Method and system for reconfigurable parallel lookups using multiple shared memories

Patent metadata

Field	Value
Publication number	US-9620213-B2
Application number	US-201314142511-A
Country	US
Kind code	B2
Filing date	Dec 27, 2013
Priority date	Dec 27, 2013
Publication date	Apr 11, 2017
Grant date	Apr 11, 2017

Abstract

Embodiments of the present invention relate to multiple parallel lookups using a pool of shared memories by proper configuration of interconnection networks. The number of shared memories reserved for each lookup is reconfigurable based on the memory capacity needed by that lookup. The shared memories are grouped into homogeneous tiles. Each lookup is allocated a set of tiles based on the memory capacity needed by that lookup. The tiles allocated for each lookup do not overlap with other lookups such that all lookups can be performed in parallel without collision. Each lookup is reconfigurable to be either hash-based or direct-access. The interconnection networks are programmed based on how the tiles are allocated for each lookup.

First claim

We claim:

1. A system on-chip configured to support N parallel lookups using a pool of shared memories, the system on-chip comprising:
a pool of T×M shared memories are grouped into T tiles;
M index converters for each of N lookup paths;
a central reconfigurable interconnect fabric for connecting N input ports to the T tiles;
an output reconfigurable interconnect fabric for connecting the T tiles to N output ports; and
N output result collectors, wherein each of the N output result collectors is per one lookup path, wherein the system on-chip is configured to perform N parallel lookups against the pool of T×M shared memories along the N lookup paths, wherein N, T and M are positive integer values.

2. The system on-chip of claim 1 , wherein the T tiles are partitioned and allocated for the lookup paths based on memory capacity needed by each of the lookup paths.

3. The system on-chip of claim 1 , wherein a number of tiles allocated for each lookup path of the N lookup paths is a power of 2, and a tile cannot overlap among partitions.

4. The system on-chip of claim 1 , wherein each lookup path is configurable to be a hash-based lookup or a direct-access lookup.

5. The system on-chip of claim 1 , wherein index converter i of M index converters of each lookup path of the N lookup paths is used to access memory i in one of the T tiles allocated for that lookup path.

6. The system on-chip of claim 1 , wherein each of M index converters of each lookup path of the N lookup paths is configurable based on a number of tiles allocated for that lookup path of the N lookup paths.

7. The system on-chip of claim 1 , wherein the central reconfigurable interconnect fabric includes M configurable N×T networks.

8. The system on-chip of claim 1 , wherein each of the N×T networks is one of a crossbar and a configurable butterfly.

9. The system on-chip of claim 1 , wherein the output reconfigurable interconnect fabric includes T configurable 1×N de-multiplexors.

10. The system on-chip of claim 1 , wherein one of N output result collectors associated with a lookup path of the N lookup paths is configured to collect results from allocated tiles for the lookup path and is configured to select one final result from results outputted by the allocated tiles.

11. The system on-chip of claim 1 , wherein a hit result for each of the T tiles is based on key matching results between pre-programmed keys in memories of that tile and an input key of that tile.

12. A system on-chip configured to support N parallel lookups using a pool of shared memories, the system on-chip comprising:
T×M shared memories are grouped into T tiles;
M index converters for each lookup path;
a central reconfigurable interconnect fabric for connecting N input ports to the T tiles;
an output reconfigurable interconnect fabric for connecting the T tiles to N output ports; and
N output result collectors, wherein each of the N output result collectors is per one lookup path, wherein each of the T tiles includes:
M memories for supporting D-LEFT lookups with M ways per lookup;
a matching block for comparing pre-programmed keys in the M memories with an input key; and
a selection block for selecting a hit result for that tile, wherein N, T and M are positive integer values.

13. A system on-chip configured to support N parallel lookups using a pool of shared memories, the system on-chip comprising:
T×M shared memories are grouped into T tiles;
M index converters for each lookup path;
a central reconfigurable interconnect fabric for connecting N input ports to the T tiles;
an output reconfigurable interconnect fabric for connecting the T tiles to N output ports; and
N output result collectors, wherein each of the N output result collectors is per one lookup path, wherein each of the shared memories has 2 m entries, wherein each of the entries contains P pairs of programmable {key, data} for supporting D-LEFT lookups with P buckets per way, wherein P, N, T and M are positive integer values.

14. A system on-chip configured to support N parallel lookups using a pool of shared memories, the system on-chip comprising:
T×M shared memories are grouped into T tiles;
M index converters for each lookup path;
a central reconfigurable interconnect fabric for connecting N input ports to the T tiles;
an output reconfigurable interconnect fabric for connecting the T tiles to N output ports; and
N output result collectors, wherein each of the N output result collectors is per one lookup path, wherein each of M index converters of each lookup path further comprises:
log 2 (T)+1 hash functions and log 2 (T)+1 non-hash functions, wherein outputs of the functions have bitwidths ranging from m bits to log 2 (T)+m bits;
a first configurable register for selecting one of the functions; and
a second configurable register for selecting a tile offset such that a lookup index points to a correct tile among allocated tiles of that lookup path, wherein the allocated tiles are selected from the T tiles, wherein m, N, T and M are positive integer values.

15. A system on-chip configured to support N parallel lookups using a pool of shared memories, the system on-chip comprising:
T×M shared memories are grouped into T tiles;
M index converters for each lookup path;
a central reconfigurable interconnect fabric for connecting N input ports to the T tiles;
an output reconfigurable interconnect fabric for connecting the T tiles to N output ports; and
N output result collectors, wherein each of the N output result collectors is per one lookup path, wherein an output index of each of the M index converters has log 2 (T)+m bits, wherein the log 2 (T) most significant bits in the output index are used to point to one of the T tiles and the m last significant bits in the output index are used as a memory read address, wherein m, N, T and M are positive integer values.

Assignees

• Cavium Inc

Inventors

• Tran Anh T
• Schmidt Gerald
• Daniel Tsahi
• Shrivastava Saurabh

Classifications

• G06F12/0864

  using pseudo-associative means, e.g. set-associative or hashing · CPC title

• H04L45/7453

  using hashing · CPC title

• G06F3/061

  Improving I/O performance · CPC title

• G06F3/0683

  Plurality of storage devices · CPC title

• G11C15/04 Primary

  using semiconductor elements · CPC title