Integrate thermal-aware platform design, thermal control with workload management and shaping in a distributed, multi-scale strategy, to achieve the highest performance compatible with temperature constraints.
The development of a synergistic performance, power and thermal management strategy requires major breakthrough in several areas, namely architectures, run-time systems, resource management middleware, code optimization tools and programming models.
Bring together techniques from computer architecture and circuits, control theory, combinatorial and continuous optimization, statistical model-building and artificial intelligence. Results will be demonstrated on of physical and virtual prototypes, proving practical applicability and relevance for industrial applications.
Start 1st April 2012 – Duration 60 months
NEWS
Best PhD Presentation @WEEE 2014
Poster Title: Monitoring and Resource Management Techniques for Energy Eciency in Supercomputer Environments Francesco Fraternali has been awarded with the Best PhD Presentation Award sponsored…
Award: IEEE/ACM Design Automation and Test in Europe (DATE) Best IP Award 2014 – Best IP of the Day: Thursday, March 27, 2014
Multitherman ERC Advance researchers won the Best IP Award of the day @ DATE 2014 Conference. Multitherman together with CEA-LETI has proposed a novel technique…
Multitherman won the TT award Hipeac 2013
Andrea Bartolini, “Advance Energy/Thermal control techniques for supercomputer operating cost reduction” with CINECA (winner of HiPEAC 2013 technology transfer awards http://www.hipeac.net/content/hipeac-technology-transfer-awards )
Multitherman winner of HiPEAC Paper Award – 2013
Pietro Mercati, Andrea Bartolini, Francesco Paterna, Tajana Simunic Rosing,Luca Benini, “Workload and user experience-aware dynamic reliability management in multicore processors” (winner of HiPEAC Paper Award…
NVIDIA POSTER AWARD @ 8th HiPEAC conference
Daniele Bortolotti, Andrea Bartolini, Luca Benini poster title “An Ambient Temperature Variation Tolerance Scheme for ULP Shared-memory processor Cluster” presented at 8th HiPEAC conference, Berlin…
Comments are closed, but trackbacks and pingbacks are open.