You can generally go with the rule of thumb of "one foot per nanosecond" for the speed of light. Signals rattle along data lines a little slower because they are contained on a circuit board and not in free space, so it's more like "150mm per nanosecond" is the metric equivalent of propagation delay. That sounds pretty fast - and it is! It's like 50-60 percent of the speed of light.

But your average 3GHz multi-core CPU is doing a half dozen instructions per nanosecond. That means if you have your RAM over here and your CPU over there on your motherboard, you're going to have wait a measurable, impactful, amount of time for data to go back and forth between the two.

So the mobile/Apple idea of sticking your RAM directly on top of your CPU has some merit.

my ADHD is acting up to much to read all the text above, so in case it wasn't included: the is a physical limit to frequency in conventional conductors. normally metals have only ohm resistance, which does not depend on frequency and is generally rather low, but for instance in the case of copper a capacitative resistance significantly rises at around 1ghz, which gets only worse. this comes from structural effects in the lattice which form like small capacitors. i don't know the exact details from a solid state point of view, just remember the fact itself from a fiber optics lecture.

long story short: for high frequency (ergo, high data throughout) signals the resistance becomes insane, so you want to have your conductors as short as possible.

another thing that just pops into mind: i remember that for pci-5 the motherboard length is also more limited, due to the same reason.

Like a primer? Sorry, I don't know anything off the top of my head, but all this stuff is literaly 1st-year computer engineering in college. The basic of ISAs, circuits, low level programming and computer design are all kinda background you need to understand why RAM trace length is so important.

There are definitely college courses you can look up and read for free.

Most "guides" you'd find on Google repeat outdated information; watch out for that. That's why the Apple "memory on the CPU" thing keeps persisting, as most discussion isn't even updated to account for CAMM modules.

But ECE focused magazines are good about covering and explaining commercial memory tech:

https://semiengineering.com/

https://www.eetimes.com/

PC hardware news sites used to be good with this, too. That's where I learned some of this. But they've mostly died out :( And the YouTubers that replaced them are not the same.

Also, if you have a more specific question about memory types, I can try to answer them.

But honestly my knowledge getting dated too. For example, I don't know much about the specifics of GDDR7 (RTX 5000 memory) off the top of my head.