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.
JR
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
>byte
>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.
>8-bit/10-bit
>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,
>Rich
>
> ----------------------------------------------------------
>
>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
>
>
>