a = ...;

int p = ...;

@Approx

@Precise

p + p;

p + a;

a + a;

+ : @Precise int, @Precise int → @Precise int

+ : @Approx int, @Approx int → @Approx int

Logic approximation: overloading

✗

int a = ...;

int p = ...;

@Approx

@Precise

if ( p = 2;}

a == 10) {

Control flow

✓int a = ...;

int p = ...;

@Approx

@Precise

if ( p = 2;}

a == 10 ) {endorse( )

Control flow

float mean() { calculate mean }

float[] nums = ...;class FloatSet {

new @Approx FloatSet()

new @Precise FloatSet()

}

Objects

float mean() { calculate mean }

float[] nums = ...;class FloatSet {

@Context

}

Objects

float mean() { calculate mean }

float[] nums = ...;class FloatSet {

@Context

}

@Approx float mean_APPROX() { take mean of first ½}

@Approx FloatSet someSet = ...;someSet.mean();

Java language extensionusing type annotations

Proposed approximate hardware

Potential energy savingsin existing Java programs

StorageAND

NOR

NAND

Logic Algorithms

λ

EnerJ

Hypothetical hardware

CPU

Hypothetical hardware

Memory

Registers Functional Units

Data Cache

Lower SRAM supply voltageLower DRAM refresh rate

Reduced VDD

Smaller FP mantissa

Java language extensionusing type annotations

Proposed approximate hardware

Potential energy savingsin existing Java programs

0%

25%

50%

75%

100%

FFT SOR MonteCarlo SMM LU ZXing jME ImageJ Raytracer

33%34%

19%

4%

23%

14%20%

25%

33%

Annotated declarations

SciMark2 algorithms other kernelsfull application

Annotations are sparse & straightforward to insert

0%

25%

50%

75%

100%

FFT SOR MonteCarlo SMM LU ZXing jME ImageJ Raytracer

Base Mild Medium Aggressive

Total energy used

Saved 10%—50% of total execution energy

(in simulation)

0%

25%

50%

75%

100%

FFT SOR MonteCarlo SMM LU ZXing jME ImageJ Raytracer

Base Mild Medium Aggressive

Quality-of-service tradeoff: output error

“Mild” configuration is a good fit for all

Some applications can tolerate more approximation

Also in the paper:

Formal semantics

Noninterference claim

Object layout

Hardware model

Quality-of-service metrics

EnerJ:Save energyusing programmer controlsover execution correctness.