The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Mar. 26, 2019

Filed:

Aug. 08, 2017
Applicant:

Vivante Corporation, San Jose, CA (US);

Inventor:

Mankit Lo, Fremont, CA (US);

Assignee:

VIVANTE CORPORATION, San Jose, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G09G 5/00 (2006.01); G06N 3/04 (2006.01); G06F 17/16 (2006.01); H04N 19/132 (2014.01); G06F 7/76 (2006.01); G06F 17/15 (2006.01); G06F 7/544 (2006.01); H04N 19/42 (2014.01);
U.S. Cl.
CPC ...
G06N 3/04 (2013.01); G06F 7/5443 (2013.01); G06F 7/764 (2013.01); G06F 17/153 (2013.01); G06F 17/16 (2013.01); H04N 19/132 (2014.11); H04N 19/42 (2014.11); G06F 2207/4824 (2013.01);
Abstract

A convolution engine, such as a convolution neural network, operates efficiently with respect to sparse kernels by implementing zero skipping. An input tile is loaded and accumulated sums are calculated for the input tile for non-zero coefficients by shifting the tile according to a row and column index of the coefficient in the kernel. Each coefficient is applied individually to tile and the result written to an accumulation buffer before moving to the next non-zero coefficient. A 3D or 4D convolution may be implemented in this manner with separate regions of the accumulation buffer storing accumulated sums for different indexes along one dimension. Images are completely processed and results for each image are stored in the accumulation buffer before moving to the next image.


Find Patent Forward Citations

Loading…