Randomized accuracy-aware program transformations for efficient approximate computations

Zhu, Ziwei; Misailovíc, Saša; Kelner, Jonathan A.; Rinard, Martin

doi:10.1145/2103621.2103710

Cited by 35 publications

(43 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is important because 1) such exact shapes can be difficult for developers to identify and specify and 2) known tractable classes of probability distributions are not closed under many operations found in standard programming languages, which can complicate attempts to develop compositional program analyses that work with such exact shapes [27,43,65,72].…”

Section: Relymentioning

confidence: 99%

“…For approximate computations, quantitative reliability allows a developer to reify and verify the results of the fault injection and accuracy explorations that are typically used to identify the minimum acceptable reliability of a computation [43,44,68,72]. For checkable computations, quantitative reliability allows a developer to use the performance specifications of both the computation and its checker to determine the computation's overall performance given thatwith some probability -it may produce an incorrect answer and therefore needs to be reexecuted.…”

Section: Case Studiesmentioning

confidence: 99%

“…Dynamic techniques observe the accuracy impact of program transformations [1,2,29,41,42,44,59,60,62,68], or injected soft errors [20,37,38,64,70]. Researchers have developed static techniques that use probabilistic reasoning to characterize the accuracy impact of various phenomena [6,18,43,47,56,72]. And of course, the accuracy impact of the floating point approximation to real arithmetic has been extensively studied by numerical analysts [17].…”

Section: Accuracy Analysismentioning

confidence: 99%

See 2 more Smart Citations

Verifying quantitative reliability for programs that execute on unreliable hardware

Carbin¹,

Misailovíc²,

Rinard³

2013

SIGPLAN Not.

Self Cite

View full text Add to dashboard Cite

Emerging high-performance architectures are anticipated to contain unreliable components that may exhibit soft errors, which silently corrupt the results of computations. Full detection and masking of soft errors is challenging, expensive, and, for some applications, unnecessary. For example, approximate computing applications (such as multimedia processing, machine learning, and big data analytics) can often naturally tolerate soft errors.We present Rely, a programming language that enables developers to reason about the quantitative reliability of an application -namely, the probability that it produces the correct result when executed on unreliable hardware. Rely allows developers to specify the reliability requirements for each value that a function produces.We present a static quantitative reliability analysis that verifies quantitative requirements on the reliability of an application, enabling a developer to perform sound and verified reliability engineering. The analysis takes a Rely program with a reliability specification and a hardware specification that characterizes the reliability of the underlying hardware components and verifies that the program satisfies its reliability specification when executed on the underlying unreliable hardware platform. We demonstrate the application of quantitative reliability analysis on six computations implemented in Rely.

show abstract

Section: Relymentioning

confidence: 99%

Section: Case Studiesmentioning

confidence: 99%

Section: Accuracy Analysismentioning

confidence: 99%

See 1 more Smart Citation

Verifying quantitative reliability for programs that execute on unreliable hardware

Carbin¹,

Misailovíc²,

Rinard³

2013

SIGPLAN Not.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to these dynamic techniques, researchers have developed static program analyses for reasoning about programs transformed using accuracy-aware transformations [5,6,10,25,47], for verifying continuity of computations [9,10], and for verifying the precision of numerical computations [11]. Researchers have also developed techniques for reasoning about reducedbitwidth floating point computations [14,28].…”

Section: Related Workmentioning

confidence: 99%

“…Software Approximate Computation. Researchers have developed many systems that apply approximate computing techniques in software to reduce the amount of energy and/or time required to execute computations running on standard exact, reliable hardware platforms [20,24,25,32,33,40,47]. In Chisel, the source of the approximation is the hardware -Chisel synthesizes acceptably reliable and accurate software that executes on unreliable approximate hardware platforms.…”

Section: Related Workmentioning

confidence: 99%

Chisel

Misailovíc¹,

Carbin²,

Achour³

et al. 2014

Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages &Amp; Applications

Self Cite

View full text Add to dashboard Cite

The accuracy of an approximate computation is the distance between the result that the computation produces and the corresponding fully accurate result. The reliability of the computation is the probability that it will produce an acceptably accurate result. Emerging approximate hardware platforms provide approximate operations that, in return for reduced energy consumption and/or increased performance, exhibit reduced reliability and/or accuracy.We present Chisel, a system for reliability-and accuracyaware optimization of approximate computational kernels that run on approximate hardware platforms. Given a combined reliability and/or accuracy specification, Chisel automatically selects approximate kernel operations to synthesize an approximate computation that minimizes energy consumption while satisfying its reliability and accuracy specification.We evaluate Chisel on five applications from the image processing, scientific computing, and financial analysis domains. The experimental results show that our implemented optimization algorithm enables Chisel to optimize our set of benchmark kernels to obtain energy savings from 8.7% to 19.8% compared to the original (exact) kernel implementations while preserving important reliability guarantees.

show abstract

Certifying Solutions for Numerical Constraints

Darulová

Kunčak

2013

Runtime Verification

View full text Add to dashboard Cite

Abstract. A large portion of software is used for numerical computation in mathematics, physics and engineering. Among the aspects that make verification in this domain difficult is the need to quantify numerical errors, such as roundoff errors and errors due to the use of approximate numerical methods. Much of numerical software uses self-stabilizing iterative algorithms, for example, to find solutions of nonlinear equations.To support such algorithms, we present a runtime verification technique that checks, given a nonlinear equation and a tentative solution, whether this value is indeed a solution to within a specified precision. Our technique combines runtime verification approaches with information about the analytical equation being solved. It is independent of the algorithm used for finding the solution and is therefore applicable to a wide range of problems. We have implemented our technique for the Scala programming language using our affine arithmetic library and the macro facility of Scala 2.10.

show abstract

Randomized accuracy-aware program transformations for efficient approximate computations

Cited by 35 publications

References 37 publications

Verifying quantitative reliability for programs that execute on unreliable hardware

Verifying quantitative reliability for programs that execute on unreliable hardware

Chisel

Certifying Solutions for Numerical Constraints

Contact Info

Product

Resources

About