Qualcomm Incorporated

3D Open Motion, LLC

Jeffrey Leger

Andrew Evan Gruber

Colin Christopher Sharp

Liang Li

Maurice Franklin Ribble

Elina Kamenetskaya

David A Southard

Balaji Calidas

Ruihao Zhang

Georges Grinstein

John Peter Lee

Bradford E MacPherson

Maurice Ribble

The present disclosure relates to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may modify at least one texture memory object to support a data structure for one or more tensor objects. The apparatus may also determine one or more supported memory layouts for the one or more tensor objects based on the modified at least one texture memory object. Additionally, the apparatus may access data associated with the one or more tensor objects based on the one or more supported memory layouts, the data for each of the one or more tensor objects corresponding to at least one data instruction. The apparatus may also execute the at least one data instruction based on the accessed data associated with the one or more tensor objects.

Methods and apparatus for tensor object support in machine learning workloads

This disclosure describes techniques for automatically selecting a rendering mode for use by a graphics processing unit (GPU) to render graphics data for display. More specifically, the techniques include evaluating at least two metrics associated with rendering graphics data of one or more rendering units, and automatically selecting either an immediate rendering mode or a deferred rendering mode for a current rendering unit based on the evaluated metrics. The selected rendering mode may be the one of the rendering modes predicted to use less power and/or system bandwidth to render the graphics data of the current rendering unit. A rendering unit may comprise a set of frames, a frame, a portion of a frame, multiple render targets associated with a frame, a single render target associated with a frame, or a portion of a single render target.

Rendering mode selection in graphics processing units

A hierarchical 3D graphics model can be viewed as a hierarchical graph of its nodes and their associated motions, with the mathematical type of motions graphically indicated. A user can click on a displayed motion to edit it. A motion API provides one or more of the following features: (1) spatial predicate functions; (2) functions for scaling motion intensity; (3) classes for shake, spin, and swing motions; (4) motion classes with a GUI interfaced for defining their duty cycle; (5) functions for defining and computing 0 through 2 order derivatives of 3D position and orientation as function of time; (6) behaviors that constrain motions by boundaries in which the constraint is a reflection, clamp, andor onto constraint, or in which the boundary is a composite boundary. Motions can be defined by successive calls to an API and then be saved in a file.

Apparatuses, methods, computer programming, and propagated signals for modeling motion in computer applications

Growing community of inventors

Tyngsboro, MA, United States of America

Jeffrey Leger