Performance–Power Tradeoffs in Parallel Applications
A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "F: Electrical Engineering".
Deadline for manuscript submissions: closed (28 February 2022) | Viewed by 9187
Special Issue Editors
Interests: parallel and distributed computing; power-aware computing; interconnection networks; high-performance computing
Special Issue Information
Dear Colleagues,
Power consumption management is becoming a critical factor in the design of applications and computing systems. In current supercomputers and data centers, the energy cost is quickly going to overcome the cost of the physical system itself, and the end of Dennard Scaling and Moore’s Law is further exacerbating the problem.
More important, besides economic considerations, power consumption has a considerable impact on the environment since the CO2 emissions of data centers are on par with those of entire countries or worldwide airline industries.
For these reasons, researchers and developers have started to consider energy efficiency, not only computing performance, as one of the key metrics to assess the quality of their applications and systems.
The goal of this Special Issue is to gather innovative contributions describing problems and solutions in managing the tradeoffs between performance, power consumption, and energy efficiency in parallel and HPC applications.
Topics of interest include (but are not limited to) the following:
- Software-driven management of power consumption:
- energy measurement tools;
- dynamic voltage and frequency scaling (DVFS);
- clock modulation;
- thread packing;
- thread placement on both homogeneous and heterogenous CPUs;
- concurrency throttling;
- concurrency control;
- power and performance modeling;
- hard-disk power-management techniques;
- power-efficient interconnection networks and network interfaces;
- approximate computing
- High-level programming APIs for specifying energy/performance requirements:
- domain-specific languages;
- new user libraries/frameworks;
- customization of existing frameworks (e.g., OpenMP, MPI)
- Large-scale power management techniques and tools:
- operating system support for power-management;
- power shifting;
- job schedulers;
- interactions between power capping and fault tolerance;
- power-efficient allocation policies
- Architectures and Technology for high-performance energy-efficient computing:
- improvement of energy efficiency of HPC or data center applications with GPU, FPGAs or other devices;
- reconfigurable hardware, dataflow architecture, custom/novel architectures for energy efficiency;
- energy assessment of specialized hardware/domain-specific architecture
Dr. Daniele De Sensi
Dr. Tiziano De Matteis
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Energies is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- power-aware computing
- energy efficiency
- parallel computing
- autonomic computing
- energy-efficient architectures
