Invention Grant
- Patent Title: Optimization of neural networks using hardware calculation efficiency and adjustment factors
-
Application No.: US16528982Application Date: 2019-08-01
-
Publication No.: US11243743B2Publication Date: 2022-02-08
- Inventor: Jeffrey Hoyle Johnson
- Applicant: Facebook, Inc.
- Applicant Address: US CA Menlo Park
- Assignee: Facebook, Inc.
- Current Assignee: Facebook, Inc.
- Current Assignee Address: US CA Menlo Park
- Agency: Baker Botts L.L.P.
- Main IPC: G06F7/483
- IPC: G06F7/483 ; G06F7/544 ; G06F7/556 ; G06N20/00 ; G06N3/063

Abstract:
In one embodiment, a method includes receiving a request for an operation to be performed; determining that the operation is associated with a machine-learning algorithm, and in response, route the operation to a computing circuit; performing, at the computing circuit, the operation, including: determining a linear domain product of a first log-domain number and a second log-domain number associated with the operation based on a summation of the first log-domain number and the second log-domain number and output a third log-domain number approximating the linear domain product of the first log-domain number and the second log-domain number; converting the third log-domain number to a first linear-domain number; summing the first linear-domain number and a second linear-domain number associated with the operation, and output a third linear-domain number as the summed result.
Information query