HiPEAC 2023 Workshop

Wednesday, 18 January 2023 10:00 – 17:30

EVEREST + DAPHNE: Workshop on Design and Programming High-performance, distributed, reconfigurable and heterogeneous platforms for extreme-scale analytics

Organizers

Francesco Regazzoni, Univerisity of Amsterdam, The Netherlands and Università della Svizzera italiana, Switzerland
Christian Pilato, Politecnico di Milano, Italy
Jeronimo Castrillon, TU Dresden, Germany
Antonella Galizia, IMATI-CNR, italy and CIMA Foundation, Italy
 

Workshop Description

The heterogeneous and distributed nature of the data involved in extreme-scale analytics requires developing novel computing systems seamlessly combining HPC, edge, and IoT devices. Seamless integration is, however, not sufficient since the whole power of these computing systems can be unleashed only when the problem is ad- dressed holistically. i.e., when the computation and communication within the system are co-designed together and throughout the entire design flow. Indeed, this integration ultimately requires novel design approaches, necessary data-driven, and to give designers the tools needed to simplify the programmability of such heterogeneous and distributed architectures. To expose the HiPEAC community to the main results of the projects funded in the domain of new methodologies and solutions addressing challenges of extreme-scale analytics (ICT-12-2018-2020 and ICT-51-2020 H2020 calls), and to foster the exchange of ideas between all the involved stakeholders, we propose to organize a work-shop presenting relevant cases of study and the latest achievements in the field of design and co-design methods, domain-specific languages, high-level synth sis, computational frameworks, and workflow organization in high-performance platforms for extreme-scale analytics.

The workshop is organized by the EVEREST consortium (https://everest-h2020.eu) and the DAPHNE consor- tium (https://daphne-eu.eu/) and we involve interested projects funded under the ICT-12-2018-2020 and ICT-51-2020 H2020 calls. The workshop targets the large community of high-performance computing and big data analytics, going beyond the partners of the EVEREST and DAPHNE projects. Attendees will be exposed to the main challenges and opportunities in the domain, gather information on the recent research results achieved by the most recent collaborative projects financed by the H2020 framework, and have the possibility to exchange ideas and discuss open problems with academic and industrial stakeholders.

Workshop Program

10:00 – Opening: Welcome and Workshop Overview

Keynote session 1 (chair: Matthias Boehm TU Berlin)

  • Looking at Horizon 2020 ICT-51-2020 five years later, BERTOLO Stefano, EVEREST Project Officer Keynote

  • ICT projects in the frame of EU policies, PLAZZOTTA Beatrice, DAPHNE Project Officer Keynote

Keynote session 2 (chair Christian Pilato – Politecnico di Milano)

  • From projects to sustainable Data and AI ecosystems for value creation. Ana García Robles, Big Data Value Association

11:00 – 11:30 Coffee break

11:30 – 12:30 Project Introductions (chair Antonella Galizia – IMATI-CNR)

  • Bridging the gaps among application, hardware, and system designers: The EVEREST experience (20min, Christian Pilato, Politecnico di Milano)

  • Multimodal Extreme Scale Data Analytics for Smart Cities Environments (20min, George Hatzivasilis – FORTH)

  • DAPHNE Overview (20min, Matthias Boehm, TU Berlin)

12:30 – 13:00 EVEREST Deep Dive (chair Antonella Galizia – IMATI-CNR)

  • A modern HLS compilation flow for big data applications (15min, Serena Curzel, Politecnico di Milano)

  • Security Challenge in EVEREST (15min, Francesco Regazzoni, University of Amsterdam and Università della Svizzera italiana)

13:00 – 14:00 Buffet lunch

14:00 – 14:30 DAPHNE Deep Dive (chair Matthias Boehm, TU Berlin)

  • HPC Deployment / Use Cases (20min, Aleš Zamuda, Uni Maribor/EuroHPC)

  • Multi-level Scheduling (20min, Ahmed Hamdy Mohamed Eleliemy, Uni Basel)

14:30 – 15:30 Panel Synergies in collaborative projects on high performance computing for extreme-scale big data analytics

Moderator: Francesco Regazzoni, University of Amsterdam and Università della Svizzera italiana

Panelists:

  • Ana García Robles (Big Data Value Association)
  • Christian Pilato (Politecnico di Milano)
  • Matthias Boehm (TU Berlin)
  • George Hatzivasilis (FORTH)

15:30 – 16:00 Coffee break

16:00 – 16:45 Hands on and PhD students Pitch presentations

  • EVEREST PhD students Pitch presentations:
  1. Automated Anomaly Detection to improve Security in a High- Performance Heterogeneous Environment – Tom Slooff (Università della Svizzera italiana) (presentation delivered by Subhadeep Banik, Università della Svizzera italiana)
  2. Dynamic Autotuning for Adaptive and Energy-Aware Applications – Roberto Rocco (Politecnico di Milano) and Gianluca Palermo (Politecnico di Milano)
  • DAPHNE Hands-on Lab (20min, Patrick Damme, TU Berlin)

• Closing