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:
Oct. 22, 2019

Filed:

Jun. 29, 2015
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Douglas C. Burger, Bellevue, WA (US);

Derek Chiou, Bellevue, WA (US);

Eric Chung, Woodinville, WA (US);

Andrew R. Putnam, Seattle, WA (US);

Assignee:
Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06F 15/18 (2006.01); G06N 20/00 (2019.01); G06F 9/46 (2006.01); G06F 9/50 (2006.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 9/46 (2013.01); G06F 9/50 (2013.01); Y02D 10/22 (2018.01);
Abstract

A method is provided for processing on an acceleration component a machine learning classification model. The machine learning classification model includes a plurality of decision trees, the decision trees including a first amount of decision tree data. The acceleration component includes an acceleration component die and a memory stack disposed in an integrated circuit package. The memory die includes an acceleration component memory having a second amount of memory less than the first amount of decision tree data. The memory stack includes a memory bandwidth greater than about 50 GB/sec and a power efficiency of greater than about 20 MB/sec/mW. The method includes slicing the model into a plurality of model slices, each of the model slices having a third amount of decision tree data less than or equal to the second amount of memory, storing the plurality of model slices on the memory stack, and for each of the model slices, copying the model slice to the acceleration component memory, and processing the model slice using a set of input data on the acceleration component to produce a slice result.


Find Patent Forward Citations

Loading…