[llvm] [AArch64] Add C1-Nano scheduling model (PR #182316)

[David Green via llvm-commits]

davemgreen wrote:

> So the question is whether we should be creating a new "C1" test directory for the C1 product line (like this C1-Nano PR currently does), or should we put them into the existing "Cortex" test directory (like the current C1-Ultra PR does)?

I would put them in the same folder, probably Cortex is good enough. The important continuation is the A55->A510->A520->C1-Nano (presumably to C2 Nano in the future too). Otherwise the cpus in the C1 generation are not very similar in terms of microarchitecture.

Using the #includes is great for the basic instr tests and helps not having minor differences between them all. They just haven't all been ported to it yet.

https://github.com/llvm/llvm-project/pull/182316