←back to thread

AI engineers claim new algorithm reduces AI power consumption by 95%

(www.tomshardware.com)
352 points ferriswil | 1 comments | 19 Oct 24 18:03 UTC | HN request time: 0.354s | source
Show context
robomartin ◴[19 Oct 24 19:26 UTC] No.41890056[source]▶
I posted this about a week ago:

https://news.ycombinator.com/item?id=41816598

This has been done for decades in digital circuits, FPGA’s, Digital Signal Processing, etc. Floating point is both resource and power intensive and using FP without the use of dedicated FP processing hardware is something that has been avoided and done without for decades unless absolutely necessary.

replies(3): >>41890331 #>>41890498 #>>41890812 #
1. fidotron ◴[19 Oct 24 21:09 UTC] No.41890812[source]▶
Right, the ML people are learning, slowly, about the importance of optimizing for silicon simplicity, not just reduction of symbols in linear algebra.

Their rediscovery of fixed point was bad enough but the “omg if we represent poses as quaternions everything works better” makes any game engine dev for the last 30 years explode.