Towards Energy-Efficient Computing: Adaptive Management Strategies from Software to Systems
Event details
| Date | 01.07.2015 |
| Hour | 16:15 › 17:15 |
| Speaker | Bio: Ayse K. Coskun is an associate professor in the Electrical and Computer Engineering Department at Boston University. She received her MS and PhD degrees in Computer Science and Engineering from University of California, San Diego. Coskun’s research interests are energy-efficient computing, 3D-stacked architectures, embedded systems, and intelligent management of data centers. Prof. Coskun worked at Sun Microsystems (now Oracle), San Diego prior to her current position at BU. Coskun is a recipient of the NSF CAREER award. She currently serves as an associate editor for IEEE Embedded Systems Letters and writes a bi-monthly column on green computing at the Circuit Cellar magazine. |
| Location | |
| Category | Conferences - Seminars |
Energy efficiency is a central issue in all computing domains. In data centers, operational and cooling costs impose significant sustainability challenges. In tandem, computing systems run increasingly complex, highly performance demanding workloads, making the existing energy management policies inadequate. High power densities also increase the chip temperatures and thermal variations, which degrade system reliability, add to the system design complexity, and increase monetary cost of cooling.
Achieving the target exascale computing performance, and also, designing a sustainable cloud computing future require the design of dynamic and intelligent techniques that recognize the hardware-software characteristics and optimize the interplay among performance, energy, and temperature in an application-aware manner. This talk discusses how to design adaptive workload management and power modulation methods at server and at data center scale to help achieve a sustainable computing future. The talk includes techniques for integrating data centers into the emerging smart grid programs and touches upon some of the key data analytics challenges in computing systems.
Achieving the target exascale computing performance, and also, designing a sustainable cloud computing future require the design of dynamic and intelligent techniques that recognize the hardware-software characteristics and optimize the interplay among performance, energy, and temperature in an application-aware manner. This talk discusses how to design adaptive workload management and power modulation methods at server and at data center scale to help achieve a sustainable computing future. The talk includes techniques for integrating data centers into the emerging smart grid programs and touches upon some of the key data analytics challenges in computing systems.
Practical information
- General public
- Free
Organizer
- EE Institute
Contact
- suzanne.buffat@epfl.ch