[compiler-rt] [AMDGPU] Add another SIFoldOperands instance after shrink (PR #67878)

[Stanislav Mekhanoshin via llvm-commits]

rampitec wrote:

> I've just tested this on 10000 graphics shaders and it seems to make no difference at all. I tried gfx900 and gfx1100. Can anyone else from the graphics team confirm this?

It seems the most impact is on the pre-gfx9 targets, very similar to https://github.com/llvm/llvm-project/pull/68028 and for the same reason: there were no no-carry add/sub. The rest of the impact is when an add/sub is created late in the pipeline.

https://github.com/llvm/llvm-project/pull/67878