[AMDGPU] Save VGPR of whole wave when spilling

[sebastian-ne]

Summary

Spilling SGPRs to scratch uses a temporary VGPR. LLVM currently cannot
determine if a VGPR is used in other lanes or not, so we need to save
all lanes of the VGPR. We even need to save the VGPR if it is marked as
dead.

The generated code depends on two things:

• Can we scavenge an SGPR to save EXEC?
• And can we scavenge a VGPR?

If we can scavenge an SGPR, we

• save EXEC into the SGPR
• set the needed lane mask
• save the temporary VGPR
• write the spilled SGPR into VGPR lanes
• save the VGPR again to the target stack slot
• restore the VGPR
• restore EXEC

If we were not able to scavenge an SGPR, we do the same operations, but
everytime the temporary VGPR is written to memory, we

• write VGPR to memory
• flip exec (s_not exec, exec)
• write VGPR again (previously inactive lanes)

Surprisingly often, we are able to scavenge an SGPR, even though we are
at the brink of running out of SGPRs.
Scavenging a VGPR does not have a great effect (saves three instructions
if no SGPR was scavenged), but we need to know if the VGPR we use is
live before or not, otherwise the machine verifier complains.

[foad]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1428

If the scavenger finds a vgpr that it thinks is dead, would that mean we only have to save the inactive lanes?

llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll

49

What causes this change?

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1428

Yes, we can do that.

If you don’t mind, I’ll put that in a later patch. I’m currently preparing a patch on top of this one to get rid of the code duplication here.
That should also allow to get rid of the temporary RegScavenger below.

llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll

49

Above these tested lines, the VGPR gets saved to scratch in a buffer_store_dword.
The same VGPR is the destination in buffer_load_dword below, so waiting for expcnt(0) makes sure we do not overwrite it before the store happened (the docs say expcnt waits until writes to the last level cache happened, so I guess the store→load is the reason).

[piotr]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1322

Not sure if that's a concern in this context, but doesn't it potentially clobber SCC?

[foad]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1428

If you don’t mind, I’ll put that in a later patch.

Sure. I was just checking my understanding.

[critson]

I am a little dubious about the whole approach.

If every SGPR spill that goes to scratch has to do an extra store+load (or multiple) then is that not potentially worse than the performance hit of reserving an entire VGPR for spilling in the case that we know we are going to have to use one? (I guess perhaps we have no way of knowing we need one?)

I get that this is basically an edge case (and we want to avoid SGPR spill to memory in the long run through other changes), but I wonder if we can qualify/quantify how rare this edge case is?
If it is truly rare, then I guess it matter a lot less how performant the resulting code is.

As an aside, if we are moving to using flat scratch in the main, is it possible to replace most of this with s_scratch_store / s_scratch_load and avoid the need for an VGPR entirely?

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1322

Clobbering SCC is an ongoing concern with spill code; however, buildSpillLoadStore can already generate arithmetic instructions which can clobber SCC, so this is not a new concern.
It's possible that if there is an issue we are going to run into it faster as this will clobber SCC everytime.

1335

Any reason for XOR rather than NOT?

llvm/test/CodeGen/AMDGPU/partial-sgpr-to-vgpr-spills.ll

1097

These two instructions are not doing anything.

[kerbowa]

In D96336#2553008, @critson wrote:

If every SGPR spill that goes to scratch has to do an extra store+load (or multiple) then is that not potentially worse than the performance hit of reserving an entire VGPR for spilling in the case that we know we are going to have to use one? (I guess perhaps we have no way of knowing we need one?)

We currently unconditionally reserve one VGPR for SGPR spills. I'm working on changing this so that we have the option of reserving a variable amount of VGPRs based on some register pressure threshold. Spilling SGPRs to memory should be a last resort anyway, and I've seen the issue raised in this patch multiple times. It's worth having something less broken when we run out of lanes in reserved VGPRs.

[sebastian-ne]

I am a little dubious about the whole approach.

Me too, I’m also not happy about needing inline assembly, so if you have an idea to improve some or all of that, I’m all ears.

If every SGPR spill that goes to scratch has to do an extra store+load (or multiple) then is that not potentially worse than the performance hit of reserving an entire VGPR for spilling in the case that we know we are going to have to use one? (I guess perhaps we have no way of knowing we need one?)

Yes. If we knew that we need to spill an SGPR, we would just reserve a VGPR to spill the SGPR to and not spill to scratch at all. The problem is, we don’t know. (Matt plans to fix that by splitting register allocation into two phases, first allocating SGPRs, then VPGRs.)

I get that this is basically an edge case (and we want to avoid SGPR spill to memory in the long run through other changes), but I wonder if we can qualify/quantify how rare this edge case is?

I fear it’s less rare than we want. We hit this bug in a not-so-big shader that was forced to run with high occupancy and this limited to 64 VGPRs. However, it should get rare once the register allocation always spills SGPRs to VGPRs.

As an aside, if we are moving to using flat scratch in the main, is it possible to replace most of this with s_scratch_store / s_scratch_load and avoid the need for an VGPR entirely?

That would make sense, but it feels like s_scratch instructions got removed in newer hardware.

We currently unconditionally reserve one VGPR for SGPR spills.

Interesting, I missed that. As the VGPR is reserved in SITargetLowering::finalizeLowering, this is currently not done for GlobalISel?

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1335

No reason, I’ll change that. Thanks for the note

llvm/test/CodeGen/AMDGPU/partial-sgpr-to-vgpr-spills.ll

1097

Right, I’m working on fixing that in a later patch, same as Jay’s optimization.

[sebastian-ne]

Use s_not instead of s_xor.

[sebastian-ne]

• Fake use inline asm should have sideeffects
• Use SGPRs to save EXEC only if IsKill when restoring VGPR
• Update spill-special-sgpr.mir test

[arsenm]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1270

Can you spell out the expected instruction sequence in the comment

1306–1312

Definitely should not be introducing inline asm. Can't you just add an implicit def on the first instruction in the sequence, or introduce a special purpose pseudo?

1328

Do you mean identity copies?

1352

Can't you just add this as an implicit use to the last instruction in the sequence?

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1306–1312

That sounds better, thanks. For stores, the first instruction is a buffer_store VGPR, …, so there is no previous instruction I can add a define to.
For a pseudo, what would be the best pass to remove it again? (Maybe SIInsertWaitcntsPass?)

1328

No, that is about the superfluous s_mov instructions that @critson noticed. I fixed that in a patch on top of this one (I’ll put that on Phabricator after removing the inline assembly).

[arsenm]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1306–1312

It doesn't need to be removed, it can just be emitted as a comment

[sebastian-ne]

Get rid of inline assembly with implicit use and FAKE_DEF pseudo (yay).

[arsenm]

llvm/lib/Target/AMDGPU/SIInstructions.td

117–118 ↗

(On Diff #323020)

I think a better name would be something like COPY_INACTIVE_LANES or something like that?

[sebastian-ne]

Rename FAKE_DEF pseudo to COPY_INACTIVE_LANES.

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIInstructions.td

117–118 ↗

(On Diff #323020)

Hm, it doesn’t really copy anything. (Also, the VGPR could be dead in other lanes as well.) How about DEF_INACTIVE_LANES?

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1270

I added a comment with generated instructions in D96517 (SIRegisterInfo.cpp:L1449).

Direct link (will cease to work when the review is updated): https://reviews.llvm.org/D96517#C2404245NL1449

[arsenm]

llvm/lib/Target/AMDGPU/SIInstructions.td

114 ↗

(On Diff #323033)

Replace make with mark, or remove as?

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

Why doesn't this use the normal emergency stack slot?

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

How do I get the emergency stack slot?

[sebastian-ne]

Fix crash when emitting ISA (change COPY_INACTIVE_LANES to a real instruction).

[arsenm]

In D96336#2553296, @kerbowa wrote:

In D96336#2553008, @critson wrote:

If every SGPR spill that goes to scratch has to do an extra store+load (or multiple) then is that not potentially worse than the performance hit of reserving an entire VGPR for spilling in the case that we know we are going to have to use one? (I guess perhaps we have no way of knowing we need one?)

We currently unconditionally reserve one VGPR for SGPR spills. I'm working on changing this so that we have the option of reserving a variable amount of VGPRs based on some register pressure threshold. Spilling SGPRs to memory should be a last resort anyway, and I've seen the issue raised in this patch multiple times. It's worth having something less broken when we run out of lanes in reserved VGPRs.

We don't need a pressure heuristic to decide to reserve VGPRs ahead of time, we can just split the allocation process as in D55301

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

You don't get it, it just is what automatically happens when you attempt to use the scavenger and it fails to find a free register. It's possible we would need to add SGPR spills as one of the conditions where it will be necessary

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

Thanks for the explanation. The RegScavenger won’t spill all lanes though. Also, it won’t spill if the register is dead in the currently active lanes (which we want to fix here).
So, I don’t think using the scavenger works, unless we can tell the RegScavenger to spill the whole wave, and lower that to spill – flip exec – spill – flip exec again.

[arsenm]

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

Even if you don't use it's mechanism, it still has the emergency slot available in the function frame you can re-use

[sebastian-ne]

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

Yes, it would be nice do re-use that, but i don’t see a way to get an emergency slot from the RegScavenger.
We could save the emergency slot in SIFrameLowering when allocating the slot, but we cannot check if it is unused when we need it to spill an SGPR. Unconditionally using it can overwrite a saved register.

[arsenm]

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

498–499

RegScavenger::getScavengingFrameIndices reports its emergency slots. It shouldn't be live at any context where you would need it, as that would defeat the point.

[sebastian-ne]

Use emergency spill slot to save VGPR if there is one.

If there is none (SILowerSGPRSpills runs before PrologEpilogInserter, which creates the emergency slot), create one.

I think it doesn’t really work because the PrologEpilogInserter gets another RegScavenger than we have in SILowerSGPRSpills, so the slot will still not be shared.
Maybe save the created slot in SIFrameLowering, so it can be used in SIFrameLowering::processFunctionBeforeFrameFinalized?

[arsenm]

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

1245–1247

I don't understand why you would need to check this

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1342

I believe you don't need to split this when using scratch instructions

1350–1356

I don't really like adding this here on demand. You need to be sure this is called after frame finalization. This should be created up front

1359–1360

I don't follow this UseKillFromMI vs. isKill. Just use the isKill?

1361

There shouldn't be any temporary reg scavenger created locally. Also, using forward scavenging is deprecated

1429

Ditto

[sebastian-ne]

Rewrite code around reusing the emergency spill slot. I hope it looks better that way.
It now works like this:

1. SILowerSGPRSpills calls SIRegisterInfo::spillSGPR
2. SIRegisterInfo::spillSGPR calls SIMachineFunctionInfo::getScavengeFI, which allocates a stack slot and saves it in SIMachineFunctionInfo::ScavengeFI
3. Later, in the PrologEpilogInserter, SIFrameLowering::processFunctionBeforeFrameFinalized reuses the stack slot from SIMachineFunctionInfo::ScavengeFI or creates a new one if there is none (through calling SIMachineFunctionInfo::getScavengeFI)

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1342

With scratch instructions, the code looks like this:

scratch_store_dword_saddr v0, s33, …
s_not_b32 exec_lo, exec_lo
scratch_store_dword_saddr v0, s33, …
s_not_b32 exec_lo, exec_lo

scratch instructions obey the exec mask, so I don’t think we can fuse this.

1359–1360

Fixed, should be more obvious now.

1361

I fixed that in D96517. It it should be part of this patch, I can move it.

[sebastian-ne]

Rebased

[arsenm]

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

1352–1353

Still have a temporary scavenger here. Also should use the reverse iteration method

[t-tye]

In D96336#2553493, @sebastian-ne wrote:

As an aside, if we are moving to using flat scratch in the main, is it possible to replace most of this with s_scratch_store / s_scratch_load and avoid the need for an VGPR entirely?

That would make sense, but it feels like s_scratch instructions got removed in newer hardware.

The scalar cache is not coherent with the vector cache so how would s_scratch be used? Seems it would need explicit invalidation of both the vector and scalar caches. The scalar cache is also a writeback cache so it would need to be explicitly written back to avoid clobbering memory. I also believe the scalar writes were removed in recent hardware.

llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll

49

Are you sure exp_cnt does what you describe? In older hardware exp_cnt was used to ensure input registers had been consumed by an instruction, but that is not longer true as the hardware now has interlocks making using expr_cnt no longer serve this purpose (although are hazards in some multi-dword cases.

The other wait_cnt counters act to indicate if the memory operation is visible. But the hardware ensures single location coherence per thread so why must this be waited on?

[sebastian-ne]

llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll

49

The test checks GFX6, does that count as old hardware? :)

[sebastian-ne]

Merged with D96517 and rewritten.
I hope the new version is easier to understand and creates better code.

I tried using scavengeRegisterBackwards, but it turned out that the RegScavenger is in forward mode, so we would need to switch back and forth. Also, scavenging backwards does not necessarily coincide with the liveness information, which was the main point of using the scavenger here.

The largest performance hit of this change is the s_waitcnt after restoring the temporary VGPR.
We do need to add a use of the load somewhere, otherwise it can be eliminated. I tried marking the load as volatile, which prevents it from being removed, but that also adds an s_waitcnt straight after the load.

[sebastian-ne]

Fix spilling when no SGPR can be scavenged to save exec. Storing the VGPR when it holds the SGPRs needs to be unconditionally done for active and inactive lanes.
Also add a test case for this case.

[sebastian-ne]

Remove now unused code from a previous revision.

[arsenm]

LGTM, although should look into updating the MFI serialization

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

483–485

Should also add this to the serialized MachineFunctionInfo. This may be a separate patch because I'm not sure we are correctly serializing any frame indexes right now, so some new infrastructure changes may be required

llvm/lib/Target/AMDGPU/GCNSubtarget.h

public:
   }
 
   /// \returns true if the machine has merged shaders in which s0-s7 are
   /// reserved by the hardware and user SGPRs start at s8
   bool hasMergedShaders() const {
     return getGeneration() >= GFX9;
   }
 
+  /// \returns true if the machine supports saveexec_b32 instructions.
+  bool hasSaveExecB32() const { return getGeneration() >= GFX10; }
+
   /// \returns SGPR allocation granularity supported by the subtarget.
   unsigned getSGPRAllocGranule() const {
     return AMDGPU::IsaInfo::getSGPRAllocGranule(this);
   }
 
   /// \returns SGPR encoding granularity supported by the subtarget.
   unsigned getSGPREncodingGranule() const {
     return AMDGPU::IsaInfo::getSGPREncodingGranule(this);

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

assert(allSGPRSpillsAreDead(MF) &&
          "SGPR spill should have been removed in SILowerSGPRSpills");
 
   // FIXME: The other checks should be redundant with allStackObjectsAreDead,
   // but currently hasNonSpillStackObjects is set only from source
   // allocas. Stack temps produced from legalization are not counted currently.
   if (!allStackObjectsAreDead(MFI)) {
     assert(RS && "RegScavenger required if spilling");
 
-    if (FuncInfo->isEntryFunction()) {
-      int ScavengeFI = MFI.CreateFixedObject(
-        TRI->getSpillSize(AMDGPU::SGPR_32RegClass), 0, false);
-      RS->addScavengingFrameIndex(ScavengeFI);
-    } else {
-      int ScavengeFI = MFI.CreateStackObject(
-          TRI->getSpillSize(AMDGPU::SGPR_32RegClass),
-          TRI->getSpillAlign(AMDGPU::SGPR_32RegClass), false);
-      RS->addScavengingFrameIndex(ScavengeFI);
-    }
+    // Add an emergency spill slot
+    RS->addScavengingFrameIndex(FuncInfo->getScavengeFI(MFI, *TRI));
   }
 }
 
 // Only report VGPRs to generic code.
 void SIFrameLowering::determineCalleeSaves(MachineFunction &MF,
                                            BitVector &SavedVGPRs,
                                            RegScavenger *RS) const {
   TargetFrameLowering::determineCalleeSaves(MF, SavedVGPRs, RS);
   SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h

private:
   DenseMap<int, VGPRSpillToAGPR> VGPRToAGPRSpills;
 
   // AGPRs used for VGPR spills.
   SmallVector<MCPhysReg, 32> SpillAGPR;
 
   // VGPRs used for AGPR spills.
   SmallVector<MCPhysReg, 32> SpillVGPR;
 
+  // Emergency stack slot. Sometimes, we create this before finalizing the stack
+  // frame, so save it here and add it to the RegScavenger later.
+  Optional<int> ScavengeFI;
+
 public: // FIXME
   /// If this is set, an SGPR used for save/restore of the register used for the
   /// frame pointer.
   Register SGPRForFPSaveRestoreCopy;
   Optional<int> FramePointerSaveIndex;
 
   /// If this is set, an SGPR used for save/restore of the register used for the
   /// base pointer.
   Register SGPRForBPSaveRestoreCopy;
   Optional<int> BasePointerSaveIndex;
 
   Register VGPRReservedForSGPRSpill;
   bool isCalleeSavedReg(const MCPhysReg *CSRegs, MCPhysReg Reg);
 
 public:
   SIMachineFunctionInfo(const MachineFunction &MF);
 
   bool initializeBaseYamlFields(const yaml::SIMachineFunctionInfo &YamlMFI);
 
   ArrayRef<SpilledReg> getSGPRToVGPRSpills(int FrameIndex) const {
     auto I = SGPRToVGPRSpills.find(FrameIndex);
public:
 
   bool haveFreeLanesForSGPRSpill(const MachineFunction &MF,
                                  unsigned NumLane) const;
   bool allocateSGPRSpillToVGPR(MachineFunction &MF, int FI);
   bool reserveVGPRforSGPRSpills(MachineFunction &MF);
   bool allocateVGPRSpillToAGPR(MachineFunction &MF, int FI, bool isAGPRtoVGPR);
   void removeDeadFrameIndices(MachineFrameInfo &MFI);
 
+  int getScavengeFI(MachineFrameInfo &MFI, const SIRegisterInfo &TRI);
+
   bool hasCalculatedTID() const { return TIDReg != 0; };
   Register getTIDReg() const { return TIDReg; };
   void setTIDReg(Register Reg) { TIDReg = Reg; }
 
   unsigned getBytesInStackArgArea() const {
     return BytesInStackArgArea;
   }
 

llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp

if (i != FramePointerSaveIndex && i != BasePointerSaveIndex)
       MFI.setStackID(i, TargetStackID::Default);
 
   for (auto &R : VGPRToAGPRSpills) {
     if (R.second.FullyAllocated)
       MFI.RemoveStackObject(R.first);
   }
 }
 
+int SIMachineFunctionInfo::getScavengeFI(MachineFrameInfo &MFI,
+                                         const SIRegisterInfo &TRI) {
+  if (ScavengeFI)
+    return *ScavengeFI;
+  if (isEntryFunction()) {
+    ScavengeFI = MFI.CreateFixedObject(
+        TRI.getSpillSize(AMDGPU::SGPR_32RegClass), 0, false);
+  } else {
+    ScavengeFI = MFI.CreateStackObject(
+        TRI.getSpillSize(AMDGPU::SGPR_32RegClass),
+        TRI.getSpillAlign(AMDGPU::SGPR_32RegClass), false);
+  }
+  return *ScavengeFI;
+}
+
 MCPhysReg SIMachineFunctionInfo::getNextUserSGPR() const {
   assert(NumSystemSGPRs == 0 && "System SGPRs must be added after user SGPRs");
   return AMDGPU::SGPR0 + NumUserSGPRs;
 }
 
 MCPhysReg SIMachineFunctionInfo::getNextSystemSGPR() const {
   return AMDGPU::SGPR0 + NumUserSGPRs + NumSystemSGPRs;
 }

llvm/lib/Target/AMDGPU/SIRegisterInfo.h

 #define GET_REGINFO_HEADER
 #include "AMDGPUGenRegisterInfo.inc"
 
 namespace llvm {
 
 class GCNSubtarget;
 class LiveIntervals;
 class RegisterBank;
+struct SGPRSpillBuilder;
 class SIMachineFunctionInfo;
 
 class SIRegisterInfo final : public AMDGPUGenRegisterInfo {
 private:
   const GCNSubtarget &ST;
   bool SpillSGPRToVGPR;
   bool isWave32;
   BitVector RegPressureIgnoredUnits;
void resolveFrameIndex(MachineInstr &MI, Register BaseReg,
                          int64_t Offset) const override;
 
   bool isFrameOffsetLegal(const MachineInstr *MI, Register BaseReg,
                           int64_t Offset) const override;
 
   const TargetRegisterClass *getPointerRegClass(
     const MachineFunction &MF, unsigned Kind = 0) const override;
 
-  void buildSGPRSpillLoadStore(MachineBasicBlock::iterator MI, int Index,
-                               int Offset, unsigned EltSize, Register VGPR,
-                               int64_t VGPRLanes, RegScavenger *RS,
-                               bool IsLoad) const;
+  bool buildWaveVGPRSpillLoadStore(SGPRSpillBuilder &SB, bool IsLoad,
+                                   bool SGPRIsFree = false) const;
+
+  void buildVGPRSpillLoadStore(SGPRSpillBuilder &SB, int Index, int Offset,
+                               bool IsLoad, bool IsKill = true) const;
+
+  void buildSGPRSpillLoadStore(SGPRSpillBuilder &SB, int Offset,
+                               int64_t VGPRLanes) const;
 
   /// If \p OnlyToVGPR is true, this will only succeed if this
   bool spillSGPR(MachineBasicBlock::iterator MI,
                  int FI, RegScavenger *RS,
                  bool OnlyToVGPR = false) const;
 
   bool restoreSGPR(MachineBasicBlock::iterator MI,
                    int FI, RegScavenger *RS,

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

 
 // Map numbers of DWORDs to indexes in SubRegFromChannelTable.
 // Valid indexes are shifted 1, such that a 0 mapping means unsupported.
 // e.g. for 8 DWORDs (256-bit), SubRegFromChannelTableWidthMap[8] = 8,
 //      meaning index 7 in SubRegFromChannelTable.
 static const std::array<unsigned, 17> SubRegFromChannelTableWidthMap = {
     0, 1, 2, 3, 4, 5, 6, 7, 8, 0, 0, 0, 0, 0, 0, 0, 9};
 
+namespace llvm {
+
+// A temporary struct to spill SGPRs.
+// This is mostly to spill SGPRs to memory. Spilling SGPRs into VGPR lanes emits
+// just v_writelane and v_readlane.
+//
+// When spilling to memory, the SGPRs are written into VGPR lanes and the VGPR
+// is saved to scratch (or the other way around for loads).
+// For this, a VGPR is required where the needed lanes can be clobbered. The
+// RegScavenger can provide a VGPR where currently active lanes can be
+// clobbered, but we still need to save inactive lanes.
+// The high-level steps are:
+// - Try to scavenge SGPR(s) to save exec
+// - Try to scavenge VGPR
+// - Save needed, all or inactive lanes of a TmpVGPR
+// - Spill/Restore SGPRs using TmpVGPR
+// - Restore TmpVGPR
+//
+// To save all lanes of TmpVGPR, exec needs to be saved and modified. If we
+// cannot scavenge temporary SGPRs to save exec, we use the following code:
+// buffer_store_dword TmpVGPR ; only if active lanes need to be saved
+// s_not exec, exec
+// buffer_store_dword TmpVGPR ; save inactive lanes
+// s_not exec, exec
+struct SGPRSpillBuilder {
+  struct PerVGPRData {
+    unsigned PerVGPR;
+    unsigned NumVGPRs;
+    int64_t VGPRLanes;
+  };
+
+  // The SGPR to save
+  Register SuperReg;
+  MachineBasicBlock::iterator MI;
+  ArrayRef<int16_t> SplitParts;
+  unsigned NumSubRegs;
+  bool IsKill;
+  const DebugLoc &DL;
+
+  /* When spilling to stack */
+  // The SGPRs are written into this VGPR, which is then written to scratch
+  // (or vice versa for loads).
+  Register TmpVGPR = AMDGPU::NoRegister;
+  // Temporary spill slot to save TmpVGPR to.
+  int TmpVGPRIndex = 0;
+  // If TmpVGPR is live before the spill or if it is scavenged.
+  bool TmpVGPRLive = false;
+  // Scavenged SGPR to save EXEC.
+  Register SavedExecReg = AMDGPU::NoRegister;
+  // Stack index to write the SGPRs to.
+  int Index;
+  unsigned EltSize = 4;
+
+  RegScavenger &RS;
+  MachineBasicBlock &MBB;
+  MachineFunction &MF;
+  SIMachineFunctionInfo &MFI;
+  const SIInstrInfo &TII;
+  const SIRegisterInfo &TRI;
+  bool IsWave32;
+  Register ExecReg;
+  unsigned MovOpc;
+  unsigned NotOpc;
+
+  SGPRSpillBuilder(const SIRegisterInfo &TRI, const SIInstrInfo &TII,
+                   bool IsWave32, MachineBasicBlock::iterator MI, int Index,
+                   RegScavenger &RS)
+      : SuperReg(MI->getOperand(0).getReg()), MI(MI),
+        IsKill(MI->getOperand(0).isKill()), DL(MI->getDebugLoc()), Index(Index),
+        RS(RS), MBB(*MI->getParent()), MF(*MBB.getParent()),
+        MFI(*MF.getInfo<SIMachineFunctionInfo>()), TII(TII), TRI(TRI),
+        IsWave32(IsWave32) {
+    const TargetRegisterClass *RC = TRI.getPhysRegClass(SuperReg);
+    SplitParts = TRI.getRegSplitParts(RC, EltSize);
+    NumSubRegs = SplitParts.empty() ? 1 : SplitParts.size();
+
+    if (IsWave32) {
+      ExecReg = AMDGPU::EXEC_LO;
+      MovOpc = AMDGPU::S_MOV_B32;
+      NotOpc = AMDGPU::S_NOT_B32;
+    } else {
+      ExecReg = AMDGPU::EXEC;
+      MovOpc = AMDGPU::S_MOV_B64;
+      NotOpc = AMDGPU::S_NOT_B64;
+    }
+
+    assert(SuperReg != AMDGPU::M0 && "m0 should never spill");
+    assert(SuperReg != AMDGPU::EXEC_LO && SuperReg != AMDGPU::EXEC_HI &&
+           SuperReg != AMDGPU::EXEC && "exec should never spill");
+  }
+
+  PerVGPRData getPerVGPRData() {
+    PerVGPRData Data;
+    Data.PerVGPR = IsWave32 ? 32 : 64;
+    Data.NumVGPRs = (NumSubRegs + (Data.PerVGPR - 1)) / Data.PerVGPR;
+    Data.VGPRLanes = (1LL << std::min(Data.PerVGPR, NumSubRegs)) - 1LL;
+    return Data;
+  }
+
+  // Tries to scavenge SGPRs to save EXEC and a VGPR. Uses v0 if no VGPR is
+  // free.
+  // Writes these instructions if an SGPR can be scavenged:
+  // s_mov_b64 s[6:7], exec   ; Save exec
+  // s_mov_b64 exec, 3        ; Wanted lanemask
+  // buffer_store_dword v1    ; Write scavenged VGPR to emergency slot
+  //
+  // Writes these instructions if no SGPR can be scavenged:
+  // buffer_store_dword v0    ; Only if no free VGPR was found
+  // s_not_b64 exec, exec
+  // buffer_store_dword v0    ; Save inactive lanes
+  //                          ; exec stays inverted, it is flipped back in
+  //                          ; restore.
+  void prepare() {
+    // Scavenged temporary VGPR to use. It must be scavenged once for any number
+    // of spilled subregs.
+    // FIXME: The liveness analysis is limited and does not tell if a register
+    // is in use in lanes that are currently inactive. We can never be sure if
+    // a register as actually in use in another lane, so we need to save all
+    // used lanes of the chosen VGPR.
+    TmpVGPR = RS.scavengeRegister(&AMDGPU::VGPR_32RegClass, MI, 0, false);
+
+    // Reserve temporary stack slot
+    TmpVGPRIndex = MFI.getScavengeFI(MF.getFrameInfo(), TRI);
+    if (TmpVGPR) {
+      // Found a register that is dead in the currently active lanes, we only
+      // need to spill inactive lanes.
+      TmpVGPRLive = false;
+    } else {
+      // Pick v0 because it doesn't make a difference.
+      TmpVGPR = AMDGPU::VGPR0;
+      TmpVGPRLive = true;
+    }
+
+    // Try to scavenge SGPRs to save exec
+    assert(!SavedExecReg && "Exec is already saved, refuse to save again");
+    const TargetRegisterClass &RC =
+        IsWave32 ? AMDGPU::SGPR_32RegClass : AMDGPU::SGPR_64RegClass;
+    RS.setRegUsed(SuperReg);
+    SavedExecReg = RS.scavengeRegister(&RC, MI, 0, false);
+
+    int64_t VGPRLanes = getPerVGPRData().VGPRLanes;
+
+    if (SavedExecReg) {
+      // Set exec to needed lanes
+      BuildMI(MBB, MI, DL, TII.get(MovOpc), SavedExecReg).addReg(ExecReg);
+      auto I = BuildMI(MBB, MI, DL, TII.get(MovOpc), ExecReg).addImm(VGPRLanes);
+      if (!TmpVGPRLive)
+        I.addReg(TmpVGPR, RegState::ImplicitDefine);
+      // Spill needed lanes
+      TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ false);
+    } else {
+      // Spill active lanes
+      if (TmpVGPRLive)
+        TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ false,
+                                    /*IsKill*/ false);
+      // Spill inactive lanes
+      auto I = BuildMI(MBB, MI, DL, TII.get(NotOpc), ExecReg).addReg(ExecReg);
+      if (!TmpVGPRLive)
+        I.addReg(TmpVGPR, RegState::ImplicitDefine);
+      TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ false);
+    }
+  }
+
+  // Writes these instructions if an SGPR can be scavenged:
+  // buffer_load_dword v1     ; Write scavenged VGPR to emergency slot
+  // s_waitcnt vmcnt(0)       ; If a free VGPR was found
+  // s_mov_b64 exec, s[6:7]   ; Save exec
+  //
+  // Writes these instructions if no SGPR can be scavenged:
+  // buffer_load_dword v0     ; Restore inactive lanes
+  // s_waitcnt vmcnt(0)       ; If a free VGPR was found
+  // s_not_b64 exec, exec
+  // buffer_load_dword v0     ; Only if no free VGPR was found
+  void restore() {
+    if (SavedExecReg) {
+      // Restore used lanes
+      TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ true,
+                                  /*IsKill*/ false);
+      // Restore exec
+      auto I = BuildMI(MBB, MI, DL, TII.get(MovOpc), ExecReg)
+                   .addReg(SavedExecReg, RegState::Kill);
+      // Add an implicit use of the load so it is not dead.
+      // FIXME This inserts an unnecessary waitcnt
+      if (!TmpVGPRLive) {
+        I.addReg(TmpVGPR, RegState::Implicit);
+      }
+    } else {
+      // Restore inactive lanes
+      TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ true,
+                                  /*IsKill*/ false);
+      auto I = BuildMI(MBB, MI, DL, TII.get(NotOpc), ExecReg).addReg(ExecReg);
+      if (!TmpVGPRLive) {
+        I.addReg(TmpVGPR, RegState::Implicit);
+      }
+      // Restore active lanes
+      if (TmpVGPRLive)
+        TRI.buildVGPRSpillLoadStore(*this, TmpVGPRIndex, 0, /*IsLoad*/ true);
+    }
+  }
+
+  // Write TmpVGPR to memory or read TmpVGPR from memory.
+  // Either using a single buffer_load/store if exec is set to the needed mask
+  // or using
+  // buffer_load
+  // s_not exec, exec
+  // buffer_load
+  // s_not exec, exec
+  void readWriteTmpVGPR(unsigned Offset, bool IsLoad) {
+    if (SavedExecReg) {
+      // Spill needed lanes
+      TRI.buildVGPRSpillLoadStore(*this, Index, Offset, IsLoad);
+    } else {
+      // Spill active lanes
+      if (TmpVGPRLive)
+        TRI.buildVGPRSpillLoadStore(*this, Index, Offset, IsLoad,
+                                    /*IsKill*/ false);
+      // Spill inactive lanes
+      BuildMI(MBB, MI, DL, TII.get(NotOpc), ExecReg).addReg(ExecReg);
+      TRI.buildVGPRSpillLoadStore(*this, Index, Offset, IsLoad);
+      BuildMI(MBB, MI, DL, TII.get(NotOpc), ExecReg).addReg(ExecReg);
+    }
+  }
+};
+
+} // namespace llvm
+
 SIRegisterInfo::SIRegisterInfo(const GCNSubtarget &ST)
     : AMDGPUGenRegisterInfo(AMDGPU::PC_REG, ST.getAMDGPUDwarfFlavour()), ST(ST),
       SpillSGPRToVGPR(EnableSpillSGPRToVGPR), isWave32(ST.isWave32()) {
 
   assert(getSubRegIndexLaneMask(AMDGPU::sub0).getAsInteger() == 3 &&
          getSubRegIndexLaneMask(AMDGPU::sub31).getAsInteger() == (3ULL << 62) &&
          (getSubRegIndexLaneMask(AMDGPU::lo16) |
           getSubRegIndexLaneMask(AMDGPU::hi16)).getAsInteger() ==
void SIRegisterInfo::buildSpillLoadStore(MachineBasicBlock::iterator MI,
   if (ScratchOffsetRegDelta != 0) {
     // Subtract the offset we added to the ScratchOffset register.
     BuildMI(*MBB, MI, DL, TII->get(AMDGPU::S_SUB_U32), SOffset)
         .addReg(SOffset)
         .addImm(ScratchOffsetRegDelta);
   }
 }
 
-// Generate a VMEM access which loads or stores the VGPR containing an SGPR
-// spill such that all the lanes set in VGPRLanes are loaded or stored.
-// This generates exec mask manipulation and will use SGPRs available in MI
-// or VGPR lanes in the VGPR to save and restore the exec mask.
-void SIRegisterInfo::buildSGPRSpillLoadStore(MachineBasicBlock::iterator MI,
-                                             int Index, int Offset,
-                                             unsigned EltSize, Register VGPR,
-                                             int64_t VGPRLanes,
-                                             RegScavenger *RS,
-                                             bool IsLoad) const {
-  MachineBasicBlock *MBB = MI->getParent();
-  MachineFunction *MF = MBB->getParent();
-  SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
-  const SIInstrInfo *TII = ST.getInstrInfo();
-
-  Register SuperReg = MI->getOperand(0).getReg();
-  const TargetRegisterClass *RC = getPhysRegClass(SuperReg);
-  ArrayRef<int16_t> SplitParts = getRegSplitParts(RC, EltSize);
-  unsigned NumSubRegs = SplitParts.empty() ? 1 : SplitParts.size();
-  unsigned FirstPart = Offset * 32;
-  unsigned ExecLane = 0;
-
-  bool IsKill = MI->getOperand(0).isKill();
-  const DebugLoc &DL = MI->getDebugLoc();
-
-  // Cannot handle load/store to EXEC
-  assert(SuperReg != AMDGPU::EXEC_LO && SuperReg != AMDGPU::EXEC_HI &&
-         SuperReg != AMDGPU::EXEC && "exec should never spill");
-
-  // On Wave32 only handle EXEC_LO.
-  // On Wave64 only update EXEC_HI if there is sufficent space for a copy.
-  bool OnlyExecLo = isWave32 || NumSubRegs == 1 || SuperReg == AMDGPU::EXEC_HI;
-
-  unsigned ExecMovOpc = OnlyExecLo ? AMDGPU::S_MOV_B32 : AMDGPU::S_MOV_B64;
-  Register ExecReg = OnlyExecLo ? AMDGPU::EXEC_LO : AMDGPU::EXEC;
-  Register SavedExecReg;
-
-  // Backup EXEC
-  if (OnlyExecLo) {
-    SavedExecReg =
-        NumSubRegs == 1
-            ? SuperReg
-            : Register(getSubReg(SuperReg, SplitParts[FirstPart + ExecLane]));
-  } else {
-    // If src/dst is an odd size it is possible subreg0 is not aligned.
-    for (; ExecLane < (NumSubRegs - 1); ++ExecLane) {
-      SavedExecReg = getMatchingSuperReg(
-          getSubReg(SuperReg, SplitParts[FirstPart + ExecLane]), AMDGPU::sub0,
-          &AMDGPU::SReg_64_XEXECRegClass);
-      if (SavedExecReg)
-        break;
-    }
-  }
-  assert(SavedExecReg);
-  BuildMI(*MBB, MI, DL, TII->get(ExecMovOpc), SavedExecReg).addReg(ExecReg);
-
-  // Setup EXEC
-  BuildMI(*MBB, MI, DL, TII->get(ExecMovOpc), ExecReg).addImm(VGPRLanes);
-
+void SIRegisterInfo::buildVGPRSpillLoadStore(SGPRSpillBuilder &SB, int Index,
+                                             int Offset, bool IsLoad,
+                                             bool IsKill) const {
   // Load/store VGPR
-  MachineFrameInfo &FrameInfo = MF->getFrameInfo();
+  MachineFrameInfo &FrameInfo = SB.MF.getFrameInfo();
   assert(FrameInfo.getStackID(Index) != TargetStackID::SGPRSpill);
 
-  Register FrameReg = FrameInfo.isFixedObjectIndex(Index) && hasBasePointer(*MF)
-                          ? getBaseRegister()
-                          : getFrameRegister(*MF);
+  Register FrameReg =
+      FrameInfo.isFixedObjectIndex(Index) && hasBasePointer(SB.MF)
+          : getFrameRegister(SB.MF);
 
   Align Alignment = FrameInfo.getObjectAlign(Index);
-  MachinePointerInfo PtrInfo =
-      MachinePointerInfo::getFixedStack(*MF, Index);
-  MachineMemOperand *MMO = MF->getMachineMemOperand(
+  MachinePointerInfo PtrInfo = MachinePointerInfo::getFixedStack(SB.MF, Index);
+  MachineMemOperand *MMO = SB.MF.getMachineMemOperand(
       PtrInfo, IsLoad ? MachineMemOperand::MOLoad : MachineMemOperand::MOStore,
-      EltSize, Alignment);
+      SB.EltSize, Alignment);
 
   if (IsLoad) {
     unsigned Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_LOAD_DWORD_SADDR
                                           : AMDGPU::BUFFER_LOAD_DWORD_OFFSET;
-    buildSpillLoadStore(MI, Opc,
-          Index,
-          VGPR, false,
-          FrameReg,
-          Offset * EltSize, MMO,
-          RS);
+    buildSpillLoadStore(SB.MI, Opc, Index, SB.TmpVGPR, false, FrameReg,
+                        Offset * SB.EltSize, MMO, &SB.RS);
   } else {
     unsigned Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_STORE_DWORD_SADDR
                                           : AMDGPU::BUFFER_STORE_DWORD_OFFSET;
-    buildSpillLoadStore(MI, Opc, Index, VGPR,
-                        IsKill, FrameReg,
-                        Offset * EltSize, MMO, RS);
+    buildSpillLoadStore(SB.MI, Opc, Index, SB.TmpVGPR, IsKill, FrameReg,
+                        Offset * SB.EltSize, MMO, &SB.RS);
     // This only ever adds one VGPR spill
-    MFI->addToSpilledVGPRs(1);
-  }
-
-  // Restore EXEC
-  BuildMI(*MBB, MI, DL, TII->get(ExecMovOpc), ExecReg)
-      .addReg(SavedExecReg, getKillRegState(IsLoad || IsKill));
-
-  // Restore clobbered SGPRs
-  if (IsLoad) {
-    // Nothing to do; register will be overwritten
-  } else if (!IsKill) {
-    // Restore SGPRs from appropriate VGPR lanes
-    if (!OnlyExecLo) {
-      BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32),
-              getSubReg(SuperReg, SplitParts[FirstPart + ExecLane + 1]))
-          .addReg(VGPR)
-          .addImm(ExecLane + 1);
-    }
-    BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32),
-            NumSubRegs == 1 ? SavedExecReg
-                            : Register(getSubReg(
-                                  SuperReg, SplitParts[FirstPart + ExecLane])))
-        .addReg(VGPR, RegState::Kill)
-        .addImm(ExecLane);
+    SB.MFI.addToSpilledVGPRs(1);
   }
 }
 
 bool SIRegisterInfo::spillSGPR(MachineBasicBlock::iterator MI,
                                int Index,
                                RegScavenger *RS,
                                bool OnlyToVGPR) const {
-  MachineBasicBlock *MBB = MI->getParent();
-  MachineFunction *MF = MBB->getParent();
-  SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
+  SGPRSpillBuilder SB(*this, *ST.getInstrInfo(), isWave32, MI, Index, *RS);
 
-  ArrayRef<SIMachineFunctionInfo::SpilledReg> VGPRSpills
-    = MFI->getSGPRToVGPRSpills(Index);
+  ArrayRef<SIMachineFunctionInfo::SpilledReg> VGPRSpills =
+      SB.MFI.getSGPRToVGPRSpills(Index);
   bool SpillToVGPR = !VGPRSpills.empty();
   if (OnlyToVGPR && !SpillToVGPR)
     return false;
 
-  const SIInstrInfo *TII = ST.getInstrInfo();
-
-  Register SuperReg = MI->getOperand(0).getReg();
-  bool IsKill = MI->getOperand(0).isKill();
-  const DebugLoc &DL = MI->getDebugLoc();
-
-  assert(SpillToVGPR || (SuperReg != MFI->getStackPtrOffsetReg() &&
-                         SuperReg != MFI->getFrameOffsetReg()));
-
-  assert(SuperReg != AMDGPU::M0 && "m0 should never spill");
-  assert(SuperReg != AMDGPU::EXEC_LO && SuperReg != AMDGPU::EXEC_HI &&
-         SuperReg != AMDGPU::EXEC && "exec should never spill");
-
-  unsigned EltSize = 4;
-  const TargetRegisterClass *RC = getPhysRegClass(SuperReg);
-
-  ArrayRef<int16_t> SplitParts = getRegSplitParts(RC, EltSize);
-  unsigned NumSubRegs = SplitParts.empty() ? 1 : SplitParts.size();
+  assert(SpillToVGPR || (SB.SuperReg != SB.MFI.getStackPtrOffsetReg() &&
+                         SB.SuperReg != SB.MFI.getFrameOffsetReg()));
 
   if (SpillToVGPR) {
-    for (unsigned i = 0, e = NumSubRegs; i < e; ++i) {
-      Register SubReg = NumSubRegs == 1
-                            ? SuperReg
-                            : Register(getSubReg(SuperReg, SplitParts[i]));
+    for (unsigned i = 0, e = SB.NumSubRegs; i < e; ++i) {
+      Register SubReg =
+          SB.NumSubRegs == 1
+              ? SB.SuperReg
+              : Register(getSubReg(SB.SuperReg, SB.SplitParts[i]));
       SIMachineFunctionInfo::SpilledReg Spill = VGPRSpills[i];
 
-      bool UseKill = IsKill && i == NumSubRegs - 1;
+      bool UseKill = SB.IsKill && i == SB.NumSubRegs - 1;
 
       // Mark the "old value of vgpr" input undef only if this is the first sgpr
       // spill to this specific vgpr in the first basic block.
-      auto MIB =
-          BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_WRITELANE_B32), Spill.VGPR)
+      auto MIB = BuildMI(SB.MBB, MI, SB.DL, SB.TII.get(AMDGPU::V_WRITELANE_B32),
+                         Spill.VGPR)
                      .addReg(SubReg, getKillRegState(UseKill))
                      .addImm(Spill.Lane)
                      .addReg(Spill.VGPR);
 
-      if (i == 0 && NumSubRegs > 1) {
+      if (i == 0 && SB.NumSubRegs > 1) {
         // We may be spilling a super-register which is only partially defined,
         // and need to ensure later spills think the value is defined.
-        MIB.addReg(SuperReg, RegState::ImplicitDefine);
+        MIB.addReg(SB.SuperReg, RegState::ImplicitDefine);
       }
 
-      if (NumSubRegs > 1)
-        MIB.addReg(SuperReg, getKillRegState(UseKill) | RegState::Implicit);
+      if (SB.NumSubRegs > 1)
+        MIB.addReg(SB.SuperReg, getKillRegState(UseKill) | RegState::Implicit);
 
       // FIXME: Since this spills to another register instead of an actual
       // frame index, we should delete the frame index when all references to
       // it are fixed.
     }
   } else {
-    // Scavenged temporary VGPR to use. It must be scavenged once for any number
-    // of spilled subregs.
-    Register TmpVGPR = RS->scavengeRegister(&AMDGPU::VGPR_32RegClass, MI, 0);
-    RS->setRegUsed(TmpVGPR);
+    SB.prepare();
 
-    // SubReg carries the "Kill" flag when SubReg == SuperReg.
-    unsigned SubKillState = getKillRegState((NumSubRegs == 1) && IsKill);
+    // SubReg carries the "Kill" flag when SubReg == SB.SuperReg.
+    unsigned SubKillState = getKillRegState((SB.NumSubRegs == 1) && SB.IsKill);
 
-    unsigned PerVGPR = 32;
-    unsigned NumVGPRs = (NumSubRegs + (PerVGPR - 1)) / PerVGPR;
-    int64_t VGPRLanes = (1LL << std::min(PerVGPR, NumSubRegs)) - 1LL;
+    // Per VGPR helper data
+    auto PVD = SB.getPerVGPRData();
 
-    for (unsigned Offset = 0; Offset < NumVGPRs; ++Offset) {
+    for (unsigned Offset = 0; Offset < PVD.NumVGPRs; ++Offset) {
       unsigned TmpVGPRFlags = RegState::Undef;
 
       // Write sub registers into the VGPR
-      for (unsigned i = Offset * PerVGPR,
-                    e = std::min((Offset + 1) * PerVGPR, NumSubRegs);
+      for (unsigned i = Offset * PVD.PerVGPR,
+                    e = std::min((Offset + 1) * PVD.PerVGPR, SB.NumSubRegs);
            i < e; ++i) {
-        Register SubReg = NumSubRegs == 1
-                              ? SuperReg
-                              : Register(getSubReg(SuperReg, SplitParts[i]));
+        Register SubReg =
+            SB.NumSubRegs == 1
+                ? SB.SuperReg
+                : Register(getSubReg(SB.SuperReg, SB.SplitParts[i]));
 
         MachineInstrBuilder WriteLane =
-            BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_WRITELANE_B32), TmpVGPR)
+            BuildMI(SB.MBB, MI, SB.DL, SB.TII.get(AMDGPU::V_WRITELANE_B32),
+                    SB.TmpVGPR)
                 .addReg(SubReg, SubKillState)
-                .addImm(i % PerVGPR)
-                .addReg(TmpVGPR, TmpVGPRFlags);
+                .addImm(i % PVD.PerVGPR)
+                .addReg(SB.TmpVGPR, TmpVGPRFlags);
         TmpVGPRFlags = 0;
 
         // There could be undef components of a spilled super register.
         // TODO: Can we detect this and skip the spill?
-        if (NumSubRegs > 1) {
-          // The last implicit use of the SuperReg carries the "Kill" flag.
+        if (SB.NumSubRegs > 1) {
+          // The last implicit use of the SB.SuperReg carries the "Kill" flag.
           unsigned SuperKillState = 0;
-          if (i + 1 == NumSubRegs)
-            SuperKillState |= getKillRegState(IsKill);
-          WriteLane.addReg(SuperReg, RegState::Implicit | SuperKillState);
+          if (i + 1 == SB.NumSubRegs)
+            SuperKillState |= getKillRegState(SB.IsKill);
+          WriteLane.addReg(SB.SuperReg, RegState::Implicit | SuperKillState);
         }
       }
 
       // Write out VGPR
-      buildSGPRSpillLoadStore(MI, Index, Offset, EltSize, TmpVGPR, VGPRLanes,
-                              RS, false);
+      SB.readWriteTmpVGPR(Offset, /*IsLoad*/ false);
     }
+
+    SB.restore();
   }
 
   MI->eraseFromParent();
-  MFI->addToSpilledSGPRs(NumSubRegs);
+  SB.MFI.addToSpilledSGPRs(SB.NumSubRegs);
   return true;
 }
 
 bool SIRegisterInfo::restoreSGPR(MachineBasicBlock::iterator MI,
                                  int Index,
                                  RegScavenger *RS,
                                  bool OnlyToVGPR) const {
-  MachineFunction *MF = MI->getParent()->getParent();
-  MachineBasicBlock *MBB = MI->getParent();
-  SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
+  SGPRSpillBuilder SB(*this, *ST.getInstrInfo(), isWave32, MI, Index, *RS);
 
-  ArrayRef<SIMachineFunctionInfo::SpilledReg> VGPRSpills
-    = MFI->getSGPRToVGPRSpills(Index);
+  ArrayRef<SIMachineFunctionInfo::SpilledReg> VGPRSpills =
+      SB.MFI.getSGPRToVGPRSpills(Index);
   bool SpillToVGPR = !VGPRSpills.empty();
   if (OnlyToVGPR && !SpillToVGPR)
     return false;
 
-  const SIInstrInfo *TII = ST.getInstrInfo();
-  const DebugLoc &DL = MI->getDebugLoc();
-
-  Register SuperReg = MI->getOperand(0).getReg();
-
-  assert(SuperReg != AMDGPU::M0 && "m0 should never spill");
-  assert(SuperReg != AMDGPU::EXEC_LO && SuperReg != AMDGPU::EXEC_HI &&
-         SuperReg != AMDGPU::EXEC && "exec should never spill");
-
-  unsigned EltSize = 4;
-
-  const TargetRegisterClass *RC = getPhysRegClass(SuperReg);
-
-  ArrayRef<int16_t> SplitParts = getRegSplitParts(RC, EltSize);
-  unsigned NumSubRegs = SplitParts.empty() ? 1 : SplitParts.size();
-
   if (SpillToVGPR) {
-    for (unsigned i = 0, e = NumSubRegs; i < e; ++i) {
-      Register SubReg = NumSubRegs == 1
-                            ? SuperReg
-                            : Register(getSubReg(SuperReg, SplitParts[i]));
+    for (unsigned i = 0, e = SB.NumSubRegs; i < e; ++i) {
+      Register SubReg =
+          SB.NumSubRegs == 1
+              ? SB.SuperReg
+              : Register(getSubReg(SB.SuperReg, SB.SplitParts[i]));
 
       SIMachineFunctionInfo::SpilledReg Spill = VGPRSpills[i];
-      auto MIB = BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32), SubReg)
-                     .addReg(Spill.VGPR)
-                     .addImm(Spill.Lane);
-      if (NumSubRegs > 1 && i == 0)
-        MIB.addReg(SuperReg, RegState::ImplicitDefine);
+      auto MIB =
+          BuildMI(SB.MBB, MI, SB.DL, SB.TII.get(AMDGPU::V_READLANE_B32), SubReg)
+      if (SB.NumSubRegs > 1 && i == 0)
+        MIB.addReg(SB.SuperReg, RegState::ImplicitDefine);
     }
   } else {
-    Register TmpVGPR = RS->scavengeRegister(&AMDGPU::VGPR_32RegClass, MI, 0);
-    RS->setRegUsed(TmpVGPR);
+    SB.prepare();
 
-    unsigned PerVGPR = 32;
-    unsigned NumVGPRs = (NumSubRegs + (PerVGPR - 1)) / PerVGPR;
-    int64_t VGPRLanes = (1LL << std::min(PerVGPR, NumSubRegs)) - 1LL;
+    // Per VGPR helper data
+    auto PVD = SB.getPerVGPRData();
 
-    for (unsigned Offset = 0; Offset < NumVGPRs; ++Offset) {
+    for (unsigned Offset = 0; Offset < PVD.NumVGPRs; ++Offset) {
       // Load in VGPR data
-      buildSGPRSpillLoadStore(MI, Index, Offset, EltSize, TmpVGPR, VGPRLanes,
-                              RS, true);
+      SB.readWriteTmpVGPR(Offset, /*IsLoad*/ true);
 
       // Unpack lanes
-      for (unsigned i = Offset * PerVGPR,
-                    e = std::min((Offset + 1) * PerVGPR, NumSubRegs);
+      for (unsigned i = Offset * PVD.PerVGPR,
+                    e = std::min((Offset + 1) * PVD.PerVGPR, SB.NumSubRegs);
            i < e; ++i) {
-        Register SubReg = NumSubRegs == 1
-                              ? SuperReg
-                              : Register(getSubReg(SuperReg, SplitParts[i]));
+        Register SubReg =
+            SB.NumSubRegs == 1
+                ? SB.SuperReg
+                : Register(getSubReg(SB.SuperReg, SB.SplitParts[i]));
 
         bool LastSubReg = (i + 1 == e);
-        auto MIB =
-            BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32), SubReg)
-                .addReg(TmpVGPR, getKillRegState(LastSubReg))
+        auto MIB = BuildMI(SB.MBB, MI, SB.DL,
+                           SB.TII.get(AMDGPU::V_READLANE_B32), SubReg)
+                       .addReg(SB.TmpVGPR, getKillRegState(LastSubReg))
                        .addImm(i);
-        if (NumSubRegs > 1 && i == 0)
-          MIB.addReg(SuperReg, RegState::ImplicitDefine);
+        if (SB.NumSubRegs > 1 && i == 0)
+          MIB.addReg(SB.SuperReg, RegState::ImplicitDefine);
       }
     }
+
+    SB.restore();
   }
 
   MI->eraseFromParent();
   return true;
 }
 
 /// Special case of eliminateFrameIndex. Returns true if the SGPR was spilled to
 /// a VGPR and the stack slot can be safely eliminated when all other users are

llvm/test/CodeGen/AMDGPU/control-flow-fastregalloc.ll

 ; GCN: s_mov_b64 exec, s{{\[}}[[ANDEXEC_LO]]:[[ANDEXEC_HI]]{{\]}}
 ; GCN-NEXT: s_cbranch_execz [[END:BB[0-9]+_[0-9]+]]
 
 
 ; GCN: [[LOOP:BB[0-9]+_[0-9]+]]:
 ; GCN: buffer_load_dword v[[VAL_LOOP_RELOAD:[0-9]+]], off, s[0:3], 0 offset:[[LOAD0_OFFSET]] ; 4-byte Folded Reload
 ; GCN: v_subrev_i32_e32 [[VAL_LOOP:v[0-9]+]], vcc, v{{[0-9]+}}, v[[VAL_LOOP_RELOAD]]
 ; GCN: s_cmp_lg_u32
+; VMEM: buffer_store_dword
+; VMEM: buffer_store_dword
+; VMEM: buffer_store_dword
 ; GCN: buffer_store_dword [[VAL_LOOP]], off, s[0:3], 0 offset:{{[0-9]+}} ; 4-byte Folded Spill
 ; GCN-NEXT: s_cbranch_scc1 [[LOOP]]
 
 ; GCN: buffer_store_dword [[VAL_LOOP]], off, s[0:3], 0 offset:[[VAL_SUB_OFFSET:[0-9]+]] ; 4-byte Folded Spill
 
 ; GCN: [[END]]:
 ; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_LO_LANE]]
 ; VGPR: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], [[SPILL_VGPR]], [[SAVEEXEC_HI_LANE]]

llvm/test/CodeGen/AMDGPU/frame-setup-without-sgpr-to-vgpr-spills.ll

 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-spill-sgpr-to-vgpr=true < %s | FileCheck -check-prefixes=GCN,SPILL-TO-VGPR %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-spill-sgpr-to-vgpr=false < %s | FileCheck -check-prefixes=GCN,NO-SPILL-TO-VGPR %s
 
 ; Check frame setup where SGPR spills to VGPRs are disabled or enabled.
 
 declare hidden void @external_void_func_void() #0
 
 ; GCN-LABEL: {{^}}callee_with_stack_and_call:
 ; SPILL-TO-VGPR:      buffer_store_dword v40, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; SPILL-TO-VGPR:      v_writelane_b32 v40, s33, 2
 ; SPILL-TO-VGPR:      v_writelane_b32 v40, s30, 0
 ; SPILL-TO-VGPR:      v_writelane_b32 v40, s31, 1
 ; NO-SPILL-TO-VGPR:   v_mov_b32_e32 v0, s33
 ; NO-SPILL-TO-VGPR:   buffer_store_dword v0, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
+; NO-SPILL-TO-VGPR:   s_mov_b64 exec, s[4:5]
+; NO-SPILL-TO-VGPR:   s_mov_b64 s[6:7], exec
+; NO-SPILL-TO-VGPR:   s_mov_b64 exec, 3
+; NO-SPILL-TO-VGPR:   buffer_store_dword v1, off, s[0:3], s33 offset:16
 ; NO-SPILL-TO-VGPR:   v_writelane_b32 v1, s30, 0
 ; NO-SPILL-TO-VGPR:   v_writelane_b32 v1, s31, 1
 ; NO-SPILL-TO-VGPR:   buffer_store_dword v1, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; NO-SPILL-TO-VGPR:   buffer_load_dword v1, off, s[0:3], s33 offset:16
+; NO-SPILL-TO-VGPR:   s_waitcnt vmcnt(0)
+; NO-SPILL-TO-VGPR:   s_mov_b64 exec, s[6:7]
 
 ; GCN:                s_swappc_b64 s[30:31], s[4:5]
 
 ; SPILL-TO-VGPR:      v_readlane_b32 s4, v40, 0
 ; SPILL-TO-VGPR:      v_readlane_b32 s5, v40, 1
-; NO-SPILL-TO-VGPR:   buffer_load_dword v1, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
-; NO-SPILL-TO-VGPR:   v_readlane_b32 s4, v1, 0
-; NO-SPILL-TO-VGPR:   v_readlane_b32 s5, v1, 1
+; NO-SPILL-TO-VGPR:   v_readlane_b32 s4, v2, 0
+; NO-SPILL-TO-VGPR:   v_readlane_b32 s5, v2, 1
 
 ; SPILL-TO-VGPR:      v_readlane_b32 s33, v40, 2
 ; NO-SPILL-TO-VGPR:   buffer_load_dword v0, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
 ; NO-SPILL-TO-VGPR:   v_readfirstlane_b32 s33, v0
 define void @callee_with_stack_and_call() #0 {
   %alloca = alloca i32, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
   call void @external_void_func_void()
   ret void
 }
 
 attributes #0 = { nounwind }

llvm/test/CodeGen/AMDGPU/partial-sgpr-to-vgpr-spills.ll

 ; GCN-NEXT:    v_writelane_b32 v31, s15, 59
 ; GCN-NEXT:    v_writelane_b32 v31, s16, 60
 ; GCN-NEXT:    v_writelane_b32 v31, s17, 61
 ; GCN-NEXT:    v_writelane_b32 v31, s18, 62
 ; GCN-NEXT:    v_writelane_b32 v31, s19, 63
 ; GCN-NEXT:    ;;#ASMSTART
 ; GCN-NEXT:    ; def s[2:3]
 ; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    s_mov_b64 s[4:5], exec
+; GCN-NEXT:    s_mov_b64 exec, 3
+; GCN-NEXT:    buffer_store_dword v0, off, s[52:55], 0
 ; GCN-NEXT:    v_writelane_b32 v0, s2, 0
 ; GCN-NEXT:    v_writelane_b32 v0, s3, 1
-; GCN-NEXT:    s_mov_b64 s[2:3], exec
-; GCN-NEXT:    s_mov_b64 exec, 3
 ; GCN-NEXT:    buffer_store_dword v0, off, s[52:55], 0 offset:4 ; 4-byte Folded Spill
-; GCN-NEXT:    s_mov_b64 exec, s[2:3]
+; GCN-NEXT:    buffer_load_dword v0, off, s[52:55], 0
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    s_mov_b64 exec, s[4:5]
 ; GCN-NEXT:    s_mov_b32 s1, 0
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    s_cmp_lg_u32 s0, s1
 ; GCN-NEXT:    s_cbranch_scc1 BB2_2
 ; GCN-NEXT:  ; %bb.1: ; %bb0
 ; GCN-NEXT:    v_readlane_b32 s36, v31, 32
 ; GCN-NEXT:    v_readlane_b32 s37, v31, 33
 ; GCN-NEXT:    v_readlane_b32 s38, v31, 34

 ; GCN-NEXT:    v_readlane_b32 s12, v31, 56
 ; GCN-NEXT:    v_readlane_b32 s13, v31, 57
 ; GCN-NEXT:    v_readlane_b32 s14, v31, 58
 ; GCN-NEXT:    v_readlane_b32 s15, v31, 59
 ; GCN-NEXT:    v_readlane_b32 s16, v31, 60
 ; GCN-NEXT:    v_readlane_b32 s17, v31, 61
 ; GCN-NEXT:    v_readlane_b32 s18, v31, 62
 ; GCN-NEXT:    v_readlane_b32 s19, v31, 63
-; GCN-NEXT:    s_mov_b64 s[0:1], exec
+; GCN-NEXT:    s_mov_b64 s[2:3], exec
 ; GCN-NEXT:    s_mov_b64 exec, 3
+; GCN-NEXT:    buffer_store_dword v0, off, s[52:55], 0
 ; GCN-NEXT:    buffer_load_dword v0, off, s[52:55], 0 offset:4 ; 4-byte Folded Reload
-; GCN-NEXT:    s_mov_b64 exec, s[0:1]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_readlane_b32 s0, v0, 0
 ; GCN-NEXT:    v_readlane_b32 s1, v0, 1
+; GCN-NEXT:    buffer_load_dword v0, off, s[52:55], 0
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    s_mov_b64 exec, s[2:3]
 ; GCN-NEXT:    ;;#ASMSTART
 ; GCN-NEXT:    ; use s[36:51]
 ; GCN-NEXT:    ;;#ASMEND
 ; GCN-NEXT:    ;;#ASMSTART
 ; GCN-NEXT:    ; use s[4:19]
 ; GCN-NEXT:    ;;#ASMEND
 ; GCN-NEXT:    ;;#ASMSTART
 ; GCN-NEXT:    ; use s[0:1]
bb0:
   call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr3) #0
   call void asm sideeffect "; use $0", "s"(<2 x i32> %wide.sgpr4) #0
   br label %ret
 
 ret:
   ret void
 }
 
+; Same as @no_vgprs_last_sgpr_spill, some SGPR spills must go to memory.
+; Additionally, v0 is live throughout the function.
+define amdgpu_kernel void @no_vgprs_last_sgpr_spill_live_v0(i32 %in) #1 {
+; GCN-LABEL: no_vgprs_last_sgpr_spill_live_v0:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_mov_b32 s52, SCRATCH_RSRC_DWORD0
+; GCN-NEXT:    s_mov_b32 s53, SCRATCH_RSRC_DWORD1
+; GCN-NEXT:    s_mov_b32 s54, -1
+; GCN-NEXT:    s_mov_b32 s55, 0xe8f000
+; GCN-NEXT:    s_add_u32 s52, s52, s3
+; GCN-NEXT:    s_addc_u32 s53, s53, 0
+; GCN-NEXT:    s_load_dword s0, s[0:1], 0x9
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def s[4:19]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    v_writelane_b32 v31, s4, 0
+; GCN-NEXT:    v_writelane_b32 v31, s5, 1
+; GCN-NEXT:    v_writelane_b32 v31, s6, 2
+; GCN-NEXT:    v_writelane_b32 v31, s7, 3
+; GCN-NEXT:    v_writelane_b32 v31, s8, 4
+; GCN-NEXT:    v_writelane_b32 v31, s9, 5
+; GCN-NEXT:    v_writelane_b32 v31, s10, 6
+; GCN-NEXT:    v_writelane_b32 v31, s11, 7
+; GCN-NEXT:    v_writelane_b32 v31, s12, 8
+; GCN-NEXT:    v_writelane_b32 v31, s13, 9
+; GCN-NEXT:    v_writelane_b32 v31, s14, 10
+; GCN-NEXT:    v_writelane_b32 v31, s15, 11
+; GCN-NEXT:    v_writelane_b32 v31, s16, 12
+; GCN-NEXT:    v_writelane_b32 v31, s17, 13
+; GCN-NEXT:    v_writelane_b32 v31, s18, 14
+; GCN-NEXT:    v_writelane_b32 v31, s19, 15
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def s[4:19]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    v_writelane_b32 v31, s4, 16
+; GCN-NEXT:    v_writelane_b32 v31, s5, 17
+; GCN-NEXT:    v_writelane_b32 v31, s6, 18
+; GCN-NEXT:    v_writelane_b32 v31, s7, 19
+; GCN-NEXT:    v_writelane_b32 v31, s8, 20
+; GCN-NEXT:    v_writelane_b32 v31, s9, 21
+; GCN-NEXT:    v_writelane_b32 v31, s10, 22
+; GCN-NEXT:    v_writelane_b32 v31, s11, 23
+; GCN-NEXT:    v_writelane_b32 v31, s12, 24
+; GCN-NEXT:    v_writelane_b32 v31, s13, 25
+; GCN-NEXT:    v_writelane_b32 v31, s14, 26
+; GCN-NEXT:    v_writelane_b32 v31, s15, 27
+; GCN-NEXT:    v_writelane_b32 v31, s16, 28
+; GCN-NEXT:    v_writelane_b32 v31, s17, 29
+; GCN-NEXT:    v_writelane_b32 v31, s18, 30
+; GCN-NEXT:    v_writelane_b32 v31, s19, 31
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def s[4:19]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    v_writelane_b32 v31, s4, 32
+; GCN-NEXT:    v_writelane_b32 v31, s5, 33
+; GCN-NEXT:    v_writelane_b32 v31, s6, 34
+; GCN-NEXT:    v_writelane_b32 v31, s7, 35
+; GCN-NEXT:    v_writelane_b32 v31, s8, 36
+; GCN-NEXT:    v_writelane_b32 v31, s9, 37
+; GCN-NEXT:    v_writelane_b32 v31, s10, 38
+; GCN-NEXT:    v_writelane_b32 v31, s11, 39
+; GCN-NEXT:    v_writelane_b32 v31, s12, 40
+; GCN-NEXT:    v_writelane_b32 v31, s13, 41
+; GCN-NEXT:    v_writelane_b32 v31, s14, 42
+; GCN-NEXT:    v_writelane_b32 v31, s15, 43
+; GCN-NEXT:    v_writelane_b32 v31, s16, 44
+; GCN-NEXT:    v_writelane_b32 v31, s17, 45
+; GCN-NEXT:    v_writelane_b32 v31, s18, 46
+; GCN-NEXT:    v_writelane_b32 v31, s19, 47
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def s[4:19]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    v_writelane_b32 v31, s4, 48
+; GCN-NEXT:    v_writelane_b32 v31, s5, 49
+; GCN-NEXT:    v_writelane_b32 v31, s6, 50
+; GCN-NEXT:    v_writelane_b32 v31, s7, 51
+; GCN-NEXT:    v_writelane_b32 v31, s8, 52
+; GCN-NEXT:    v_writelane_b32 v31, s9, 53
+; GCN-NEXT:    v_writelane_b32 v31, s10, 54
+; GCN-NEXT:    v_writelane_b32 v31, s11, 55
+; GCN-NEXT:    v_writelane_b32 v31, s12, 56
+; GCN-NEXT:    v_writelane_b32 v31, s13, 57
+; GCN-NEXT:    v_writelane_b32 v31, s14, 58
+; GCN-NEXT:    v_writelane_b32 v31, s15, 59
+; GCN-NEXT:    v_writelane_b32 v31, s16, 60
+; GCN-NEXT:    v_writelane_b32 v31, s17, 61
+; GCN-NEXT:    v_writelane_b32 v31, s18, 62
+; GCN-NEXT:    v_writelane_b32 v31, s19, 63
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def s[2:3]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    s_mov_b64 s[4:5], exec
+; GCN-NEXT:    s_mov_b64 exec, 3
+; GCN-NEXT:    buffer_store_dword v0, off, s[52:55], 0
+; GCN-NEXT:    v_writelane_b32 v0, s2, 0
+; GCN-NEXT:    v_writelane_b32 v0, s3, 1
+; GCN-NEXT:    buffer_store_dword v0, off, s[52:55], 0 offset:4 ; 4-byte Folded Spill
+; GCN-NEXT:    buffer_load_dword v0, off, s[52:55], 0
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    s_mov_b64 exec, s[4:5]
+; GCN-NEXT:    s_mov_b32 s1, 0
+; GCN-NEXT:    s_waitcnt lgkmcnt(0)
+; GCN-NEXT:    s_cmp_lg_u32 s0, s1
+; GCN-NEXT:    s_cbranch_scc1 BB3_2
+; GCN-NEXT:  ; %bb.1: ; %bb0
+; GCN-NEXT:    v_readlane_b32 s36, v31, 32
+; GCN-NEXT:    v_readlane_b32 s37, v31, 33
+; GCN-NEXT:    v_readlane_b32 s38, v31, 34
+; GCN-NEXT:    v_readlane_b32 s39, v31, 35
+; GCN-NEXT:    v_readlane_b32 s40, v31, 36
+; GCN-NEXT:    v_readlane_b32 s41, v31, 37
+; GCN-NEXT:    v_readlane_b32 s42, v31, 38
+; GCN-NEXT:    v_readlane_b32 s43, v31, 39
+; GCN-NEXT:    v_readlane_b32 s44, v31, 40
+; GCN-NEXT:    v_readlane_b32 s45, v31, 41
+; GCN-NEXT:    v_readlane_b32 s46, v31, 42
+; GCN-NEXT:    v_readlane_b32 s47, v31, 43
+; GCN-NEXT:    v_readlane_b32 s48, v31, 44
+; GCN-NEXT:    v_readlane_b32 s49, v31, 45
+; GCN-NEXT:    v_readlane_b32 s50, v31, 46
+; GCN-NEXT:    v_readlane_b32 s51, v31, 47
+; GCN-NEXT:    v_readlane_b32 s0, v31, 16
+; GCN-NEXT:    v_readlane_b32 s1, v31, 17
+; GCN-NEXT:    v_readlane_b32 s2, v31, 18
+; GCN-NEXT:    v_readlane_b32 s3, v31, 19
+; GCN-NEXT:    v_readlane_b32 s4, v31, 20
+; GCN-NEXT:    v_readlane_b32 s5, v31, 21
+; GCN-NEXT:    v_readlane_b32 s6, v31, 22
+; GCN-NEXT:    v_readlane_b32 s7, v31, 23
+; GCN-NEXT:    v_readlane_b32 s8, v31, 24
+; GCN-NEXT:    v_readlane_b32 s9, v31, 25
+; GCN-NEXT:    v_readlane_b32 s10, v31, 26
+; GCN-NEXT:    v_readlane_b32 s11, v31, 27
+; GCN-NEXT:    v_readlane_b32 s12, v31, 28
+; GCN-NEXT:    v_readlane_b32 s13, v31, 29
+; GCN-NEXT:    v_readlane_b32 s14, v31, 30
+; GCN-NEXT:    v_readlane_b32 s15, v31, 31
+; GCN-NEXT:    v_readlane_b32 s16, v31, 0
+; GCN-NEXT:    v_readlane_b32 s17, v31, 1
+; GCN-NEXT:    v_readlane_b32 s18, v31, 2
+; GCN-NEXT:    v_readlane_b32 s19, v31, 3
+; GCN-NEXT:    v_readlane_b32 s20, v31, 4
+; GCN-NEXT:    v_readlane_b32 s21, v31, 5
+; GCN-NEXT:    v_readlane_b32 s22, v31, 6
+; GCN-NEXT:    v_readlane_b32 s23, v31, 7
+; GCN-NEXT:    v_readlane_b32 s24, v31, 8
+; GCN-NEXT:    v_readlane_b32 s25, v31, 9
+; GCN-NEXT:    v_readlane_b32 s26, v31, 10
+; GCN-NEXT:    v_readlane_b32 s27, v31, 11
+; GCN-NEXT:    v_readlane_b32 s28, v31, 12
+; GCN-NEXT:    v_readlane_b32 s29, v31, 13
+; GCN-NEXT:    v_readlane_b32 s30, v31, 14
+; GCN-NEXT:    v_readlane_b32 s31, v31, 15
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; def v0
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use s[16:31]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use s[0:15]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    v_readlane_b32 s4, v31, 48
+; GCN-NEXT:    v_readlane_b32 s5, v31, 49
+; GCN-NEXT:    v_readlane_b32 s6, v31, 50
+; GCN-NEXT:    v_readlane_b32 s7, v31, 51
+; GCN-NEXT:    v_readlane_b32 s8, v31, 52
+; GCN-NEXT:    v_readlane_b32 s9, v31, 53
+; GCN-NEXT:    v_readlane_b32 s10, v31, 54
+; GCN-NEXT:    v_readlane_b32 s11, v31, 55
+; GCN-NEXT:    v_readlane_b32 s12, v31, 56
+; GCN-NEXT:    v_readlane_b32 s13, v31, 57
+; GCN-NEXT:    v_readlane_b32 s14, v31, 58
+; GCN-NEXT:    v_readlane_b32 s15, v31, 59
+; GCN-NEXT:    v_readlane_b32 s16, v31, 60
+; GCN-NEXT:    v_readlane_b32 s17, v31, 61
+; GCN-NEXT:    v_readlane_b32 s18, v31, 62
+; GCN-NEXT:    v_readlane_b32 s19, v31, 63
+; GCN-NEXT:    s_mov_b64 s[2:3], exec
+; GCN-NEXT:    s_mov_b64 exec, 3
+; GCN-NEXT:    buffer_store_dword v1, off, s[52:55], 0
+; GCN-NEXT:    buffer_load_dword v1, off, s[52:55], 0 offset:4 ; 4-byte Folded Reload
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    v_readlane_b32 s0, v1, 0
+; GCN-NEXT:    v_readlane_b32 s1, v1, 1
+; GCN-NEXT:    buffer_load_dword v1, off, s[52:55], 0
+; GCN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-NEXT:    s_mov_b64 exec, s[2:3]
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use s[36:51]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use s[4:19]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use s[0:1]
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:    ;;#ASMSTART
+; GCN-NEXT:    ; use v0
+; GCN-NEXT:    ;;#ASMEND
+; GCN-NEXT:  BB3_2: ; %ret
+; GCN-NEXT:    s_endpgm
+  call void asm sideeffect "", "~{v[0:7]}" () #0
+  call void asm sideeffect "", "~{v[8:15]}" () #0
+  call void asm sideeffect "", "~{v[16:23]}" () #0
+  call void asm sideeffect "", "~{v[24:27]}"() #0
+  call void asm sideeffect "", "~{v[28:29]}"() #0
+  call void asm sideeffect "", "~{v30}"() #0
+
+  %wide.sgpr0 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr1 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr2 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr3 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
+  %wide.sgpr4 = call <2 x i32> asm sideeffect "; def $0", "=s" () #0
+  %cmp = icmp eq i32 %in, 0
+  br i1 %cmp, label %bb0, label %ret
+
+bb0:
+  %vgpr0 = call i32 asm sideeffect "; def $0", "=v" () #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr0) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr1) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr2) #0
+  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr3) #0
+  call void asm sideeffect "; use $0", "s"(<2 x i32> %wide.sgpr4) #0
+  call void asm sideeffect "; use $0", "v"(i32 %vgpr0) #0
+  br label %ret
+
+ret:
+  ret void
+}
+
 attributes #0 = { nounwind }
 attributes #1 = { nounwind "amdgpu-waves-per-eu"="8,8" }

llvm/test/CodeGen/AMDGPU/sgpr-spill.mir

-# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=CHECK,GCN64,MUBUF %s
-# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=CHECK,GCN32,MUBUF %s
-# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-enable-flat-scratch -run-pass=prologepilog %s -o - | FileCheck -check-prefixes=CHECK,GCN64,FLATSCR %s
-
-
-# CHECK-LABEL: name: check_spill
-
-# FLATSCR: $sgpr33 = S_MOV_B32 0
-# FLATSCR: $flat_scr_lo = S_ADD_U32 $sgpr0, $sgpr11, implicit-def $scc
-# FLATSCR: $flat_scr_hi = S_ADDC_U32 $sgpr1, 0, implicit-def $scc, implicit $scc
-
-# S32 with kill
-# CHECK: V_WRITELANE
-# CHECK: $sgpr12 = S_MOV_B32 $exec_lo
-# CHECK: $exec_lo = S_MOV_B32 1
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET killed $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 4
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr{{[0-9]+}}, $sgpr33, 4
-# CHECK: $exec_lo = S_MOV_B32 killed $sgpr12
-
-# S32 without kill
-# CHECK: V_WRITELANE
-# CHECK: $sgpr12 = S_MOV_B32 $exec_lo
-# CHECK: $exec_lo = S_MOV_B32 1
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 4
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr{{[0-9]+}}, $sgpr33, 4
-# CHECK: $sgpr12 = V_READLANE
-
-# S64 with kill
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 3
-# GCN64: $exec = S_MOV_B64 3
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET killed $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 8
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr{{[0-9]+}}, $sgpr33, 8
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S64 without kill
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 3
-# GCN64: $exec = S_MOV_B64 3
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 8
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr{{[0-9]+}}, $sgpr33, 8
-# GCN32: $exec_lo = S_MOV_B32 $sgpr12
-# GCN64: $exec = S_MOV_B64 $sgpr12_sgpr13
-# GCN64: $sgpr13 = V_READLANE
-# CHECK: $sgpr12 = V_READLANE
-
-# S96
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 7
-# GCN64: $exec = S_MOV_B64 7
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET killed $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 16
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr{{[0-9]+}}, $sgpr33, 16
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S128
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 15
-# GCN64: $exec = S_MOV_B64 15
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET killed $vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 28
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr{{[0-9]+}}, $sgpr33, 28
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S160
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 31
-# GCN64: $exec = S_MOV_B64 31
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET {{(killed )?}}$vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 44
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR {{(killed )?}}$vgpr{{[0-9]+}}, $sgpr33, 44
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S256
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 255
-# GCN64: $exec = S_MOV_B64 255
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET {{(killed )?}}$vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 64
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR {{(killed )?}}$vgpr{{[0-9]+}}, $sgpr33, 64
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S512
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 65535
-# GCN64: $exec = S_MOV_B64 65535
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET {{(killed )?}}$vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 96
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR {{(killed )?}}$vgpr{{[0-9]+}}, $sgpr33, 96
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-
-# S1024
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# CHECK: V_WRITELANE
-# GCN32: $sgpr64 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr64_sgpr65 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 4294967295
-# GCN64: $exec = S_MOV_B64 4294967295
-# MUBUF:   BUFFER_STORE_DWORD_OFFSET {{(killed )?}}$vgpr{{[0-9]+}}, ${{(sgpr[0-9_]+)*}}, $sgpr33, 160
-# FLATSCR: SCRATCH_STORE_DWORD_SADDR {{(killed )?}}$vgpr{{[0-9]+}}, $sgpr33, 160
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr64
-# GCN64: $exec = S_MOV_B64 killed $sgpr64_sgpr65
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=GCN64-MUBUF %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=GCN32-MUBUF %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -amdgpu-enable-flat-scratch -run-pass=prologepilog %s -o - | FileCheck -check-prefix=GCN64-FLATSCR %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -filetype=obj -verify-machineinstrs -start-before=prologepilog %s -o /dev/null
+# Check not crashing when emitting ISA
 
 --- |
 
   define amdgpu_kernel void @check_spill() #0 {
     ret void
   }
 
   define amdgpu_kernel void @check_reload() #0 {
argumentInfo:
     privateSegmentBuffer: { reg: '$sgpr4_sgpr5_sgpr6_sgpr7' }
     kernargSegmentPtr: { reg: '$sgpr8_sgpr9' }
     workGroupIDX:    { reg: '$sgpr10' }
     privateSegmentWaveByteOffset: { reg: '$sgpr11' }
 body:             |
   bb.0:
     liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7
 
+    ; GCN32-LABEL: name: check_spill
+    ; GCN32: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr11
+    ; GCN32: $sgpr33 = S_MOV_B32 0
+    ; GCN32: $sgpr96 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: $sgpr97 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: $sgpr98 = S_MOV_B32 4294967295, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: $sgpr99 = S_MOV_B32 834756608, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: $sgpr96 = S_ADD_U32 $sgpr96, $sgpr11, implicit-def $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: $sgpr97 = S_ADDC_U32 $sgpr97, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN32: INLINEASM &"", 0 /* attdialect */, implicit-def $vgpr0
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 killed $sgpr12, 0, undef $vgpr0
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 1, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: INLINEASM &"", 1 /* sideeffect attdialect */, implicit $vgpr0
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 1, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: $sgpr12 = V_READLANE_B32 killed $vgpr0, 0
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit killed $sgpr12_sgpr13
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 3, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 8, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 3, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 8, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: $sgpr12 = V_READLANE_B32 killed $vgpr0, 0
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: renamable $sgpr12_sgpr13_sgpr14 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 7, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 16, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.2, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12_sgpr13_sgpr14_sgpr15 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 15, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 28, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.3, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 31, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 44, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.4, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr17, 5, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr18, 6, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr19, 7, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 255, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 64, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.5, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr17, 5, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr18, 6, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr19, 7, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr20, 8, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr21, 9, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr22, 10, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr23, 11, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr24, 12, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr25, 13, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr26, 14, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr27, 15, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32: $sgpr12 = S_OR_SAVEEXEC_B32 65535, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 96, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.6, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; GCN32: renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_XOR_B32 $exec_lo, -1, implicit-def $scc
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr64, 0, undef $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr65, 1, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr66, 2, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr67, 3, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr68, 4, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr69, 5, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr70, 6, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr71, 7, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr72, 8, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr73, 9, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr74, 10, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr75, 11, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr76, 12, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr77, 13, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr78, 14, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr79, 15, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr80, 16, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr81, 17, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr82, 18, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr83, 19, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr84, 20, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr85, 21, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr86, 22, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr87, 23, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr88, 24, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr89, 25, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr90, 26, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr91, 27, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr92, 28, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr93, 29, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr94, 30, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $vgpr0 = V_WRITELANE_B32 $sgpr95, 31, $vgpr0, implicit killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32: $sgpr64 = S_OR_SAVEEXEC_B32 4294967295, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN32: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 160, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.7, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 -1
+    ; GCN32: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.8, addrspace 5)
+    ; GCN32: $exec_lo = S_MOV_B32 killed $sgpr64
+    ; FLATSCR-LABEL: name: check_spill
+    ; FLATSCR: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr11, $sgpr0_sgpr1
+    ; FLATSCR: $sgpr33 = S_MOV_B32 0
+    ; FLATSCR: $flat_scr_lo = S_ADD_U32 $sgpr0, $sgpr11, implicit-def $scc
+    ; FLATSCR: $flat_scr_hi = S_ADDC_U32 $sgpr1, 0, implicit-def $scc, implicit $scc
+    ; FLATSCR: renamable $sgpr12 = IMPLICIT_DEF
+    ; FLATSCR: INLINEASM &"", 0 /* attdialect */, implicit-def $vgpr0
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 killed $sgpr12, 0, undef $vgpr0
+    ; FLATSCR: $sgpr12 = S_MOV_B32 $exec_lo
+    ; FLATSCR: $exec_lo = S_MOV_B32 1
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 4, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.0, addrspace 5)
+    ; FLATSCR: $exec_lo = S_MOV_B32 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: INLINEASM &"", 1 /* sideeffect attdialect */, implicit $vgpr0
+    ; FLATSCR: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; FLATSCR: renamable $sgpr12 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0
+    ; FLATSCR: $sgpr12 = S_MOV_B32 $exec_lo
+    ; FLATSCR: $exec_lo = S_MOV_B32 1
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 4, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.0, addrspace 5)
+    ; FLATSCR: $exec_lo = S_MOV_B32 killed $sgpr12
+    ; FLATSCR: $sgpr12 = V_READLANE_B32 killed $vgpr0, 0
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit killed $sgpr12_sgpr13
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 3
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 8, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.1, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 3
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 8, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.1, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: $sgpr13 = V_READLANE_B32 $vgpr0, 1
+    ; FLATSCR: $sgpr12 = V_READLANE_B32 killed $vgpr0, 0
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: renamable $sgpr12_sgpr13_sgpr14 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 7
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 16, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.2, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 15
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 28, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.3, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 31
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 44, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.4, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr17, 5, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr18, 6, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr19, 7, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 255
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 64, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.5, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr13, 1, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr14, 2, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr15, 3, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr16, 4, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr17, 5, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr18, 6, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr19, 7, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr20, 8, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr21, 9, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr22, 10, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr23, 11, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr24, 12, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr25, 13, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr26, 14, $vgpr0, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr27, 15, $vgpr0, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; FLATSCR: $sgpr12_sgpr13 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 65535
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 96, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.6, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr12_sgpr13
+    ; FLATSCR: renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_XOR_B64 $exec, -1, implicit-def $scc
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr64, 0, undef $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr65, 1, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr66, 2, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr67, 3, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr68, 4, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr69, 5, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr70, 6, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr71, 7, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr72, 8, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr73, 9, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr74, 10, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr75, 11, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr76, 12, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr77, 13, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr78, 14, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr79, 15, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr80, 16, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr81, 17, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr82, 18, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr83, 19, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr84, 20, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr85, 21, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr86, 22, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr87, 23, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr88, 24, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr89, 25, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr90, 26, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr91, 27, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr92, 28, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr93, 29, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr94, 30, $vgpr0, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $vgpr0 = V_WRITELANE_B32 $sgpr95, 31, $vgpr0, implicit killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; FLATSCR: $sgpr64_sgpr65 = S_MOV_B64 $exec
+    ; FLATSCR: $exec = S_MOV_B64 4294967295
+    ; FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 160, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.7, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 -1
+    ; FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.8, addrspace 5)
+    ; FLATSCR: $exec = S_MOV_B64 killed $sgpr64_sgpr65
+    ; GCN64-MUBUF-LABEL: name: check_spill
+    ; GCN64-MUBUF: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr11
+    ; GCN64-MUBUF: $sgpr33 = S_MOV_B32 0
+    ; GCN64-MUBUF: $sgpr28 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: $sgpr29 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: $sgpr30 = S_MOV_B32 4294967295, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: $sgpr31 = S_MOV_B32 14680064, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: $sgpr28 = S_ADD_U32 $sgpr28, $sgpr11, implicit-def $scc, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: $sgpr29 = S_ADDC_U32 $sgpr29, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr28_sgpr29_sgpr30_sgpr31
+    ; GCN64-MUBUF: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 1, implicit-def $vgpr0
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr0 = V_WRITELANE_B32 killed $sgpr12, 0, undef $vgpr0
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN64-MUBUF: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr0
+    ; GCN64-MUBUF: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 1, implicit-def $vgpr1
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr1 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr1
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN64-MUBUF: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr1
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 3, implicit-def $vgpr2
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr2 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr2, implicit $sgpr12_sgpr13
+    ; GCN64-MUBUF: $vgpr2 = V_WRITELANE_B32 $sgpr13, 1, $vgpr2, implicit killed $sgpr12_sgpr13
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 8, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN64-MUBUF: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr2
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 3, implicit-def $vgpr3
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr3, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr3 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN64-MUBUF: $vgpr3 = V_WRITELANE_B32 $sgpr13, 1, $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr3, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 8, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN64-MUBUF: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr3
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13_sgpr14 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 7, implicit-def $vgpr4
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr4, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN64-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr13, 1, $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN64-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr14, 2, $vgpr4, implicit killed $sgpr12_sgpr13_sgpr14
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr4, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 16, 0, 0, 0, implicit $exec :: (store 4 into %stack.2, addrspace 5)
+    ; GCN64-MUBUF: $vgpr4 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr4
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 15, implicit-def $vgpr5
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr5, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr13, 1, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr14, 2, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr15, 3, $vgpr5, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr5, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 28, 0, 0, 0, implicit $exec :: (store 4 into %stack.3, addrspace 5)
+    ; GCN64-MUBUF: $vgpr5 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr5
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 31, implicit-def $vgpr6
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr6, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr13, 1, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr14, 2, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr15, 3, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr16, 4, $vgpr6, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr6, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 44, 0, 0, 0, implicit $exec :: (store 4 into %stack.4, addrspace 5)
+    ; GCN64-MUBUF: $vgpr6 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr6
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 255, implicit-def $vgpr7
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr7, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr13, 1, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr14, 2, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr15, 3, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr16, 4, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr17, 5, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr18, 6, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr19, 7, $vgpr7, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr7, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 64, 0, 0, 0, implicit $exec :: (store 4 into %stack.5, addrspace 5)
+    ; GCN64-MUBUF: $vgpr7 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr7
+    ; GCN64-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 65535, implicit-def $vgpr8
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr8, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr13, 1, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr14, 2, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr15, 3, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr16, 4, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr17, 5, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr18, 6, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr19, 7, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr20, 8, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr21, 9, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr22, 10, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr23, 11, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr24, 12, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr25, 13, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr26, 14, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr27, 15, $vgpr8, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr8, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 96, 0, 0, 0, implicit $exec :: (store 4 into %stack.6, addrspace 5)
+    ; GCN64-MUBUF: $vgpr8 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr8
+    ; GCN64-MUBUF: renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
+    ; GCN64-MUBUF: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GCN64-MUBUF: $exec = S_MOV_B64 4294967295, implicit-def $vgpr9
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr9, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr64, 0, undef $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr65, 1, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr66, 2, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr67, 3, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr68, 4, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr69, 5, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr70, 6, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr71, 7, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr72, 8, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr73, 9, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr74, 10, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr75, 11, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr76, 12, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr77, 13, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr78, 14, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr79, 15, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr80, 16, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr81, 17, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr82, 18, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr83, 19, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr84, 20, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr85, 21, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr86, 22, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr87, 23, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr88, 24, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr89, 25, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr90, 26, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr91, 27, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr92, 28, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr93, 29, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr94, 30, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr95, 31, $vgpr9, implicit killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr9, $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 160, 0, 0, 0, implicit $exec :: (store 4 into %stack.7, addrspace 5)
+    ; GCN64-MUBUF: $vgpr9 = BUFFER_LOAD_DWORD_OFFSET $sgpr28_sgpr29_sgpr30_sgpr31, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-MUBUF: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr9
+    ; GCN32-MUBUF-LABEL: name: check_spill
+    ; GCN32-MUBUF: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr11
+    ; GCN32-MUBUF: $sgpr33 = S_MOV_B32 0
+    ; GCN32-MUBUF: $sgpr96 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: $sgpr97 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: $sgpr98 = S_MOV_B32 4294967295, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: $sgpr99 = S_MOV_B32 834756608, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: $sgpr96 = S_ADD_U32 $sgpr96, $sgpr11, implicit-def $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: $sgpr97 = S_ADDC_U32 $sgpr97, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
+    ; GCN32-MUBUF: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 1, implicit-def $vgpr0
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr0 = V_WRITELANE_B32 killed $sgpr12, 0, undef $vgpr0
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN32-MUBUF: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr0
+    ; GCN32-MUBUF: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 1, implicit-def $vgpr1
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr1 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr1
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GCN32-MUBUF: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr1
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 3, implicit-def $vgpr2
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr2 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr2, implicit $sgpr12_sgpr13
+    ; GCN32-MUBUF: $vgpr2 = V_WRITELANE_B32 $sgpr13, 1, $vgpr2, implicit killed $sgpr12_sgpr13
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 8, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN32-MUBUF: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr2
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 3, implicit-def $vgpr3
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr3, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr3 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN32-MUBUF: $vgpr3 = V_WRITELANE_B32 $sgpr13, 1, $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr3, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 8, 0, 0, 0, implicit $exec :: (store 4 into %stack.1, addrspace 5)
+    ; GCN32-MUBUF: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr3
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13_sgpr14 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 7, implicit-def $vgpr4
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr4, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN32-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr13, 1, $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN32-MUBUF: $vgpr4 = V_WRITELANE_B32 $sgpr14, 2, $vgpr4, implicit killed $sgpr12_sgpr13_sgpr14
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr4, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 16, 0, 0, 0, implicit $exec :: (store 4 into %stack.2, addrspace 5)
+    ; GCN32-MUBUF: $vgpr4 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr4
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 15, implicit-def $vgpr5
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr5, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr13, 1, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr14, 2, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32-MUBUF: $vgpr5 = V_WRITELANE_B32 $sgpr15, 3, $vgpr5, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr5, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 28, 0, 0, 0, implicit $exec :: (store 4 into %stack.3, addrspace 5)
+    ; GCN32-MUBUF: $vgpr5 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr5
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 31, implicit-def $vgpr6
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr6, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr13, 1, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr14, 2, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr15, 3, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32-MUBUF: $vgpr6 = V_WRITELANE_B32 $sgpr16, 4, $vgpr6, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr6, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 44, 0, 0, 0, implicit $exec :: (store 4 into %stack.4, addrspace 5)
+    ; GCN32-MUBUF: $vgpr6 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr6
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 255, implicit-def $vgpr7
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr7, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr13, 1, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr14, 2, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr15, 3, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr16, 4, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr17, 5, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr18, 6, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: $vgpr7 = V_WRITELANE_B32 $sgpr19, 7, $vgpr7, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr7, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 64, 0, 0, 0, implicit $exec :: (store 4 into %stack.5, addrspace 5)
+    ; GCN32-MUBUF: $vgpr7 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr7
+    ; GCN32-MUBUF: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 65535, implicit-def $vgpr8
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr8, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr13, 1, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr14, 2, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr15, 3, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr16, 4, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr17, 5, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr18, 6, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr19, 7, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr20, 8, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr21, 9, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr22, 10, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr23, 11, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr24, 12, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr25, 13, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr26, 14, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: $vgpr8 = V_WRITELANE_B32 $sgpr27, 15, $vgpr8, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr8, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 96, 0, 0, 0, implicit $exec :: (store 4 into %stack.6, addrspace 5)
+    ; GCN32-MUBUF: $vgpr8 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr8
+    ; GCN32-MUBUF: renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
+    ; GCN32-MUBUF: $sgpr0 = S_MOV_B32 $exec_lo
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 4294967295, implicit-def $vgpr9
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr9, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr64, 0, undef $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr65, 1, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr66, 2, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr67, 3, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr68, 4, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr69, 5, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr70, 6, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr71, 7, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr72, 8, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr73, 9, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr74, 10, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr75, 11, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr76, 12, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr77, 13, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr78, 14, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr79, 15, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr80, 16, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr81, 17, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr82, 18, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr83, 19, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr84, 20, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr85, 21, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr86, 22, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr87, 23, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr88, 24, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr89, 25, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr90, 26, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr91, 27, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr92, 28, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr93, 29, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr94, 30, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: $vgpr9 = V_WRITELANE_B32 $sgpr95, 31, $vgpr9, implicit killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN32-MUBUF: BUFFER_STORE_DWORD_OFFSET killed $vgpr9, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 160, 0, 0, 0, implicit $exec :: (store 4 into %stack.7, addrspace 5)
+    ; GCN32-MUBUF: $vgpr9 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN32-MUBUF: $exec_lo = S_MOV_B32 killed $sgpr0, implicit $vgpr9
+    ; GCN64-FLATSCR-LABEL: name: check_spill
+    ; GCN64-FLATSCR: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr11, $sgpr0_sgpr1
+    ; GCN64-FLATSCR: $sgpr33 = S_MOV_B32 0
+    ; GCN64-FLATSCR: $flat_scr_lo = S_ADD_U32 $sgpr0, $sgpr11, implicit-def $scc
+    ; GCN64-FLATSCR: $flat_scr_hi = S_ADDC_U32 $sgpr1, 0, implicit-def $scc, implicit $scc
+    ; GCN64-FLATSCR: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 1, implicit-def $vgpr0
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr0 = V_WRITELANE_B32 killed $sgpr12, 0, undef $vgpr0
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr0, $sgpr33, 4, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.0, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr0 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr0
+    ; GCN64-FLATSCR: renamable $sgpr12 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 1, implicit-def $vgpr1
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr1 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr1
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr1, $sgpr33, 4, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.0, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr1 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr1
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 3, implicit-def $vgpr2
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr2, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr2 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr2, implicit $sgpr12_sgpr13
+    ; GCN64-FLATSCR: $vgpr2 = V_WRITELANE_B32 $sgpr13, 1, $vgpr2, implicit killed $sgpr12_sgpr13
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr2, $sgpr33, 8, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.1, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr2 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr2
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 3, implicit-def $vgpr3
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr3, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr3 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN64-FLATSCR: $vgpr3 = V_WRITELANE_B32 $sgpr13, 1, $vgpr3, implicit $sgpr12_sgpr13
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr3, $sgpr33, 8, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.1, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr3 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr3
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13_sgpr14 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 7, implicit-def $vgpr4
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr4, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr4 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN64-FLATSCR: $vgpr4 = V_WRITELANE_B32 $sgpr13, 1, $vgpr4, implicit $sgpr12_sgpr13_sgpr14
+    ; GCN64-FLATSCR: $vgpr4 = V_WRITELANE_B32 $sgpr14, 2, $vgpr4, implicit killed $sgpr12_sgpr13_sgpr14
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr4, $sgpr33, 16, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.2, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr4 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr4
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 15, implicit-def $vgpr5
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr5, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr5 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-FLATSCR: $vgpr5 = V_WRITELANE_B32 $sgpr13, 1, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-FLATSCR: $vgpr5 = V_WRITELANE_B32 $sgpr14, 2, $vgpr5, implicit $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-FLATSCR: $vgpr5 = V_WRITELANE_B32 $sgpr15, 3, $vgpr5, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr5, $sgpr33, 28, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.3, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr5 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr5
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 31, implicit-def $vgpr6
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr6, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr6 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-FLATSCR: $vgpr6 = V_WRITELANE_B32 $sgpr13, 1, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-FLATSCR: $vgpr6 = V_WRITELANE_B32 $sgpr14, 2, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-FLATSCR: $vgpr6 = V_WRITELANE_B32 $sgpr15, 3, $vgpr6, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-FLATSCR: $vgpr6 = V_WRITELANE_B32 $sgpr16, 4, $vgpr6, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr6, $sgpr33, 44, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.4, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr6 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr6
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 255, implicit-def $vgpr7
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr7, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr13, 1, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr14, 2, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr15, 3, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr16, 4, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr17, 5, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr18, 6, $vgpr7, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: $vgpr7 = V_WRITELANE_B32 $sgpr19, 7, $vgpr7, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr7, $sgpr33, 64, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.5, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr7 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr7
+    ; GCN64-FLATSCR: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 65535, implicit-def $vgpr8
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr8, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr12, 0, undef $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr13, 1, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr14, 2, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr15, 3, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr16, 4, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr17, 5, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr18, 6, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr19, 7, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr20, 8, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr21, 9, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr22, 10, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr23, 11, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr24, 12, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr25, 13, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr26, 14, $vgpr8, implicit $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: $vgpr8 = V_WRITELANE_B32 $sgpr27, 15, $vgpr8, implicit killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr8, $sgpr33, 96, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.6, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr8 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr8
+    ; GCN64-FLATSCR: renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
+    ; GCN64-FLATSCR: $sgpr2_sgpr3 = S_MOV_B64 $exec
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 4294967295, implicit-def $vgpr9
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr9, $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr64, 0, undef $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr65, 1, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr66, 2, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr67, 3, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr68, 4, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr69, 5, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr70, 6, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr71, 7, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr72, 8, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr73, 9, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr74, 10, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr75, 11, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr76, 12, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr77, 13, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr78, 14, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr79, 15, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr80, 16, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr81, 17, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr82, 18, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr83, 19, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr84, 20, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr85, 21, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr86, 22, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr87, 23, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr88, 24, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr89, 25, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr90, 26, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr91, 27, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr92, 28, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr93, 29, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr94, 30, $vgpr9, implicit $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: $vgpr9 = V_WRITELANE_B32 $sgpr95, 31, $vgpr9, implicit killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95
+    ; GCN64-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr9, $sgpr33, 160, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.7, addrspace 5)
+    ; GCN64-FLATSCR: $vgpr9 = SCRATCH_LOAD_DWORD_SADDR $sgpr33, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GCN64-FLATSCR: $exec = S_MOV_B64 killed $sgpr2_sgpr3, implicit $vgpr9
     renamable $sgpr12 = IMPLICIT_DEF
     SI_SPILL_S32_SAVE killed $sgpr12, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     renamable $sgpr12 = IMPLICIT_DEF
     SI_SPILL_S32_SAVE $sgpr12, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     renamable $sgpr12_sgpr13 = IMPLICIT_DEF
     SI_SPILL_S64_SAVE killed $sgpr12_sgpr13, %stack.1, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
bb.0:
     SI_SPILL_S256_SAVE killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19, %stack.5, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
     SI_SPILL_S512_SAVE killed $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27, %stack.6, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     renamable $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95 = IMPLICIT_DEF
     SI_SPILL_S1024_SAVE killed $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95, %stack.7, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
-
-# CHECK-LABEL: name: check_reload
-
-# FLATSCR: $sgpr33 = S_MOV_B32 0
-# FLATSCR: $flat_scr_lo = S_ADD_U32 $sgpr0, $sgpr11, implicit-def $scc
-# FLATSCR: $flat_scr_hi = S_ADDC_U32 $sgpr1, 0, implicit-def $scc, implicit $scc
-
-# S32
-# CHECK: $sgpr12 = S_MOV_B32 $exec_lo
-# CHECK: $exec_lo = S_MOV_B32 1
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 4
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 4
-# CHECK: $exec_lo = S_MOV_B32 killed $sgpr12
-# CHECK: $sgpr12 = V_READLANE
-
-# S64
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 3
-# GCN64: $exec = S_MOV_B64 3
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 8
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 8
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-
-# S96
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 7
-# GCN64: $exec = S_MOV_B64 7
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 16
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 16
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-# CHECK: $sgpr14 = V_READLANE
-
-# S128
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 15
-# GCN64: $exec = S_MOV_B64 15
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 28
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 28
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-# CHECK: $sgpr14 = V_READLANE
-# CHECK: $sgpr15 = V_READLANE
-
-# S160
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 31
-# GCN64: $exec = S_MOV_B64 31
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 44
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 44
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-# CHECK: $sgpr14 = V_READLANE
-# CHECK: $sgpr15 = V_READLANE
-# CHECK: $sgpr16 = V_READLANE
-
-# S256
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 255
-# GCN64: $exec = S_MOV_B64 255
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 64
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 64
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-# CHECK: $sgpr14 = V_READLANE
-# CHECK: $sgpr15 = V_READLANE
-# CHECK: $sgpr16 = V_READLANE
-# CHECK: $sgpr17 = V_READLANE
-# CHECK: $sgpr18 = V_READLANE
-# CHECK: $sgpr19 = V_READLANE
-
-# S512
-# GCN32: $sgpr12 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr12_sgpr13 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 65535
-# GCN64: $exec = S_MOV_B64 65535
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 96
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 96
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr12
-# GCN64: $exec = S_MOV_B64 killed $sgpr12_sgpr13
-# CHECK: $sgpr12 = V_READLANE
-# CHECK: $sgpr13 = V_READLANE
-# CHECK: $sgpr14 = V_READLANE
-# CHECK: $sgpr15 = V_READLANE
-# CHECK: $sgpr16 = V_READLANE
-# CHECK: $sgpr17 = V_READLANE
-# CHECK: $sgpr18 = V_READLANE
-# CHECK: $sgpr19 = V_READLANE
-# CHECK: $sgpr20 = V_READLANE
-# CHECK: $sgpr21 = V_READLANE
-# CHECK: $sgpr22 = V_READLANE
-# CHECK: $sgpr23 = V_READLANE
-# CHECK: $sgpr24 = V_READLANE
-# CHECK: $sgpr25 = V_READLANE
-# CHECK: $sgpr26 = V_READLANE
-# CHECK: $sgpr27 = V_READLANE
-
-# S1024
-# GCN32: $sgpr64 = S_MOV_B32 $exec_lo
-# GCN64: $sgpr64_sgpr65 = S_MOV_B64 $exec
-# GCN32: $exec_lo = S_MOV_B32 4294967295
-# GCN64: $exec = S_MOV_B64 4294967295
-# MUBUF:   BUFFER_LOAD_DWORD_OFFSET ${{(sgpr[0-9_]+)*}}, $sgpr33, 160
-# FLATSCR: SCRATCH_LOAD_DWORD_SADDR $sgpr33, 160
-# GCN32: $exec_lo = S_MOV_B32 killed $sgpr64
-# GCN64: $exec = S_MOV_B64 killed $sgpr64_sgpr65
-# CHECK: $sgpr64 = V_READLANE
-# CHECK: $sgpr65 = V_READLANE
-# CHECK: $sgpr66 = V_READLANE
-# CHECK: $sgpr67 = V_READLANE
-# CHECK: $sgpr68 = V_READLANE
-# CHECK: $sgpr69 = V_READLANE
-# CHECK: $sgpr70 = V_READLANE
-# CHECK: $sgpr71 = V_READLANE
-# CHECK: $sgpr72 = V_READLANE
-# CHECK: $sgpr73 = V_READLANE
-# CHECK: $sgpr74 = V_READLANE
-# CHECK: $sgpr75 = V_READLANE
-# CHECK: $sgpr76 = V_READLANE
-# CHECK: $sgpr77 = V_READLANE
-# CHECK: $sgpr78 = V_READLANE
-# CHECK: $sgpr79 = V_READLANE
-# CHECK: $sgpr80 = V_READLANE
-# CHECK: $sgpr81 = V_READLANE
-# CHECK: $sgpr82 = V_READLANE
-# CHECK: $sgpr83 = V_READLANE
-# CHECK: $sgpr84 = V_READLANE
-# CHECK: $sgpr85 = V_READLANE
-# CHECK: $sgpr86 = V_READLANE
-# CHECK: $sgpr87 = V_READLANE
-# CHECK: $sgpr88 = V_READLANE
-# CHECK: $sgpr89 = V_READLANE
-# CHECK: $sgpr90 = V_READLANE
-# CHECK: $sgpr91 = V_READLANE
-# CHECK: $sgpr92 = V_READLANE
-# CHECK: $sgpr93 = V_READLANE
-# CHECK: $sgpr94 = V_READLANE
-# CHECK: $sgpr95 = V_READLANE
-
 ---
 name:            check_reload
 tracksRegLiveness: true
 liveins:
   - { reg: '$sgpr4_sgpr5' }
   - { reg: '$sgpr6_sgpr7' }
   - { reg: '$sgpr8' }
 frameInfo:

llvm/test/CodeGen/AMDGPU/si-spill-sgpr-stack.ll

 ; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=SGPR %s
 
 ; Make sure this doesn't crash.
 ; ALL-LABEL: {{^}}test:
 ; ALL: s_mov_b32 s[[LO:[0-9]+]], SCRATCH_RSRC_DWORD0
 ; ALL: s_mov_b32 s[[HI:[0-9]+]], 0xe80000
 
 ; Make sure we are handling hazards correctly.
 ; SGPR: buffer_load_dword [[VHI:v[0-9]+]], off, s[{{[0-9]+:[0-9]+}}], 0 offset:4
-; SGPR-NEXT: s_mov_b64 exec, s[0:1]
 ; SGPR-NEXT: s_waitcnt vmcnt(0)
 ; SGPR-NEXT: v_readlane_b32 s{{[0-9]+}}, [[VHI]], 0
 ; SGPR-NEXT: v_readlane_b32 s{{[0-9]+}}, [[VHI]], 1
 ; SGPR-NEXT: v_readlane_b32 s{{[0-9]+}}, [[VHI]], 2
 ; SGPR-NEXT: v_readlane_b32 s[[HI:[0-9]+]], [[VHI]], 3
-; SGPR-NEXT: s_nop 4
-; SGPR-NEXT: buffer_store_dword v0, off, s[0:[[HI]]{{\]}}, 0
+; SGPR-NEXT: buffer_load_dword [[VHI]], off, s[96:99], 0
+; SGPR-NEXT: s_waitcnt vmcnt(0)
+; SGPR-NEXT: s_mov_b64 exec, s[4:5]
+; SGPR-NEXT: s_nop 1
+; SGPR-NEXT: buffer_store_dword v0, off, s[0:3], 0
 
 ; ALL: s_endpgm
 define amdgpu_kernel void @test(i32 addrspace(1)* %out, i32 %in) {
   call void asm sideeffect "", "~{s[0:7]}" ()
   call void asm sideeffect "", "~{s[8:15]}" ()
   call void asm sideeffect "", "~{s[16:23]}" ()
   call void asm sideeffect "", "~{s[24:31]}" ()
   call void asm sideeffect "", "~{s[32:39]}" ()

llvm/test/CodeGen/AMDGPU/spill-m0.ll

 ; RUN: llc -O0 -amdgpu-spill-sgpr-to-vgpr=1 -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=TOVGPR -check-prefix=GCN %s
 ; RUN: llc -O0 -amdgpu-spill-sgpr-to-vgpr=1 -march=amdgcn -mcpu=tonga  -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=TOVGPR -check-prefix=GCN %s
 ; RUN: llc -O0 -amdgpu-spill-sgpr-to-vgpr=0 -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=TOVMEM -check-prefix=GCN %s
 ; RUN: llc -O0 -amdgpu-spill-sgpr-to-vgpr=0 -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=TOVMEM -check-prefix=GCN %s
 
 ; XXX - Why does it like to use vcc?
 
 ; GCN-LABEL: {{^}}spill_m0:
 
 ; GCN: #ASMSTART
 ; GCN-NEXT: s_mov_b32 m0, 0
 ; GCN-NEXT: #ASMEND
 ; GCN-DAG: s_mov_b32 [[M0_COPY:s[0-9]+]], m0
 
 ; TOVGPR: v_writelane_b32 [[SPILL_VREG:v[0-9]+]], [[M0_COPY]], [[M0_LANE:[0-9]+]]
 
+; TOVMEM: s_mov_b64 [[COPY_EXEC:s\[[0-9]+:[0-9]+\]]], exec
+; TOVMEM: s_mov_b64 exec, 1
 ; TOVMEM: v_writelane_b32 [[SPILL_VREG:v[0-9]+]], [[M0_COPY]], 0
-; TOVMEM: s_mov_b32 [[COPY_EXEC_LO:s[0-9]+]], exec_lo
-; TOVMEM: s_mov_b32 exec_lo, 1
 ; TOVMEM: buffer_store_dword [[SPILL_VREG]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:4 ; 4-byte Folded Spill
-; TOVMEM: s_mov_b32 exec_lo, [[COPY_EXEC_LO]]
+; TOVMEM: s_mov_b64 exec, [[COPY_EXEC]]
 
 ; GCN: s_cbranch_scc1 [[ENDIF:BB[0-9]+_[0-9]+]]
 
 ; GCN: [[ENDIF]]:
 ; TOVGPR: v_readlane_b32 [[M0_RESTORE:s[0-9]+]], [[SPILL_VREG]], [[M0_LANE]]
 ; TOVGPR: s_mov_b32 m0, [[M0_RESTORE]]
 
 ; TOVMEM: buffer_load_dword [[RELOAD_VREG:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:4 ; 4-byte Folded Reload

llvm/test/CodeGen/AMDGPU/spill-scavenge-offset.ll

; mark most VGPR registers as used to increase register pressure
   %outptr = getelementptr <1280 x i32>, <1280 x i32> addrspace(1)* %out, i32 %tid
   store <1280 x i32> %a, <1280 x i32> addrspace(1)* %outptr
 
   ret void
 }
 
 ; CHECK-LABEL: test_limited_sgpr
 ; GFX6: s_add_u32 s32, s32, 0x[[OFFSET:[0-9a-f]+]]
+; GFX6-NEXT: s_waitcnt expcnt(0)
 ; GFX6-NEXT: buffer_load_dword v{{[0-9]+}}, off, s[{{[0-9:]+}}], s32
 ; GFX6-NEXT: s_sub_u32 s32, s32, 0x[[OFFSET:[0-9a-f]+]]
 ; GFX6: NumSgprs: 48
 ; GFX6: ScratchSize: 8608
 
 ; FLATSCR:           s_movk_i32 [[SOFF1:s[0-9]+]], 0x
 ; GFX9-FLATSCR-NEXT: s_waitcnt vmcnt(0)
 ; FLATSCR-NEXT:      scratch_store_dwordx4 off, v[{{[0-9:]+}}], [[SOFF1]] ; 16-byte Folded Spill

llvm/test/CodeGen/AMDGPU/spill-special-sgpr.mir

bb.0:
     ; GFX9: $sgpr33 = S_MOV_B32 0
     ; GFX9: $sgpr12 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $sgpr13 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $sgpr14 = S_MOV_B32 4294967295, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $sgpr15 = S_MOV_B32 14680064, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $sgpr12 = S_ADD_U32 $sgpr12, $sgpr9, implicit-def $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $sgpr13 = S_ADDC_U32 $sgpr13, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
     ; GFX9: $vcc = IMPLICIT_DEF
+    ; GFX9: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX9: $exec = S_MOV_B64 3, implicit-def $vgpr0
+    ; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
     ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
     ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit $vcc
-    ; GFX9: $vcc = S_MOV_B64 $exec
-    ; GFX9: $exec = S_MOV_B64 3
-    ; GFX9: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
-    ; GFX9: $exec = S_MOV_B64 $vcc
-    ; GFX9: $vcc_hi = V_READLANE_B32 $vgpr0, 1
-    ; GFX9: $vcc_lo = V_READLANE_B32 killed $vgpr0, 0
-    ; GFX9: $vcc = IMPLICIT_DEF
-    ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
-    ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit killed $vcc
-    ; GFX9: $vcc = S_MOV_B64 $exec
-    ; GFX9: $exec = S_MOV_B64 3
     ; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
-    ; GFX9: $exec = S_MOV_B64 killed $vcc
-    ; GFX9: $vcc = S_MOV_B64 $exec
-    ; GFX9: $exec = S_MOV_B64 3
-    ; GFX9: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
-    ; GFX9: $exec = S_MOV_B64 killed $vcc
-    ; GFX9: $vcc_lo = V_READLANE_B32 $vgpr0, 0, implicit-def $vcc
-    ; GFX9: $vcc_hi = V_READLANE_B32 killed $vgpr0, 1
+    ; GFX9: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX9: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr0
+    ; GFX9: $vcc = IMPLICIT_DEF
+    ; GFX9: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX9: $exec = S_MOV_B64 3, implicit-def $vgpr1
+    ; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GFX9: $vgpr1 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr1, implicit $vcc
+    ; GFX9: $vgpr1 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr1, implicit killed $vcc
+    ; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GFX9: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX9: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr1
+    ; GFX9: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX9: $exec = S_MOV_B64 3, implicit-def $vgpr2
+    ; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GFX9: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
+    ; GFX9: $vcc_lo = V_READLANE_B32 $vgpr2, 0, implicit-def $vcc
+    ; GFX9: $vcc_hi = V_READLANE_B32 killed $vgpr2, 1
+    ; GFX9: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX9: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr2
     ; GFX10-LABEL: name: check_vcc
     ; GFX10: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9
     ; GFX10: $sgpr33 = S_MOV_B32 0
     ; GFX10: $sgpr96 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $sgpr97 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $sgpr98 = S_MOV_B32 4294967295, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $sgpr99 = S_MOV_B32 836853760, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $sgpr96 = S_ADD_U32 $sgpr96, $sgpr9, implicit-def $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $sgpr97 = S_ADDC_U32 $sgpr97, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
     ; GFX10: $vcc = IMPLICIT_DEF
+    ; GFX10: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX10: $exec = S_MOV_B64 3, implicit-def $vgpr0
+    ; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
     ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
     ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit $vcc
-    ; GFX10: $vcc = S_MOV_B64 $exec
-    ; GFX10: $exec = S_MOV_B64 3
-    ; GFX10: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
-    ; GFX10: $exec = S_MOV_B64 $vcc
-    ; GFX10: $vcc_hi = V_READLANE_B32 $vgpr0, 1
-    ; GFX10: $vcc_lo = V_READLANE_B32 killed $vgpr0, 0
-    ; GFX10: $vcc = IMPLICIT_DEF
-    ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
-    ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit killed $vcc
-    ; GFX10: $vcc = S_MOV_B64 $exec
-    ; GFX10: $exec = S_MOV_B64 3
     ; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
-    ; GFX10: $exec = S_MOV_B64 killed $vcc
-    ; GFX10: $vcc = S_MOV_B64 $exec
-    ; GFX10: $exec = S_MOV_B64 3
-    ; GFX10: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
-    ; GFX10: $exec = S_MOV_B64 killed $vcc
-    ; GFX10: $vcc_lo = V_READLANE_B32 $vgpr0, 0, implicit-def $vcc
-    ; GFX10: $vcc_hi = V_READLANE_B32 killed $vgpr0, 1
+    ; GFX10: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX10: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr0
+    ; GFX10: $vcc = IMPLICIT_DEF
+    ; GFX10: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX10: $exec = S_MOV_B64 3, implicit-def $vgpr1
+    ; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GFX10: $vgpr1 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr1, implicit $vcc
+    ; GFX10: $vgpr1 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr1, implicit killed $vcc
+    ; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr1, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
+    ; GFX10: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX10: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr1
+    ; GFX10: $sgpr0_sgpr1 = S_MOV_B64 $exec
+    ; GFX10: $exec = S_MOV_B64 3, implicit-def $vgpr2
+    ; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr2, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (store 4 into %fixed-stack.0, align 16, addrspace 5)
+    ; GFX10: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
+    ; GFX10: $vcc_lo = V_READLANE_B32 $vgpr2, 0, implicit-def $vcc
+    ; GFX10: $vcc_hi = V_READLANE_B32 killed $vgpr2, 1
+    ; GFX10: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load 4 from %fixed-stack.0, align 16, addrspace 5)
+    ; GFX10: $exec = S_MOV_B64 killed $sgpr0_sgpr1, implicit $vgpr2
     $vcc = IMPLICIT_DEF
     SI_SPILL_S64_SAVE $vcc, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     $vcc = IMPLICIT_DEF
     SI_SPILL_S64_SAVE killed $vcc, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 
     $vcc = SI_SPILL_S64_RESTORE %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
 ...