News for hackers. Stuff that matters.

A comment on 5/3nm Wars Begin. Parent comment

Re:5/3nm Wars Begin by Fronzie on Saturday January 25, 2020 @02:50PM (#22148242)
> Smaller transistors use less power.

Don't the smaller transistors also have higher leakage? I thought that below 10nm scaling down further would not give power benefits.

[ Parent | on HN ]
Re:5/3nm Wars Begin by unlinked_dll on Saturday January 25, 2020 @03:06PM (#22148336)
It's called Dennard Scaling [0] and it ran out about 15 years ago

[0] https://en.wikipedia.org/wiki/Dennard_scaling

[ Parent | on HN ]
Re:5/3nm Wars Begin by Dylan16807 on Saturday January 25, 2020 @05:48PM (#22149119)
Having constant power density with continuous performance improvements broke down.

But we're not yet at the point where power density increases as fast as transistor density.

[ Parent | on HN ]
Re:5/3nm Wars Begin by chas on Saturday January 25, 2020 @07:08PM (#22149480)
While this is true for many process nodes, it is not true in general. For instance, the transition to FinFETs greatly reduced leakage power in TSMC 16nm in comparison to their 28nm processes.
[ Parent | on HN ]