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
@@ -1052,8 +1052,8 @@
     addPass(&SIInsertHardClausesID);
 
   addPass(&SIRemoveShortExecBranchesID);
-  addPass(&SIPreEmitPeepholeID);
   addPass(&SIInsertSkipsPassID);
+  addPass(&SIPreEmitPeepholeID);
   addPass(&BranchRelaxationPassID);
 }
 
diff --git a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
--- a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -57,10 +57,13 @@
   unsigned SkipThreshold = 0;
   MachineDominatorTree *MDT = nullptr;
 
+  MachineBasicBlock *EarlyExitBlock = nullptr;
+
   bool shouldSkip(const MachineBasicBlock &From,
                   const MachineBasicBlock &To) const;
 
   bool dominatesAllReachable(MachineBasicBlock &MBB);
+  void createEarlyExitBlock(MachineBasicBlock &MBB);
   void skipIfDead(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
                   DebugLoc DL);
 
@@ -161,6 +164,33 @@
   return true;
 }
 
+static void generatePsEndPgm(MachineBasicBlock &MBB,
+                             MachineBasicBlock::iterator I, DebugLoc DL,
+                             const SIInstrInfo *TII) {
+  // Generate "null export; s_endpgm".
+  BuildMI(MBB, I, DL, TII->get(AMDGPU::EXP_DONE))
+      .addImm(0x09) // V_008DFC_SQ_EXP_NULL
+      .addReg(AMDGPU::VGPR0, RegState::Undef)
+      .addReg(AMDGPU::VGPR0, RegState::Undef)
+      .addReg(AMDGPU::VGPR0, RegState::Undef)
+      .addReg(AMDGPU::VGPR0, RegState::Undef)
+      .addImm(1)  // vm
+      .addImm(0)  // compr
+      .addImm(0); // en
+  BuildMI(MBB, I, DL, TII->get(AMDGPU::S_ENDPGM)).addImm(0);
+}
+
+void SIInsertSkips::createEarlyExitBlock(MachineBasicBlock &MBB) {
+  MachineFunction *MF = MBB.getParent();
+  DebugLoc DL;
+
+  assert(!EarlyExitBlock);
+  EarlyExitBlock = MF->CreateMachineBasicBlock();
+  MF->insert(MF->end(), EarlyExitBlock);
+
+  generatePsEndPgm(*EarlyExitBlock, EarlyExitBlock->end(), DL, TII);
+}
+
 /// Insert an "if exec=0 { null export; s_endpgm }" sequence before the given
 /// iterator. Only applies to pixel shaders.
 void SIInsertSkips::skipIfDead(MachineBasicBlock &MBB,
@@ -168,11 +198,6 @@
   MachineFunction *MF = MBB.getParent();
   assert(MF->getFunction().getCallingConv() == CallingConv::AMDGPU_PS);
 
-  // Currently, SI_KILL_*_TERMINATOR is expected to occur only as the last
-  // terminator of a basic block. If this ever changes, we need to optionally
-  // split MBB here.
-  assert(I == MBB.end());
-
   // It is possible for an SI_KILL_*_TERMINATOR to sit at the bottom of a
   // basic block that has no further successors (e.g., there was an
   // `unreachable` there in IR). This can happen with original source of the
@@ -186,34 +211,40 @@
   // In this case, we write the "null_export; s_endpgm" skip code in the
   // already-existing basic block.
   auto NextBBI = std::next(MBB.getIterator());
-  bool NoSuccessor = llvm::find(MBB.successors(), &*NextBBI) == MBB.succ_end();
-  MachineBasicBlock *SkipBB;
+  bool NoSuccessor = I == MBB.end() &&
+                     llvm::find(MBB.successors(), &*NextBBI) == MBB.succ_end();
 
   if (NoSuccessor) {
-    SkipBB = &MBB;
+    generatePsEndPgm(MBB, I, DL, TII);
   } else {
-    // Create a new basic block that will contain the "null export; s_endpgm"
-    // and set up the branching to go around it.
-    SkipBB = MF->CreateMachineBasicBlock();
-    MF->insert(NextBBI, SkipBB);
+    if (!EarlyExitBlock) {
+      createEarlyExitBlock(MBB);
+      // Update next block pointer to reflect any new blocks
+      NextBBI = std::next(MBB.getIterator());
+    }
 
-    BuildMI(&MBB, DL, TII->get(AMDGPU::S_CBRANCH_EXECNZ)).addMBB(&*NextBBI);
-    MBB.addSuccessor(SkipBB);
+    auto BranchMI = BuildMI(MBB, I, DL, TII->get(AMDGPU::S_CBRANCH_EXECZ))
+                        .addMBB(EarlyExitBlock);
+
+    // Split the block if the branch will not come at the end.
+    auto Next = std::next(BranchMI->getIterator());
+    if (Next != MBB.end() && !Next->isTerminator()) {
+      MachineBasicBlock *SplitBB =
+          MF->CreateMachineBasicBlock(MBB.getBasicBlock());
+      MF->insert(NextBBI, SplitBB);
+      SplitBB->splice(SplitBB->begin(), &MBB, I, MBB.end());
+      SplitBB->transferSuccessorsAndUpdatePHIs(&MBB);
+      // FIXME: the expectation is that this will be used near the beginning
+      //        of a block so just assume all registers are still live.
+      for (auto LiveIn : MBB.liveins())
+        SplitBB->addLiveIn(LiveIn);
+      MBB.addSuccessor(SplitBB);
+      MDT->addNewBlock(SplitBB, &MBB);
+    }
 
-    MDT->addNewBlock(SkipBB, &MBB);
+    MBB.addSuccessor(EarlyExitBlock);
+    MDT->getBase().insertEdge(&MBB, EarlyExitBlock);
   }
-
-  // Generate "null export; s_endpgm".
-  BuildMI(SkipBB, DL, TII->get(AMDGPU::EXP_DONE))
-      .addImm(0x09) // V_008DFC_SQ_EXP_NULL
-      .addReg(AMDGPU::VGPR0, RegState::Undef)
-      .addReg(AMDGPU::VGPR0, RegState::Undef)
-      .addReg(AMDGPU::VGPR0, RegState::Undef)
-      .addReg(AMDGPU::VGPR0, RegState::Undef)
-      .addImm(1)  // vm
-      .addImm(0)  // compr
-      .addImm(0); // en
-  BuildMI(SkipBB, DL, TII->get(AMDGPU::S_ENDPGM)).addImm(0);
 }
 
 /// Translate a SI_KILL_*_TERMINATOR into exec-manipulating instructions.
@@ -428,6 +459,7 @@
     Kill->eraseFromParent();
   }
   KillInstrs.clear();
+  EarlyExitBlock = nullptr;
 
   return MadeChange;
 }
diff --git a/llvm/test/CodeGen/AMDGPU/insert-skips-kill-uncond.mir b/llvm/test/CodeGen/AMDGPU/insert-skips-kill-uncond.mir
--- a/llvm/test/CodeGen/AMDGPU/insert-skips-kill-uncond.mir
+++ b/llvm/test/CodeGen/AMDGPU/insert-skips-kill-uncond.mir
@@ -14,13 +14,13 @@
 
 # CHECK: bb.1:
 # CHECK: V_CMPX_LE_F32_e32
-# CHECK-NEXT: S_CBRANCH_EXECNZ %bb.2, implicit $exec
+# CHECK-NEXT: S_CBRANCH_EXECZ %bb.3, implicit $exec
 
-# CHECK: bb.3:
-# CHECK-NEXT: EXP_DONE
+# CHECK: bb.2:
 # CHECK: S_ENDPGM 0
 
-# CHECK: bb.2:
+# CHECK: bb.3:
+# CHECK-NEXT: EXP_DONE
 # CHECK: S_ENDPGM 0
 
 name: kill_uncond_branch
diff --git a/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll b/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
--- a/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
+++ b/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
@@ -12,11 +12,11 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_0_imm_neg:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: s_mov_b64 exec, 0
-; CHECK-NEXT: s_cbranch_execnz BB1_2
+; CHECK-NEXT: s_cbranch_execz BB1_2
 ; CHECK-NEXT: ; %bb.1:
-; CHECK-NEXT: exp null off, off, off, off done vm
 ; CHECK-NEXT: s_endpgm
 ; CHECK-NEXT: BB1_2:
+; CHECK-NEXT: exp null off, off, off, off done vm
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_0_imm_neg() #0 {
   call void @llvm.amdgcn.kill(i1 false)
@@ -27,15 +27,14 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_0_imm_neg_x2:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: s_mov_b64 exec, 0
-; CHECK-NEXT: s_cbranch_execnz BB2_2
-; CHECK:      exp null
-; CHECK-NEXT: s_endpgm
-; CHECK:      BB2_2:
+; CHECK-NEXT: s_cbranch_execz BB2_3
+; CHECK-NEXT: ; %bb.1:
 ; CHECK-NEXT: s_mov_b64 exec, 0
-; CHECK-NEXT: s_cbranch_execnz BB2_4
-; CHECK:      exp null
+; CHECK-NEXT: s_cbranch_execz BB2_3
+; CHECK-NEXT: ; %bb.2:
 ; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB2_4:
+; CHECK-NEXT: BB2_3:
+; CHECK:      exp null
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_0_imm_neg_x2() #0 {
   call void @llvm.amdgcn.kill(i1 false)
@@ -46,10 +45,11 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_var:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v0
-; CHECK-NEXT: s_cbranch_execnz BB3_2
-; CHECK:      exp null
+; CHECK-NEXT: s_cbranch_execz BB3_2
+; CHECK-NEXT: ; %bb.1:
 ; CHECK-NEXT: s_endpgm
 ; CHECK-NEXT: BB3_2:
+; CHECK:      exp null
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_var(float %x) #0 {
   %cmp = fcmp olt float %x, 0.0
@@ -61,15 +61,14 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_var_x2_same:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v0
-; CHECK-NEXT: s_cbranch_execnz BB4_2
-; CHECK:      exp null
-; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB4_2:
+; CHECK-NEXT: s_cbranch_execz BB4_3
+; CHECK-NEXT: ; %bb.1:
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v0
-; CHECK-NEXT: s_cbranch_execnz BB4_4
-; CHECK:      exp null
+; CHECK-NEXT: s_cbranch_execz BB4_3
+; CHECK-NEXT: ; %bb.2:
 ; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB4_4:
+; CHECK-NEXT: BB4_3:
+; CHECK:      exp null
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_var_x2_same(float %x) #0 {
   %cmp = fcmp olt float %x, 0.0
@@ -82,15 +81,14 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_var_x2:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v0
-; CHECK-NEXT: s_cbranch_execnz BB5_2
-; CHECK:      exp null
-; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB5_2:
+; CHECK-NEXT: s_cbranch_execz BB5_3
+; CHECK-NEXT: ; %bb.1
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v1
-; CHECK-NEXT: s_cbranch_execnz BB5_4
-; CHECK:      exp null
+; CHECK-NEXT: s_cbranch_execz BB5_3
+; CHECK-NEXT: ; %bb.2
 ; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB5_4:
+; CHECK-NEXT: BB5_3:
+; CHECK:      exp null
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_var_x2(float %x, float %y) #0 {
   %cmp.x = fcmp olt float %x, 0.0
@@ -103,18 +101,15 @@
 ; CHECK-LABEL: {{^}}test_kill_depth_var_x2_instructions:
 ; CHECK-NEXT: ; %bb.0:
 ; CHECK-NEXT: v_cmpx_gt_f32_e32 vcc, 0, v0
-; CHECK-NEXT: s_cbranch_execnz BB6_2
+; CHECK-NEXT: s_cbranch_execz BB6_3
 ; CHECK-NEXT: ; %bb.1:
-; CHECK-NEXT: exp
-; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB6_2:
 ; CHECK: v_mov_b32_e64 v7, -1
 ; CHECK: v_cmpx_gt_f32_e32 vcc, 0, v7
-; CHECK-NEXT: s_cbranch_execnz BB6_4
-; CHECK-NEXT: ; %bb.3:
-; CHECK-NEXT: exp
+; CHECK-NEXT: s_cbranch_execz BB6_3
+; CHECK-NEXT: ; %bb.2:
 ; CHECK-NEXT: s_endpgm
-; CHECK-NEXT: BB6_4:
+; CHECK-NEXT: BB6_3:
+; CHECK-NEXT: exp null
 ; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @test_kill_depth_var_x2_instructions(float %x) #0 {
   %cmp.x = fcmp olt float %x, 0.0
@@ -237,6 +232,62 @@
   ret void
 }
 
+; CHECK-LABEL: {{^}}test_kill_control_flow_return:
+
+; CHECK: v_cmp_eq_u32_e64 [[KILL_CC:s\[[0-9]+:[0-9]+\]]], s0, 1
+; CHECK: s_and_b64 exec, exec, s[2:3]
+; CHECK-NEXT: s_cbranch_execz [[EXIT_BB:BB[0-9]+_[0-9]+]]
+
+; CHECK: s_cmp_lg_u32 s{{[0-9]+}}, 0
+; CHECK: s_cbranch_scc0 [[COND_BB:BB[0-9]+_[0-9]+]]
+; CHECK: s_branch [[RETURN_BB:BB[0-9]+_[0-9]+]]
+
+; CHECK: [[COND_BB]]:
+; CHECK: v_mov_b32_e64 v7, -1
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_nop_e64
+; CHECK: v_mov_b32_e32 v0, v7
+
+; CHECK: [[EXIT_BB]]:
+; CHECK-NEXT: exp null
+; CHECK-NEXT: s_endpgm
+
+; CHECK: [[RETURN_BB]]:
+define amdgpu_ps float @test_kill_control_flow_return(i32 inreg %arg) #0 {
+entry:
+  %kill = icmp eq i32 %arg, 1
+  %cmp = icmp eq i32 %arg, 0
+  call void @llvm.amdgcn.kill(i1 %kill)
+  br i1 %cmp, label %bb, label %exit
+
+bb:
+  %var = call float asm sideeffect "
+    v_mov_b32_e64 v7, -1
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64
+    v_nop_e64", "={v7}"()
+  br label %exit
+
+exit:
+  %ret = phi float [ %var, %bb ], [ 0.0, %entry ]
+  ret float %ret
+}
+
 ; CHECK-LABEL: {{^}}test_kill_divergent_loop:
 ; CHECK: v_cmp_eq_u32_e32 vcc, 0, v0
 ; CHECK-NEXT: s_and_saveexec_b64 [[SAVEEXEC:s\[[0-9]+:[0-9]+\]]], vcc
@@ -295,12 +346,9 @@
 ; CHECK-LABEL: {{^}}phi_use_def_before_kill:
 ; CHECK: v_cndmask_b32_e64 [[PHIREG:v[0-9]+]], 0, -1.0,
 ; CHECK: v_cmpx_lt_f32_e32 vcc, 0,
-; CHECK-NEXT: s_cbranch_execnz [[BB4:BB[0-9]+_[0-9]+]]
+; CHECK-NEXT: s_cbranch_execz [[EXITBB:BB[0-9]+_[0-9]+]]
 
-; CHECK: exp
-; CHECK-NEXT: s_endpgm
-
-; CHECK: [[KILLBB:BB[0-9]+_[0-9]+]]:
+; CHECK: ; %[[KILLBB:bb.[0-9]+]]:
 ; CHECK-NEXT: s_cbranch_scc0 [[PHIBB:BB[0-9]+_[0-9]+]]
 
 ; CHECK: [[PHIBB]]:
@@ -313,6 +361,10 @@
 
 ; CHECK: [[ENDBB]]:
 ; CHECK-NEXT: s_endpgm
+
+; CHECK: [[EXITBB]]:
+; CHECK: exp null
+; CHECK-NEXT: s_endpgm
 define amdgpu_ps void @phi_use_def_before_kill(float inreg %x) #0 {
 bb:
   %tmp = fadd float %x, 1.000000e+00