I'm in the HPC space, and pretty much everything I do on the GPU is bound by how quickly I can get data in and out of DRAM.
The point at which data motion to/from DRAM is not the bottleneck is when you do enough work per byte of data moved. How much work is that? On today's server GPUs it's in the region of 50--100 double precision floating point operations per byte. You can work out an exact number by taking the theoretical maximum floating point operations per unit time you can execute and divide by DRAM throughput (data moved per unit time).
O(50--100) double precision flops per byte is a _lot_ of work. We're talking BLAS-3 type operations. Anything level 2 or lower, or sparse operations, are typically bandwidth bound.
The more RAM you have on device, the fewer swaps you need to do (none at all if it's big enough), and the less those operations get amortized, bringing you closer to theoretical max throughput.
Matrix multiples are such that going from fitting 75% of your values to fitting 100% of your values can mean an order of magnitude speedup.
I work with problems so huge they do not fit on a single device. Multiple devices each own a small piece of the global problem. They solve a local problem and they must communicate over a network in order to solve the global problem. This is almost universally true.
You would know more than I in this field, and I expect it really is better to swap a partition than it is to use a network.
There are certain methods in HPC applications that are almost universally avoided because of how terribly they scale to a large distributed memory system. Matrix multiplies are one of them. Outside of a handful of ab initio computational chemistry algorithms (which are incredibly important), basically the only reason someone does a large dense matrix-multiply on a supercomputer is usually because they're running a benchmark and they're not solving a real science problem.
Folks more knowledgeable than me here feel free to jump in.
What I'm saying is it's not like a global solver (ie taking into account all to all interactions) wouldn't be more accurate right? It's just an insane proposition because surprise surprise that would require an enormous matmul during the update, which you can't do efficiently, even on a GPU, for the same reason the ML folks can't: the arithmetic intensity isn't high enough and so you can incur i/o costs (memory or network, same thing at this scale).
Neural networks, which are the basis for nearly all modern AI, are implemented as a mixture of sparse and dense matrix multiplies, depending on the neural architecture.
RAM bandwidth is basically always going to be a bottleneck. Microsft's proposal to get around this is to just keep everything in SRAM and pipe chips together.