Logo Cineca Logo SCAI

You are here

ParCo 2017: Mini-Symposium on Energy Aware Scientific Computing on low power and heterogeneous architectures

ORGANIZERS:

  • Daniele Cesini (INFN – Italian Institute for Nuclear Physics)
  • Sebastiano Fabio Schifano (University of Ferrara)
  • Tommaso Boccali (INFN – Italian Institute for Nuclear Physics)
  • Piero Vicini (INFN – Italian Institute for Nuclear Physics)

 

SCOPE:

Energy consumption is increasingly becoming one of the most relevant issue for computing platforms for scientific applications and workloads. This has then required the use of energy-efficient processors, ranging from many-core architectures, like GP-GPU and Xeon-Phi, to Systems-on-Chip (SoCs). These processors feature a high performance-per-watt ratio, aimed on one side at energy efficiency, but requiring on the other side careful programming and optimization, to provide high level of computing performances. Also off-the-shelf low-power Systems-on-Chip, originally designed for the embedded and mobile market, are becoming attractive for scientific and industrial applications given their increasing computing performances, coupled with relatively low cost and power demand. Scientific computing and mobile/embedded sectors, historically very isolated and confined to specific markets, are now experiencing a convergence under the driving forces of high computational power demands, power consumption limitations and cost effectiveness.
This mini-symposium will provide a forum to discuss and share knowledge on developing, running and using computing systems based on low power, energy-efficient, and heterogeneous architectures. The main topics covered are (but not limited to):

  • building computing systems based on low power/low cost heterogeneous architectures, including off-the-shelf components
  • developing energy-aware scientific applications on heterogeneous systems
  • running scientific workflows on low power architectures
  • computing performance and costs evaluation of low power systems
  • low power architectures for scalable storage systems
  • artificial intelligence applications and neural network simulations on Systems-on-Chip

Paper publication:

All papers presented as part of mini-symposia will be considered for publication in the proceedings. This will be done in liaison with the organizer(s) of the respective mini-symposium.
Authors can submit a full paper of maximum 10 pages or an extended abstract of minimal 4 pages. The approved contributions will be presented at the conference and the accepted full papers are published in the ParCo proceedings. Details regarding the format, presentation and paper submission are given on the author guidelines page.

Important dates:

  • Jun 30, 2017: Submission deadline for extended abstracts or full paper
  • Jul 17, 2017: Notification of decision
  • Jul 30, 2017: Camera-ready of extended abstracts due
  • Sep 25th, 2017: Full paper submission
  • Oct 17th, 2017: Notification of full paper decision
  • Oct 27th, 2017: Full paper camera-ready due

Contact:

low-power-parco17 at  lists.cnaf.infn.it