IP Library › Granted Patent US 12,229,566
Granted Patent B2
US 12,229,566 · App. 18/070,148 · Granted Feb 18, 2025

Application programming interface to indicate accelerator error handlers

Inventors: Karthik Raghavan Ravi (Bangalore, IN); Ashutosh Jain (Bengaluru, IN); Rahul Suresh (Bangalore, IN)
Assignee: NVIDIA Corporation
G06F9/3861G06F9/3836G06F9/3877G06F9/541
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,229,566
App. No.
18/070,148
Granted
Feb 18, 2025
Kind
B2
Abstract

Apparatuses, systems, and techniques to execute one or more application programming interfaces (APIs) to perform one or more operations for one or more accelerators within a heterogeneous processor. In at least one embodiment, one or more processors are to perform one or more instructions in response to one or more APIs to indicate one or more functions to be performed in response to one or more errors from one or more accelerators within a heterogeneous processor.

Claims (23)

1. A processor comprising:

one or more circuits to use an application programming interface (API) to identify one or more error handlers to handle one or more errors from one or more accelerators within a heterogeneous processor.

2. The processor of claim 1 , wherein the one or more error handlers comprise one or more instructions that, if performed, cause the one or more circuits to perform one or more computational operations in response to the one or more errors.

3. The processor of claim 1 , wherein the one or more error handlers comprise one or more instructions that, if performed, cause the one or more accelerators within the heterogeneous processor to perform one or more computational operations in response to the one or more errors.

4. The processor of claim 1 , wherein the one or more error handlers comprise function pointers to indicate one or more computational operations to be performed in response to the one or more errors.

5. The processor of claim 1 , wherein the one or more errors are to be generated by the one or more accelerators within the heterogeneous processor and one or more other errors are to be generated by one or more other accelerators, and the one or more other errors are to be handled by one or more other error handlers.

6. The processor of claim 1 , wherein the API is to receive one or more parameters comprising one or more pointers to indicate one or more instructions to be performed in response to the one or more errors.

7. The processor of claim 1 , wherein the processor is a central 7 , processing unit (CPU).

8. A system comprising:

one or more processors to use an application programming interface (API) to identify one or more error handlers to handle one or more errors from one or more accelerators within a heterogeneous processor.

9. The system of claim 8 , wherein the one or more error handlers comprise one or more instructions that, if performed, cause the one or more processors to perform one or more computational operations in response to the one or more errors.

10. The system of claim 8 , wherein the one or more error handlers comprise one or more instructions that, if performed, cause the one or more accelerators within the heterogeneous processor to perform one or more computational operations in response to the one or more errors.

11. The system of claim 8 , wherein the API is to receive one or more parameters comprising one or more pointers to indicate the one or more error handlers and the one or more error handlers comprise one or more instructions to be performed in response to the one or more errors.

12. The system of claim 8 , wherein the one or more error handlers are pointers to indicate one or more instructions to be performed in response to the one or more errors.

13. The system of claim 8 , wherein the one or more errors are to be generated by the one or more accelerators within the heterogeneous processor and one or more other errors are to be generated by one or more other accelerators, and the one or more other errors are to be handled by one or more other error handlers.

14. The system of claim 8 , wherein the one or more processors comprise a central processing unit (CPU).

15. A method comprising:

using an application programming interface (API) to identify one or more error handlers to handle one or more errors from one or more accelerators within a heterogeneous processor.

16. The method of claim 15 , wherein the one or more error handlers comprise one or more instructions that, if performed, cause one or more computational operations to be performed in response to the one or more errors.

17. The method of claim 15 , further comprising performing, in response to the one or more errors, one or more instructions by the one or more accelerators within the heterogeneous processor.

18. The method of claim 15 , wherein the one or more error handlers are pointers to indicate one or more instructions to be performed in response to the one or more errors.

19. The method of claim 15 , wherein, in response to the API, the one or more error handlers are to be registered with a parallel computing environment to handle the one or more errors.

20. The method of claim 15 , further comprising receiving, by the API, one or more parameters to indicate the one or more error handlers, where the one or more error handlers comprise one or more pointers to one or more instructions to be performed in response to the one or more errors.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 1, 2022
From: RAVI, KARTHIK RAGHAVAN; JAIN, ASHUTOSH; SURESH, RAHUL
To: NVIDIA CORPORATION
Reel/Frame 061938/0474 →
Continuity (1)
Related Publication 20240176622A1 · May 30, 2024
References Cited (6)
US 10819680B1 · Santan · 2020 [cited by examiner]
US 20090119677A1 · Stefansson · 2009 [cited by examiner]
US 20140146062A1 · Kiel · 2014 [cited by examiner]
US 20210182132A1 · Chen · 2021 [cited by examiner]
US 20210390033A1 · Singhal · 2021 [cited by examiner]
IEEE, “IEEE Standard 754-2008 (Revision of IEEE Standard 754-1985): IEEE Standard for Floating-Point Arithmetic,” Aug. 29, 2008, 70 pages. [cited by applicant]
Cited By (1)
US 12,613,821