[llvm] [AArch64] Consider negated powers of 2 when calculating throughput cost (PR #143013)

[David Green via llvm-commits]

https://github.com/davemgreen commented:

Yeah sounds good to me for signed divides. The divide cost code could do with some work, I had a patch to try and address some of it but it didn't get very far.

Looking at the codegen, should we be adding 1 extra fro the cost of the neg?

https://github.com/llvm/llvm-project/pull/143013