In order to reach exascale performance current HPC servers need to be improved. Simple scaling is not a feasible solution due to the increasing utility costs and power consumption limitations. Apart from improvements in implementation technology, what is needed is to refine the HPC application development as well as the architecture of the future HPC systems.
ECOSCALE tackles this challenge by employing a scalable programming environment and hardware architecture tailored to the characteristics and trends of current and future HPC applications, reducing significantly the data traffic as well as the energy consumption and delays. ECOSCALE follows a holistich approach providing a novel heterogeneous energy-efficient hierarchical architecture, a hybrid MPI+OpenCL programming environment and a runtime system. The ECOSCALE architecture, programming model and runtime system follows a hierarchical approach where the system is partitioned into multiple autonomous Workers (i.e. compute nodes). Workers are interconnected in a tree-like structure in order to form larger Partitioned Global Address Space (PGAS) partitions, which are further hierarchically interconnected via an MPI protocol.
To further increase the energy efficiency of the system as well as its resilience, the ECOSCALE Workers will employ reconfigurable accelerators that can perform coherent memory accesses in the virtual address space utilizing an IOMMU. The ECOSCALE architecture will support shared partitioned reconfigurable resources accessed by any Worker in a PGAS partition, and, more importantly, automated hardware synthesis of these resources from an OpenCL-based programming model.