Identifying duplicate indices in an input index stream
US10049487B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 23, 2016 |
| Grant date | Aug 14, 2018 |
| Priority date | — |
| Expiry date | Nov 23, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T15/80
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for removing duplicate indices from an index stream are disclosed. The techniques involve dividing the indices into chunks. For any particular chunk, the techniques involve examining each index in the chunk to determine whether a “match” exists for that index within a reuse depth sliding window. The reuse depth sliding window includes a fixed number of indices immediately prior to the index being examined for a match. If a match exists, then the index is marked as non-unique and is assigned a position value equal to the position value of the matching index. If a match does not exist, then the index is marked as unique and assigned the next available position value for the chunk. After assigning position values to indices in a chunk, the indices in the chunk are transmitted to a vertex shader stage for processing in the order indicated by the position values.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.