The high-performance computing (HPC) community is working diligently towards building, supporting and using exascale supercomputers. However, while considerable progress has been made in systems software – including programming models and runtime systems – in providing more transparent support for large-scale deployments, there is a long way to go in terms of providing highly efficient, generic and portable support. In particular, there is no available integrated ecosystem of programming environment components targeting highly productive exascale programming that can exploit the full power of emerging hardware.
This is where EPEEC comes in. The project consortium will significantly advance and integrate existing state-of-the-art components based on European technology (programming models, runtime systems, and tools) with key features enabling three overarching objectives: high coding productivity, high performance, and energy awareness.
How We Use the Huge Performance of Supercomputers
Our part in the EPEEC project, in which we are a partner, will be the implementation of the distributed programming model GASPI along with its GPI implementation. GPI is a critical component that enables EPEEC to combat the exascale.
»Given the imminent arrival of exascale supercomputers, we want to make harness the huge performance of these machines with GPI. We are happy to work with our European partners on solution for large-scale simulators leading to the discovery of new drugs or actually doing rocket science« says Valeria Bartsch, our expert from the Competence Center High Performance Computing, who heads our work for the EPEEC.
Fraunhofer Institute for Industrial Mathematics ITWM