Preprint

FZJ-2019-00785

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png The DEEP-ER project: I/O and resiliency extensions for the Cluster-Booster architecture

Kreuzer, A.FZJ* ; Amaya, J. ; Leger, R. ; Eicker, N.FZJ* ; Suarez, E. (Corresponding author)FZJ*

2018

Please use a persistent id in citations: http://hdl.handle.net/2128/21412

Abstract: The recently completed research project DEEP-ER has developed a variety of hardware and software technologies to improve the I/O capabilities of next generation high-performance computers, and to enable applications recovering from the larger hardware failure rates expected on these machines.The heterogeneous Cluster-Booster architecture – first introduced in the predecessor DEEP project – has been extended by a multi-level memory hierarchy employing non-volatile and network-attached memory devices. Based on this hardware infrastructure, an I/O and resiliency software stack has been implemented combining and extending well established libraries and software tools, and sticking to standard user-interfaces. Realworld scientific codes have tested the projects’ developments and demonstrated the improvements achieved without compromising the portability of the applications.

Note: Presented in Conference HPCC 2018. Publication accepted for the Proceedings HPCC 2018 but not yet online.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 513 - Supercomputer Facility (POF3-513) (POF3-513)
2. DEEP - Dynamical Exascale Entry Platform (287530) (287530)
3. DEEP-ER - DEEP Extended Reach (610476) (610476)
4. DEEP-EST - DEEP - Extreme Scale Technologies (754304) (754304)

Appears in the scientific report 2018

---

Database coverage:

---