Optimo: A 65Nm 270Mhz 143.2Mw Programmable Spatial-Array-Processor With A Hierarchical Multi-Cast On-Chip Network For Solving Distributed Optimizations
暂无分享,去创建一个
This paper presents OPTIMO, a 65nm, 16-b, fully-programmable, spatial-array processor with 49-cores and a hierarchical multi-cast network for solving distributed optimizations. We demonstrate six template algorithms and their applications and measure a peak energy-efficiency of 0.279 TOPS/W.
[1] Stephen P. Boyd,et al. Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..