Joe DeFuria
Legend
Someone else posted this a second ago...now it's gone? Anyway:
http://www.digit-life.com/news.html?1324#1324
The synthetic fill-rate tests do support the theory:
http://www.digit-life.com/articles2/xabre/xabre600.html#p5
Would be interesting to see if if 2x4 is actually true. But then "who cares" right? Accuracy in specifications is just a guideline for PR, not something that really needs to be satisfied.
Hmmm....interestingly:
http://www.beyond3d.com/reviews/powercolor/xabre400/index.php?p=4
Did B3D ever follow-up with SiS on that question?
http://www.digit-life.com/news.html?1324#1324
As indicated by our SiS Xabre 600 performance tests, this GPU features different rendering architecture than claimed by SiS: not 4 pipelines with 2 texture modules in each, but 2 pipelines with 4 texture modules in each.
The synthetic fill-rate tests do support the theory:
http://www.digit-life.com/articles2/xabre/xabre600.html#p5
Would be interesting to see if if 2x4 is actually true. But then "who cares" right? Accuracy in specifications is just a guideline for PR, not something that really needs to be satisfied.
Hmmm....interestingly:
http://www.beyond3d.com/reviews/powercolor/xabre400/index.php?p=4
The first thing that we can see is that there is a large disparity between the single texture and multi-texture fill-rates. With four pixel pipelines and two texture units per pipe, we would expect to see a single texture fill-rate roughly double what is displayed there. Comparing the single to multi-texture rates, it would suggest a configuration of two pixels pipelines each with for texture units.
Did B3D ever follow-up with SiS on that question?