Index: lib/Target/AMDGPU/SIInsertSkips.cpp
===================================================================
--- lib/Target/AMDGPU/SIInsertSkips.cpp
+++ lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -251,6 +251,7 @@
        BI != BE; BI = NextBB) {
     NextBB = std::next(BI);
     MachineBasicBlock &MBB = *BI;
+    bool HaveSkipBlock = false;
 
     if (!ExecBranchStack.empty() && ExecBranchStack.back() == &MBB) {
       // Reached convergence point for last divergent branch.
@@ -280,6 +281,11 @@
         // FIXME: Shouldn't this be handled by BranchFolding?
         if (MBB.isLayoutSuccessor(MI.getOperand(0).getMBB()))
           MI.eraseFromParent();
+        // Remove the given unconditional branch when a skip block has been
+        // inserted after the current one and let skip the two instructions
+        // performing the kill if the exec mask is non-zero.
+        if (HaveSkipBlock)
+          MI.eraseFromParent();
         break;
       }
       case AMDGPU::SI_KILL_TERMINATOR: {
@@ -288,9 +294,9 @@
 
         if (ExecBranchStack.empty()) {
           if (skipIfDead(MI, *NextBB)) {
+            HaveSkipBlock = true;
             NextBB = std::next(BI);
             BE = MF.end();
-            Next = MBB.end();
           }
         } else {
           HaveKill = true;