efficient decoders for polar codes in 5g can machine
play

Efficient Decoders for Polar Codes in 5G: Can Machine Learning Help? - PowerPoint PPT Presentation

Mar 22, 2023 •117 likes •695 views

Efficient Decoders for Polar Codes in 5G: Can Machine Learning Help? Seyyed Ali Hashemi Stanford University SystemX Conference November 19, 2019 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 1 / 20 5th Gen. of

  1. Efficient Decoders for Polar Codes in 5G: Can Machine Learning Help? Seyyed Ali Hashemi Stanford University SystemX Conference November 19, 2019 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 1 / 20

  2. 5th Gen. of Cellular Mobile Communications (5G) Stringent requirements: Peak (20 Gb/s) and user experienced (1 Gb/s) data rate End-to-end latency (1 ms) Scenarios: eMBB, mMTC, URLLC Data channel: actual information Control channel: system parameters → Polar Codes S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 2 / 20

  3. Polar Code Challenges in 5G Simple polar decoding algorithms do not perform well with moderate code lengths Effective algorithms are slow and complex to implement S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 3 / 20

  4. Outline Polar Codes 1 Fast Decoding 2 Memory-Efficient Decoding 3 Can Machine Learning Help? 4 Conclusion 5 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 4 / 20

  5. Polar Codes Forward Error Correction (FEC) Transmitter Channel Receiver Improves transmission reliability Repetition code: 0 Channel 1 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 5 / 20

  6. Polar Codes Forward Error Correction (FEC) Transmitter Channel Receiver Improves transmission reliability Repetition code: Encoder 000 0 Channel 010 0 Decoder S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 5 / 20

  7. Polar Codes Polar Codes Channel Capacity Maximum rate at which information can be reliably transmitted Polar Codes Provably achieve channel capacity at infinite code length Selected for 5G eMBB control channel: short codes S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 6 / 20

  8. Polar Codes Polar Encoding layer 0 1 u 0 x 0 u 1 x 1 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 7 / 20

  9. Polar Codes Polar Encoding layer 0 1 u 0 x 0 u 1 x 1 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 7 / 20

  10. Polar Codes Polar Encoding layer 0 1 2 u 0 x 0 u 1 x 1 u 2 x 2 u 3 x 3 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 7 / 20

  11. Polar Codes Polar Encoding layer 0 1 2 3 u 0 x 0 u 1 x 1 u 2 x 2 u 3 x 3 u 4 x 4 u 5 x 5 u 6 x 6 u 7 x 7 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 7 / 20

  12. Polar Codes Polar Encoding layer 0 1 2 3 x 0 0 F x 1 F 0 x 2 0 F u 3 x 3 I x 4 0 F u 5 x 5 I u 6 x 6 I u 7 x 7 I Input bits are divided into information ( I ) and frozen ( F ) bits S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 7 / 20

  13. Polar Codes Polar Decoding layer 0 1 2 3 x 0 0 F x 1 F 0 x 2 0 F u 3 x 3 I x 4 0 F u 5 x 5 I u 6 x 6 I u 7 x 7 I S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 8 / 20

  14. Polar Codes Polar Decoding layer 0 1 2 3 x 0 0 F x 1 F 0 x 2 0 F u 3 x 3 I x 4 0 F u 5 x 5 I u 6 x 6 I u 7 x 7 I S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 8 / 20

  15. Polar Codes Successive-Cancellation (SC) Decoding layer 3 α β 2 β r α l α r β l 1 0 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 9 / 20

  16. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 List size L = 4 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  17. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  18. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  19. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  20. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  21. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  22. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  23. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  24. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Bits are decoded one by one → High latency! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  25. Polar Codes SC List (SCL) Decoding layer 3 2 1 0 Roughly L times the memory usage of SC → High area! S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 10 / 20

  26. Fast Decoding Fast-SSCL Decoding layer 3 2 1 0 Conventional SCL S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 11 / 20

  27. Fast Decoding Fast-SSCL Decoding layer 3 2 1 Rate-0 0 Fast-SSCL: Exact reformulation of Rate-0 nodes S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 11 / 20

  28. Fast Decoding Fast-SSCL Decoding layer 3 2 Rep 1 0 Fast-SSCL: Exact reformulation of repetition (Rep) nodes S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 11 / 20

  29. Fast Decoding Fast-SSCL Decoding layer 3 2 Rep 1 Rate-1 0 Fast-SSCL: Exact reformulation of Rate-1 nodes S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 11 / 20

  30. Fast Decoding Fast-SSCL Decoding layer 3 2 Rep SPC 1 0 Fast-SSCL-SPC: Exact reformulation of single parity-check (SPC) nodes for L = 2 S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 11 / 20

  31. Fast Decoding Performance for P (1024 , 512) L : 2 4 8 16 32 Fast-SSCL: Fast-SSCL-SPC: 10 0 10 − 1 10 − 1 10 − 2 10 − 2 10 − 3 FER BER 10 − 3 10 − 4 10 − 4 10 − 5 10 − 5 10 − 6 10 − 6 10 − 7 1 2 3 1 2 3 E b / N 0 [dB] E b / N 0 [dB] S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 12 / 20

  32. Fast Decoding Hardware Implementation TSMC 65 nm Implementation Results for P (1024 , 512) Area [mm 2 ] Decoder Frequency [MHz] Throughput [Mb/s] SCL(8) 2 . 686 722 272 Fast-SSCL(8) 3 . 622 ( ↑ 36 %) 722 1053 ( ↑ 287 %) Fast-SSCL-SPC(8) 3 . 975 ( ↑ 48 %) 722 1198 ( ↑ 340 %) S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 13 / 20

  33. Memory-Efficient Decoding Memory-Efficient SCL memory layer 2 3 3 4 × 2 2 2 4 × 2 1 1 4 × 2 0 0 36 Conventional SCL S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 14 / 20

  34. Memory-Efficient Decoding Memory-Efficient SCL memory layer 2 3 3 1 × 2 2 2 1 × 2 1 1 4 × 2 0 0 18 Partitioned SCL (PSCL) S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 14 / 20

  35. Memory-Efficient Decoding Memory-Efficient SCL memory layer 2 3 3 2 × 2 2 2 2 × 2 1 1 4 × 2 0 0 24 Generalized PSCL (GPSCL) S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 14 / 20

  36. Memory-Efficient Decoding Memory-Efficient SCL memory layer 2 3 3 1 × 2 2 2 2 × 2 1 1 4 × 2 0 0 20 Layered PSCL (LPSCL) S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 14 / 20

  37. Memory-Efficient Decoding Performance for P (1024 , 512): GPSCL and LPSCL 10 8 8 10 0 9 8 8 8 8 8 10 − 1 8 8 8 8 8 8 8 8 7 10 − 2 FER 10 − 3 10 − 4 10 − 5 GPSCL(8,8,8) SCL(8) 10 − 6 1 2 3 E b / N 0 [dB] S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 15 / 20

  38. Memory-Efficient Decoding Performance for P (1024 , 512): GPSCL and LPSCL 10 8 8 10 0 9 8 8 8 8 8 10 − 1 8 8 8 8 8 8 8 8 7 10 1 1 10 − 2 9 1 1 1 1 FER 8 1 1 1 1 1 1 1 1 10 − 3 7 10 − 4 GPSCL(8,8,8) SCL(8) 10 − 5 GPSCL(8,8,1) PSCL(8,8) 10 − 6 1 2 3 E b / N 0 [dB] S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 15 / 20

  39. Memory-Efficient Decoding Performance for P (1024 , 512): GPSCL and LPSCL 10 8 8 10 0 9 8 8 8 8 8 10 − 1 8 8 8 8 8 8 8 8 7 10 1 1 10 − 2 9 1 1 1 1 FER 8 1 1 1 1 1 1 1 1 10 − 3 7 10 2 2 10 − 4 9 2 2 2 2 GPSCL(8,8,8) SCL(8) 8 2 2 2 2 2 2 2 2 GPSCL(8,8,1) 10 − 5 7 PSCL(8,8) GPSCL(8,8,2) 10 − 6 1 2 3 E b / N 0 [dB] S. A. Hashemi Efficient Decoders for Polar Codes in 5G SystemX Conference 15 / 20

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Design of Energy-Efficient LDPC Codes and Decoders Elsa Dupraz 16/04/2019 Section 1:

Design of Energy-Efficient LDPC Codes and Decoders Elsa Dupraz 16/04/2019 Section 1:

Design of Energy-Efficient LDPC Codes and Decoders Elsa Dupraz 16/04/2019 Section 1: Introduction 2 OUTLINE Introduction LDPC codes and decoders Perf. analysis of faulty decoders Effect of faults in the decoders Conclusion 1.

1.09k views • 51 slides
1 Hello Hi! My name is Ido, and we are going to talk about polar codes As you may know,

1 Hello Hi! My name is Ido, and we are going to talk about polar codes As you may know,

1 Hello Hi! My name is Ido, and we are going to talk about polar codes As you may know, polar codes were invented in 2009 by Erdal Arkan. When presenting them, Im going to try and strike a good balance between a simple explanation

675 views • 20 slides
An Efficient, Portable and Generic Library for Successive Cancellation Decoding of Polar Codes

An Efficient, Portable and Generic Library for Successive Cancellation Decoding of Polar Codes

An Efficient, Portable and Generic Library for Successive Cancellation Decoding of Polar Codes Adrien Cassagne 1 , 2 Bertrand Le Gal 1 Camille Leroux 1 Olivier Aumage 2 Denis Barthou 2 1 IMS, Univ. Bordeaux, INP, France 2 Inria / Labri, Univ.

559 views • 20 slides
Practical Design and Decoding of Polar Codes Vera Miloslavskaya Saint-Petersburg State

Practical Design and Decoding of Polar Codes Vera Miloslavskaya Saint-Petersburg State

Practical Design and Decoding of Polar Codes Vera Miloslavskaya Saint-Petersburg State Polytechnic University veram@dcn.icc.spbstu.ru January 2015 Polar Codes Polar codes can achieve the capacity of 1 0 0 0 0 0 0 0 an arbitrary

323 views • 4 slides
Non-Binary Polar Codes using Reed-Solomon Codes and Algebraic Geometry Codes Ryuhei Mori

Non-Binary Polar Codes using Reed-Solomon Codes and Algebraic Geometry Codes Ryuhei Mori

Non-Binary Polar Codes using Reed-Solomon Codes and Algebraic Geometry Codes Ryuhei Mori Toshiyuki Tanaka Graduate School of Informatics, Kyoto University Information Theory Workshop 2010 Contents Exponent of matrix Reed-Solomon matrix

307 views • 20 slides
List-Decoding of Polar Codes Ido Tal and Alexander Vardy University of California San Diego 9500

List-Decoding of Polar Codes Ido Tal and Alexander Vardy University of California San Diego 9500

List-Decoding of Polar Codes Ido Tal and Alexander Vardy University of California San Diego 9500 Gilman Drive, La Jolla, CA 92093, USA Problem and goal Channel polarization is slow. For short to moderate code lengths, polar codes have

1.53k views • 106 slides
COLOR CODE DECODERS FROM TORIC CODE DECODERS Aleksander Kubica work w/ N. Delfosse

COLOR CODE DECODERS FROM TORIC CODE DECODERS Aleksander Kubica work w/ N. Delfosse

COLOR CODE DECODERS FROM TORIC CODE DECODERS Aleksander Kubica work w/ N. Delfosse arXiv: 1905.07393 TOPOLOGICAL QUANTUM ERROR-CORRECTING CODES Want to reliably store & process q. information. Need

545 views • 12 slides
On Polar Grassmann Codes I. Cardinali Abstract In this note we offer a short summary of the

On Polar Grassmann Codes I. Cardinali Abstract In this note we offer a short summary of the

On Polar Grassmann Codes I. Cardinali Abstract In this note we offer a short summary of the content of the lecture on polar Grassmann codes given at the Indian Intitute of Technology, Mumbai, during the International Conference on Algebraic

509 views • 8 slides
Polar Codes for Noncoherent MIMO Signalling Philip R. Balogun, Ian Marsland, Ramy Gohary, and

Polar Codes for Noncoherent MIMO Signalling Philip R. Balogun, Ian Marsland, Ramy Gohary, and

Polar Codes for Noncoherent MIMO Signalling ICC 2016 Polar Codes for Noncoherent MIMO Signalling Philip R. Balogun, Ian Marsland, Ramy Gohary, and Halim Yanikomeroglu Department of Systems and Computer Engineering, Carleton University, Canada

493 views • 36 slides
On the Construction of Polar Codes for Channels with Moderate Input Alphabet Sizes Ido Tal 1 /

On the Construction of Polar Codes for Channels with Moderate Input Alphabet Sizes Ido Tal 1 /

On the Construction of Polar Codes for Channels with Moderate Input Alphabet Sizes Ido Tal 1 / 19 Problem: Construction of polar (LDPC) codes, for a channel with moderate input alphabet size q . Say, q 16. Punchline: Provably hard

548 views • 19 slides
A GPU Implementation of Belief Propagation Decoder for Polar Codes Bharath Kumar Reddy L. and

A GPU Implementation of Belief Propagation Decoder for Polar Codes Bharath Kumar Reddy L. and

A GPU Implementation of Belief Propagation Decoder for Polar Codes Bharath Kumar Reddy L. and Nitin Chandrachoodan Indian Institute of Technology Madras Nov 6, 2012 Bharath et al. (IIT Madras) GPU Polar Codes Nov 6, 2012 1 / 29 Outline

366 views • 36 slides
Combinational Logic Building Blocks Chapter 6 Combinational Logic Introduction Decoders Basic

Combinational Logic Building Blocks Chapter 6 Combinational Logic Introduction Decoders Basic

Combinational Logic Building Blocks Chapter 6 Combinational Logic Introduction Decoders Basic Decoder Decoders Decoders With Enable Decoders Truth Tables Decoders Implementation Decoders Designing with Decoders Any Boolean function

415 views • 29 slides
Polar Codes for the Deletion Channel: Weak and Strong Polarization Ido Tal 1 Henry D. Pfister 2

Polar Codes for the Deletion Channel: Weak and Strong Polarization Ido Tal 1 Henry D. Pfister 2

Polar Codes for the Deletion Channel: Weak and Strong Polarization Ido Tal 1 Henry D. Pfister 2 Arman Fazeli 3 Alexander Vardy 3 1 Technion 2 Duke 3 UCSD Big picture first A polar coding scheme for the deletion channel where the: Deletion

893 views • 30 slides
Combining Hard and Soft Decoders for Hypergraph Product Codes Antoine Grospellier 1 ; Lucien Grou`

Combining Hard and Soft Decoders for Hypergraph Product Codes Antoine Grospellier 1 ; Lucien Grou`

Classical code construction Noiseless syndrome Noisy syndrome Summary Combining Hard and Soft Decoders for Hypergraph Product Codes Antoine Grospellier 1 ; Lucien Grou` es 1 ; Anirudh Krishna 2 ; Anthony Leverrier 1 1 INRIA Paris, 2 Universit

662 views • 28 slides
Computer Generation of Efficient Software Viterbi Decoders Frdric de Mesmay, Srinivas

Computer Generation of Efficient Software Viterbi Decoders Frdric de Mesmay, Srinivas

Carnegie Mellon Computer Generation of Efficient Software Viterbi Decoders Frdric de Mesmay, Srinivas Chellappa, Franz Franchetti, Markus Pschel Electrical and Computer Engineering Carnegie Mellon University Co-Founder SpiralGen, Inc.

475 views • 26 slides
Polar Codes for Classical, Private, and Quantum Communication and Superactivation! (with Joseph

Polar Codes for Classical, Private, and Quantum Communication and Superactivation! (with Joseph

Polar Codes for Classical, Private, and Quantum Communication and Superactivation! (with Joseph M. Renes) Mark M. Wilde School of Computer Science McGill University In collaboration with Saikat Guha arXiv:1109.2591, arXiv:1109.5346 Second

368 views • 21 slides
Computer Systems Lecture 7 Assembly Language Intro CS 230 - Spring 2020 2-1 System Layers

Computer Systems Lecture 7 Assembly Language Intro CS 230 - Spring 2020 2-1 System Layers

CS 230 Introduction to Computers and Computer Systems Lecture 7 Assembly Language Intro CS 230 - Spring 2020 2-1 System Layers Python/C/Racket Code Multiprocessing and Operating Systems Build and Runtime Environments Memory and

717 views • 30 slides
Welcome to 1st Grade Curriculum Night At Pittsfjeld Elementary Conferences & Attendance:

Welcome to 1st Grade Curriculum Night At Pittsfjeld Elementary Conferences & Attendance:

Welcome to 1st Grade Curriculum Night At Pittsfjeld Elementary Conferences & Attendance: Please click in the chat to sign in with your childs name for attendance Mrs. Duman Ms. Kilmewald Principals Message

289 views • 26 slides
Design Thinking Design Thinking Is Innovation magic? Asked to describe innovation processes, Tim

Design Thinking Design Thinking Is Innovation magic? Asked to describe innovation processes, Tim

Design Thinking Design Thinking Is Innovation magic? Asked to describe innovation processes, Tim Brennan of Apples Creative Services drew the following picture: 2 3 The Growth Leader Field Research Survey Database 70+ leaders from the

684 views • 34 slides
FSE & Try them online: http://rise4fun.com Margus Veanes Margus Veanes David Molnar Slide

FSE & Try them online: http://rise4fun.com Margus Veanes Margus Veanes David Molnar Slide

Nikolaj Bjrner Microsoft Research Deduction at Scale, Schlo Ringberg March 7 FSE & Try them online: http://rise4fun.com Margus Veanes Margus Veanes David Molnar Slide shamelessly stolen and adapted from [Patrice Godefroid, ISSTA

462 views • 23 slides
Trading Communication and Computing for Distributed Matrix Multiplication ISIT, June 21-26, 2020

Trading Communication and Computing for Distributed Matrix Multiplication ISIT, June 21-26, 2020

Multi-Cell Mobile Edge Coded Computing: Trading Communication and Computing for Distributed Matrix Multiplication ISIT, June 21-26, 2020 Emerging Mobile Applications Computation-intensive Delay-sensitive 2 Mobile Edge Computing

444 views • 21 slides
The Probabilistic Method Week 10: Applications Joshua Brody CS49/Math59 Fall 2015 Reading

The Probabilistic Method Week 10: Applications Joshua Brody CS49/Math59 Fall 2015 Reading

The Probabilistic Method Week 10: Applications Joshua Brody CS49/Math59 Fall 2015 Reading Quiz What is the Hamming Distance between two n-bit strings x,y? (A) dist(x,y) = #i such that x i != y i (B) dist(x,y) = sqrt( i |x i - y i |) (C)

446 views • 19 slides
ts rs s r

ts rs s r

ts rs s r t rs s Prr

962 views • 79 slides
Private information retrieval schemes based on codes Julien Lavauzelle IRMAR, Universit de

Private information retrieval schemes based on codes Julien Lavauzelle IRMAR, Universit de

Private information retrieval schemes based on codes Julien Lavauzelle IRMAR, Universit de Rennes 1 Sminaire Mathmatiques Discrtes, Codes et Cryptographie 20/02/2020 Cryptographic primitives based on codes Best-known cryptographic

957 views • 91 slides

More recommend