A fast fourier transformation algorithm for single-chip cloud computers using RCCE

Wasuwee Sodsong, Bernd Burgstaller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Multimedia applications, spectrum analyses and data compression algorithms employ Fourier transformations as one of their main components to transform series from the time to the spectral domain and vice versa. Effective fast Fourier transformation (FFT) algorithms imply performance enhancements in related applications. Although architecturespecific programs achieve better performance, many FFT implementations were designed to be hardware independent and unaware of the underlining architecture. In this paper we introduce a novel FFT algorithm based on the RCCE native message passing library for the single-chip cloud computer (SCC). We parallelized the recursive (divide-and-conquer) radix- 2 FFT such that the inputs for all processing units are independent. Private memories are used to avoid cache coherence issues, and the algorithm was designed to minimize the message passing overhead. Preliminary experimental results were conducted using the RCCE emulator on an Intel Xeon 2 CPU quad-core computer. The emulator results showed promising scalability and speed-ups over the sequential implementation. Based on hardware availability, we plan to run the experiments on real SCC hardware for the final version of this paper.

Original languageEnglish
Title of host publication3rd Many-Core Applications Research Community Symposium, MARC 2011
Pages85-87
Number of pages3
Publication statusPublished - 2011 Dec 1
Event3rd Symposium on Many-Core Applications Research Community, MARC 2011 - Ettlingen, Germany
Duration: 2011 Jul 52011 Jul 6

Publication series

Name3rd Many-Core Applications Research Community Symposium, MARC 2011

Other

Other3rd Symposium on Many-Core Applications Research Community, MARC 2011
CountryGermany
CityEttlingen
Period11/7/511/7/6

Fingerprint

Message passing
Hardware
Data compression
Computer hardware
Program processors
Scalability
Availability
Data storage equipment
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Software

Cite this

Sodsong, W., & Burgstaller, B. (2011). A fast fourier transformation algorithm for single-chip cloud computers using RCCE. In 3rd Many-Core Applications Research Community Symposium, MARC 2011 (pp. 85-87). (3rd Many-Core Applications Research Community Symposium, MARC 2011).
Sodsong, Wasuwee ; Burgstaller, Bernd. / A fast fourier transformation algorithm for single-chip cloud computers using RCCE. 3rd Many-Core Applications Research Community Symposium, MARC 2011. 2011. pp. 85-87 (3rd Many-Core Applications Research Community Symposium, MARC 2011).
@inproceedings{4b1bcb6617ba4956a7d86384a5bc6f77,
title = "A fast fourier transformation algorithm for single-chip cloud computers using RCCE",
abstract = "Multimedia applications, spectrum analyses and data compression algorithms employ Fourier transformations as one of their main components to transform series from the time to the spectral domain and vice versa. Effective fast Fourier transformation (FFT) algorithms imply performance enhancements in related applications. Although architecturespecific programs achieve better performance, many FFT implementations were designed to be hardware independent and unaware of the underlining architecture. In this paper we introduce a novel FFT algorithm based on the RCCE native message passing library for the single-chip cloud computer (SCC). We parallelized the recursive (divide-and-conquer) radix- 2 FFT such that the inputs for all processing units are independent. Private memories are used to avoid cache coherence issues, and the algorithm was designed to minimize the message passing overhead. Preliminary experimental results were conducted using the RCCE emulator on an Intel Xeon 2 CPU quad-core computer. The emulator results showed promising scalability and speed-ups over the sequential implementation. Based on hardware availability, we plan to run the experiments on real SCC hardware for the final version of this paper.",
author = "Wasuwee Sodsong and Bernd Burgstaller",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9783866447172",
series = "3rd Many-Core Applications Research Community Symposium, MARC 2011",
pages = "85--87",
booktitle = "3rd Many-Core Applications Research Community Symposium, MARC 2011",

}

Sodsong, W & Burgstaller, B 2011, A fast fourier transformation algorithm for single-chip cloud computers using RCCE. in 3rd Many-Core Applications Research Community Symposium, MARC 2011. 3rd Many-Core Applications Research Community Symposium, MARC 2011, pp. 85-87, 3rd Symposium on Many-Core Applications Research Community, MARC 2011, Ettlingen, Germany, 11/7/5.

A fast fourier transformation algorithm for single-chip cloud computers using RCCE. / Sodsong, Wasuwee; Burgstaller, Bernd.

3rd Many-Core Applications Research Community Symposium, MARC 2011. 2011. p. 85-87 (3rd Many-Core Applications Research Community Symposium, MARC 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A fast fourier transformation algorithm for single-chip cloud computers using RCCE

AU - Sodsong, Wasuwee

AU - Burgstaller, Bernd

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Multimedia applications, spectrum analyses and data compression algorithms employ Fourier transformations as one of their main components to transform series from the time to the spectral domain and vice versa. Effective fast Fourier transformation (FFT) algorithms imply performance enhancements in related applications. Although architecturespecific programs achieve better performance, many FFT implementations were designed to be hardware independent and unaware of the underlining architecture. In this paper we introduce a novel FFT algorithm based on the RCCE native message passing library for the single-chip cloud computer (SCC). We parallelized the recursive (divide-and-conquer) radix- 2 FFT such that the inputs for all processing units are independent. Private memories are used to avoid cache coherence issues, and the algorithm was designed to minimize the message passing overhead. Preliminary experimental results were conducted using the RCCE emulator on an Intel Xeon 2 CPU quad-core computer. The emulator results showed promising scalability and speed-ups over the sequential implementation. Based on hardware availability, we plan to run the experiments on real SCC hardware for the final version of this paper.

AB - Multimedia applications, spectrum analyses and data compression algorithms employ Fourier transformations as one of their main components to transform series from the time to the spectral domain and vice versa. Effective fast Fourier transformation (FFT) algorithms imply performance enhancements in related applications. Although architecturespecific programs achieve better performance, many FFT implementations were designed to be hardware independent and unaware of the underlining architecture. In this paper we introduce a novel FFT algorithm based on the RCCE native message passing library for the single-chip cloud computer (SCC). We parallelized the recursive (divide-and-conquer) radix- 2 FFT such that the inputs for all processing units are independent. Private memories are used to avoid cache coherence issues, and the algorithm was designed to minimize the message passing overhead. Preliminary experimental results were conducted using the RCCE emulator on an Intel Xeon 2 CPU quad-core computer. The emulator results showed promising scalability and speed-ups over the sequential implementation. Based on hardware availability, we plan to run the experiments on real SCC hardware for the final version of this paper.

UR - http://www.scopus.com/inward/record.url?scp=84870568817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870568817&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84870568817

SN - 9783866447172

T3 - 3rd Many-Core Applications Research Community Symposium, MARC 2011

SP - 85

EP - 87

BT - 3rd Many-Core Applications Research Community Symposium, MARC 2011

ER -

Sodsong W, Burgstaller B. A fast fourier transformation algorithm for single-chip cloud computers using RCCE. In 3rd Many-Core Applications Research Community Symposium, MARC 2011. 2011. p. 85-87. (3rd Many-Core Applications Research Community Symposium, MARC 2011).