IP Library Granted Patent US 11,741,397
Granted Patent B2
US 11,741,397 · App. 16/694,926 · Granted Aug 29, 2023

Artificial neural network emulation of hotspots

Inventor: Nicholas Malaya (Austin, TX)
Assignee: Advanced Micro Devices, Inc.
G06N20/10G06N3/04G06N3/08
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 11,741,397
App. No.
16/694,926
Granted
Aug 29, 2023
Kind
B2
Abstract

Methods, devices, and systems for emulating a compute kernel with an ANN. The compute kernel is executed on a processor, and it is determined whether the compute kernel is a hotspot kernel. If the compute kernel is a hotspot kernel, the compute kernel is emulated with an ANN, and the ANN is substituted for the compute kernel.

Claims (41)

1. A method for emulating a compute kernel with an artificial neural network (ANN), the method comprising:

executing the compute kernel on a processor;

determining whether the compute kernel is a hotspot kernel; and

if the compute kernel is a hotspot kernel:

emulating the compute kernel with an ANN, and

substituting the ANN for the compute kernel.

2. The method of claim 1 , wherein determining whether the compute kernel is a hotspot kernel comprises comparing a compute resource utilization of the compute kernel with a threshold.

3. The method of claim 1 , wherein determining whether the compute kernel is a hotspot kernel comprises comparing a compute resource utilization of the compute kernel with a compute resource utilization of a different compute kernel.

4. The method of claim 1 , wherein emulating the compute kernel with an ANN comprises offline-training the ANN prior to executing the compute kernel.

5. The method of claim 4 , wherein offline-training the ANN comprises:

inputting, to the ANN, training data typical of inputs to the compute kernel,

comparing outputs from the ANN to known correct outputs corresponding to the training data; and

adjusting the ANN based on differences between the outputs from the ANN and the known correct outputs.

6. The method of claim 1 , wherein emulating the compute kernel with an ANN comprises online-training the ANN based on execution of the compute kernel.

7. The method of claim 6 , wherein offline-training the ANN comprises:

inputting, to the ANN, inputs which were input to the compute kernel,

comparing outputs from the ANN to known correct outputs corresponding to the inputs which were input to the compute kernel; and

adjusting the ANN based on differences between the outputs from the ANN and the known correct outputs.

8. The method of claim 1 , wherein emulating the compute kernel with an ANN comprises offline-training the ANN prior to executing the compute kernel, and refining the ANN using online-training based on execution of the compute kernel.

9. The method of claim 1 , wherein substituting the ANN for the compute kernel comprises executing the ANN on the processor.

10. The method of claim 1 , wherein substituting the ANN for the compute kernel comprises executing the ANN on a different processor in communication with the processor.

11. A computing device configured to emulate a compute kernel with an artificial neural network (ANN), the computing device comprising:

a processor configured to execute the compute kernel and to determine whether the compute kernel is a hotspot kernel;

the processor further configured to, if the compute kernel is a hotspot kernel:

emulate the compute kernel with an ANN, and

substitute the ANN for the compute kernel.

12. The computing device of claim 11 , wherein determining whether the compute kernel is a hotspot kernel comprises comparing a compute resource utilization of the compute kernel with a threshold.

13. The computing device of claim 11 , wherein determining whether the compute kernel is a hotspot kernel comprises comparing a compute resource utilization of the compute kernel with a compute resource utilization of a different compute kernel.

14. The computing device of claim 11 , wherein emulating the compute kernel with an ANN comprises offline-training the ANN prior to executing the compute kernel.

15. The computing device of claim 14 , wherein offline-training the ANN comprises:

inputting, to the ANN, training data typical of inputs to the compute kernel,

comparing outputs from the ANN to known correct outputs corresponding to the training data; and

adjusting the ANN based on differences between the outputs from the ANN and the known correct outputs.

16. The computing device of claim 11 , wherein emulating the compute kernel with an ANN comprises online-training the ANN based on execution of the compute kernel.

17. The computing device of claim 16 , wherein the processor is further configured to offline-train the ANN, the processor further configured to

input, to the ANN, inputs which were input to the compute kernel,

compare outputs from the ANN to known correct outputs corresponding to the inputs which were input to the compute kernel; and

adjust the ANN based on differences between the outputs from the ANN and the known correct outputs.

18. The computing device of claim 11 , wherein emulating the compute kernel with an ANN comprises offline-training the ANN prior to executing the compute kernel, and refining the ANN using online-training based on execution of the compute kernel.

19. The computing device of claim 11 , wherein substituting the ANN for the compute kernel comprises executing the ANN on the processor.

20. The computing device of claim 11 , wherein substituting the ANN for the compute kernel comprises executing the ANN on a different processor in communication with the processor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 4, 2019
From: MALAYA, NICHOLAS
To: ADVANCED MICRO DEVICES, INC.
Reel/Frame 051182/0657 →
Continuity (1)
Related Publication 20210158222A1 · May 27, 2021