Finally, I believe the "GPU fad" I spoke of back in 1998 will end by 2030. Thereafter, we'll have some mix of random-access-optimized and vector-optimized computing units, and will address them by just writing code, without any recognizable GPU pipeline or fixed-function units.
-
-
Make wider GPUs and figure out how to make them MCM. Or just do better with optimizing the rendering engine to make better use of the tools we already have available for that: crossfire and SLI.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.