Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: Hari Byte vs. Word Striping

At first blush, I would argue that this abstract describes the
"byte-striped" approach.  The bit about "word synchronization" sounds like
byte lane deskew.


At 12:54 PM 11/26/99 -0800, Rich Taborek wrote:
>Sorry, I forgot to fill out the details of criteria #14 prior to sending the 
>note out.
>Here it is:
>14) Patent Protection:
>Word-Striping: US Patent 5570356: High bandwidth communications system 
>having multiple
>serial links
>Inventors: Finney, Damon W. , San Jose, CA; Jenkins, Michael O. , San
Jose, CA;
>Rayfield, Michael J. , Tucson, AZ
>Assignee: IBM Corp.
>Issue Date: Oct. 29, 1996
>Abstract: A data communication system includes a phase splitting circuit to 
>split a high
>speed parallel data word into a number of individual parallel data bytes, a 
>multiplexor for each of the phases of a phase splitting circuit, encoding and
>serialization circuits for converting each byte such as an 8-bit byte to an 
>encoded form
>suitable for serial transmission such as by employing the Widmer et al. 
>code, transmitting each encoded byte across one of a number of serial 
>transmission links
>to a receiving device where the data is deserialized and decoded to recover 
>the original
>byte which is then synchronized by a byte synchronization circuit. The byte
>synchronization circuits are then coupled to a word synchronization circuit 
>where the
>original high bandwidth data word is recovered and transmitted on an 
>internal high speed
>parallel bus within the receiving device.
>Byte-Striping: None known.
>Advantage: Byte-Striping.
>Best regards,
>  ----------------------------------------------------------
>Richard Taborek Sr.   1441 Walnut Dr.   Campbell, CA 95008 USA
>Tel: 408-330-0488 or 408-370-9233           Cell: 408-832-3957
>Email: rtaborek@xxxxxxxxxx or rtaborek@xxxxxxxxxxxxx