[llvm] [AMDGPU] Model structured control-flow lane masks as i1 (PR #209158)

[Pankaj Dwivedi via llvm-commits]

================
@@ -339,10 +340,13 @@ define float @global_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory(pt
 ; GFX942-NEXT:    buffer_inv sc1
 ; GFX942-NEXT:    v_cmp_eq_u32_e32 vcc, v3, v5
 ; GFX942-NEXT:    s_or_b64 s[0:1], vcc, s[0:1]
+; GFX942-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
----------------
PankajDwivedi-25 wrote:

also keeping that undef to init 0 might work but is that really correct.

https://github.com/llvm/llvm-project/pull/209158