SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: graphicsguru who wrote (255209)8/5/2008 2:36:51 AM
From: fastpathguruRead Replies (1) | Respond to of 275872
 
Why? They're doing tile-based rendering. Which resource do you
expect to get saturated? Each tile is essentially independent, and the
tiles don't have to speak to each other. The transformed geometry
gets broadcast to all CPUs. It's the perfect case for parallelism.

Who transforms the geometry?

A lot more work these days is being done in the front-end to get realism through detail in geometry; where textures are creating geometry, meshes are tesselated, etc. and all this has to be done before a scene can be diced up into tiles.

Tile rendering is not a solution without tradeoffs... It has a computational overhead of its own.

fpg



To: graphicsguru who wrote (255209)8/5/2008 9:41:19 AM
From: combjellyRead Replies (1) | Respond to of 275872
 
"Which resource do you expect to get saturated?"

Memory bus, ring bus. While I grant you that it parallelizes pretty well, the memory bus has to come under pressure at some point.


HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2026 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News