[NVPTX] Fix issue introduced in D10321

[wengxt]

Summary

Really check if %SP is not used in other places, instead of checking only exact
one non-dbg use.

Patched by Xuetian Weng.

[jingyue]

LGTM

[jholewinski]

LTGM

lib/Target/NVPTX/NVPTXFrameLowering.cpp

if (MF.getFrameInfo()->hasStackObjects()) {
     // This instruction really occurs before first instruction
     // in the BB, so giving it no debug location.
     DebugLoc dl = DebugLoc();
 
     // mov %SPL, %depot;
     // cvta.local %SP, %SPL;
     if (static_cast<const NVPTXTargetMachine &>(MF.getTarget()).is64Bit()) {
       // Check if %SP is actually used
-      if (MR.hasOneNonDBGUse(NVPTX::VRFrame)) {
+      if (!MR.use_empty(NVPTX::VRFrame)) {
         MI = BuildMI(MBB, MI, dl, MF.getSubtarget().getInstrInfo()->get(
                                       NVPTX::cvta_local_yes_64),
                      NVPTX::VRFrame)
                  .addReg(NVPTX::VRFrameLocal);
       }
-
       BuildMI(MBB, MI, dl,
               MF.getSubtarget().getInstrInfo()->get(NVPTX::MOV_DEPOT_ADDR_64),
               NVPTX::VRFrameLocal)
           .addImm(MF.getFunctionNumber());
     } else {
       // Check if %SP is actually used
-      if (MR.hasOneNonDBGUse(NVPTX::VRFrame)) {
+      if (!MR.use_empty(NVPTX::VRFrame)) {
         MI = BuildMI(MBB, MI, dl, MF.getSubtarget().getInstrInfo()->get(
                                       NVPTX::cvta_local_yes),
                      NVPTX::VRFrame)
                  .addReg(NVPTX::VRFrameLocal);
       }
       BuildMI(MBB, MI, dl,
               MF.getSubtarget().getInstrInfo()->get(NVPTX::MOV_DEPOT_ADDR),
               NVPTX::VRFrameLocal)

test/CodeGen/NVPTX/local-stack-frame.ll

 ; PTX64:        st.local.u32  [%rd{{[0-9]+}}], %r{{[0-9]+}};
 define void @foo3(i32 %a) {
   %local = alloca [3 x i32], align 4
   %1 = bitcast [3 x i32]* %local to i32*
   %2 = getelementptr inbounds i32, i32* %1, i32 %a
   store i32 %a, i32* %2
   ret void
 }
+
+; PTX32:        cvta.local.u32   %SP, %SPL;
+; PTX32:        add.u32          {{%r[0-9]+}}, %SP, 0;
+; PTX32:        st.local.u32     [{{%r[0-9]+}}], {{%r[0-9]+}}
+; PTX32:        st.local.u32     [{{%r[0-9]+}}], {{%r[0-9]+}}
+; PTX64:        cvta.local.u64   %SP, %SPL;
+; PTX64:        add.u64          {{%rd[0-9]+}}, %SP, 0;
+; PTX64:        st.local.u32     [{{%rd[0-9]+}}], {{%r[0-9]+}}
+; PTX64:        st.local.u32     [{{%rd[0-9]+}}], {{%r[0-9]+}}
+define void @foo4() {
+  %A = alloca i32
+  %B = alloca i32
+  store i32 0, i32* %A
+  store i32 0, i32* %B
+  call void @bar(i32* %A)
+  call void @bar(i32* %B)
+  ret void
+}