Parallel decoding of LDPC convolutional codes using OpenMP and GPU

Chi H. Chan, Chung Ming Lau

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

5 Citations (Scopus)

Abstract

Recently, there have been different applications, namely 10GBase-T Ethernet, video broadcasting and satellite communication, utilizing low-density parity-check (LDPC) codes as the forward-error-correction codes. The main reason is that the error performance of LDPC codes can be very close to the Shannon limit. LDPC codes can be further categorized into LDPC block codes (LDPC-BCs) and LDPC convolutional codes (LDPC-CCs). It has also been discovered that LDPC-CCs usually outperform LDPC-BCs. Simulation of LDPC-BCs and LDPC-CCs can take a lot of time because the decoding algorithms are relatively complex. Fortunately, the decoding steps can be performed in parallel. In this paper, we create three different platforms for simulating the error performance of LDPC-CCs. The first two platforms are run on a Central Processing Unit (CPU) while the third one involves the use of a Graphics Processing Unit (GPU). We show that using GPU can improve the simulation speed substantially.
Original languageEnglish
Title of host publication2012 IEEE Symposium on Computers and Communications, ISCC 2012
Pages000225-000227
DOIs
Publication statusPublished - 28 Sep 2012
Event17th IEEE Symposium on Computers and Communication, ISCC 2012 - Cappadocia, Turkey
Duration: 1 Jul 20124 Jul 2012

Conference

Conference17th IEEE Symposium on Computers and Communication, ISCC 2012
Country/TerritoryTurkey
CityCappadocia
Period1/07/124/07/12

Keywords

  • CPU
  • error performance
  • GPU
  • LDPC code
  • LDPC convolutional code

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Software
  • Mathematics(all)
  • Signal Processing

Cite this