Power and energy are now recognized as first-order constraints in high-performance computing. Optimizing performance under power and energy bounds requires coordination across not only the software stack (compilers, operating and runtime systems, job schedulers) but also coordination with cooling systems and outwards to electrical suppliers. As we continue to move towards exascale and extreme scale computing, understanding how power translates to performance becomes an increasingly critical problem.
The purpose of this workshop is to provide a forum where cutting-edge research in the above topic can be shared with others in the community. We welcome submissions addressing power aware computing issues. All papers will be subject to single-blind peer review, and the quality of standard papers is expected to be high.
Topics of particular interest include (but are not limited to):
Performance optimization under node, job, cluster and site power bounds
Power/performance tradeoffs across accelerators, processors and DRAM
Cooling/performance tradeoffs
Translating budgetary bounds into power and energy bounds.
Power-efficient system design, from computer center to silicon
Effects of compiler optimizations on application power and energy efficiency
Power- and energy-aware job schedulers, runtime systems and operating systems
Models of power and performance, from processors and components to computer centers
Evaluations of hardware power and energy controls
Applications specific power and energy optimization
05月29日
2017
会议日期
初稿截稿日期
初稿录用通知日期
终稿截稿日期
注册截止日期
留言