Back to search

University of Patras

Μεθοδολογίες σχεδίασης υψηλής απόδοσης για ενσωματωμένες πλατφόρμες

Abstract

dc:description

In this Ph.D. dissertation, design methodologies for embedded platforms with the aim of improving the performance of realistic applications executed on them are proposed. The considered system platforms target on arithmetic intensive applications, as in the case of Digital Signal Processing and multimedia applications. The applications are coded in a high-level language, fact that eases the implementation of applications in the considered processing platforms. The methodologies have been automated, with the usage of prototype and commercial tools, for the efficient and rapid evaluation of the design and mapping solutions. Initially, a method is proposed for the effective implementation of Digital Signal Processing applications on a microprocessor system that includes as an accelerator of critical application parts a flexible data-path. The effectiveness of the proposed data-path relative to existing ones is illustrated for a set of characteristic arithmetic intensive kernels. An automated synthesis methodology for kernels is presented. This synthesis method is incorporated on a design flow for the considered system that aims in improving application performance and reducing energy consumption. Afterwards, a software framework that implements a formalized methodology for partitioning Digital Signal Processing and multimedia applications between mixed granularity reconfigurable hardware parts is presented. Critical application parts are accelerated on the coarse-grained reconfigurable hardware for satisfying timing constraints of application code mapped on the reconfigurable logic of the platform. The fine-grained reconfigurable hardware is implemented by an embedded Field Programmable Gate Array (FPGA), whereas the coarse-grained reconfigurable logic by an our-developed high-performance reconfigurable data-path. The efficiency of the prototype software is justified using realistic applications. Analytical experiments illustrate that important performance improvements are achieved, while the targeted timing constraints are satisfied for all the tested applications. The incorporation of a proposed flexible template of a Coarse Grained Reconfigurable Array (CGRA) in two different system on chip is presented. For the efficient execution of computational intensive parts on the CGRA an automated mapping process, that it is based on a software loop pipelining algorithm, is developed. The efficiency of the CGRA and of its respective mapping procedure are realized with the execution of real-life applications. In the first system, the CGRA together with an FPGA form the reconfigurable logic of a hybrid platform. In the second system on chip, the CGRA is directly attached to a general purposed microprocessor acting as a co-processor for the execution of critical loops. Automated design frameworks are proposed for the efficient and straightforward implementation of complete applications on the systems. Finally, a hardware/software partitioning methodology is proposed for the performance improvements of realistic applications in an embedded system on chip that it is composed by a programmable microprocessor and an FPGA reconfigurable hardware. The methodology has been automated in a large extend with the usage of academic and commercial tools. The FPGA acts as an accelerator for critical code segments improving by this way the performance of applications close to maximum theoretical bounds. Extensive experiments with different types of microprocessors and FPGAs show the effectiveness of the methodology.

Degree

thesis:*
Grantor dc:publisher
University of Patras
Year dc:date
2007

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Galanis, Michail
  • Γαλάνης, Μιχαήλ

Subjects

dc:subject × 14

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/18102

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Galanis, Michail; Γαλάνης, Μιχαήλ. Μεθοδολογίες σχεδίασης υψηλής απόδοσης για ενσωματωμένες πλατφόρμες. University of Patras, 2007. http://hdl.handle.net/10442/hedi/18102