Giovanni Agosta interviewed by The Next Platform web TV - RECIPE
10 luglio 2020
Sommario
Prof. Giovanni Agosta interviewed (as Technical Manager) by The Next Platform web TV to discuss the RECIPE project in Europe, which is aimed at hyper-efficient exascale computing.
RECIPE (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems) provides a hierarchical runtime resource management infrastructure to optimise energy efficiency and minimise the occurrence of thermal hotspots, while enforcing the time constraints imposed by the applications, and ensuring reliability for both time-critical and throughput-oriented computation.
The main goals are:
RECIPE, together with M2DC and MANGO, is one of the main current European projects on HPC/Exascale computing. Some of the most important players in Europe are part of RECIPE’s consortium: Politecnico di Milano provides expertise on resource management and programming models as well as scientific coordination.
The interview is available at: https://youtu.be/SEuHZxlV7a8
RECIPE (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems) provides a hierarchical runtime resource management infrastructure to optimise energy efficiency and minimise the occurrence of thermal hotspots, while enforcing the time constraints imposed by the applications, and ensuring reliability for both time-critical and throughput-oriented computation.
The main goals are:
- To increase the energy efficiency (performance/watt) of 25% with an improvement of 15% of Mean Time To Failure due to proactive thermal management; energy-delay product improved up to 25%;
- To reduce the occurrence of fault executions by 20% with recovery times compatible to real-time performance and full exploitation of available resources under non-saturated conditions.
RECIPE, together with M2DC and MANGO, is one of the main current European projects on HPC/Exascale computing. Some of the most important players in Europe are part of RECIPE’s consortium: Politecnico di Milano provides expertise on resource management and programming models as well as scientific coordination.
The interview is available at: https://youtu.be/SEuHZxlV7a8