Invention Grant
- Patent Title: Automatic generation of computation kernels for approximating elementary functions
-
Application No.: US17569566Application Date: 2022-01-06
-
Publication No.: US12001311B2Publication Date: 2024-06-04
- Inventor: Daniel Khankin
- Applicant: Next Silicon Ltd
- Applicant Address: IL Tel Aviv
- Assignee: Next Silicon Ltd
- Current Assignee: Next Silicon Ltd
- Current Assignee Address: IL Givatayim
- Main IPC: G06F11/34
- IPC: G06F11/34 ; G06F11/30 ; G06F17/17

Abstract:
An apparatus for computing functions using polynomial-based approximation, comprising one or more processing circuitries configured for computing a polynomial-based approximant approximating a function by executing one or more iterations. Each iteration comprising computing the polynomial-based approximant using scaled fixed-point unit(s) according to a constructed set of coefficients, minimizing an approximation error of the computed polynomial-based approximant compared to the function while complying with one or more constraints selected from a group comprising at least: an accuracy, a compute graph size, a computation complexity, and a hardware utilization of the processing circuitry(s), adjusting one or more of the coefficients in case the approximation error is incompliant with the constraint(s) and initiating another iteration. The polynomial-based approximant and its adjusted set of coefficients for which the computed polynomial-based approximant complies with the constraint(s) may be output to one or more processing circuitries configured to approximate the function by computing the polynomial-based approximant.
Public/Granted literature
- US20230214307A1 AUTOMATIC GENERATION OF COMPUTATION KERNELS FOR APPROXIMATING ELEMENTARY FUNCTIONS Public/Granted day:2023-07-06
Information query