Method and apparatus for non-speculative pre-fetch operation in data packet processing
View Patent ↗A system is provided for enabling a non-speculative pre-fetch operation for processing instructions to be performed in the background ahead of immediate packet processing by a packet processor. The system comprises a packet-management unit for accepting data packets and enqueuing them for processing, a processor unit for processing the data packets, a processor core memory for holding context registers and functional units for processing, a memory for holding a plurality of instruction threads and a software-configurable hardware table for relating queues to pointers to beginnings of instruction threads. The packet-management unit selects an available context in the processor core for processing of a data packet, consults the table, and communicates the pointer to the processor, enabling the processor to perform the non-speculative pre-fetch for instructions.
1. A system for processing packets, the system comprising:
a packet management unit (PMU) to:
select a context for processing a data packet;
identify a thread for use in processing the data packet;
convey an identification of the thread and the context; and
load information corresponding to the packet into the context; and
a processing unit to:
receive the identification of the thread and the context from the PMU; and
initiate a pre-fetch of instructions of the thread prior to the PMU completing the load of the information into the context.
2. The system of claim 1 , wherein the packet management unit is identifies said thread by accessing a table which associates threads with packet types.
3. The system of claim 2 , wherein said table comprises a plurality of queues, each of said queues for storing packets of a particular type.
4. The system of claim 3 , wherein for each of said queues, the table comprises an identifier which identifies a thread for use in processing packets of a corresponding type.
5. The system of claim 4 , wherein said identifier comprises an address of a first instruction of a thread.
6. The system of claim 2 , wherein the table comprises a software configurable hardware table.
7. The system of claim 1 , wherein said processing unit comprises a first portion for processing the data packets, and a second portion comprising a pool of context registers.
8. The system of claim 7 , wherein said PMU selects said context from said pool of contexts via a dedicated link which couples the PMU to the processing unit.
9. The system of claim 1 , wherein the processing unit pre-fetches one or more of said instructions at least partially in parallel with the PMU loading the information corresponding to the packet into the context.
10. The system of claim 3 , wherein the PMU further en-queues a received data packet into one of said queues according to a classification scheme.
11. The system of claim 10 , wherein the classification scheme is based on packet type and/or priority.
12. The system of claim 11 , wherein said packet types include voice over Internet protocol packets and/or e-mail packets.
13. The system of claim 3 , wherein in response to receiving a given packet of an undetermined type, the PMU stores the given packet in a special queue dedicated for storing unclassified packets, and convey an identification of a thread configured to identify packet types.
14. The system of claim 1 , wherein said PMU and processing unit are part of a dynamic multi-streaming processor.
15. The system as recited in claim 1 , wherein said pre-fetch is non-speculative.
16. A method for processing data packets, the method comprising:
selecting a context for processing a data packet;
identifying a thread for use in processing the data packet;
conveying an identification of the thread and the context;
loading information corresponding to the packet into the context; and
initiating a pre-fetch of instructions of the thread prior to completing said loading of the information into the context.
17. The method of claim 16 , wherein said identifying comprises accessing a table which associates threads with packet types.
18. The method of claim 17 , wherein said table comprises a plurality of queues, each of said queues being configured to store packets of a particular type.
19. The method of claim 18 , wherein for each of said queues, the table comprises an identifier which identifies a thread for use in processing packets of a corresponding type.
20. The method of claim 19 , wherein said identifier comprises an address of a first instruction of a thread.
21. The method of claim 17 , wherein the table comprises a software configurable hardware table.
22. The method of claim 21 , wherein said method comprises selecting said context from a pool of contexts.
23. The method of claim 16 , wherein pre-fetching said instructions is performed at least partially in parallel with the loading of the information corresponding to the packet into the context.
24. The method of claim 18 , further comprising en-queuing a received data packet into one of said queues according to a classification scheme.
25. The method of claim 24 , wherein the classification scheme is based on packet type and/or priority.
26. The method of claim 25 , wherein said packet types include voice over Internet protocol packets and/or e-mail packets.
27. The method of claim 18 , wherein in response to receiving a given packet of an undetermined type, the method comprises storing the given packet in a special queue dedicated for storing unclassified packets, and conveying an identification of a thread configured to identify packet types.
28. The method of claim 16 , wherein said pre-fetch is non-speculative.