Approximate computing paradigm provides methods to optimize algorithms with considering both computational accuracy and complexity. This paradigm can be exploited at different levels of abstraction, from technological to application levels. Approximate computing at algorithm level aims at reducing computational complexity by approximating or skipping block functions of the computation. Numerous applications in the signal and image processing domain integrate algorithms based on discrete optimization techniques. These techniques minimize a cost function by exploring the search space. In this paper, a new approach is proposed to exploit the computation-skipping approximate computing concept by using the Smart Search Space Reduction (SSSR) technique. SSSR enables early selection of the best candidate configurations to reduce the search space. An efficient SSSR technique adjusts configuration selectivity to reduce execution complexity while selecting the most suitable functions to skip. The High Efficiency Video Coding (HEVC) encoder in All Intra (AI) profile is used as a case study to illustrate the benefits of SSSR. In this application, two functions use discrete optimization to explore different solutions and select the one leading to the minimal cost in terms of bitrate/quality and computational energy: coding-tree partitioning and intra-mode prediction. By applying SSSR to this use case, energy reductions from 20% to 70% are explored through Pareto in Rate-Energy space.
Embedded applications integrate more and more sophisticated computations. These computations are generally a composition of elementary functions and can easily be approximated by polynomials. Indeed, polynomial approximation methods allow to find a trade-off between accuracy and computation time. Software implementation of polynomial approximation in fixed-point processors is considered. To obtain a moderate approximation error, segmentation of the interval I on which the function is computed, is necessary. This paper presents a method to compute the values of a function on I using non-uniform segmentation, and polynomial approximation. Nonuniform segmentation allows to minimize the number of segments created and is modeled by a tree-structure. The specifications of the segmentation set the balance between memory space requirement and computation time. The method is illustrated with the function (− log(x)) on the interval [2 −5 ; 2 0 ] and showed a speed-up mean of 97.7 compared to the use of the library libm on the Digital Signal Processor C55x.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.