Run-Time Technique for Simultaneous Aging and Power Optimization in GPGPUs
DAC（2014）
摘要
High-performance general-purpose graphics processing units (GPGPUs) may suffer from serious power and negative bias temperature instability (NBTI) problems. In this paper, we propose a framework for run-time aging and power optimization. Our technique is based on the observation that many GPGPU applications achieve optimal performance with only a portion of cores due to either bandwidth saturation or shared resource contention. During run-time, given the dynamically tracked NBTI-induced threshold voltage shift and the problem size of GPGPU applications, our algorithm returns the optimal number of cores using detailed performance modeling. The unused cores are power-gated for power saving and NBTI recovery. Experiments show that our proposed technique achieves on average 34% reduction in NBTI-induced threshold voltage shift and 19% power reduction, while the average performance degradation is less than 1%.
更多查看译文
关键词
parallel processing,power optimization,design,bandwidth saturation,power aware computing,high-performance general-purpose graphic processing units,power saving,shared resource contention,negative bias temperature instability problems,nbti recovery,graphics processing units,general-purpose graphics processing unit,single-instruction-stream, multiple-data-stream processors,multiprocessing systems,performance degradation,run-time aging,general-purpose graphics processing unit (gpgpu),performance modeling,performance evaluation,negative bias temperature instability,gpgpu applications,power,dynamically tracked nbti-induced threshold voltage shift,power-gated unused cores,negative bias temperature instability (nbti),performance,kernel,optimization,computational modeling,instruction sets,bandwidth,degradation
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要