Quality programmable vector processors for approximate computing

Venkataramani, Swagath; Chippa, Vinay K.; Chakradhar, Srimat; Roy, Kaushik; Raghunathan, Anand

doi:10.1145/2540708.2540710

Cited by 218 publications

(118 citation statements)

References 21 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…To exploit the capabilities of architectures that have variable-precision floating point units [40,56,120,121], we now present Chisel's analysis that unifies reasoning about reliability and accuracy. Specifically, we extend reliability predicates with the ability to characterize the difference in a the values of variables between the kernel's exact and approximate executions.…”

Section: Accuracy Constraint Constructionmentioning

confidence: 99%

Accuracy-aware optimization of approximate programs

Misailovíc¹

2015

2015 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (CASES)

View full text Add to dashboard Cite

Many modern applications (such as multimedia processing, machine learning, and big-data analytics) exhibit a natural tradeoff between the accuracy of the results they produce and the application's execution time or energy consumption. These applications allow us to investigate new, more aggressive optimization approaches.This dissertation presents a foundation of program optimization systems that expose and profitably exploit tradeoffs between the accuracy of the results that the program produces and the time and energy required to produce those results. These systems apply accuracy-aware program transformations that intentionally change the semantics of optimized programs.A key challenge to applying accuracy-aware transformations is understanding the uncertainty that the transformations introduce into the program's execution. To address this challenge, this dissertation presents program analysis techniques that quantify the uncertainty introduced by program transformations. First, this dissertation identifies the properties of subcomputations that are amenable to loop perforation (an accuracy-aware transformation that skips loop iterations). Second, it presents how static analysis can derive expressions that characterize the frequency and magnitude of errors. Third, it presents a system that automatically applies accuracy-aware transformations by formulating accuracy-

show abstract

Section: Accuracy Constraint Constructionmentioning

confidence: 99%

Accuracy-aware optimization of approximate programs

Misailovíc¹

2015

2015 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (CASES)

View full text Add to dashboard Cite

show abstract

“…The work in [20] proposes such instruction-set and microarchitecture extensions that enable operation-level precision scaling for energy savings in a computation-oriented vector processor. In all of these cases, however, source-or binary-level annotations have to be manually determined by the programmer using other optimization techniques.…”

Section: Related Workmentioning

confidence: 99%

“…Approximate computing generally exploits tradeoffs between computational complexity and energy or performance at various levels ranging from algorithms to transistors. Recent work in this area has been focused on precision-scalable software realizations on general-purpose programmable approximate processors [19,20]. Similar to traditional fixed-point hardware design, word length of computations in the underlying hardware is thereby flexibly controlled through sourcelevel program annotations and instruction set extensions.…”

Section: Introductionmentioning

confidence: 99%

Fine Grain Precision Scaling for Datapath Approximations in Digital Signal Processing Systems

Lee

Gerstlauer

2015

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

“…Researchers have previously proposed multiple hardware architecture designs that improve the performance or energy consumption of processors by reducing precision or increasing the incidence of error [8,9,15,18,19,28,30,35,44,46,47]. Researchers have also proposed a variety of approximate DRAM and SRAM designs.…”

Section: Related Workmentioning

confidence: 99%

“…Motivated by the benefits available via relaxing stringent correctness and precision requirements, researchers have proposed a variety of approximate computing platforms [6,9,10,19,22,26,28,30,36,45,47]. Many of these platforms are populated with components that feature higher error rates and/or less accurate execution in return for reduced energy consumption and/or increased performance.…”

Section: Introductionmentioning

confidence: 99%

Approximate computation with outlier detection in Topaz

Achour

Rinard

2015

SIGPLAN Not.

View full text Add to dashboard Cite

We present Topaz, a new task-based language for computations that execute on approximate computing platforms that may occasionally produce arbitrarily inaccurate results. Topaz maps tasks onto the approximate hardware and integrates the generated results into the main computation. To prevent unacceptably inaccurate task results from corrupting the main computation, Topaz deploys a novel outlier detection mechanism that recognizes and precisely reexecutes outlier tasks. Outlier detection enables Topaz to work effectively with approximate hardware platforms that have complex fault characteristics, including platforms with bit pattern dependent faults (in which the presence of faults may depend on values stored in adjacent memory cells). Our experimental results show that, for our set of benchmark applications, outlier detection enables Topaz to deliver acceptably accurate results (less than 1% error) on our target approximate hardware platforms. Depending on the application and the hardware platform, the overall energy savings range from 5 to 13 percent. Without outlier detection, only one of the applications produces acceptably accurate results.

show abstract

Quality programmable vector processors for approximate computing

Cited by 218 publications

References 21 publications

Accuracy-aware optimization of approximate programs

Accuracy-aware optimization of approximate programs

Fine Grain Precision Scaling for Datapath Approximations in Digital Signal Processing Systems

Approximate computation with outlier detection in Topaz

Contact Info

Product

Resources

About