[llvm] [AMDGPU] Do not replace SALU floating point multiply with VALU-only ldexp (PR #145048)

[Shilei Tian via llvm-commits]

================
@@ -2,19 +2,34 @@
 ; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG %s
 ; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL %s
 
+; TODO: GlobalISel should avoid generating v_ldexp_f32.
----------------
shiltian wrote:

If that's not too much effort, can you also do it in GIsel as well?

https://github.com/llvm/llvm-project/pull/145048