one said:version said:GS is a very good and fast chip ,
with present-day technology such as 200M transistor and 500MHZ may make faster GS ,
5 GS on one chip = 20MB eDram , 500MHZ , 80 pixelunits , 600 GB/sec , 1 GigaPoly/s , 40 Gigapixel/s !!!!
if use sony 0,65 process(400M trans 800 MHZ) ,10 GS in one chip = 40MB eDram , 800MHZ , 160 pixelunits , 2 TERAByte/sec , 3.5 GigaPoly/s , 120 Gigapixel/s !!!!
ps3's GPU will be faster ?
In my very rough overview:
Sony's 250nm GPU = GS > RIVA TNT2 family = nVIDIA's 250nm GPU
nVIDIA-Sony 65nm GPU > 10 GS in 65nm one chip
But I'm not sure how nVIDIA-Sony PS3 GPU is better than 10 GS in one chip, at least one thing is sure that Sony determined it's better than a bunch of GS on steroids which they demonstrated in GSCube. Though you can expect there's a trade-off in exchange of raw power, it may be better in cost, in thermal design, in game-related fixed-function efficiency, in developer-friendlyness, I don't know.
raycasting or deferred technology?
if sony-nvidia use 256 rasterizer in chip and 1-2 pixelshaderpipeline
256 rasterizers work fast and write to memory pixel 's attribute(Z,normals, texture,shaderprogramaddress etc...)
after ,gpu read pixels,attributes and send to pixelpipeline to run current shaderprogram
with procedure accessible 6-200 Gigapoly/s
this is possible?