Exploiting computation skip to reduce energy consumption by approximate computing, an HEVC encoder case study

Abstract

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.

Approximation-Aware Design of an Image-Based Control System

“…To validate this claim, we consider strict power budgets of 5W and 15W in Sec. VII, which is common for edge devices 8 . For both these power budgets, the accurate setting (S0) results in LKAS failure due to long sampling period (see Fig.…”

“…Compute-centric approximations: Compute-centric efforts are focused on reducing the compute workload across algorithm, architecture and circuit-levels. Commonly used algorithmic approximations are computation skipping [8], precision scaling [9] and replacing error-resilient computeintensive functions with neural networks [10]. A similar learning approach to design ISPs for new camera systems is proposed in [11].…”

IMACS: A Framework for Performance Evaluation of Image Approximation in a Closed-loop System

“…Another case study, showing advantages of approximate computing in the domain of biometric security systems, targeting an iris scanning application is demonstrated in [13]. The impact of approximate computing on a high-efficiency video coding (HEVC) encoder is explored in [14] leading to considerable energy benefits that can enable the use of such encoders in ultra-low power applications such as in the Internet of Things (IoT) domain. Approximation of compute-intensive nonlinear model predictive control (NMPC) algorithms for deployment in low-power embedded systems is shown in [15].…”

Morphological Transformation In Poor Lighting Images For Image Contrast Enhancement

“…Justusson et al[5] discussed the use of estimated registering in equipment based PC vision. Receiving the ideas of versatile pressure and inexact quantization, C. Chen et al[6] proposed a picture sensor structure for PC vision undertakings that altogether moves the pixel organize scheme, sub sampled picture information that accomplish a significant decrease in vitality while keeping the classification exactness of regular DNN datasets, for example, the CIFAR-10, inside satisfactory levels. J. Baili et al[8] identified that assumed figuring can be used in spaces other than AI or picture preparing and showed a start to finish contextual investigation on the space of biometric security frameworks focusing on an iris checking application.…”