Back to results

Massachusetts Institute of Technology

Many-core architectures with time predictable execution Support for hard real-time applications

Abstract

dc:description.abstract

Hybrid control systems are a growing domain of application. They are pervasive and their complexity is increasing rapidly. Distributed control systems for future "Intelligent Grid" and renewable energy generation systems are demanding high-performance, hard real-time computation, and more programmability. General-purpose computer systems are primarily designed to process data and not to interact with physical processes as required by these systems. Generic general-purpose architectures even with the use of real-time operating systems fail to meet the hard realtime constraints of hybrid system dynamics. ASIC, FPGA, or traditional embedded design approaches to these systems often result in expensive, complicated systems that are hard to program, reuse, or maintain. In this thesis, we propose a domain-specific architecture template targeting hybrid control system applications. Using power electronics control applications, we present new modeling techniques, synthesis methodologies, and a parameterizable computer architecture for these large distributed control systems. We propose a new system modeling approach, called Adaptive Hybrid Automaton, based on previous work in control system theory, that uses a mixed-model abstractions and lends itself well to digital processing. We develop a domain-specific architecture based on this modeling that uses heterogeneous processing units and predictable execution, called MARTHA. We develop a hard real-time aware router architecture to enable deterministic on-chip interconnect network communication. We present several algorithms for scheduling task-based applications onto these types of heterogeneous architectures. We create Heracles, an open-source, functional, parameterized, synthesizable many-core system design toolkit, that can be used to explore future multi/many-core processors with different topologies, routing schemes, processing elements or cores, and memory system organizations. Using the Heracles design tool we build a prototype of the proposed architecture using a state-of-the-art FPGA-based platform, and deploy and test it in actual physical power electronics systems. We develop and release an open-source, small representative set of power electronics system applications that can be used for hard real-time application benchmarking.

Degree

thesis:*
Department dc:contributor.department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Grantor dc:publisher
Massachusetts Institute of Technology
Year dc:date.issued
2013

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kinsy, Michel A
Advisor dc:contributor.advisor
  • Srinivas Devadas.

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
Language dc:language.iso
eng

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1721.1/82351
OAI identifier oai:identifier
oai:dspace.mit.edu:1721.1/82351

Chain of custody

source
Harvested from
MIT
Base URL
dspace.mit.edu/oai/request
Last updated
2026-07-22
Source record
OAI-PMH GetRecord
citation

Kinsy, Michel A. Many-core architectures with time predictable execution Support for hard real-time applications. Massachusetts Institute of Technology, 2013. http://hdl.handle.net/1721.1/82351