Posted: 27 Jun 2013
Tagged: Green500
Balaji Subramaniam took point on our annual analysis of the Green500 this year, and reached out to Winston Saunders to include the Exascalar metric and draw some new conclusions based on the list.
Abstract:
A recent study shows that computation per kilowatt-hour has doubled every 1.57 years, akin to Moore’s Law. While this trend is encouraging, its implications to high-performance computing (HPC) are not yet clear. For instance, DARPA’s target of a 20-MW exaflop system will require a 56.8-fold performance improvement with only a 2.4-fold increase in power consumption, which seems unachievable in light of the above trend. To provide a more comprehensive perspective, we analyze current trends in energy efficiency from the Green500 and project expectations for the near future.
Specifically, we first provide an analysis of energy efficiency trends in HPC systems from the Green500. We then model and forecast the energy efficiency of future HPC systems. Next, we present \textit{exascalar} – a holistic metric to measure the distance from the exaflop goal. Finally, we discuss our efforts to standardize power measurement methodologies in order to provide the community with reliable and accurate efficiency data.
BibTex:@INPROCEEDINGS{6604520,
author={Subramaniam, B. and Saunders, W. and Scogland, T. and Wu-chun Feng},
booktitle={Green Computing Conference (IGCC), 2013 International},
title={Trends in energy-efficient computing: A perspective from the Green500},
year={2013},
pages={1-8},
keywords={energy conservation;green computing;parallel processing;power aware computing;DARPA;Green500;HPC systems;energy efficiency;energy-efficient computing;exaflop goal;exascalar;high-performance computing;holistic metric;Computers;Green products;Lead},
doi={10.1109/IGCC.2013.6604520},}