[namibj]

Because DDR3/4/5 dies are made to a price with half to three quarters of their IO pins shared between the dies in parallel on a rank of a channel, and for capacity often up to around 6 ranks per channel. E.g. high capacity server DDR4 memory, say on AMD SP3, may have 108 dies on each of 8 channels of a socket.

So if you can move complexity over to the controller you can spend 100:1 ratio in unit cost. So you get to make the memory dies very dumb by e.g. feeding a source synchronous sampling clock that's centered on writes and edge aligned on reads leaving the controller to have a DLL master/slave setup to center the clock at each data group of a channel and only retain a minimal integer PLL in the dies themselves.

[Neywiny]

You need to train whether you're on one die or 100. It's about your per bit skew and PVT

[namibj]

Yes, I was just pointing out why we choose to make the memory chips so fragile/dependant on the controller doing all the magic training for them.

[Neywiny]

Well no, your comment answered that we need training because the dies are made cheaply. But no amount of money would prevent the need to train out static and dynamic delays. If it wasn't in the controller it'd be in the memory and the question of why it's needed would still be relevant.