Search

Nowadays, the development of security applications is a relevant topic in the Internet of Things (IoT) and cyber-physical systems (CPS) fields. Different embedded architectures have been adopted in these areas, but the RISC-V parallel ultra-low-power (PULP) architecture stands out as a particularly efficient system. However, it has never been proposed to enable cryptography. In the context of video stream security, stream ciphers enable an efficient solution to ensure data privacy, and the exploitation of the PULP multi-core accelerator cluster paves the way to an efficient implementation of these ciphers. In this paper, we exploit the capability of the PULP architecture coupled with the code safety provided by the RUST programming language to design and implement an efficient stream encryption algorithm. We present a wrapper system between the development libraries of a PULP platform enabling the secure execution of a verified RUST-written implementation of ChaCha20 and AES-CTR, targeting a microdrones based video surveillance system. Experimental tests have resulted in an encryption efficiency of ChaCha20 of 2.3 cycles per Byte (cB), placing the resulting implementation at the state-of-the-art, in direct competition with higher-class architectures like Apple M1 (2.0 cB)., OASIcs, Vol. 107, 14th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 12th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2023), pages 3:1-3:12

This document means to provide detailed descriptions of all systems made available in-kind by partners in their supercomputing centers to the EUPEX project. Overall, 6 partners provide system resources in-kind. The availability of the in-kind pilot systems as first phase is key to define the require-ments for the Exascale pilot architecture and characteristics. Relying on representative application profile analysis and co-design studies performed on the in-kind systems, WP3 will provide valuable inputs to both WP4 and WP5 in order to specify the Pilot hardware and software components. Applications porting, optimization and scaling tests will be done on these systems made available in-kind, based on state-of-the-art ARM technologies, innovative inter-connect, optionally connected to accelerated modules. Some systems although not based upon ARM, offer interesting features, which are exposed. In chapter 2, " In-kind resources as first stage towards the pilots for EUPEX partners", the key role of in-kind systems in the timeline project is reminded, as “beta” pilot sys-tems design (see figure 1), needs application and software stack requirements input. Phases of In-kind systems presentation and their role in the project are described. The descriptions given in chapter 3 “In-Kind systems for EUPEX project” cover hard-ware and software aspects, architecture, software ecosystem, integration and data or-ganisation, services, types and amount of resources available for the EUPEX project, explanation on process to get access (including security and authentication con-straints), and resources grant process. On top of this, two partners also provide OpenStack partitions and Gitlab services as in-kind contribution. These systems will provide annex support for EUPEX activities (cf. Section 4). IT4Innovations’s will provide GitLab services CEA’s OpenStack partition will host the OCEAN code repository as well as the EUPEX-internal ticketing system Users of EUPEX in-kind systems, mainly from WP3 and WP5, will find in this document a hand-book to identify the outcomes targeted for their assessment activities for co-design, and all the information to obtain resources and access.&nbsp

Modern scientific discoveries are driven by an unsatisfiable demand for computational resources. To solve large problems in science, engineering, and business, data centers provide High-Performance Computing (HPC) systems with aggregation of the computing capacity of thousand of computing nodes. Anomaly prediction is critical in order to preserve the continuity of the service of HPC systems and prevent hardware deterioration. In the datacenter, a thermal anomaly occurs when the balance of cooling capacity and computational demand is disturbed. Moreover, this is identifiable from a suspicious/abnormal pattern in the monitoring signals. In this poster, the anomaly prediction task in the HPC systems is investigated by defining complex statistical rules-based and Deep Learning DL-based anomaly detection methods, then utilizing these anomaly detection methods in an anomaly prediction framework.