diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -1033,6 +1033,12 @@
   addPass(createSIShrinkInstructionsPass());
   addPass(createSIModeRegisterPass());
 
+  if (getOptLevel() > CodeGenOpt::None)
+    addPass(&SIInsertHardClausesID);
+
+  addPass(&SIRemoveShortExecBranchesID);
+  addPass(&SIInsertSkipsPassID);
+  addPass(&SIPreEmitPeepholeID);
   // The hazard recognizer that runs as part of the post-ra scheduler does not
   // guarantee to be able handle all hazards correctly. This is because if there
   // are multiple scheduling regions in a basic block, the regions are scheduled
@@ -1045,12 +1051,6 @@
   // FIXME: This stand-alone pass will emit indiv. S_NOP 0, as needed. It would
   // be better for it to emit S_NOP <N> when possible.
   addPass(&PostRAHazardRecognizerID);
-  if (getOptLevel() > CodeGenOpt::None)
-    addPass(&SIInsertHardClausesID);
-
-  addPass(&SIRemoveShortExecBranchesID);
-  addPass(&SIInsertSkipsPassID);
-  addPass(&SIPreEmitPeepholeID);
   addPass(&BranchRelaxationPassID);
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/hazard-pass-ordering.mir b/llvm/test/CodeGen/AMDGPU/hazard-pass-ordering.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hazard-pass-ordering.mir
@@ -0,0 +1,24 @@
+# RUN: llc -march=amdgcn -mcpu=gfx908 -start-before=si-pre-emit-peephole %s -o - | FileCheck -check-prefix=GCN %s
+
+# Verify that the dedicated hazard recognizer pass is run after late peephole
+# optimizations. New hazards can be introduced if instructions are removed by
+# passes that are run before the final hazard recognizer.
+
+---
+# GCN-LABEL: {{^}}mai_hazard_pass_ordering_optimize_vcc_branch:
+# GCN: v_accvgpr_read_b32
+# GCN-NEXT: s_nop
+# GCN-NEXT: flat_load_dword
+name:            mai_hazard_pass_ordering_optimize_vcc_branch
+body:             |
+  bb.0:
+    $vgpr0 = V_MOV_B32_e32 1, implicit $exec
+    $vgpr2 = V_ACCVGPR_READ_B32 killed $agpr0, implicit $exec
+    $sgpr8_sgpr9 = S_MOV_B64 -1
+    $vgpr3 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
+    $vcc = S_ANDN2_B64 $exec, killed renamable $sgpr8_sgpr9, implicit-def dead $scc
+    S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
+
+  bb.1:
+    S_ENDPGM 0
+...