METHOD AND APPARATUS FOR LOOP AND BRANCH INSTRUCTIONS IN A PROGRAMMABLE GRAPHICS PIPELINE

Patent №

US 6,825,843

Granted

2004-11-30

Filed 2002

Owner

NVIDIA CORPORATION

AI components

1

hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10302411

A method and apparatus for executing loop and branch program instructions in a programmable graphics shader. The programmable graphics shader converts a sequence of instructions comprising a portion of a shader program and selects a first set of fragments to be processed. Subsequent sequences of instructions are converted until all of the instructions comprising the shader program have been executed on the first set of fragments. Each remaining set of fragments is processed by the shader program until all of the fragments are processed in the same manner. Furthermore, the instructions can contain one or more loop or branch program instructions that are conditionally executed. Additionally, when instructions within a loop as defined by a loop instruction are being executed a current loop count is pipelined through the programmable graphics shader and used as an index to access graphics memory.

AI hardwareG06T 15/005G06F 9/3017G06F 9/325G06F 9/3853

AI classification

AI hardware0.99
Planning0.30
Natural language0.03
Knowledge representation0.00
Evolutionary computation0.00
Vision0.00
Speech0.00
Machine learning0.00

Ownership

NVIDIA CORPORATION

assignment · 143790987

Assignors

ALLEN, ROGER L., ZATZ, HAROLD ROBERT FELDMAN

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC