AN 846: Intel® Stratix® 10 Forward Error Correction

Download PDF
ID 683805
Date 7/02/2018
Public
Document Table of Contents
Document Table of Contents x
1. Introduction 2. Necessity of Error Correction 3. FEC Selection 4. FEC in Intel® Stratix® 10 H-Tile Devices 5. FEC in Intel® Stratix® 10 E-Tile Devices 6. FEC Implementation Using the E-Tile Channel Placement Tool 7. FEC in Practical Application 8. Hardware Results 9. Document Revision History for AN 846: Intel® Stratix® 10 Forward Error Correction
2. Necessity of Error Correction x
2.1. Solutions to Transmission Errors 2.2. Error Correction Codes 2.3. What is FEC?
2.1. Solutions to Transmission Errors x
2.1.1. Parity and Cyclic Redundancy Check 2.1.2. Error Correction Code (ECC) Block Coding
2.3. What is FEC? x
2.3.1. FEC Definitions
3. FEC Selection x
3.1. Key Considerations when Choosing a FEC
4. FEC in Intel® Stratix® 10 H-Tile Devices x
4.1. Fire Code (802.3ap, 10GBASE-KR)
4.1. Fire Code (802.3ap, 10GBASE-KR) x
4.1.1. FEC Block Format 4.1.2. FEC Block Composition 4.1.3. FEC Sublayer for BASE-R PHYs 4.1.4. L-Tile/H-Tile Implementation
4.1.4. L-Tile/H-Tile Implementation x
4.1.4.1. Transcode Encoder 4.1.4.2. KR FEC Encoder 4.1.4.3. KR FEC Scrambler 4.1.4.4. KR FEC TX Gearbox 4.1.4.5. KR FEC RX Gearbox 4.1.4.6. Transcode Decoder
5. FEC in Intel® Stratix® 10 E-Tile Devices x
5.1. Types of RS-FEC 5.2. 100GBASE-KR4 5.3. 100GBASE-KP4 5.4. FEC Decoders 5.5. Specifications 5.6. Functions Within the RS-FEC Sublayer
5.1. Types of RS-FEC x
5.1.1. RS (528, 514, t = 7, m = 10) 5.1.2. RS (544, 514, t = 15, m = 10) 5.1.3. Supported RS-FEC Modes in E-Tile Devices
5.2. 100GBASE-KR4 x
5.2.1. 100GBASE-KR4 Mapping (IEEE802.3bj Clause 91)
5.3. 100GBASE-KP4 x
5.3.1. 100GBASE-KP4 Mapping (IEEE802.3bj Clause 91)
5.6. Functions Within the RS-FEC Sublayer x
5.6.1. Lane Block Synchronization 5.6.2. Alignment Lock and Deskew 5.6.3. Lane Re-order 5.6.4. Alignment Marker Removal 5.6.5. 64B/66B to 256B/257B Transcoder
7. FEC in Practical Application x
7.1. Datacenter Applications Scenario
8. Hardware Results x
8.1. Test Design 8.2. Test Setup 8.3. Insertion Loss Plots 8.4. FEC Statistics Tool 8.5. Hardware Data 8.6. Comparison to the Specification 8.7. References
1. Introduction
2. Necessity of Error Correction
3. FEC Selection
4. FEC in Intel® Stratix® 10 H-Tile Devices
5. FEC in Intel® Stratix® 10 E-Tile Devices
6. FEC Implementation Using the E-Tile Channel Placement Tool
7. FEC in Practical Application
8. Hardware Results
9. Document Revision History for AN 846: Intel® Stratix® 10 Forward Error Correction

2.2. Error Correction Codes

There are two types of ECC codes, binary and non-binary.

In binary codes, the encoder and decoder operate on a bit basis. The 10GBASE-KR Fire Code FEC is an example of a binary code. In non-binary codes, the encoder and decoder operate on a byte or symbol basis. Symbols may be any number of bits. Galois finite field arithmetic is used and the Reed Solomon code is an example of a non-binary code.

Cyclic block codes are defined by a generator polynomial g(x). Encoding consists of adding a set of parity bits or symbols onto the data to create a code word, also called a codeword or a block. The parity is the remainder of the block from the polynomial division of the data bits by g(x). This is easily implemented using a linear feedback shift register (LFSR). Error detection and correction calculates the syndrome of the received code word. The syndrome is the difference between the locally-generated and received parity. If the syndrome is zero, the code word is correct. If the syndrome is non-zero, then the syndrome can determine the most likely error.

Level Two Title