diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -1737,7 +1737,7 @@
             VgprUse.insert(RegNo);
             // If at least one of Op's registers is in the score brackets, the
             // value is likely loaded outside of the loop.
-            if (Brackets.getRegScore(RegNo, VM_CNT) > 0) {
+            if (Brackets.getRegScore(RegNo, VM_CNT) > Brackets.getScoreLB(VM_CNT)) {
               UsesVgprLoadedOutside = true;
               break;
             }
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir b/llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir
--- a/llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir
+++ b/llvm/test/CodeGen/AMDGPU/waitcnt-vmcnt-loop.mir
@@ -535,3 +535,40 @@
     S_ENDPGM 0
 
 ...
+---
+
+# This test case checks that we flush the vmcnt counter only if necessary
+# (i.e. if a waitcnt is needed for the vgpr use we find in the loop)
+
+# GFX10-LABEL: waitcnt_vm_necessary
+# GFX10-LABEL: bb.0:
+# GFX10: S_WAITCNT 16240
+# GFX10: $vgpr4
+# GFX10-NOT: S_WAITCNT
+# GFX10-LABEL: bb.1:
+# GFX10-NOT: S_WAITCNT
+
+# GFX9-LABEL: waitcnt_vm_necessary
+# GFX9-LABEL: bb.0:
+# GFX9: S_WAITCNT 3952
+# GFX9: $vgpr4
+# GFX9-NOT: S_WAITCNT
+# GFX9-LABEL: bb.1:
+# GFX9-NOT: S_WAITCNT
+
+name:            waitcnt_vm_necessary
+body:             |
+  bb.0:
+    successors: %bb.1(0x80000000)
+
+    $vgpr0_vgpr1_vgpr2_vgpr3 = GLOBAL_LOAD_DWORDX4 killed $vgpr0_vgpr1, 0, 0, implicit $exec
+    $vgpr4 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
+
+  bb.1:
+    successors: %bb.1(0x40000000)
+
+    $vgpr5 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit $exec
+    S_CBRANCH_SCC1 %bb.1, implicit killed $scc
+    S_ENDPGM 0
+
+...