Comment by 0_____0

2 days ago

Layout is a puzzle, especially with particularly high density layouts, but some of this is ameliorated by high layer count and fine trace/space boards becoming cheaper. Definitely not black magic. RF layout is black magic, let's not steal their thunder here.

High speed PCBs are RF. At high enough frequencies, traces become waveguides, and the result cannot be predicted analytically. Simulation is your only light in this mess.

  • I have been lucky to not have to lay out anything that had frequencies of interest over 1Ghz or so. What's your experience been? E.g. types of signals, frequency range, issues you ran into?

    • Signals that arrive faster than what the speed of light should physically allow for that trace length because you made the corners too sharp and then instead of flowing along your path the electricity creates a magnetic field which then induces a current and that allows the signal to tunnel through non-conductive walls.

      High speed boards cannot be simulated well. Because they are far from deterministic. That's what makes them so different from coding.

      1 reply →

It's just across-modal. The list of components are linear list, connections between components are graphs, placements are geometrically constrained, and overall shape is both geometric and external to the board. So you can't just mechanically derive the board from mere linear textual descriptions of it.

A lot of automagic "AGI achieved" LLM projects has this same problem, that it is assumed that brief literal prompt shall fully constrain the end result so long it is well thought out. And it's just not how it - the reality, or animal brains - works.

  • You need a LOT of context about what the components are and how they're being used in order to route them. Extreme case is an FPGA where a GPIO might be a DAC output or one half of a SERDES diff pair.

    • Doesn't even have to be that extreme: there is no way port placements of a Mac Mini can be mathematically derived from a plain English natural language prompt, and yet that's what they're trying to do. It's just the reality that not everything happen or could be done in literal languages. I guess it takes few more years before everyone accepts that.