diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 6fbe5d45ce0a..45c427c18784 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -1382,7 +1382,6 @@ bool WaitcntBrackets::merge(const WaitcntBrackets &Other) {
 
   for (auto T : inst_counter_types()) {
     // Merge event flags for this counter
-    const bool OldOutOfOrder = counterOutOfOrder(T);
     const unsigned OldEvents = PendingEvents & WaitEventMaskForInst[T];
     const unsigned OtherEvents = Other.PendingEvents & WaitEventMaskForInst[T];
     if (OtherEvents & ~OldEvents)
@@ -1425,7 +1424,7 @@ bool WaitcntBrackets::merge(const WaitcntBrackets &Other) {
       }
     }
 
-    if (RegStrictDom && !OldOutOfOrder)
+    if (RegStrictDom)
       StrictDom = true;
   }
 
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt.mir b/llvm/test/CodeGen/AMDGPU/waitcnt.mir
index 96bd9b3ff6f2..5f065f9be831 100644
--- a/llvm/test/CodeGen/AMDGPU/waitcnt.mir
+++ b/llvm/test/CodeGen/AMDGPU/waitcnt.mir
@@ -44,6 +44,10 @@
   define amdgpu_kernel void @subregs16bit() {
     ret void
   }
+
+  define amdgpu_kernel void @waitcnt_backedge() {
+    ret void
+  }
 ...
 ---
 
@@ -332,3 +336,35 @@ body: |
       $vgpr1 = FLAT_LOAD_USHORT killed $vgpr2_vgpr3, 0, 0, implicit $exec, implicit $flat_scr
       V_NOP_e32 implicit $exec, implicit $vgpr0_lo16, implicit $vgpr1_lo16
 ...
+
+---
+# Waitcnt required before the use of $sgpr10_sgpr11, as the S_LOAD also writes
+# to $sgpr10_sgpr11, and can occur first in the program running order.
+
+# CHECK-LABEL: name: waitcnt_backedge
+# CHECK: S_WAITCNT
+# CHECK: $sgpr10_sgpr11 = S_CSELECT_B64
+# CHECK: $sgpr10_sgpr11 = S_LOAD_DWORDX2_IMM
+
+
+name: waitcnt_backedge
+body: |
+  bb.0:
+    renamable $sgpr4_sgpr5_sgpr6_sgpr7 = S_LOAD_DWORDX4_IMM renamable $sgpr2_sgpr3, 32, 0 :: (load (s128) from `i32 addrspace(4)* undef`, addrspace 4)
+
+  bb.4:
+    renamable $sgpr10_sgpr11 = S_CSELECT_B64 -1, 0, implicit killed $scc
+    renamable $vgpr1 = BUFFER_LOAD_DWORD_OFFEN killed renamable $vgpr5, renamable $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+    renamable $sgpr10_sgpr11 = S_LOAD_DWORDX2_IMM killed renamable $sgpr0_sgpr1, 0, 0 :: (load (s64) from `i32 addrspace(4)* undef`, align 4, addrspace 4)
+    S_CBRANCH_SCC0 %bb.9, implicit killed $scc
+
+  bb.9:
+    renamable $vgpr1 = V_CNDMASK_B32_e64 0, 0, 0, 1, killed $sgpr14_sgpr15, implicit $exec
+    S_CBRANCH_SCC0 %bb.14, implicit killed $scc
+
+  bb.10:
+    S_BRANCH %bb.4
+
+  bb.14:
+    S_ENDPGM 0
+...