Categories
Events

SEA Minisymposium at CSE23

26 February-3 March 2023 – Amsterdam, Netherlands – The conference on Computational Science and Engineering (CSE) is run by the Society for Industrial and Applied Mathematics (SIAM). It seeks to enable in-depth technical discussions on a wide variety of major computational efforts on large-scale problems in science and engineering, foster the interdisciplinary culture required to […]

Categories
Publications

Building blocks for network-accelerated distributed file systems

Research paper by our partner ETHZ, accepted at the SC22 Conference  that took place online from 14 to 18 November 2022 in Dallas, TX, USA. This paper was produced in collaboration with DEEP-SEA and was a BEST PAPER FINALIST! Abstract High-performance clusters and datacenters pose increasingly demanding requirements on storage systems. If these systems do not operate at scale, […]

Categories
News

Congratulations to Torsten Hoefler ETHZ for his Sidney Fernbach award

Live from SC22: Pr Torsten Hoefler, director of the Scalable Parallel Computing Laboratory (SPCL) at ETH Zurich that is involved in our project, received the 2022 IEEE Computer Society Sidney Fernbach award. This award recognises Torsten’s outstanding contribution to application-aware design of HPC algorithms, systems and architectures, and trnasformative impact on scientific computing and industry. We are […]

Categories
Events

HiPEAC 2023

16-18 January 2023 – Toulouse, France – RED-SEA will be at the 2023 edition of the HiPEAC conference, together with the SEA projects: The SEA projects will have a shared booth. RED-SEA has been invited to talk in the CONCERTO workshop, a workshop on projeCts crOss-synergy iN advanCing Exascale platfoRms and quanTum cOmputing, organised by […]

Categories
Events

SC22 Conference

13-18 November 2022 – Dallas, TX, USA – RED-SEA will be at SC22! Come and meet us.

Categories
Publications

NeVerMore: Exploiting RDMA Mistakes in NVMe-oF Storage Applications

Research paper by our partner ETHZ, accepted at the ACM Conference on Computer and Communications Security (CCS)  that took place from 7 to 11 November 2022 in Los Angeles, CA, USA. Abstract This paper presents a security analysis of the InfiniBand architecture, a prevalent RDMA standard, and NVMe-over-Fabrics (NVMe-oF), a prominent protocol for industrial disaggregated storage […]

Categories
Events

ACM CCS 2022

7-11 November 2022 – Los Angeles, CA, USA – The ACM Conference on Computer and Communications Security (CCS) is the flagship annual conference of the Special Interest Group on Security, Audit and Control (SIGSAC) of the Association for Computing Machinery (ACM). A RED-SEA research paper prepared by ETHZ has been accepted: “NeVerMore: Exploiting RDMA Mistakes in NVMe-oF Storage […]

Categories
Blog

Extending ParaStation MPI by BXI Support

Authors: Simon Pickartz (ParTec), Carsten Clauss (ParTec) The ParaStation MPI communication stack is a central pillar of ParaStation Modulo. This is a comprehensive software suite especially designed for systems following the design principles of the Modular Supercomputing Architecture (MSA). It is the selected middleware powering the DEEP projects but is also extensively used in production […]

Categories
News

Two new RED-SEA deliverables available

The RED-SEA researchers have recently shared their findings in two project deliverables. Check our Results page! D2.3 RoCE and IPoverBXI Evaluation Report D4.3 Planned MPI-related optimizations You may also be interested in our latest blog post: Development of multirail feature in MPC for BXI interconnect.

Categories
Blog

Development of multirail feature in MPC for BXI interconnect

Authors: Gilles Moreau (CEA), Hugo Taboada (CEA), Marc Pérache (CEA) 1  Introduction Context Nowadays, HPC applications scale to several hundred nodes, and MPI has become the de facto standard for internode communication. It abstracts Point-to-Point (P2P) communication to the application developer while taking advantage of the underlying network. With ever increasing demand for bandwidth-oriented communications, […]