diff --git a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
--- a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
+++ b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
@@ -491,6 +491,7 @@
   const unsigned SearchLimit = 16;
   unsigned Count = 0;
   bool KilledT = false;
+  bool UsedT = false;
   for (auto Iter = std::next(MovT.getIterator()),
             E = MovT.getParent()->instr_end();
        Iter != E && Count < SearchLimit && !KilledT; ++Iter, ++Count) {
@@ -498,6 +499,9 @@
     MachineInstr *MovY = &*Iter;
     KilledT = MovY->killsRegister(T, &TRI);
 
+    bool PrevUsedT = UsedT;
+    UsedT = UsedT || instReadsReg(MovY, T, Tsub, TRI);
+
     if ((MovY->getOpcode() != AMDGPU::V_MOV_B32_e32 &&
          MovY->getOpcode() != AMDGPU::COPY) ||
         !MovY->getOperand(1).isReg()        ||
@@ -573,7 +577,10 @@
     dropInstructionKeepingImpDefs(*MovY, TII);
     MachineInstr *Next = &*std::next(MovT.getIterator());
 
-    if (MRI.use_nodbg_empty(T)) {
+    if (T.isVirtual() ? MRI.use_nodbg_empty(T)
+                      : (MovY->getOperand(1).isKill() && !PrevUsedT)) {
+      // For physical registers: the use of T in MovY is killed, and we didn't
+      // see any other uses of T before MovY.
       dropInstructionKeepingImpDefs(MovT, TII);
     } else {
       Xop.setIsKill(false);
diff --git a/llvm/test/CodeGen/AMDGPU/v_swap_b32.mir b/llvm/test/CodeGen/AMDGPU/v_swap_b32.mir
--- a/llvm/test/CodeGen/AMDGPU/v_swap_b32.mir
+++ b/llvm/test/CodeGen/AMDGPU/v_swap_b32.mir
@@ -46,13 +46,13 @@
     liveins: $vgpr0, $vgpr1, $sgpr30_sgpr31
     $vgpr2 = V_MOV_B32_e32 killed $vgpr0, implicit $exec
     $vgpr0 = V_MOV_B32_e32 killed $vgpr1, implicit $exec
-    $vgpr1 = V_MOV_B32_e32 killed $vgpr2, implicit $exec
+    $vgpr1 = V_MOV_B32_e32 $vgpr2, implicit $exec
     S_SETPC_B64_return $sgpr30_sgpr31, implicit $vgpr0, implicit $vgpr2, implicit $vgpr1
 ...
 
-# FIXME: should not remove the def of $vgpr2 because $vgpr2_vgpr3 is live out
 # GCN-LABEL: name: swap_phys_liveout_superreg
 # GCN: bb.0:
+# GCN-NEXT: $vgpr2 = V_MOV_B32_e32 $vgpr0, implicit $exec
 # GCN-NEXT: $vgpr0, $vgpr1 = V_SWAP_B32 $vgpr1, $vgpr0, implicit $exec
 # GCN-NEXT: S_SETPC_B64_return
 ---
@@ -62,7 +62,7 @@
     liveins: $vgpr0, $vgpr1, $sgpr30_sgpr31
     $vgpr2 = V_MOV_B32_e32 killed $vgpr0, implicit $exec
     $vgpr0 = V_MOV_B32_e32 killed $vgpr1, implicit $exec
-    $vgpr1 = V_MOV_B32_e32 killed $vgpr2, implicit $exec
+    $vgpr1 = V_MOV_B32_e32 $vgpr2, implicit $exec
     S_SETPC_B64_return $sgpr30_sgpr31, implicit $vgpr0, implicit $vgpr2_vgpr3, implicit $vgpr1
 ...