Special Issue on Advancing on Approximate Computing: Methodologies, Architectures and Algorithms
摘要截稿:
全文截稿: 2020-01-13
影响因子: 6.125
期刊难度:
CCF分类: C类
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 计算机:理论方法 - 1区
Overview
In the modern computing era, characterized by saturated performance and high production costs, Approximate Computing has been representing the most attractive breakthrough for efficient system design. Such an innovative paradigm leverages the intrinsic error resilience of applications to inaccuracy in their inner calculations, in order to trade output result quality, under a certain maximum acceptable error threshold, off for system performance gain, such as calculation time and power demanding. In particular, for audio, image and video processing, data mining and information retrieval, approximate results turn out hard to distinguish from perfect ones, while their computation is less expensive. In recent years, Approximate Computing applicability is broadening in many scientific areas since suitable solutions come from approximate arithmetic operators, implemented both at hardware and software level, but from unreliable memory architectures, integrated circuit test, compilers and many others too.
The special issue on "Advancing on Approximate Computing: Methodologies, Architectures and Algorithms" seeks for original contributions about the Approximate Computing paradigm; main areas of interest include, but are not limited to, the following:
Modeling, specification, and verification of approximate circuits and systems
Test and fault tolerance of approximate circuits and systems
Dependability of approximate circuits and systems
Error Resilient Near-Threshold Computing
Computing on unreliable hardware
Approximation induced error modeling and propagation
On-line test, monitoring and reconfiguration of approximate circuits and systems
Applications and case studies
Software-based fault tolerant technique for approximate computing