diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -95,6 +95,10 @@
   cl::desc("Do not align and prefetch loops"),
   cl::init(false));
 
+static cl::opt<bool> VGPRReserveforSGPRSpill(
+    "amdgpu-reserve-vgpr-for-sgpr-spill",
+    cl::desc("Allocates one VGPR for future SGPR Spill"), cl::init(false));
+
 static bool hasFP32Denormals(const MachineFunction &MF) {
   const SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
   return Info->getMode().allFP32Denormals();
@@ -10755,6 +10759,15 @@
   }
 
   TargetLoweringBase::finalizeLowering(MF);
+
+  // Allocate a VGPR for future SGPR Spill if
+  // "amdgpu-reserve-vgpr-for-sgpr-spill" option is used
+  if (VGPRReserveforSGPRSpill) {
+    int fi = MF.getFrameInfo().CreateStackObject(4, 4, false, nullptr,
+                                                 TargetStackID::SGPRSpill);
+    Info->allocateSGPRSpillToVGPR(MF, fi);
+    MF.getFrameInfo().RemoveStackObject(fi);
+  }
 }
 
 void SITargetLowering::computeKnownBitsForFrameIndex(const SDValue Op,
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -308,6 +308,9 @@
   for (MCPhysReg Reg : MFI->getVGPRSpillAGPRs())
     reserveRegisterTuples(Reserved, Reg);
 
+  for (auto SSpill : MFI->getSGPRSpillVGPRs())
+    reserveRegisterTuples(Reserved, SSpill.VGPR);
+
   return Reserved;
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll b/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/reserve-vgpr-for-sgpr-spill.ll
@@ -0,0 +1,20 @@
+; RUN: llc -mtriple amdgcn-amd-amdhsa --amdgpu-reserve-vgpr-for-sgpr-spill -mcpu=gfx803 -O0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
+
+declare i32 @child_func(i32 %0, [255 x i32] %b) #0
+; GCN-LABEL: {{^}}parent_func:
+; CHECK: 	v_writelane_b32 v32, s34, 4
+; CHECK: 	v_writelane_b32 v32, s30, 2
+; CHECK: 	v_writelane_b32 v32, s31, 3
+; CHECK: 	v_readlane_b32 s6, v32, 2
+; CHECK: 	v_readlane_b32 s7, v32, 3
+; CHECK: 	v_readlane_b32 s34, v32, 4
+; GCN: ; NumVgprs: 256
+define fastcc i32 @parent_func(i32 %0, i32 %1, [255 x i32] %b) #1 {
+entry:
+  %ret0 = tail call fastcc i32 @child_func(i32 %0, [255 x i32] %b)
+  %res0 = add i32 %ret0, %0
+  ret i32 %res0
+}
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind "no-frame-pointer-elim"="true" }
\ No newline at end of file