[llvm] [AMDGPU] Lazily emit waitcnts on function entry (PR #73122)

[Jay Foad via llvm-commits]

================
@@ -11,20 +11,18 @@
 define amdgpu_cs_chain void @set_inactive_chain_arg(ptr addrspace(1) %out, i32 %inactive, i32 %active) {
 ; GFX11-LABEL: set_inactive_chain_arg:
 ; GFX11:       ; %bb.0:
-; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX11-NEXT:    v_mov_b32_e32 v0, v11
+; GFX11-NEXT:    s_waitcnt expcnt(0)
 ; GFX11-NEXT:    s_not_b32 exec_lo, exec_lo
 ; GFX11-NEXT:    v_mov_b32_e32 v0, v10
 ; GFX11-NEXT:    s_not_b32 exec_lo, exec_lo
 ; GFX11-NEXT:    global_store_b32 v[8:9], v0, off
-; GFX11-NEXT:    s_nop 0
-; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
----------------
jayfoad wrote:

This change is good. This patch naturally fixes the same bug that #72245 fixes.

https://github.com/llvm/llvm-project/pull/73122