[llvm] [CodeGen][Spill2Reg] Initial patch (PR #118832)

[Wei Xiao via llvm-commits]

williamweixiao wrote:

> I'd like to ensure this patch doesn't get too focussed on just working for gpr->vector spills. In my experience those profitable cases are pretty rare. What has been more useful has been cases such as storing scalar f32/f64 in the upper elements of xmm registers, or even using ymm upper halfs to store xmm vector data, and to a lesser extent storing a i32 in the upper 32-bits of a i64 gpr.

Yes, we also observed some cases in which spilling float value into GPR can help performance (suppose GPR register pressure is low meanwhile).

https://github.com/llvm/llvm-project/pull/118832