A Parallel Decoding Algorithm of LDPC Codes using CUDA

被引：23

作者：

Wang, Shuang ^{[1
]}

Cheng, Samuel ^{[1
]}

Wu, Qiang ^{[2
]}

机构：

[1] Univ Oklahoma, Sch Elect & Comp Engn, Tulsa, OK 74135 USA

[2] LLC, Soft Imaging, Houston, TX 77062 USA

来源：

2008 42ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, VOLS 1-4 | 2008年

关键词：

D O I：

10.1109/ACSSC.2008.5074385

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

A parallel belief propagation algorithm for decoding low-density parity-cheek (LDPC) Codes is presented in this paper based on Compute Unified Device Architecture (CUDA). As a new hardware and software architecture for addressing and managing computations, CUDA offers parallel data computing using the highly multithreaded coprocessor driven by very high memory bandwidth GPU. The parallel decoding algorithm, based on CUDA, allows that all bit-nodes or check-nodes work simultaneously, thus provides an efficient and fast way for implementing the decoder.

引用

页码：171 / +

页数：2

共 13 条

[1]

BERNHARD MJ, LDPC CODES BRIEF TUT

[2]

Daesun Oh., 2007, IEEE INT S CIRC SYST, P1855

[3] LOW-DENSITY PARITY-CHECK CODES [J].

GALLAGER, RG .

IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (01) :21-&

[4]

Gallager RG, 1963, LOW DENSITY PARITY C

[5]

Howland C., 2001, 2001 IEEE INT S CIRC, V4, P742

[6] Factor graphs and the sum-product algorithm [J].

Kschischang, FR ;

Frey, BJ ;

Loeliger, HA .

IEEE TRANSACTIONS ON INFORMATION THEORY, 2001, 47 (02) :498-519

[7]

LARS N, 2004, GP2 ACM WORKSH GEN P

[8] Near Shannon limit performance of low density parity check codes [J].

MacKay, DJC ;

Neal, RM .

ELECTRONICS LETTERS, 1996, 32 (18) :1645-1646

[9]

MARK WR, P SIGGRAPH 2003

[10]

NVIDIA Corporation, 2007, NVIDIA CUDA Compute Unified Device Architecture Programming Guide

← 1 2 →