RECIPE (REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems) is a new FETHPC-02-2017 - Transition to Exascale Computing - project lead by Politecnico di Milano – Dipartimento di Elettronica, Informazione e Bioingegneria. The Project Coordinator is prof. William Fornaciari, the Project Technical Manager is prof. Giovanni Agosta and the duration is 36 months: May 2018 - April 2021.

RECIPE, in addition to other running projects of the HEAP Lab (M2DC, MANGO) contributes to positioning of POLIMI as one of the biggest cluster of projects on HPC/Exascale computing in Europe.

RECIPE provides: a hierarchical runtime resource management infrastructure optimizing energy efficiency and minimizing 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. A number of goals have been identified, the more relevant are: increase in energy efficiency (performance/watt) of 25% with an improvement of 15% of MTTF due to proactive thermal management; energy-delay product improved up to 25%; 20% reduction of occurring in fault executions with recovery times compatible to real-time performance and full exploitation of available resources under non-saturated conditions.

The consortium is aggregating some of the most important players in Europe: POLIMI is providing expertise on resource management and programming models as well as scientific coordination; EPFL, the leading provider of thermal models for HPC; UPV, one of the key innovators in optimized interconnection networks, and CeRICT, providing expertise on accelerators; as well as two supercomputing centers: BSC, one of the leading HPC providers in Europe with the MareNostrum, classed 13th in the Top 500 in June 2017, and PSNC, another Top 500 HPC center in Poland; a research hospital from Switzerland, CHUV, and an SME active in product design and development, IBTS, which provide effective exploitation avenues through industry-based use cases.