diff --git a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
--- a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
@@ -18,7 +18,9 @@
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIInstrInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/Support/CommandLine.h"
+#include "llvm/InitializePasses.h"
 
 using namespace llvm;
 
@@ -37,6 +39,8 @@
 class SIRemoveShortExecBranches : public MachineFunctionPass {
 private:
   const SIInstrInfo *TII = nullptr;
+  MachineLoopInfo *MLI = nullptr;
+
   bool getBlockDestinations(MachineBasicBlock &SrcMBB,
                             MachineBasicBlock *&TrueMBB,
                             MachineBasicBlock *&FalseMBB,
@@ -53,11 +57,20 @@
   }
 
   bool runOnMachineFunction(MachineFunction &MF) override;
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<MachineLoopInfo>();
+    AU.addPreserved<MachineLoopInfo>();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
 };
 
 } // End anonymous namespace.
 
-INITIALIZE_PASS(SIRemoveShortExecBranches, DEBUG_TYPE,
+INITIALIZE_PASS_BEGIN(SIRemoveShortExecBranches, DEBUG_TYPE,
+                "SI remove short exec branches", false, false)
+INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
+INITIALIZE_PASS_END(SIRemoveShortExecBranches, DEBUG_TYPE,
                 "SI remove short exec branches", false, false)
 
 char SIRemoveShortExecBranches::ID = 0;
@@ -123,6 +136,7 @@
 
   // Consider only the forward branches.
   if ((SrcMBB.getNumber() >= TrueMBB->getNumber()) ||
+      (MLI->getLoopFor(&SrcMBB) != MLI->getLoopFor(TrueMBB)) ||
       mustRetainExeczBranch(*FalseMBB, *TrueMBB))
     return false;
 
@@ -136,6 +150,7 @@
 bool SIRemoveShortExecBranches::runOnMachineFunction(MachineFunction &MF) {
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   TII = ST.getInstrInfo();
+  MLI = &getAnalysis<MachineLoopInfo>();
   MF.RenumberBlocks();
   bool Changed = false;
 
diff --git a/llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll b/llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll
--- a/llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll
+++ b/llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll
@@ -32,6 +32,7 @@
 ; CHECK-NEXT:    s_and_b64 s[8:9], s[8:9], exec
 ; CHECK-NEXT:    s_or_b64 s[4:5], s[4:5], s[8:9]
 ; CHECK-NEXT:    s_andn2_b64 exec, exec, s[2:3]
+; CHECK-NEXT:    s_cbranch_execz BB0_6
 ; CHECK-NEXT:  BB0_3: ; %loop
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    s_or_b64 s[6:7], s[6:7], exec
@@ -49,7 +50,7 @@
 ; CHECK-NEXT:    s_add_i32 s0, s0, 1
 ; CHECK-NEXT:    s_xor_b64 s[6:7], exec, -1
 ; CHECK-NEXT:    s_branch BB0_1
-; CHECK-NEXT:  ; %bb.6: ; %Flow2
+; CHECK-NEXT:  BB0_6: ; %Flow2
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[2:3]
 ; CHECK-NEXT:    v_mov_b32_e32 v1, 0
 ; CHECK-NEXT:    s_and_saveexec_b64 s[0:1], s[4:5]