Investigation of the use of Intelligent Systems for Efficient Mapping of Applications in Many-Core Architectures

• Grant number: 17/26421-3
• Support Opportunities: Scholarships abroad - Research
• Start date: September 01, 2018
• End date: August 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Emerson Carlos Pedrino
• Grantee: Emerson Carlos Pedrino
• Host Investigator: Gianluca Tempesti
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Institution abroad: University of York, England

Abstract

The maximum frequency of single-core processors has reached its operating limit, and chip makers have built multi-core chips, where each core operates at lower frequencies relative to chips containing only one core. In addition, with the demand for performance of complex applications growing very rapidly in recent years, there is an emerging need for multi-core and many-core processors that can communicate and provide ever-greater parallelism. For mapping applications to multiple / many-core systems, those need to be partitioned into multiple tasks that can be performed concurrently across different cores. Thus, it arises the need for developing more efficient mapping methodologies, and to provide optimum maps satisfying the constraints required by the various applications. Such a problem is classified as NP-hard, and heuristics based on the knowledge domain of the application need to be used, in this context, to find out the required solutions. Therefore, in this research project, it is intended to investigate the use of intelligent systems, in particular the use of multiobjective AGs, for automatic generation of application maps, containing as case examples concurrently tasks of computer vision, in many-core architectures implemented through FPGAs, allowing them to be fault tolerant, efficient and of high performance.

Scientific publications

(10)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CORDEIRO, NATAL HENRIQUE; PEDRINO, EMERSON CARLOS. A new methodology applied to dynamic object detection and tracking systems for visually impaired people. COMPUTERS & ELECTRICAL ENGINEERING, v. 77, p. 61-71, JUL 2019. (17/26421-3)

PEDRINO, EMERSON CARLOS; YAMADA, THIAGO; LUNARDI, THIAGO REGINATO; DE MELO VIEIRA, JR., JOSE CARLOS. Islanding detection of distributed generation by using multi-gene genetic programming based classifier. APPLIED SOFT COMPUTING, v. 74, p. 206-215, JAN 2019. (15/23297-4, 17/26421-3)

CORDEIRO, NATAL HENRIQUE; PEDRINO, EMERSON CARLOS. Collision risk prediction for visually impaired people using high level information fusion. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, v. 81, p. 180-192, MAY 2019. (17/26421-3)

PADUA, BRUNO; LIMA, DENIS; FERNANDES, MARCIO; ABUASSAL, ALI; TEMPESTI, GIANLUCA; PEDRINO, EMERSON. Hybrid Implementation of Evolutionary Algorithms in FPGAs for Automatic Generation of Morphological Image Filters. PRZEGLAD ELEKTROTECHNICZNY, v. 96, n. 4, p. 12-16, 2020. (17/26421-3)

BATISTA DOURADO, ANTONIO MIGUEL; PEDRINO, EMERSON CARLOS. Automatic generation of high performance morphological filters to fix missing data in depth images on real-time embedded systems for visually impaired people. PRZEGLAD ELEKTROTECHNICZNY, v. 96, n. 1, p. 113-117, 2020. (17/26421-3)

CORDEIRO, NATAL HENRIQUE; PEDRINO, EMERSON CARLOS. Data used for detection and tracking of dynamic objects for visually impaired people. DATA IN BRIEF, v. 26, OCT 2019. (17/26421-3)

PEDRINO, EMERSON CARLOS; DE LIMA, DENIS PEREIRA; TEMPESTI, GIANLUCA. A multiobjective metaheuristic approach for morphological filters on many-core architectures. Integrated Computer-Aided Engineering, v. 26, n. 4, p. 383-397, 2019. (17/26421-3)

CORDEIRO, NATAL HENRIQUE; PEDRINO, EMERSON CARLOS; IEEE. An Architecture for Collision Risk Prediction for Visually Impaired People. PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), v. N/A, p. 8-pg., 2018-01-01. (17/26421-3)

BATISTA DOURADO, ANTONIO MIGUEL; PEDRINO, EMERSON CARLOS. Multi-objective Cartesian Genetic Programming optimization of morphological filters in navigation systems for Visually Impaired People. APPLIED SOFT COMPUTING, v. 89, APR 2020. (17/26421-3)

GIVANILDO, RAFAEL; LIMA, DENIS; PARIS, PAULO; PEDRINO, EMERSON. Low-Cost and Accuracy Smart Meter Prototype for Smart Grids. PRZEGLAD ELEKTROTECHNICZNY, v. 97, n. 9, p. 72-77, 2021. (17/26421-3)