Università degli Studi di Napoli “Parthenope”
Directed Acyclic Graph on Cross-Application Programmable I/O
DAGonCAPIO, Environmental modelling, Artificial Intelligence, HPC Computing
Development and testing of methodologies, middleware and tools for distributed computing for cloud-HPC, AI-HPC, AI-cloud-HPC convergence and their use in interdisciplinary applications.
Tecnical details
The workflow engine is based on the evolution of DAGonStar and the integration with CAPIO, combining the main architectural features with an optimization of the execution core.
State of the Art
HPC and parallel and distributed applications strengthen enabling technologies in rapid responses to intense or extreme environmental phenomena and scenario hypotheses.
Team
The University of Naples “Parthenope” is the proposing research organization. The industrial partners are Fides Consulting S.r.l. (FIDES) and ITDM S.r.l. (ITDM).
The project “Directed Acyclic Graph on Cross-Application Programmable I/O” (DAGonCAPIO) presents a workflow engine using CAPIO for task communication via files.
- Scientific Workflows
- Directed Acyclic Graphs
- Streaming I/O
- Environmental Modeling
- Artificial Intelligence
- High-Performance Cloud Computing
PNRR M4C2 I1.4 Campione Nazionale ICSC – Cascade call SPOKE 1 – “Future HPC and Big Data”
Thematic Area: 3 – Development and testing of methodologies, middleware and tools for distributed computing for cloud-HPC, AI-HPC, AI-cloud-HPC convergence and their use in interdisciplinary applications.
Through a dominant corporate commitment, finalized to industrial research in the field of HPC/Cloud computing convergence, DAGonCAPIO will be capable of executing workflows whose tasks can be performed on on-premises, on-cloud, and hybrid. The rapid, effective, and efficient response to situations that may compromise human health or environmental conservation is a primary requirement today. For this reason, a multidisciplinary application using a coupled artificial intelligence-based model will demonstrate the functioning of DAGonCAPIO. The application will simulate the transport and dispersion of inert materials similar to pollutants released into the sea and, subsequently, will predict the quality of filter-feeding organisms bred and intended for human consumption.
Thematic Area: 3 – Development and testing of methodologies, middleware and tools for distributed computing for cloud-HPC, AI-HPC, AI-cloud-HPC convergence and their use in interdisciplinary applications.
Through a dominant corporate commitment, finalized to industrial research in the field of HPC/Cloud computing convergence, DAGonCAPIO will be capable of executing workflows whose tasks can be performed on on-premises, on-cloud, and hybrid. The rapid, effective, and efficient response to situations that may compromise human health or environmental conservation is a primary requirement today. For this reason, a multidisciplinary application using a coupled artificial intelligence-based model will demonstrate the functioning of DAGonCAPIO. The application will simulate the transport and dispersion of inert materials similar to pollutants released into the sea and, subsequently, will predict the quality of filter-feeding organisms bred and intended for human consumption.
Project details
The DAGonCAPIO workflow engine is based on the evolution of DAGonStar, combining features core architectural features with execution core optimization. This upgrade aims to maximize the efficiency and scalability of the system, using containers for management and efficient use of computational resources on different platforms. The integration with CAPIO offers a solid framework for managing dependencies between tasks, ensuring synchronization effective, and smooth progression in carrying out tasks.
Meet our Team
The proposing research organization is from the University of Naples “Parthenope” (UNP). The industrial partners are Fides Consulting S.r.l. (FIDES) e ITDM S.r.l. (ITDM).
All project partners are in the Campania region.
