Patterned memory-network data transfer

Patent metadata

Field	Value
Publication number	US-12216575-B2
Application number	US-202217858104-A
Country	US
Kind code	B2
Filing date	Jul 6, 2022
Priority date	Jul 6, 2022
Publication date	Feb 4, 2025
Grant date	Feb 4, 2025

Abstract

A network device includes a first interface, a second interface, and circuitry. The first interface is configured to communicate at least with a memory. The second interface is configured to communicate over a network with a peer network device. The circuitry is configured to receive a request to transfer data over the network between the memory and the peer network device in accordance with (i) a pattern of offsets to be accessed in the memory and (ii) a memory key representing a memory space to be accessed using the pattern, and to transfer the data in accordance with the request.

First claim

The invention claimed is:

1. A network device, comprising:
a first interface, configured to communicate at least with a memory;
a second interface, configured to communicate over a network with a peer network device; and
circuitry, configured to pre-register a plurality of patterns of offsets, to pre-associate a memory key representing a memory space to be accessed with a given pattern from the plurality of patterns of offsets, to receive a request to transfer data over the network between the memory and the peer network device, wherein the request indicates the memory key, but not the given pattern pre-associated with the memory key, and to transfer the data in accordance with the request using the memory key and the given pattern pre-associated with the memory key.

2. The network device according to claim 1 , wherein the circuitry is configured to receive the request as a work-request via the first interface.

3. The network device according to claim 1 , wherein each of the pre-registered patterns of offsets comprises one of (i) a pattern that accesses a contiguous memory space, (ii) a pattern that accesses a non-contiguous memory space, and (iii) a strided pattern.

4. The network device according to claim 1 , wherein the request specifies multiple memory keys representing respective memory spaces to be accessed using the pattern.

5. The network device according to claim 1 , wherein the memory space represented by the memory key is one of a virtual memory space and a physical memory space.

6. The network device according to claim 1 , wherein, in response to receiving a re-association instruction, the circuitry is configured to associate the memory key with a different pattern.

7. The network device according to claim 1 , wherein the pattern is pre-associated in the network device with at least one additional memory key.

8. The network device according to claim 1 , wherein the request specifies a starting virtual address or initial offset parameter for the pattern.

9. The network device according to claim 1 , wherein the pattern specifies the offsets using a nested representation that comprises at least one internal pattern.

10. The network device according to claim 1 , wherein the pattern specifies the offsets using an iterative representation that defines (i) a basic pattern to be iterated multiple times, (ii) a number of times the basic pattern is to be iterated, and (iii) an offset between successive iterations of the basic pattern.

11. The network device according to claim 1 , wherein the request is associated with a scatter or gather command.

12. The network device according to claim 1 , wherein the request is associated with an InfiniBand transaction.

13. The network device according to claim 1 , wherein the request is associated with an Ethernet transaction.

14. A method for data transfer, comprising:
in a network device, communicating with a memory and, over a network, with a peer network device;
pre-registering, in the network device, a plurality of patterns of offsets;
pre-associating a memory key representing a memory space to be accessed with a given pattern from the plurality of patterns of offsets;
receiving in the network device a request to transfer data over the network between the memory and the peer network device, wherein the request indicates the memory key, but not the given pattern pre-associated with the memory key; and
transferring the data in accordance with the request using the memory key and the given pattern pre-associated with the memory key.

15. The method according to claim 14 , wherein receiving the request comprises receiving the request as a work-request via the first interface.

16. The method according to claim 14 , wherein each of the multiple pre-registered patterns of offsets comprises one of (i) a pattern that accesses a contiguous memory space, (ii) a pattern that accesses a non-contiguous memory space, and (iii) a strided pattern.

17. The method according to claim 14 , wherein the request specifies multiple memory keys representing respective memory spaces to be accessed using the pattern.

18. The method according to claim 14 , wherein the memory space represented by the memory key is one of a virtual memory space and a physical memory space.

19. The method according to claim 14 , and comprising, in response to receiving a re-association instruction, associating the memory key with a different pattern.

20. The method according to claim 14 , wherein the pattern is pre-associated in the network device with at least one additional memory key.

21. The method according to claim 14 , wherein the request specifies a starting virtual address or initial offset parameter for the pattern.

22. The method according to claim 14 , wherein the pattern specifies the offsets using a nested representation that comprises at least one internal pattern.

23. The method according to claim 14 , wherein the pattern specifies the offsets using an iterative representation that defines (i) a basic pattern to be iterated multiple times, (ii) a number of times the basic pattern is to be iterated, and (iii) an offset between successive iterations of the basic pattern.

24. The method according to claim 14 , wherein the request is associated with a scatter or gather command.

25. The method according to claim 14 , wherein the request is associated with an InfiniBand transaction.

26. The method according to claim 14 , wherein the request is associated with an Ethernet transaction.

Assignees

• Mellanox Technologies Ltd

Inventors

• Marcovitch Daniel
• Bloch Gil
• Graham Richard
• Itigin Yossef
• Ben Moshe Ortal
• Nudelman Roman

Classifications

• G06F12/0835

  for main memory peripheral accesses (e.g. I/O or DMA) · CPC title

• G06F15/17331

  Distributed shared memory [DSM], e.g. remote direct memory access [RDMA] · CPC title

• G06F13/4027 Primary

  using bus bridges (G06F13/4022 takes precedence) · CPC title

• H04L67/141

  Setup of application sessions (admission control or resource allocation in data switching networks H04L47/70) · CPC title

• G06F13/404

  with address mapping · CPC title