Method for implementing a line speed interconnect structure

Patent metadata

Field	Value
Publication number	US-9740499-B2
Application number	US-201414213909-A
Country	US
Kind code	B2
Filing date	Mar 14, 2014
Priority date	Mar 15, 2013
Publication date	Aug 22, 2017
Grant date	Aug 22, 2017

Abstract

A method for line speed interconnect processing. The method includes receiving initial inputs from an input communications path, performing a pre-sorting of the initial inputs by using a first stage interconnect parallel processor to create intermediate inputs, and performing the final combining and splitting of the intermediate inputs by using a second stage interconnect parallel processor to create resulting outputs. The method further includes transmitting the resulting outputs out of the second stage at line speed.

First claim

What is claimed is:

1. A method for line speed interconnect processing, comprising:
receiving initial inputs from an input communications path;
performing a pre-sorting of the initial inputs by using a first stage interconnect parallel processor to create intermediate inputs, wherein the first stage interconnect processor functions by performing a presorting and pre-clustering process on the initial inputs in parallel to identify candidates among the initial inputs to be checked for pairing;
performing the final combining and splitting of the intermediate inputs by using a second stage interconnect parallel processor to create resulting outputs; and
transmitting the resulting outputs out of the second stage at line speed.

2. The method of claim 1 , wherein the second stage interconnect processor functions by performing position shuffling, pairing, and splitting of the intermediate inputs in parallel to create the resulting outputs at line speed.

3. The method of claim 1 , wherein the line speed interconnect processing is implemented in a networking architecture, wherein the initial inputs comprise networking packets.

4. The method of claim 1 , wherein the line speed interconnect processing is implemented in a cache accessing architecture, wherein the initial inputs comprise access requests to data of cache lines.

5. The method of claim 1 , wherein the line speed interconnect processing is implemented in an arbitration architecture, wherein the initial inputs comprise streams that utilize output bandwidth, and wherein the arbitration architecture arbitrates amongst the input streams using at least one of frequency and time multiplexing in parallel to create resulting output streams.

6. The method of claim 1 , wherein the line speed interconnect processing is implemented in a computer instruction architecture decoder, wherein the initial inputs comprise computer instructions that will be combined or split in parallel into machine instructions.

7. The method of claim 1 , wherein the line speed interconnect processing is implemented in a Dynamic Random Access Memory (DRAM) accessing architecture, wherein the initial inputs comprise accesses to DRAM pages that will be paired or split in parallel into optimized resulting accesses to DRAM pages.

8. A non-transitory computer readable memory having computer readable code which when executed by a computer system causes the computer system to implement a method for line speed interconnect processing, comprising:
receiving initial inputs from an input communications path;
performing a pre-sorting of the initial inputs by using a first stage interconnect parallel processor to create intermediate inputs, wherein the first stage interconnect processor functions by performing a presorting and pre-clustering process on the initial inputs in parallel to identify candidates among the initial inputs to be checked for pairing;
performing the final combining and splitting of the intermediate inputs by using a second stage interconnect parallel processor to create resulting outputs; and
transmitting the resulting outputs out of the second stage at line speed.

9. The computer readable memory of claim 8 , wherein the second stage interconnect processor functions by performing position shuffling, pairing, and splitting of the intermediate inputs in parallel to create the resulting outputs at line speed.

10. The computer readable memory of claim 8 , wherein the line speed interconnect processing is implemented in a networking architecture, wherein the initial inputs comprise networking packets.

11. The computer readable memory of claim 8 , wherein the line speed interconnect processing is implemented in a cache accessing architecture, wherein the initial inputs comprise access requests to data of cache lines.

12. The computer readable memory of claim 8 , wherein the line speed interconnect processing is implemented in an arbitration architecture, wherein the initial inputs comprise streams that utilize output bandwidth, and wherein the arbitration architecture arbitrates amongst the input streams using at least one of frequency and time multiplexing in parallel to create resulting output streams.

13. The computer readable memory of claim 8 , wherein the line speed interconnect processing is implemented in a computer instruction architecture decoder, wherein the initial inputs comprise computer instructions that will be combined or split in parallel into machine instructions.

14. The computer readable memory of claim 8 , wherein the line speed interconnect processing is implemented in a Dynamic Random Access Memory (DRAM) accessing architecture, wherein the initial inputs comprise accesses to DRAM pages that will be paired or split in parallel into optimized resulting accesses to DRAM pages.

15. A computer system, comprising:
a system memory;
a central processor unit coupled to the system memory, wherein the central processor unit executes computer readable code and causes the computer system to implement a method for line speed interconnect processing, comprising:
receiving initial inputs from an input communications path;
performing a pre-sorting of the initial inputs by using a first stage interconnect parallel processor to create intermediate inputs, wherein the first stage interconnect processor functions by performing a presorting and pre-clustering process on the initial inputs in parallel to identify candidates among the initial inputs to be checked for pairing;
performing the final combining and splitting of the intermediate inputs by using a second stage interconnect parallel processor to create resulting outputs; and
transmitting the resulting outputs out of the second stage at line speed.

16. The computer system of claim 15 , wherein the second stage interconnect processor functions by performing position shuffling, pairing, and splitting of the intermediate inputs in parallel to create the resulting outputs at line speed.

17. The computer system of claim 15 , wherein the line speed interconnect processing is implemented in a networking architecture, wherein the initial inputs comprise networking packets.

18. The computer system of claim 15 , wherein the line speed interconnect processing is implemented in a cache accessing architecture, wherein the initial inputs comprise access requests to data of cache lines.

19. The computer system of claim 15 , wherein the line speed interconnect processing is implemented in an arbitration architecture, wherein the initial inputs comprise streams that utilize output bandwidth, and wherein the arbitration architecture arbitrates amongst the input streams using at least one of frequency and time multiplexing in parallel to create resulting output streams.

20. The computer system of claim 15 , wherein the line speed interconnect processing is implemented in a computer instruction architecture decoder, wherein the initial inputs comprise computer instructions that will be combined or split in parallel into machine instructions.

21. The computer system of claim 15 , wherein the line speed interconnect processing is implemented in a Dynamic Random Access Memory (DRAM) accessing architecture, wherein the initial inputs comprise accesses to DRAM pages that will be paired or split in parallel into optimized resulting accesses to DRAM pages.

Assignees

• Intel Corp

Inventors

• Abdallah Mohammad

Classifications

• G06F12/0886

  Variable-length word access · CPC title

• G06F15/17318

  Parallel communications techniques, e.g. gather, scatter, reduce, roadcast, multicast, all to all · CPC title

• G06F2212/1041

  Resource optimization · CPC title

• G06F12/00

  Accessing, addressing or allocating within memory systems or architectures (digital input from, or digital output to record carriers, e.g. to disk storage units, G06F3/06) · CPC title

• H04L12/28

  characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks] (wireless communication networks H04W {; arrangements for dividing the transmission path H04W40/00}) · CPC title