View in EDS

Methodologies for Synthesizing and Analyzing Dynamic Dataflow Programs in Heterogeneous Systems for Edge Computing

Saved in:
Bibliographic Details
Title: Methodologies for Synthesizing and Analyzing Dynamic Dataflow Programs in Heterogeneous Systems for Edge Computing
Authors: Aurelien Bloch, Simone Casale-Brunet, Marco Mattavelli
Source: IEEE Open Journal of Circuits and Systems, Vol 2, Pp 769-781 (2021)
Publisher Information: IEEE, 2021.
Publication Year: 2021
Collection: LCC:Electric apparatus and materials. Electric circuits. Electric networks
Subject Terms: Edge computing, dynamic dataflow programs, RVC-CAL, parallel computing, SIMD, source-to-source compiler, Electric apparatus and materials. Electric circuits. Electric networks, TK452-454.4
Description: The possibility of using the increasing computing power available in cloud infrastructures requires the development of new approaches for application software development and optimization. Emerging edge computing paradigms offer the possibility of reducing bandwidth needs and of optimizing latency, features particularly relevant for Big Data applications, by bringing computation closer to the user and to the data generation processes. However, edge computing approaches pose several challenges in terms of how to be able to efficiently take advantage of a distributed network of heterogeneous processing nodes. This paper deals with this problem by extending a dynamic dataflow software development framework and related design flow tools to support heterogeneous platforms. The paper describes the methodology steps for the synthesis of application software executing on heterogeneous CPU/GPU co-processing nodes. The steps do include the optimization of the communication between heterogeneous processing elements, a technique for the efficient mapping and parallelization of computation on independent GPU partitions, and the introduction of dynamic programming approach for leveraging the SIMD nature of GPU computing. To complete the methodology of seamless porting of dataflow software and partition on CPU or GPU computing nodes, an automated methodology for exploring the configuration space and to identify high performance working points is developed.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2644-1225
Relation: https://ieeexplore.ieee.org/document/9645043/; https://doaj.org/toc/2644-1225
DOI: 10.1109/OJCAS.2021.3116342
Access URL: https://doaj.org/article/cd363e4784d04a0dba4a2beb4d60e45c
Accession Number: edsdoj.363e4784d04a0dba4a2beb4d60e45c
Database: Directory of Open Access Journals
Description
Abstract:The possibility of using the increasing computing power available in cloud infrastructures requires the development of new approaches for application software development and optimization. Emerging edge computing paradigms offer the possibility of reducing bandwidth needs and of optimizing latency, features particularly relevant for Big Data applications, by bringing computation closer to the user and to the data generation processes. However, edge computing approaches pose several challenges in terms of how to be able to efficiently take advantage of a distributed network of heterogeneous processing nodes. This paper deals with this problem by extending a dynamic dataflow software development framework and related design flow tools to support heterogeneous platforms. The paper describes the methodology steps for the synthesis of application software executing on heterogeneous CPU/GPU co-processing nodes. The steps do include the optimization of the communication between heterogeneous processing elements, a technique for the efficient mapping and parallelization of computation on independent GPU partitions, and the introduction of dynamic programming approach for leveraging the SIMD nature of GPU computing. To complete the methodology of seamless porting of dataflow software and partition on CPU or GPU computing nodes, an automated methodology for exploring the configuration space and to identify high performance working points is developed.
ISSN:26441225
DOI:10.1109/OJCAS.2021.3116342