Data protocol

• US 7,934,141 B2
• Filed: 03/03/2004
• Issued: 04/26/2011
• Est. Priority Date: 03/03/2003
• Status: Active Grant

• Current Assignee: Xilinx, Inc. (Advanced Micro Devices, Inc.)
• Original Assignee: SolarFlare Communications Incorporated (Advanced Micro Devices, Inc.)
• Inventors: Clarke, David, Pope, Steve L., Riddoch, David, Roberts, Derek
• Primary Examiner(s): Lamarre; Guy J
• Application Number:
  US10/548,126
• Publication Number:
  US 20070162609A1
• Time in Patent Office: 2,610 Days
• Field of Search: 714/758, 702/189
• US Class Current: 714/758
• CPC Class Codes: H04L 1/0061 Error detection codes
• CPC Class Codes: H04L 1/007 Unequal error protection for format H04L1/0078; for codes per se H03M13/35
• CPC Class Codes: H04L 1/0078 Avoidance of errors by organising the transmitted data in a format specifically designed to deal with errors, e.g. location forward error control, e.g. FEC, CRC H04L1/004; adaptive formatting H04L1/0006; mappings H04L27/00

Abstract

A method of transmitting data according to a data transmission protocol wherein the data is transmitted as a plurality of data frames and each data frame includes an error checking field comprising at least two sub-fields, the data of the first sub-field being formed by a first error checking method performed on data of the frame and the data of the second sub-field being formed by a second error checking method performed on the said data of the frame, the first and second methods being such that the data of the first sub-field has different error checking properties from those of the data of the second sub-field.

Claims

1. A method of transmitting data according to a data transmission protocol as a plurality of data frames, each data frame including a frame header and an error checking field comprising at least two sub-fields, the method comprising for each data frame:

forming data for a first sub-field of the error checking field by a first error checking method performed on particular data of the frame;

forming data for a second sub-field of the error checking field by a second error checking method performed on the particular data of the frame; and

transmitting the data frame;

wherein the first and second error checking methods are such that the data of the first sub-field has different error checking properties from those of the data of the second sub-field, and the frame header is excluded from the data of the frame on which the first and second error checking methods are performed.

2. A method as claimed in claim 1, wherein the error checking field is a data word in the data frame.

3. A method as claimed in claim 2, wherein the error checking field consists of data bits that are contiguous in the frame.

4. A method as claimed in claim 1, wherein the first sub-field consists of bits that are contiguous in the frame.

5. A method as claimed in claim 1, wherein each of the first and second sub-fields consists of bits that are contiguous in the frame.

6. A method as claimed in claim 1, wherein the first sub-field and the second sub-field are of equal length.

7. A method as claimed in claim 1, wherein the first and second error checking methods are cyclic redundancy check methods using respective first and second generator polynomials, and the generator polynomial for the first error checking method is different from the generator polynomial for the second error checking method.

8. A method as claimed in claim 7, wherein one of the generator polynomials is the X25 polynomial.

9. A method as claimed in claim 7, wherein one of the generator polynomials is the USB CRC-16 polynomial.

10. A method as claimed in claim 1, wherein the first and second error checking methods are such that they result in the data of the first sub-field having different statistical properties from the data of the second sub-field as regards its indication of errors in data.

11. A method as claimed in claim 1, wherein the protocol is such that each data frame comprises at least one data section, each data section comprising an address and traffic data to be applied to that address by a recipient of the data frame.

12. A method as claimed in claim 1, wherein the frame header indicates a member of the group consisting of a source address of the data frame, a destination address of the data frame and a hop count for the data frame.

13. A method as claimed in claim 1, wherein the data frame is an Ethernet frame.

14. A method as claimed in claim 1, wherein the protocol is such that the data frame comprises a frame checksum calculated over the frame.

15. A method as claimed in claim 14, wherein the frame header is included in the data on which the frame checksum is calculated.

16. A method as claimed in claim 1, comprising:

at a data transmitter forming a data frame according to the data transmission protocol;

transmitting the data frame over a data network from the data transmitter to a data receiver; and

at the data receiver verifying the received data on the basis of the data of the first and second sub-fields of the error checking field.

17. A data transceiver, for use in transmitting data according to a data transmission protocol as a plurality of data frames, each data frame in the plurality including a frame header and an error checking field comprising at least two sub-fields, comprising:

means for forming data for a first sub-field of the error checking field in each given frame in the plurality, by a first error checking method performed on particular data of the given frame;

means for forming data for a second sub-field of the error checking field in each particular frame in the plurality, by a second error checking method performed on the particular data of the particular frame; and

transmitting the data frames in the plurality,

wherein the first and second error checking methods are such that the data of the first sub-field of each subject frame in the plurality has different error checking properties from those of the data of the second sub-field of the subject frame, and the frame header of the subject frame is excluded from the data of the frame on which the first and second error checking methods are performed.