News for hackers. Stuff that matters.

A comment on Tensorbook. Parent comment

Re:Tensorbook by bitL on Wednesday December 28, 2022 @06:54AM (#34160104)
> Apple will happily do ML for hours on end ON BATTERY

At 1/10th of the speed...

[ Parent | on HN ]
Re:Tensorbook by traceroute66 on Wednesday December 28, 2022 @06:59AM (#34160141)
> At 1/10th of the speed...

Yawn.

As has already been clearly explained numerous times in this discussion, e.g. @ribit[1] below, there is no throttling on Apple Silicon when running on battery.

[1] https://news.ycombinator.com/item?id=34159456

[ Parent | on HN ]
Re:Tensorbook by bitL on Wednesday December 28, 2022 @07:01AM (#34160156)
It's not about throttling, it's about mobile 3080Ti vs M1 GPU performance. M1 hits at around GTX1650 for Deep Learning workloads in GPU benchmarks.
[ Parent | on HN ]
Re:Tensorbook by TeMPOraL on Wednesday December 28, 2022 @12:12PM (#34163154)
> there is no throttling on Apple Silicon when running on battery

... yet. The computational demand of typical work will increase to eat up the extra capacity, as it always does - and the only way for a laptop to handle the same workload plugged or unplugged is to cap its plugged-in performance.

[ Parent | on HN ]