Did Digitlife jump the gun announcing NV40?
- Thread starter g__day
- Start date
oeLangOetan
Newcomer
128 ShaderOps/clock 
chavvdarrr
Veteran
well, the guy who posted it is fired ....
joke, i think he was fast enough to save his head
joke, i think he was fast enough to save his head
Hellbinder
Banned
8 shader units per pipeline and 16 pipelines...
Someone tell me how Nvidia gets away with telling one lie after the next and everyone still thinks they are cool?
Do you have any idea how many Transistors it would take to actually make that statement true?
Someone tell me how Nvidia gets away with telling one lie after the next and everyone still thinks they are cool?
Do you have any idea how many Transistors it would take to actually make that statement true?
Pictured mirror
http://frankenstein.evilgeniuslabs.com/~pszuch/nv40/news.html
http://frankenstein.evilgeniuslabs.com/~pszuch/nv40/news.html
Mintmaster
Veteran
Guess I was lucky to see the page
Damn, that is one very impressive architecture. It may be 222 million transistors, but they'll do a lot more than double NV30's shader performance, especially since texture instructions don't prevent a simultaneous arithmetic instruction anymore.
I still think R420 will keep pace in shader speed, because most of the time you can pair a texture op with an ALU op (at least with current shaders like in HL2 and Doom3), so R300/R420 should have similar per-pipe performance to NV40 according to that diagram. R420 should have a higher clock too, right?
Now it just a question of how efficient all that is. Each pipe is clearly FAR more transistor efficient than NV30's pipe yet also more capable, so they may well have sacrificed FIFO sizes or other aspects.
Do any of you still think we'll see RGMSAA? Doesn't look like it to me, in which case Vegetto-eX's pics may well have been real.
Congrats to NVidia. Looks like the developers dream chip.
Damn, that is one very impressive architecture. It may be 222 million transistors, but they'll do a lot more than double NV30's shader performance, especially since texture instructions don't prevent a simultaneous arithmetic instruction anymore.
I still think R420 will keep pace in shader speed, because most of the time you can pair a texture op with an ALU op (at least with current shaders like in HL2 and Doom3), so R300/R420 should have similar per-pipe performance to NV40 according to that diagram. R420 should have a higher clock too, right?
Now it just a question of how efficient all that is. Each pipe is clearly FAR more transistor efficient than NV30's pipe yet also more capable, so they may well have sacrificed FIFO sizes or other aspects.
Do any of you still think we'll see RGMSAA? Doesn't look like it to me, in which case Vegetto-eX's pics may well have been real.
Congrats to NVidia. Looks like the developers dream chip.
