Hacker News Reader

Comment by smileybarry | Hacker News Reader

My guess is (slightly?) better binning in addition to "forced" PL1 and PL2 limits. Better silicon can run stable at lower voltage, ergo lower power, ergo lower temps, so I bet there's some binning for T SKUs so Dell & co. can ship not-overheating micro PCs.

View on HN

I see this frequently, but what is “better silicon”? Physically something is off about the manufacturing which impacts performance, but does not kill the chip. What are those defects?

There are 0.1% bad transistors instead of 0.2%? Heat output is more uniform? The bad transistors are clustered in such a way that signal routing is more efficient and leads to a measurable throughout difference?

Very slight changes in the transistor junctions will make them slightly more resistive, more inductive, physical variance will make them narrower, wider, etc. All of these factors, although extremely slight, will add up to different response curves of switching time vs current vs voltage.

Doping is essentially a stochastic process.

Makes sense. T series chips generally aren't as widely available as individual components as their mainstream higher power counterparts. To your point, they are available from OEMs as complete systems, who seem to get priority.

There is advice to just buy the non-T series and limit power. Interesting to see that, at least in this example, they aren't quite equal.

I saw a HN comment that chips that perform well at lower voltage don't scale as well to higher power, and vise versa. By that logic, T-binned chips would perform better at a low TDP compared to a downclocked 13900.

Reply on news.ycombinator.com