Claims
- 1. A method of transferring data from a processing element having a plurality of processing units to a centralized processor, said method comprising the steps of:
partitioning said plurality of processing units into one or more groups, and assigning each group a start time and a transfer rate; collecting data output from each group in accordance with each group's start time and transfer rate and multiplexing said data outputs into a single multiplexed data stream; transferring said multiplexed data stream to a memory input buffer; and extracting and distributing the contents of said memory input buffer to individual unit buffers, each unit buffer associated with a different processing unit.
- 2. The method according to claim 1, wherein data from all processing units associated with a group are transferred at the same rate.
- 3. The method according to claim 1, further comprising the step of buffering data for a processing unit in the event the unit operates at a rate faster than that assigned to its group.
- 4. The method according to claim 1, further comprising the step of repeating data for a processing unit in the event the unit operates at a rate slower than that assigned to its group.
- 5. The method according to claim 1, wherein the rate assigned to a group is fixed.
- 6. The method according to claim 1, wherein the rate assigned to a group is configurable.
- 7. The method according to claim 1, further comprising the step of transferring said multiplexed data stream during a configuration period whereby the demultiplexing of said data is performed using an index buffer generated by simulating the generation of said multiplexed data stream.
- 8. The method according to claim 1, wherein data is collected cyclically with data from each group collected during a cycle, a plurality of cycles making up a time slot.
- 9. The method according to claim 1, wherein said step of distributing comprises the step of extracting all data for one unit buffer from said memory input buffer before extracting data for another unit buffer.
- 10. The method according to claim 1, wherein said step of distributing comprises the step of extracting data sequentially from said input buffer and distributing it to a unit buffer corresponding to the data extracted.
- 11. The method according to claim 1, wherein one or more processing units of said processing element may be inoperative at any point in time.
- 12. An apparatus for transferring data from a processing element incorporating a plurality of processing units to a centralized processor, comprising:
a data collector adapted to collect and multiplex data output from said plurality of processing units into a single multiplexed data stream, said plurality of processing units organized into a plurality of multiplexer groups in accordance with a start time and transfer rate assigned to each multiplexer group; a memory adapted to store said multiplexed data stream; a data transfer unit adapted to transfer said multiplexed data stream output from said data collector to an input buffer in said memory; and software means operative on said centralized processor to organize said plurality of processing units into one or more multiplexer groups, each group being assigned a start time and a transfer rate, and to demultiplex and distribute the contents of said input buffer to unit buffers, each unit buffer associated with a different processing unit.
- 13. The apparatus according to claim 12, wherein data from all processing units associated with a group are transferred at the same rate.
- 14. The apparatus according to claim 12, further comprising means for buffering data for a processing unit in the event the unit operates at a rate faster than that assigned to its group.
- 15. The apparatus according to claim 12, further comprising means for repeating data for a processing unit in the event the unit operates at a rate slower than that assigned to its group.
- 16. The apparatus according to claim 12, wherein the rate assigned to a group is fixed.
- 17. The apparatus according to claim 12, wherein the rate assigned to a group is configurable.
- 18. The apparatus according to claim 12, wherein said software means is adapted to simulate the operation of said data collector and to generate an index buffer thereby, wherein said multiplexed data stream transferred to said input buffer during a configuration period is demultiplexed using said index buffer.
- 19. The apparatus according to claim 12, wherein data is collected cyclically with data from each group collected during a cycle, a plurality of cycles making up a time slot.
- 20. The apparatus according to claim 12, wherein said centralized processor is adapted to extract all data for a unit buffer from said memory input buffer before extracting data for another unit buffer.
- 21. The apparatus according to claim 12, wherein said centralized processor is adapted to extract data sequentially from said input buffer and distribute it to a unit buffer corresponding to the data extracted.
- 22. The apparatus according to claim 12, wherein one or more processing units of said processing element may be inoperative at any point in time.
- 23. A Universal Mobile Terrestrial Service (UMTS) User Equipment (UE) compatible communications transceiver, comprising:
Radio Frequency (RF) circuitry coupled to an antenna; an analog front-end processor coupled to said RF circuitry; a co-processor incorporating a plurality of processing units partitioned into one or more groups, each group having associated with it a start time and transfer rate, said co-processing adapted to collect and multiplex data output from said one or more groups into a single multiplexed data stream; a memory input buffer adapted to store said single multiplexed data stream output of said co-processor; data transfer means adapted to transfer data output from said co-processor to said memory buffer; and a processor programmed to demultiplex and distribute the contents of said memory input buffer to unit buffers, each unit buffer associated with a different processing unit.
- 24. The transceiver according to claim 23, wherein the rate assigned to a group is fixed.
- 25. The transceiver according to claim 23, wherein the rate assigned to a group is configurable.
- 26. The transceiver according to claim 23, wherein said processing units comprise fingers of a rake receiver.
- 27. The transceiver according to claim 23, further comprising means for transferring said multiplexed data stream during a configuration period whereby the demultiplexing of said buffer contents is performed using an index buffer generated by simulating the multiplexing operation of said co-processor.
- 28. The transceiver according to claim 23, wherein data is collected cyclically with data from each group collected during a cycle, a plurality of cycles making up a time slot.
- 29. The transceiver according to claim 23, wherein said processing is adapted to demultiplex and distribute all data for one unit buffer from said memory input buffer before extracting data for another unit buffer.
- 30. The transceiver according to claim 23, wherein said processor is adapted to demultiplex and distribute data sequentially from said input buffer and distribute it to a unit buffer corresponding to the data extracted.
- 31. The transceiver according to claim 23, wherein one or more processing units of said co-processor may be inoperative at any point in time.
- 32. A method of data transfer between a processing element having a plurality of processing units and a centralized processor in a Universal Mobile Terrestrial Service (UMTS) User Equipment (UE) compatible communications transceiver, said method comprising the steps of:
partitioning said plurality of processing units in said processing element into one or more groups, each group assigned a start time and a transfer rate; collecting and multiplexing data output from each group in accordance with its start time and transfer rate so as to generate a single multiplexed data stream; transferring said single multiplexed data stream to a memory input buffer; and demultiplexing and distributing on said centralized processor the contents of said memory input buffer to individual unit buffers, each unit buffer associated with a different processing unit.
- 33. The method according to claim 32, wherein the rate assigned to a group is fixed.
- 34. The method according to claim 32, wherein the rate assigned to a group is configurable.
- 35. The method according to claim 32, further comprising the step of transferring data during a configuration period whereby the demultiplexing of said buffer contents is performed using an index buffer generated by simulating the generation of said multiplexed data stream.
- 36. The method according to claim 32, wherein data is collected cyclically with data from each group collected during a cycle, a plurality of cycles making up a time slot.
- 37. The method according to claim 32, wherein said step of demultiplexing and distributing comprises demultiplexing and distributing all data for one unit buffer from said memory input buffer before extracting data for another unit buffer.
- 38. The method according to claim 32, wherein said step of demultiplexing and distributing comprises demultiplexing and distributing data sequentially from said input buffer and distributing it to a unit buffer corresponding to the data extracted.
- 39. The method according to claim 32, wherein one or more processing units of said processing element may be inoperative at any point in time.
REFERENCE TO RELATED APPLICATIONS
[0001] This application is related to U.S. Application Serial No. ______, filed Oct. 1, 2002, entitled “Information Transfer And Interrupt Event Scheduling Scheme For A Communications Transceiver Incorporating Multiple Processing Elements”, similarly assigned and incorporated herein by reference in its entirely.