ExaNoDe – European Exascale Processor Memory Node Design

ExaNoDe – European Exascale Processor Memory Node Design (Booth: EP 6)

Contact: Denis Dutoit


Commissariat à l’énergie atomique et aux énergies alternatives
MINATEC Campus 17 rue des martyrs
38054 Grenoble
France

Tel: +33 4 38 78 62 58
Fax:

ExaNoDe – European Exascale Processor Memory Node Design

E-Mail: denis.dutoit@cea.fr
Website: http://exanode.eu

ExaNoDe is a collaborative European project within the “Horizon 2020 Framework Programme”, that investigates, develops and designs a highly efficient, highly integrated, high-performance, heterogeneous compute element enabling exascale computing and demonstrated using hardware-emulated interconnect. It is addressing these important challenges through the coordinated application of several innovative solutions recently deployed by European initiatives for scalable computing: ARM-v8 low-power processors for energy efficiency, 3D interposer integration for compute density and UNIMEM advanced memory scheme for low-latency, high-bandwidth memory access, scalable to Exabyte levels.

The ExaNoDe compute element aims towards exascale compute goals through:

-          Integration of low-power processors and accelerators across scalar, SIMD, GPGPU and FPGA processing elements in the deployment of associated 3D integration technologies and in the mechanical requirements to enable the development of a high-density, high-performance integrated compute element with advanced thermal characteristics and connectivity to the next generation of system interconnect and storage;

-          Undertaking essential research to ensure the ExaNoDe compute element provides necessary support of HPC applications including I/O and storage virtualization techniques, operating system and semantically aware runtime capabilities and PGAS, OpenMP and MPI paradigms;

-          The development of an instantiation of a hardware emulation of interconnect to enable the evaluation of UNIMEM for the deployment of multiple compute elements and the evaluation, tuning and analysis of HPC mini-apps.