arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.14729eess.SPcs.AR
收藏

利用迭代算法的错误弹性以提升能效:从概念到实现

Leveraging Error Resilience of Iterative Algorithms for Energy Efficiency: from Concept to Implementation

G. A. Gillani, A. Krapukhin, A. B. J. Kokkeler

AI总结:

本文面向射电天文校准等迭代信号处理,提出按精确/近似迭代划分的统计弹性分析方法和异构精确-近似核加速器,在不增加迭代次数的前提下实现23%能耗节省。

摘要:

迭代算法被广泛应用于数字信号处理场景。本文以射电天文校准处理为案例研究,致力于揭示并利用迭代算法的内在错误弹性以获得能效收益。我们考虑采用收敛准则作为质量度量来终止迭代计算的迭代方法。我们提出一种用于高层弹性分析的自适应统计近似模型,使将迭代算法划分为精确迭代与近似迭代成为可能。我们基于异构架构实现了一款高能效加速器,其中异构性通过精确与近似处理核引入。所提方法利用算法的错误弹性,让初始迭代在近似模块上处理,而后续迭代在精确模块上处理。与精确实现相比,所提加速器设计不会增加迭代次数,并能提供足够精度以收敛到可接受的解。我们采用 TSMC 40nm Low Power(TCBN40LP)工艺的实现显示,电能消耗降低了23%。

英文摘要:

Iterative algorithms are widely used in digital signal processing applications. With the case study of radio astronomy calibration processing, this work contributes towards revealing and exploiting the intrinsic error resilience of iterative algorithms for energy efficiency benefits. We consider iterative methods that use a convergence criterion as a quality metric to terminate the iterative computations. We propose an adaptive statistical approximation model for high-level resilience analysis that provides an opportunity to divide an iterative algorithm into exact and approximate iterations. We realize an energy-efficient accelerator based on a heterogeneous architecture, where the heterogeneity is introduced using accurate and approximate processing cores. Our proposed methodology exploits the error-resilience of the algorithm, where initial iterations are processed on approximate modules while the later ones on accurate modules. The proposed accelerator design does not increase the number of iterations as compared to that of an accurate counterpart and provides sufficient precision to converge to an acceptable solution. Our implementation using TSMC 40nm Low Power (TCBN40LP) technology shows 23% savings in electrical energy consumption.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑