Publication detail

Overview of Parallel Platforms for Common High Performance Computing

FRÝZA, T. SVOBODOVÁ, J. ADAMEC, F. MARŠÁLEK, R. PROKOPEC, J.

Original Title

Overview of Parallel Platforms for Common High Performance Computing

English Title

Overview of Parallel Platforms for Common High Performance Computing

Type

journal article

Language

en

Original Abstract

The paper deals with the various parallel platforms used for high performance computing in the signal processing domain. More precisely, the methods exploiting the multicores central processing units such as message passing interface and OpenMP are taken into account. The properties of the programming methods are experimentally proved in the application of a fast Fourier transform and a discrete cosine transform and they are compared with the possibilities of MATLAB's built-in functions and Texas Instruments digital signal processors with very long instruction word architectures. New FFT and DCT implementations were proposed and tested. The implementation phase was compared with CPU based computing methods and with possibilities of the Texas Instruments digital signal processing library on C6747 floating-point DSPs. The optimal combination of computing methods in the signal processing domain and new, fast routines' implementation is proposed as well.

English abstract

The paper deals with the various parallel platforms used for high performance computing in the signal processing domain. More precisely, the methods exploiting the multicores central processing units such as message passing interface and OpenMP are taken into account. The properties of the programming methods are experimentally proved in the application of a fast Fourier transform and a discrete cosine transform and they are compared with the possibilities of MATLAB's built-in functions and Texas Instruments digital signal processors with very long instruction word architectures. New FFT and DCT implementations were proposed and tested. The implementation phase was compared with CPU based computing methods and with possibilities of the Texas Instruments digital signal processing library on C6747 floating-point DSPs. The optimal combination of computing methods in the signal processing domain and new, fast routines' implementation is proposed as well.

Keywords

Digital signal processing, fast Fourier transforms, discrete cosine transforms, parallel programming, high performance computing, message passing interface, OpenMP, MATLAB, digital signal processors, optimization.

RIV year

2012

Released

02.04.2012

Publisher

Vysoké učení technické v Brně

Location

Brno

Pages from

436

Pages to

444

Pages count

9

URL

BibTex


@article{BUT91600,
  author="Tomáš {Frýza} and Jitka {Svobodová} and Filip {Adamec} and Roman {Maršálek} and Jan {Prokopec}",
  title="Overview of Parallel Platforms for Common High Performance Computing",
  annote="The paper deals with the various parallel platforms used for high performance computing in the signal processing domain. More precisely, the methods exploiting the multicores central processing units such as message passing interface and OpenMP are taken into account. The properties of the programming methods are experimentally proved in the application of a fast Fourier transform and a discrete cosine transform and they are compared with the possibilities of MATLAB's built-in functions and Texas Instruments digital signal processors with very long instruction word architectures. New FFT and DCT implementations were proposed and tested. The implementation phase was compared with CPU based computing methods and with possibilities of the Texas Instruments digital signal processing library on C6747 floating-point DSPs. The optimal combination of computing methods in the signal processing domain and new, fast routines' implementation is proposed as well.",
  address="Vysoké učení technické v Brně",
  chapter="91600",
  institution="Vysoké učení technické v Brně",
  number="1",
  volume="21",
  year="2012",
  month="april",
  pages="436--444",
  publisher="Vysoké učení technické v Brně",
  type="journal article"
}