[llvm] [ISel][AArch64] Add CodeGen support for partial sub reductions. (PR #186809)

[Paul Walker via llvm-commits]

================

----------------
paulwalker-arm wrote:

Is the double negation necessary for floating-point? Floating-point doesn't have the same twos complement issues as integer so it should be safe to continue to negate one of the multiplicands.

https://github.com/llvm/llvm-project/pull/186809