Techniques for using contextual information

Patent metadata

Field	Value
Publication number	US-12243118-B2
Application number	US-202217575471-A
Country	US
Kind code	B2
Filing date	Jan 13, 2022
Priority date	Jan 13, 2022
Publication date	Mar 4, 2025
Grant date	Mar 4, 2025

Abstract

Apparatuses, systems, and techniques to indicate contextual information to be used by available logical processors. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to indicate a first set of contextual information to be used by a first subset of available processors.

First claim

What is claimed is:

1. A processor, comprising; one or more circuits to perform an application programming interface (API) to cause first information to be added to at least first set contextual information and second set of contextual information of one or more processors, wherein the first information is indicated by one or more parameters of the API; wherein the one or more processors comprise one or more logical processors.

2. The processor of claim 1 , wherein the one or more circuits are to add the first and second set(s) of contextual information to a list of contextual information to be loaded into graphics processing unit (GPU) contexts.

3. The processor of claim 1 , wherein the first and second set(s) of contextual information includes code to be performed by one or more logical processors.

4. The processor of claim 1 , wherein the one or more logical processors includes two or more GPU contexts and the first and second set(s) of contextual information include instructions to be performed using the two or more GPU contexts.

5. The processor of claim 1 , wherein the one or more circuits are to load the first and second set(s) of contextual information into a GPU context.

6. The processor of claim 1 , wherein the first and second set(s) of contextual information are to be specified based, at least in part, on a pointer to a location of the first and second set(s) of contextual information in memory.

7. The processor of claim 1 , wherein the one or more circuits are to load the first and second set(s) of contextual information into a set of existing GPU contexts and add the first and second set(s) of contextual information to a list of contextual information to be loaded in response to GPU context creation.

8. The processor of claim 1 , wherein the first and second set(s) of contextual information are to be specified based, at least in part, on a parameter to the API, the first and second set(s) of contextual information includes instructions to be performed by a GPU, and the one or more circuits are to add the first and second set(s) of contextual information to a list of contextual information to be loaded in response to GPU context creation.

9. The processor of claim 1 , wherein first information comprises one or more modules.

10. The processor of claim 1 , wherein causing the first info to be added to the first and second set(s) of context info comprises loading one or more modules into a first context and a second context of a processor.

11. A machine-readable medium having stored thereon instructions for an application programming interface (API), which if performed by one or more processors, are to cause the one or more processors to at least: indicate cause a first information to be added to a first and a second set(s) of contextual information; and wherein the first information is indicated by one or more parameters of the API; wherein the one or more processors comprise one or more logical processors.

12. The machine-readable medium of claim 11 , wherein the first and second set(s) of contextual information are to be specified based, at least in part, on a parameter to the API, and the first and second set(s) of contextual information include instructions to be performed by a GPU.

13. The machine-readable medium of claim 11 , wherein the instructions, which if performed by the one or more processors, are to cause the one or more processors to update a list of contextual information to include the first and second set(s) of contextual information.

14. The machine-readable medium of claim 11 , wherein the instructions, which if performed by the one or more processors, are to cause the one or more processors to indicate the first and second set(s) of contextual information based, at least in part, on a parameter to the API that specifies the first and second set(s) of contextual information.

15. The machine-readable medium of claim 11 , wherein the instructions, which if performed by the one or more processors, are to cause the one or more processors to indicate the first and second set(s) of contextual information based, at least in part, on a parameter to the API that is a pointer to a location in memory and the one or more processors are to add the first and second set(s) of contextual information to a list of contextual information to be loaded in response to GPU context creation.

16. The machine-readable medium of claim 11 , wherein the instructions, which if performed by the one or more processors, are to cause the one or more processors to indicate the first and second set(s) of contextual information based, at least in part, on a parameter to the API that indicates a location of a file or a location of binary data.

17. The machine-readable medium of claim 11 , wherein the API is a first API, the one or more processors are to indicate the first and second set(s) of contextual information is to be used based, at least in part, on adding the first and second set(s) of contextual information to a list of contextual information to be used, and wherein the instructions are also for a second API, which if performed by the one or more processors, are to cause the one or more processors to at least remove the first and second set(s) of contextual information from the list of contextual information to be used in response to a call to the second API.

18. A system, comprising: one or more processors to perform an application programming interface (API) to cause first information to be added to at least a first and second indicate a first set(s) of contextual information of one or more processors, wherein the first information is indicated by one or more parameters of the API; and one or more memories is to store the first and second set(s) of contextual information; wherein the one or more processors comprise one or more logical processors.

19. The system of claim 18 , wherein the first and second set(s) of contextual information include instructions to be performed by one or more logical processors.

20. The system of claim 18 , wherein the one or more processors are to add the first and second set(s) of contextual information to a list of contextual information to be loaded in response to creation of a GPU context.

21. The system of claim 18 , wherein the first and second set(s) of contextual information includes instructions to be performed using a GPU context, and the first and second set(s) of contextual information are to be specified based, at least in part, on a pointer to a location of the first or second set(s) of contextual information in memory.

22. The system of claim 18 , wherein the first and second set(s) of contextual information is to be specified based, at least in part, on a parameter to the API, the first and second set(s) of contextual information including instructions to be performed by a GPU, and the one or more processors are to load the first and second set(s) of contextual information into a set of existing GPU contexts and add the first and second set(s) of contextual information to a list of contextual information to be loaded in response to GPU context creation.

23. The system of claim 18 , wherein the first and second set(s) of contextual information includes a module to be performed using one or more GPU contexts.

24. A method, comprising: causing a first information to be added at to a first and a second set(s) of contextual information of one or more processors, wherein the first information is indicated, at least in par

Assignees

• Nvidia Corp

Inventors

• Fontaine David Anthony
• Piechotka Maciej Marcin
• Perelygin Kyrylo
• Ligowski Lukasz Krystian
• Jain Ashutosh
• Chauhan Jitendra Pratap Singh
• Marathe Jaydeep
• Strengert Magnus
• Tian Xiaonan
• Jodlowski Sebastian Piotr
• Woolley Jr John Clifton

Classifications

• G06T1/60

  Memory management · CPC title

• G06F9/547

  Remote procedure calls [RPC]; Web services · CPC title

• G06F9/5077

  Logical partitioning of resources; Management or configuration of virtualized resources (specific details on emulation or internal functioning of virtual machines G06F9/455) · CPC title

• G06T1/20 Primary

  Processor architectures; Processor configuration, e.g. pipelining · CPC title

• G06F9/546 Primary

  Message passing systems or structures, e.g. queues · CPC title