ECOSCALE : A Novel Framework for Utilising Multi-FPGAs in HPC Systems

δείτε την πρωτότυπη σελίδα τεκμηρίου
στον ιστότοπο του αποθετηρίου του φορέα για περισσότερες πληροφορίες και για να δείτε όλα τα ψηφιακά αρχεία του τεκμηρίου*



ECOSCALE : A Novel Framework for Utilising Multi-FPGAs in HPC Systems (EN)

Malakonakis, P
Mavroidis, I
Papaefstathiou, I
Georgopoulos, K
Ioannou, A

info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Άρθρο το οποίο έχει περάσει από ομότιμη αξιολόγηση (EL)

2020-05-22


ECOSCALE implements a scalable programming environment and architecture, aiming to substantially reduce energy consumption as well as data traffic and latency. ECOSCALE introduces a novel heterogeneous energy-efficient hierarchical architecture, as well as a hybrid programming environ-ment and runtime system. The ECOSCALE approach is hierarchical and it scales well by partitioning the physical system into multiple independent Work-ers (i.e. compute nodes). Workers are interconnected in a tree-like fashion and define a contiguous global address space that can be viewed either as a set of partitions in a Partitioned Global Address Space (PGAS), To further increase energy efficiency, as well as to provide resilience, the Workers employ recon-figurable accelerators mapped into the virtual address space utilizing a dual stage System Memory Management Unit with coherent memory access. The implemented UNILOGIC architecture supports shared partitioned reconfigura-ble resources accessed by any Worker in a PGAS partition, as well as automat-ed hardware synthesis of these resources from an OpenCL-based programming model. (EN)

FPGAs (EN)
HPC (EN)
Parallel Systems (EN)

International Conference on Information, Intelligence, Systems and Applications

Αγγλική γλώσσα

International Conference on Information, Intelligence, Systems and Applications (EL)
Information, Intelligence, Systems and Applications (EN)

International Conference on Information, Intelligence, Systems and Applications; Τόμ. 1, Αρ. 1 (2020): Project Track; 25-29 (EL)
Information, Intelligence, Systems and Applications; Τόμ. 1, Αρ. 1 (2020): Project Track; 25-29 (EN)

Copyright (c) 2020 International Conference on Information, Intelligence, Systems and Applications (EL)




*Η εύρυθμη και αδιάλειπτη λειτουργία των διαδικτυακών διευθύνσεων των συλλογών (ψηφιακό αρχείο, καρτέλα τεκμηρίου στο αποθετήριο) είναι αποκλειστική ευθύνη των αντίστοιχων Φορέων περιεχομένου.