Metadata compaction in packet coalescing

Patent metadata

Field	Value
Publication number	US-12438960-B2
Application number	US-202217691003-A
Country	US
Kind code	B2
Filing date	Mar 9, 2022
Priority date	Mar 9, 2022
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

Examples described herein relate to coalescing one or more messages into a coalesced message and representing one or more fields of the metadata of the one or more messages using one or more codes, wherein at least one of the one or more codes uses fewer bits than that of original metadata fields to compact the metadata fields. In some examples, the metadata includes at least one or more of: a target processing element (PE) number or identifier, message length, operation to perform, target address where to read or write data, source PE number or identifier, initiator address in which to write result data, or message identifier.

First claim

What is claimed is:

1. A non-transitory computer-readable medium comprising instructions stored thereon, that if executed by one or more processors, cause the one or more processors to:
coalesce one or more messages into a coalesced message and
represent one or more fields of metadata of the one or more messages using one or more codes, wherein at least one of the one or more codes uses fewer bits than that of original metadata fields to compact the metadata fields.

2. The computer-readable medium of claim 1 , wherein the metadata comprises at least one or more of: an initiator resource tracker identifier (ID), a target processing element (PE) number or identifier, message length, operation to perform, target address where to read or write data, source PE number or identifier, initiator address in which to write result data, or message identifier.

3. The computer-readable medium of claim 2 , wherein the operation to perform comprises one or more of: PUT, GET, non-fetching ATOMIC operations, or fetching ATOMIC operations.

4. The computer-readable medium of claim 1 , wherein the represent one or more fields of the metadata of the one or more messages using one or more codes is based on usages by sender and receiver processes such as number of used processing elements (PEs), or accepted lengths.

5. The computer-readable medium of claim 1 , wherein a value of the code is to indicate an escape code and a metadata is to be derived based on data that is to follow the escape code.

6. The computer-readable medium of claim 1 , wherein a value of the code is to indicate a portion of a metadata value and another portion of the metadata value is to follow the code.

7. The computer-readable medium of claim 1 , wherein the code applies to multiple payloads.

8. A method comprising:
coalescing one or more messages into a coalesced message and
representing one or more fields of metadata of the one or more messages using one or more codes, wherein at least one of the one or more codes uses fewer bits than that of original metadata fields to compact the metadata fields.

9. The method of claim 8 , wherein the metadata comprises at least one or more of: an initiator resource tracker identifier (ID), a target processing element (PE) number or identifier, message length, operation to perform, target address where to read or write data, source PE number or identifier, initiator address in which to write result data, or message identifier.

10. The method of claim 9 , wherein the operation to perform comprises one or more of: PUT, GET, non-fetching ATOMIC operations, or fetching ATOMIC operations.

11. The method of claim 8 , wherein the representing one or more fields of the metadata of the one or more messages using one or more codes is based on usages by sender and receiver processes such as number of used processing elements (PEs), or accepted lengths.

12. The method of claim 8 , wherein a value of the code is to indicate an escape code and a metadata is to be derived based on data that is to follow the escape code.

13. The method of claim 8 , wherein a value of the code is to indicate a portion of a metadata value and another portion of the metadata value is to follow the code.

14. The method of claim 8 , wherein the code applies to multiple payloads.

15. An apparatus comprising:
a network interface controller (NIC) and
at least one processor, wherein the NIC is configured to:
coalesce one or more messages into a coalesced message and
represent one or more fields of metadata of the one or more messages using one or more codes, wherein at least one of the one or more codes uses fewer bits than that of original metadata fields to compact the metadata fields.

16. The apparatus of claim 15 , wherein the metadata comprises at least one or more of: an initiator resource tracker identifier (ID), a target processing element (PE) number or identifier, message length, operation to perform, target address where to read or write data, source PE number or identifier, initiator address in which to write result data, or message identifier.

17. The apparatus of claim 16 , wherein the operation to perform comprises one or more of: PUT, GET, non-fetching ATOMIC operations, or fetching ATOMIC operations.

18. The apparatus of claim 15 , wherein the represent one or more fields of the metadata of the one or more messages using one or more codes is based on usages by sender and receiver processes such as number of used processing elements (PEs), or accepted lengths.

19. The apparatus of claim 15 , wherein a value of the code is to indicate an escape code and a metadata is to be derived based on data that is to follow the escape code.

20. The apparatus of claim 15 , wherein a value of the code is to indicate a portion of a metadata value and another portion of the metadata value is to follow the code.

Assignees

• Intel Corp

Inventors

• Keppel David
• Natarajan Chitra
• Krishnan Venkata

Classifications

• H04L49/9057

  Arrangements for supporting packet reassembly or resequencing · CPC title

• H04L49/9068 Primary

  in the network interface card · CPC title

• H04L69/22 Primary

  Parsing or analysis of headers · CPC title