alt Hacker NewsSo from CDNA3 to 4 they doubled fp16 and fp8 performance but cut fp32 and fp64 by half?
Wonder why the regression on non-AI workloads?
Replies
trueismywork • today at 11:06 AM
Non-AI workloads prefer vector units and not matrix units
So from CDNA3 to 4 they doubled fp16 and fp8 performance but cut fp32 and fp64 by half?
Wonder why the regression on non-AI workloads?
Non-AI workloads prefer vector units and not matrix units
Because those who nowadays have money for investing, do not invest them in the research problems whose solutions are urgently needed for the survival of humanity, e.g. for developing technologies for using all substances in closed cycles (like biosphere did before humans), but instead of that they invest all their money in research for the dream of developing AGI, which even if successful will be of benefit only for a small number of humans, not for all mankind.
The fp64 and fp32 performance is needed for physical simulations required by the former goal, while fp16 and fp8 performance is useful only for the latter goal.
So AMD's choice logically follows the choice of those who control the investment money.