DVFS-aware application classification to improve GPGPUs energy efficiency

Parallel Computing(2019)

引用 29|浏览71
暂无评分
摘要
•Exploring the effects of core and memory DVFS on the execution of GPU applications.•GPU characterization scheme validated on multiple GPU devices.•Classes of applications that characterize the impact of DVFS on their execution.•Average energy-savings of 20%, versus highest performance scenario.•Identification of situations with 20% energy-savings with 1% performance trade-off.
更多
查看译文
关键词
GPGPU,Application classification,DVFS,Optimal frequency,Energy savings
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