MulticoreInfo.com header image 2

Nvidia accelerates GPU pixel processing

November 23rd, 2009 · No Comments




By Aharon Etengoff
Nvidia has patented a method of optimizing the GPU pixel processing pipeline. According to company spokesperson Hector Marinez, patent no. 7609272 “helps” the shader process textures in a way that makes “full” use of any extra circuits.

“Previously, when a large texture needed to be read, one instruction would be issued, and one shader circuit would need to make several passes while other circuits sat idle,” said Marinez. 

”But [Nvidia] patent authors Emmett Kilgariff and Rui Bastos figured out a way to allow for a partial texture load. By breaking the texture load into smaller pieces – able to be completed in one pass each – all circuits can keep firing.”

Marinez explained that textures can be 32-bit, 64-bit, or 128-bit. However, anything larger than 32-bit requires more than one pass.

Full Story

  • Share/Save/Bookmark

Tags: MulticoreInfo

Like what you're reading? Come back every day for multicore news, or subscribe to RSS updates.



Stumble It!