VERTEX TEXTURE CACHE RETURNING HITS OUT OF ORDER

Patent №

US 6,972,769

Granted

2005-12-06

Filed 2004

Owner

NVIDIA CORPORATION

AI components

1

hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10934120

A vertex texture cache unit enables vertex shader programs to arbitrarily access array data while minimizing pipeline stalls due to memory latency. The vertex texture cache unit receives vertex texture requests from multiple vertex processing engines, each executing multiple vertex shader programs. The vertex texture cache unit stores frequently accessed vertex texture map data in a cache memory. When a cache miss occurs, the vertex texture cache unit continues to process subsequent vertex texture requests while data is being retrieved from memory for the cache miss. Because the vertex texture cache unit may output vertex texture map data in a different order than the corresponding vertex texture requests are received, the vertex texture cache unit maintains the association between vertex texture map data and its set of attributes, so that the vertex texture map data is formatted correctly and returned to the appropriate vertex processing engine and vertex shader program.

AI classification

AI hardware0.99
Vision0.16
Evolutionary computation0.13
Knowledge representation0.07
Machine learning0.01
Natural language0.00
Planning0.00
Speech0.00

Ownership

NVIDIA CORPORATION

assignment · 157760624

Assignors

NEBEKER, JAKOB, MOSKAL, JEFFREY B.

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

© 2026 NYSGPT2525 LLC