Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder

Zhenzhi Wu; Dake Liu; Yanjun Zhang

doi:10.1109/ICCChina.2014.7008301

Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder

Zhenzhi Wu, Dake Liu, Yanjun Zhang

School of Cyberspace Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

Layered Decoding (LD) algorithm is widely applied in high throughput QC-LDPC decoders. Among all check node update algorithms in LD, Turbo-Decoding Message-Passing (TDMP) is adopted by many proposals. A-posteriori memory access conflict under pipelined TDMP decoder incurs serious throughput decline. In this paper, several matrix reordering techniques are introduced to reduce the conflict occurrences without incurring the performance loss, which includes Row Exchange method, element Sequence Reordering method, and a conflict detector with pipeline stall insertion. They are integrated in a joint recursive deep-first searching procedure. Test results show that the efficiency improvement reaches up to 60% compared to non-optimized scenarios for 802.11n and 802.16e standards.

Original language	English
Title of host publication	2014 IEEE/CIC International Conference on Communications in China, ICCC 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	354-359
Number of pages	6
ISBN (Electronic)	9781479941469
DOIs	https://doi.org/10.1109/ICCChina.2014.7008301
Publication status	Published - 12 Jan 2015
Event	2014 IEEE/CIC International Conference on Communications in China, ICCC 2014 - Shanghai, China Duration: 13 Oct 2014 → 15 Oct 2014

Publication series

Name	2014 IEEE/CIC International Conference on Communications in China, ICCC 2014

Conference

Conference	2014 IEEE/CIC International Conference on Communications in China, ICCC 2014
Country/Territory	China
City	Shanghai
Period	13/10/14 → 15/10/14

Keywords

Conflict reduction
Matrix reordering
QC-LDPC

Access to Document

10.1109/ICCChina.2014.7008301

Cite this

Wu, Z., Liu, D., & Zhang, Y. (2015). Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder. In 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014 (pp. 354-359). Article 7008301 (2014 IEEE/CIC International Conference on Communications in China, ICCC 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCChina.2014.7008301

@inproceedings{31a3a54544b545929313feab1a326bfd,

title = "Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder",

abstract = "Layered Decoding (LD) algorithm is widely applied in high throughput QC-LDPC decoders. Among all check node update algorithms in LD, Turbo-Decoding Message-Passing (TDMP) is adopted by many proposals. A-posteriori memory access conflict under pipelined TDMP decoder incurs serious throughput decline. In this paper, several matrix reordering techniques are introduced to reduce the conflict occurrences without incurring the performance loss, which includes Row Exchange method, element Sequence Reordering method, and a conflict detector with pipeline stall insertion. They are integrated in a joint recursive deep-first searching procedure. Test results show that the efficiency improvement reaches up to 60% compared to non-optimized scenarios for 802.11n and 802.16e standards.",

keywords = "Conflict reduction, Matrix reordering, QC-LDPC",

author = "Zhenzhi Wu and Dake Liu and Yanjun Zhang",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014 ; Conference date: 13-10-2014 Through 15-10-2014",

year = "2015",

month = jan,

day = "12",

doi = "10.1109/ICCChina.2014.7008301",

language = "English",

series = "2014 IEEE/CIC International Conference on Communications in China, ICCC 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "354--359",

booktitle = "2014 IEEE/CIC International Conference on Communications in China, ICCC 2014",

address = "United States",

}

Wu, Z, Liu, D & Zhang, Y 2015, Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder. in 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014., 7008301, 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014, Institute of Electrical and Electronics Engineers Inc., pp. 354-359, 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014, Shanghai, China, 13/10/14. https://doi.org/10.1109/ICCChina.2014.7008301

Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder. / Wu, Zhenzhi; Liu, Dake; Zhang, Yanjun.
2014 IEEE/CIC International Conference on Communications in China, ICCC 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 354-359 7008301 (2014 IEEE/CIC International Conference on Communications in China, ICCC 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder

AU - Wu, Zhenzhi

AU - Liu, Dake

AU - Zhang, Yanjun

PY - 2015/1/12

Y1 - 2015/1/12

N2 - Layered Decoding (LD) algorithm is widely applied in high throughput QC-LDPC decoders. Among all check node update algorithms in LD, Turbo-Decoding Message-Passing (TDMP) is adopted by many proposals. A-posteriori memory access conflict under pipelined TDMP decoder incurs serious throughput decline. In this paper, several matrix reordering techniques are introduced to reduce the conflict occurrences without incurring the performance loss, which includes Row Exchange method, element Sequence Reordering method, and a conflict detector with pipeline stall insertion. They are integrated in a joint recursive deep-first searching procedure. Test results show that the efficiency improvement reaches up to 60% compared to non-optimized scenarios for 802.11n and 802.16e standards.

AB - Layered Decoding (LD) algorithm is widely applied in high throughput QC-LDPC decoders. Among all check node update algorithms in LD, Turbo-Decoding Message-Passing (TDMP) is adopted by many proposals. A-posteriori memory access conflict under pipelined TDMP decoder incurs serious throughput decline. In this paper, several matrix reordering techniques are introduced to reduce the conflict occurrences without incurring the performance loss, which includes Row Exchange method, element Sequence Reordering method, and a conflict detector with pipeline stall insertion. They are integrated in a joint recursive deep-first searching procedure. Test results show that the efficiency improvement reaches up to 60% compared to non-optimized scenarios for 802.11n and 802.16e standards.

KW - Conflict reduction

KW - Matrix reordering

KW - QC-LDPC

UR - http://www.scopus.com/inward/record.url?scp=84922561229&partnerID=8YFLogxK

U2 - 10.1109/ICCChina.2014.7008301

DO - 10.1109/ICCChina.2014.7008301

M3 - Conference contribution

AN - SCOPUS:84922561229

T3 - 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014

SP - 354

EP - 359

BT - 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014

Y2 - 13 October 2014 through 15 October 2014

ER -

Wu Z, Liu D, Zhang Y. Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder. In 2014 IEEE/CIC International Conference on Communications in China, ICCC 2014. Institute of Electrical and Electronics Engineers Inc. 2015. p. 354-359. 7008301. (2014 IEEE/CIC International Conference on Communications in China, ICCC 2014). doi: 10.1109/ICCChina.2014.7008301

Matrix reordering techniques for memory conflict reduction for pipelined QC-LDPC decoder

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this