Learning to approximate computing at run-time
Learning to approximate computing at run-time
复制标题
DOI：
10.1049/cp.2017.0361
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Paulo Garcia;Mehryar Emambakhsh;A. Wallace
中科院分区：
文献类型：
--
作者：
Paulo Garcia;Mehryar Emambakhsh;A. Wallace
智能传感器/信号处理系统越来越受到电力预算的限制，特别是在移动/远程环境中部署时。近似计算是一种自适应地降低系统输出准确性的过程，目的是为了获得其他指标（如功耗或内存使用）的更高性能，从而使应用程序能够适应不准确的计算。然而，它通常是静态实现的，基于启发式和测试循环，这可以防止在运行时在不同的近似之间切换。这限制了近似的通用性，并导致系统对特定输入数据的近似不足或过度近似，分别导致过度的功率使用和/或精度不足。为了避免这些问题，本文提出了一种新的近似计算方法，通过引入嵌入运行时数据先验知识的监督块。目标系统（即信号处理管道）是用可配置的水平和近似类型[1]实现的。监督器对目标系统处理的数据进行分析，并动态更新逼近，利用先验知识对计算结果的准确性建立置信度度量。此外，通过迭代评估输出，监督块可以学习并随后更新可调参数，以提高结果的质量。我们详细介绍并评估了这种方法在计算机视觉中的跟踪问题。结果表明，我们的方法在精度和功耗之间取得了很好的平衡，在我们的案例研究中实现了2.54%的节能。
Intelligent sensor/signal processing systems are increasingly constrained by tight power budgets, especially when deployed in mobile/remote environments. Approximate computing is the process of adaptively compromising the accuracy of a system's output in order to obtain higher performance for other metrics, such as power consumption or memory usage, for applications resilient to inaccurate computations. It is, however, usually statically implemented, based on heuristics and testing loops, which prevents switching between different approximations at run-time. This limits approximation versatility and results in under- or over-approximated systems for the specific input data, causing excessive power usage and/or insufficient accuracy, respectively. To avoid these issues, this paper proposes a new approximate computing approach by introducing a supervisor block embedding prior knowledge about runtime data. The target system (i.e., signal processing pipeline) is implemented with configurable levels and types of approximations [1]. Data processed by the target system is analysed by the supervisor and the approximation is updated dynamically, by using prior knowledge to establish a confidence measure on the accuracy of the computed results. Moreover, by iteratively evaluating the output, the supervisor block can learn and subsequently update tunable parameters, to improve the quality of the results. We detail and evaluate this approach for tracking problem in computer vision. Results show our approach yields promising trade-offs between accuracy and power consumption, achieving 2.54% energy saving for our case study.