diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.h b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
@@ -69,6 +69,10 @@
       Register PreloadedPrivateBufferReg, Register ScratchRsrcReg,
       Register ScratchWaveOffsetReg) const;
 
+  void emitPrologueEntryCFI(MachineBasicBlock &MBB,
+                            MachineBasicBlock::iterator MBBI,
+                            const DebugLoc &DL) const;
+
 public:
   bool hasFP(const MachineFunction &MF) const override;
 
@@ -76,6 +80,12 @@
   /// Create a CFI index for CFIInst and build a MachineInstr around it.
   void buildCFI(MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
                 const DebugLoc &DL, const MCCFIInstruction &CFIInst) const;
+  /// Create a CFI index describing a spill of an SGPR to a single lane of
+  /// a VGPR and build a MachineInstr around it.
+  void buildCFIForSGPRToVGPRSpill(MachineBasicBlock &MBB,
+                                  MachineBasicBlock::iterator MBBI,
+                                  const DebugLoc &DL, const Register SGPR,
+                                  const Register VGPR, const int Lane) const;
 };
 
 } // end namespace llvm
diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
@@ -11,12 +11,14 @@
 #include "GCNSubtarget.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIMachineFunctionInfo.h"
+#include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
 #include "llvm/MC/MCDwarf.h"
 #include "llvm/Target/TargetMachine.h"
+#include "llvm/Support/LEB128.h"
 
 using namespace llvm;
 
@@ -880,6 +882,64 @@
   return ScratchExecCopy;
 }
 
+void SIFrameLowering::emitPrologueEntryCFI(MachineBasicBlock &MBB,
+                                           MachineBasicBlock::iterator MBBI,
+                                           const DebugLoc &DL) const {
+  const MachineFunction &MF = *MBB.getParent();
+  const MachineRegisterInfo &MRI = MF.getRegInfo();
+  const MCRegisterInfo *MCRI = MF.getMMI().getContext().getRegisterInfo();
+  const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
+  const SIRegisterInfo &TRI = ST.getInstrInfo()->getRegisterInfo();
+  Register StackPtrReg =
+      MF.getInfo<SIMachineFunctionInfo>()->getStackPtrOffsetReg();
+
+  // DW_ASPACE_AMDGPU_private_wave FIXME: should be defined elsewhere
+  buildCFI(MBB, MBBI, DL,
+           MCCFIInstruction::createLLVMDefAspaceCfa(
+               nullptr, MCRI->getDwarfRegNum(StackPtrReg, false), 0, 6));
+
+  static const char PCEncodedInst[] = {
+      dwarf::DW_CFA_expression,
+      16, // PC 64
+      8,  // length
+      static_cast<char>(dwarf::DW_OP_regx),
+      62, // SGPR30
+      static_cast<char>(dwarf::DW_OP_piece),
+      4, // 32 bits
+      static_cast<char>(dwarf::DW_OP_regx),
+      63, // SGPR31
+      static_cast<char>(dwarf::DW_OP_piece),
+      4 // 32 bits
+  };
+  buildCFI(MBB, MBBI, DL,
+           MCCFIInstruction::createEscape(
+               nullptr, StringRef(PCEncodedInst, sizeof(PCEncodedInst))));
+
+  BitVector IsCalleeSaved(TRI.getNumRegs());
+  const MCPhysReg *CSRegs = MRI.getCalleeSavedRegs();
+  for (unsigned I = 0; CSRegs[I]; ++I) {
+    IsCalleeSaved.set(CSRegs[I]);
+  }
+  auto ProcessReg = [&](MCPhysReg Reg) {
+    if (IsCalleeSaved.test(Reg) || !MRI.isPhysRegModified(Reg))
+      return;
+    MCRegister DwarfReg = MCRI->getDwarfRegNum(Reg, false);
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createUndefined(nullptr, DwarfReg));
+  };
+
+  // Emit CFI rules for caller saved Arch VGPRs which are clobbered
+  for_each(AMDGPU::VGPR_32RegClass.getRegisters(), ProcessReg);
+
+  // Emit CFI rules for caller saved Accum VGPRs which are clobbered
+  if (ST.hasMAIInsts()) {
+    for_each(AMDGPU::AGPR_32RegClass.getRegisters(), ProcessReg);
+  }
+
+  // Emit CFI rules for caller saved SGPRs which are clobbered
+  for_each(AMDGPU::SGPR_32RegClass.getRegisters(), ProcessReg);
+}
+
 void SIFrameLowering::emitPrologue(MachineFunction &MF,
                                    MachineBasicBlock &MBB) const {
   SIMachineFunctionInfo *FuncInfo = MF.getInfo<SIMachineFunctionInfo>();
@@ -893,6 +953,7 @@
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   const SIInstrInfo *TII = ST.getInstrInfo();
   const SIRegisterInfo &TRI = TII->getRegisterInfo();
+  const MCRegisterInfo *MCRI = MF.getMMI().getContext().getRegisterInfo();
 
   Register StackPtrReg = FuncInfo->getStackPtrOffsetReg();
   Register FramePtrReg = FuncInfo->getFrameOffsetReg();
@@ -911,6 +972,8 @@
   // turn on all lanes before doing the spill to memory.
   Register ScratchExecCopy;
 
+  emitPrologueEntryCFI(MBB, MBBI, DL);
+
   bool HasFPSaveIndex = FuncInfo->FramePointerSaveIndex.hasValue();
   bool SpillFPToMemory = false;
   // A StackID of SGPRSpill implies that this is a spill from SGPR to VGPR.
@@ -937,14 +1000,21 @@
     if (!ScratchExecCopy)
       ScratchExecCopy = buildScratchExecCopy(LiveRegs, MF, MBB, MBBI, true);
 
+    int FI = Reg.FI.getValue();
+
     buildPrologSpill(ST, LiveRegs, MBB, MBBI, TII, Reg.VGPR,
-                     FuncInfo->getScratchRSrcReg(),
-                     StackPtrReg,
-                     Reg.FI.getValue());
+                     FuncInfo->getScratchRSrcReg(), StackPtrReg, FI);
+
+    // We spill the entire VGPR, so we can get away with just cfi_offset
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createOffset(
+                 nullptr, MCRI->getDwarfRegNum(Reg.VGPR, false),
+                 MFI.getObjectOffset(FI) * ST.getWavefrontSize()));
   }
 
   if (HasFPSaveIndex && SpillFPToMemory) {
-    assert(!MFI.isDeadObjectIndex(FuncInfo->FramePointerSaveIndex.getValue()));
+    const int FI = *FuncInfo->FramePointerSaveIndex;
+    assert(!MFI.isDeadObjectIndex(FI));
 
     if (!ScratchExecCopy)
       ScratchExecCopy = buildScratchExecCopy(LiveRegs, MF, MBB, MBBI, true);
@@ -958,12 +1028,16 @@
         .addReg(FramePtrReg);
 
     buildPrologSpill(ST, LiveRegs, MBB, MBBI, TII, TmpVGPR,
-                     FuncInfo->getScratchRSrcReg(), StackPtrReg,
-                     FuncInfo->FramePointerSaveIndex.getValue());
+                     FuncInfo->getScratchRSrcReg(), StackPtrReg, FI);
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createOffset(
+                 nullptr, MCRI->getDwarfRegNum(FramePtrReg, false),
+                 MFI.getObjectOffset(FI) * ST.getWavefrontSize()));
   }
 
   if (HasBPSaveIndex && SpillBPToMemory) {
-    assert(!MFI.isDeadObjectIndex(*FuncInfo->BasePointerSaveIndex));
+    const int BasePtrFI = *FuncInfo->BasePointerSaveIndex;
+    assert(!MFI.isDeadObjectIndex(BasePtrFI));
 
     if (!ScratchExecCopy)
       ScratchExecCopy = buildScratchExecCopy(LiveRegs, MF, MBB, MBBI, true);
@@ -977,8 +1051,11 @@
         .addReg(BasePtrReg);
 
     buildPrologSpill(ST, LiveRegs, MBB, MBBI, TII, TmpVGPR,
-                     FuncInfo->getScratchRSrcReg(), StackPtrReg,
-                     *FuncInfo->BasePointerSaveIndex);
+                     FuncInfo->getScratchRSrcReg(), StackPtrReg, BasePtrFI);
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createOffset(
+                 nullptr, MCRI->getDwarfRegNum(BasePtrReg, false),
+                 MFI.getObjectOffset(BasePtrFI) * ST.getWavefrontSize()));
   }
 
   if (ScratchExecCopy) {
@@ -992,7 +1069,7 @@
 
   // In this case, spill the FP to a reserved VGPR.
   if (HasFPSaveIndex && !SpillFPToMemory) {
-    const int FI = FuncInfo->FramePointerSaveIndex.getValue();
+    const int FI = *FuncInfo->FramePointerSaveIndex;
     assert(!MFI.isDeadObjectIndex(FI));
 
     assert(MFI.getStackID(FI) == TargetStackID::SGPRSpill);
@@ -1006,6 +1083,9 @@
         .addReg(FramePtrReg)
         .addImm(Spill[0].Lane)
         .addReg(Spill[0].VGPR, RegState::Undef);
+
+    buildCFIForSGPRToVGPRSpill(MBB, MBBI, DL, FramePtrReg, Spill[0].VGPR,
+                               Spill[0].Lane);
   }
 
   // In this case, spill the BP to a reserved VGPR.
@@ -1024,6 +1104,8 @@
         .addReg(BasePtrReg)
         .addImm(Spill[0].Lane)
         .addReg(Spill[0].VGPR, RegState::Undef);
+    buildCFIForSGPRToVGPRSpill(MBB, MBBI, DL, BasePtrReg, Spill[0].VGPR,
+                               Spill[0].Lane);
   }
 
   // Emit the copy if we need an FP, and are using a free SGPR to save it.
@@ -1032,6 +1114,11 @@
             FuncInfo->SGPRForFPSaveRestoreCopy)
         .addReg(FramePtrReg)
         .setMIFlag(MachineInstr::FrameSetup);
+    buildCFI(
+        MBB, MBBI, DL,
+        MCCFIInstruction::createRegister(
+            nullptr, MCRI->getDwarfRegNum(FramePtrReg, false),
+            MCRI->getDwarfRegNum(FuncInfo->SGPRForFPSaveRestoreCopy, false)));
   }
 
   // Emit the copy if we need a BP, and are using a free SGPR to save it.
@@ -1040,6 +1127,11 @@
             FuncInfo->SGPRForBPSaveRestoreCopy)
         .addReg(BasePtrReg)
         .setMIFlag(MachineInstr::FrameSetup);
+    buildCFI(
+        MBB, MBBI, DL,
+        MCCFIInstruction::createRegister(
+            nullptr, MCRI->getDwarfRegNum(BasePtrReg, false),
+            MCRI->getDwarfRegNum(FuncInfo->SGPRForBPSaveRestoreCopy, false)));
   }
 
   // If a copy has been emitted for FP and/or BP, Make the SGPRs
@@ -1101,6 +1193,12 @@
         .setMIFlag(MachineInstr::FrameSetup);
   }
 
+  if (HasFP) {
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createDefCfaRegister(
+                 nullptr, MCRI->getDwarfRegNum(FramePtrReg, false)));
+  }
+
   if (HasFP && RoundedSize != 0) {
     BuildMI(MBB, MBBI, DL, TII->get(AMDGPU::S_ADD_U32), StackPtrReg)
         .addReg(StackPtrReg)
@@ -1134,6 +1232,7 @@
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   const SIInstrInfo *TII = ST.getInstrInfo();
   MachineRegisterInfo &MRI = MF.getRegInfo();
+  const MCRegisterInfo *MCRI = MF.getMMI().getContext().getRegisterInfo();
   const SIRegisterInfo &TRI = TII->getRegisterInfo();
   MachineBasicBlock::iterator MBBI = MBB.getFirstTerminator();
   LivePhysRegs LiveRegs;
@@ -1184,7 +1283,7 @@
 
   Register ScratchExecCopy;
   if (HasFPSaveIndex) {
-    const int FI = FuncInfo->FramePointerSaveIndex.getValue();
+    const int FI = *FuncInfo->FramePointerSaveIndex;
     assert(!MFI.isDeadObjectIndex(FI));
     if (SpillFPToMemory) {
       if (!ScratchExecCopy)
@@ -1210,6 +1309,11 @@
     }
   }
 
+  if (hasFP(MF))
+    buildCFI(MBB, MBBI, DL,
+             MCCFIInstruction::createDefCfaRegister(
+                 nullptr, MCRI->getDwarfRegNum(StackPtrReg, false)));
+
   if (HasBPSaveIndex) {
     const int BasePtrFI = *FuncInfo->BasePointerSaveIndex;
     assert(!MFI.isDeadObjectIndex(BasePtrFI));
@@ -1541,3 +1645,56 @@
       .addCFIIndex(MF.addFrameInst(CFIInst))
       .setMIFlag(MachineInstr::FrameSetup);
 }
+
+static void encodeDwarfRegisterLocation(int DwarfReg, raw_ostream &OS) {
+  if (DwarfReg < 32) {
+    OS << uint8_t(dwarf::DW_OP_reg0 + DwarfReg);
+  } else {
+    OS << uint8_t(dwarf::DW_OP_regx);
+    encodeULEB128(DwarfReg, OS);
+  }
+}
+
+void SIFrameLowering::buildCFIForSGPRToVGPRSpill(
+    MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+    const DebugLoc &DL, const Register SGPR, const Register VGPR,
+    const int Lane) const {
+  MachineFunction &MF = *MBB.getParent();
+  const MCRegisterInfo &MCRI = *MF.getMMI().getContext().getRegisterInfo();
+  int DwarfSGPR = MCRI.getDwarfRegNum(SGPR, false);
+  int DwarfVGPR = MCRI.getDwarfRegNum(VGPR, false);
+
+  // CFI for an SGPR spilled to a single lane of a VGPR is implemented as an
+  // expression(E) rule where E is a register location description referencing
+  // a VGPR register location storage at a byte offset of the lane index
+  // multiplied by the size of an SGPR (4 bytes). In other words we generate
+  // the following DWARF:
+  //
+  // DW_CFA_expression: <SGPR>,
+  //    (DW_OP_regx <VGPR>) (DW_OP_LLVM_offset_uconst <Lane>*4)
+  //
+  // The memory location description for the current CFA is pushed on the
+  // stack before E is evaluated, but we choose not to drop it as it would
+  // require a longer expression E and DWARF defines the result of the
+  // evaulation to be the location description on the top of the stack (i.e. the
+  // implictly pushed one is just ignored.)
+  SmallString<20> CFIInst;
+  raw_svector_ostream OSCFIInst(CFIInst);
+  SmallString<20> Block;
+  raw_svector_ostream OSBlock(Block);
+
+  OSCFIInst << uint8_t(dwarf::DW_CFA_expression);
+  encodeULEB128(DwarfSGPR, OSCFIInst);
+
+  encodeDwarfRegisterLocation(DwarfVGPR, OSBlock);
+  OSBlock << uint8_t(dwarf::DW_OP_LLVM_offset_uconst);
+  // FIXME: Can this be a function of the SGPR?
+  const unsigned SGPRByteSize = 4;
+  encodeULEB128(Lane * SGPRByteSize, OSBlock);
+
+  encodeULEB128(Block.size(), OSCFIInst);
+  OSCFIInst << Block;
+
+  buildCFI(MBB, MBBI, DL,
+           MCCFIInstruction::createEscape(nullptr, OSCFIInst.str()));
+}
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-uniform.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-uniform.ll
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-uniform.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-uniform.ll
@@ -289,14 +289,14 @@
 ; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-NEXT:    s_mov_b32 s6, s33
 ; GFX10-NEXT:    s_add_u32 s33, s32, 0x3e0
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    s_and_b32 s33, s33, 0xfffffc00
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x800
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, gv@gotpcrel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, gv@gotpcrel32@hi+12
-; GFX10-NEXT:    s_mov_b32 s33, s6
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    s_mov_b32 s33, s6
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_load_dword s4, s[4:5], 0x0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/non-entry-alloca.ll
@@ -166,8 +166,8 @@
 ; GCN:       ; %bb.0: ; %entry
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    s_mov_b32 s8, s33
-; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; GCN-NEXT:    s_mov_b32 s33, s32
+; GCN-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_and_saveexec_b64 s[4:5], vcc
 ; GCN-NEXT:    s_cbranch_execz BB2_3
diff --git a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
--- a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
@@ -229,7 +229,7 @@
 ; GCN-NEXT: s_mov_b64 exec,
 ; GCN-NEXT: s_waitcnt vmcnt(0)
 ; GCN-NEXT: s_setpc_b64
-define void @spill_only_csr_sgpr() {
+define void @spill_only_csr_sgpr() #0 {
   call void asm sideeffect "; clobber s42", "~{s42}"()
   ret void
 }
@@ -270,9 +270,9 @@
 ; GCN-LABEL: {{^}}last_lane_vgpr_for_fp_csr:
 ; GCN: s_waitcnt
 ; GCN-NEXT: v_writelane_b32 v1, s33, 63
-; GCN-COUNT-60: v_writelane_b32 v1
 ; GCN: s_mov_b32 s33, s32
-; GCN-COUNT-2: v_writelane_b32 v1
+; GCN-COUNT-60: v_writelane_b32 v1
+; GCN-COUNT-1: v_writelane_b32 v1
 ; MUBUF:   buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; FLATSCR: scratch_store_dword off, v41, s33 ; 4-byte Folded Spill
 ; MUBUF:   buffer_store_dword v{{[0-9]+}}, off, s[0:3], s33 offset:8
@@ -306,9 +306,9 @@
 ; Use a copy to a free SGPR instead of introducing a second CSR VGPR.
 ; GCN-LABEL: {{^}}no_new_vgpr_for_fp_csr:
 ; GCN: s_waitcnt
-; GCN-COUNT-62: v_writelane_b32 v1,
 ; GCN: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
 ; GCN-NEXT: s_mov_b32 s33, s32
+; GCN-COUNT-62: v_writelane_b32 v1,
 ; GCN: v_writelane_b32 v1,
 ; MUBUF:   buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; FLATSCR: scratch_store_dword off, v41, s33 ; 4-byte Folded Spill
@@ -346,10 +346,10 @@
 ; GCN: s_waitcnt
 ; MUBUF-NEXT:   s_mov_b32 [[FP_COPY:s4]], s33
 ; FLATSCR-NEXT: s_mov_b32 [[FP_COPY:s0]], s33
-; MUBUF-NEXT:   s_add_u32 s33, s32, 0x7ffc0
-; FLATSCR-NEXT: s_add_u32 s33, s32, 0x1fff
-; MUBUF-NEXT:   s_and_b32 s33, s33, 0xfff80000
-; FLATSCR-NEXT: s_and_b32 s33, s33, 0xffffe000
+; MUBUF-NEXT:   s_add_u32 [[SCRATCH:s[0-9]+]], s32, 0x7ffc0
+; FLATSCR-NEXT: s_add_u32 [[SCRATCH:s[0-9]+]], s32, 0x1fff
+; MUBUF-NEXT:   s_and_b32 s33, [[SCRATCH]], 0xfff80000
+; FLATSCR-NEXT: s_and_b32 s33, [[SCRATCH]], 0xffffe000
 ; MUBUF-NEXT:   s_add_u32 s32, s32, 0x100000
 ; FLATSCR-NEXT: s_add_u32 s32, s32, 0x4000
 ; GCN-NEXT:     v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
@@ -369,19 +369,19 @@
 ; GCN-LABEL: {{^}}no_unused_non_csr_sgpr_for_fp:
 ; GCN: s_waitcnt
 ; GCN-NEXT: v_writelane_b32 v1, s33, 2
-; GCN-NEXT: v_writelane_b32 v1, s30, 0
 ; GCN-NEXT: s_mov_b32 s33, s32
+; GCN-NEXT: v_writelane_b32 v1, s30, 0
 ; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
 ; GCN: v_writelane_b32 v1, s31, 1
 ; MUBUF:   buffer_store_dword [[ZERO]], off, s[0:3], s33 offset:4
 ; FLATSCR: scratch_store_dword off, [[ZERO]], s33 offset:4
 ; GCN-NEXT:     s_waitcnt vmcnt(0)
 ; GCN: ;;#ASMSTART
-; MUBUF:        v_readlane_b32 s4, v1, 0
-; MUBUF-NEXT:   s_add_u32 s32, s32, 0x200
+; MUBUF:   s_add_u32 s32, s32, 0x200
+; MUBUF-NEXT:   v_readlane_b32 s4, v1, 0
 ; MUBUF-NEXT:   v_readlane_b32 s5, v1, 1
-; FLATSCR:      v_readlane_b32 s0, v1, 0
-; FLATSCR-NEXT: s_add_u32 s32, s32, 8
+; FLATSCR: s_add_u32 s32, s32, 8
+; FLATSCR-NEXT: v_readlane_b32 s0, v1, 0
 ; FLATSCR-NEXT: v_readlane_b32 s1, v1, 1
 ; MUBUF-NEXT:   s_sub_u32 s32, s32, 0x200
 ; FLATSCR-NEXT: s_sub_u32 s32, s32, 8
@@ -410,8 +410,8 @@
 ; FLATSCR-NEXT: scratch_store_dword off, [[CSR_VGPR:v[0-9]+]], s32 offset:8 ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
 ; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s33, 2
-; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s30, 0
 ; GCN-NEXT: s_mov_b32 s33, s32
+; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s30, 0
 
 ; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31, 1
 ; MUBUF-DAG:   buffer_store_dword
diff --git a/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll b/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
--- a/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
+++ b/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
@@ -31,8 +31,8 @@
 ; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
 ; GCN-NEXT:    v_writelane_b32 v40, s33, 2
-; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v2f32@rel32@lo+4
@@ -65,8 +65,8 @@
 ; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
 ; GCN-NEXT:    v_writelane_b32 v40, s33, 2
-; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v3f32@rel32@lo+4
@@ -99,8 +99,8 @@
 ; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
 ; GCN-NEXT:    v_writelane_b32 v40, s33, 2
-; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v4f16@rel32@lo+4
@@ -133,8 +133,8 @@
 ; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
 ; GCN-NEXT:    v_writelane_b32 v40, s33, 2
-; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_struct@rel32@lo+4
diff --git a/llvm/test/CodeGen/AMDGPU/debug-frame.ll b/llvm/test/CodeGen/AMDGPU/debug-frame.ll
--- a/llvm/test/CodeGen/AMDGPU/debug-frame.ll
+++ b/llvm/test/CodeGen/AMDGPU/debug-frame.ll
@@ -1,4 +1,5 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=asm -o - %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=asm -o - %s | FileCheck --check-prefixes=CHECK,WAVE64 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -filetype=asm -o - %s | FileCheck --check-prefixes=CHECK,WAVE32 %s
 
 ; CHECK-LABEL: kern1:
 ; CHECK: .cfi_startproc
@@ -23,7 +24,510 @@
   ret void
 }
 
-attributes #0 = { nounwind }
+; CHECK-LABEL: func_no_clobber:
+; CHECK: .cfi_startproc
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: %bb.0:
+; SGPR32 = 64
+; CHECK-NEXT: .cfi_llvm_def_aspace_cfa 64, 0, 6
+; DW_CFA_expression [0x10]
+;   PC_64 ULEB128(17)=[0x10]
+;   BLOCK_LENGTH ULEB128(8)=[0x08]
+;     DW_OP_regx [0x90]
+;       SGPR30 ULEB128(62)=[0x3e]
+;     DW_OP_piece [0x93]
+;       PIECE_SIZE [0x04]
+;     DW_OP_regx [0x90]
+;       SGPR31 ULEB128(63)=[0x3f]
+;     DW_OP_piece [0x93]
+;       PIECE_SIZE [0x04]
+; CHECK-NEXT: .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: .cfi_endproc
+define hidden void @func_no_clobber() #0 {
+entry:
+  ret void
+}
+
+; CHECK-LABEL: {{^}}callee_need_to_spill_fp_to_memory:
+; CHECK: .cfi_startproc
+
+; SGPR33 = 65
+; CHECK: v_mov_b32_e32 [[TMP_VGPR1:v[0-9]+]], s33
+; CHECK: buffer_store_dword [[TMP_VGPR1]], off, s[0:3], s32 offset:452 ; 4-byte Folded Spill
+; WAVE64: .cfi_offset 65, 28928
+; WAVE32: .cfi_offset 65, 14464
+
+; CHECK: .cfi_endproc
+define void @callee_need_to_spill_fp_to_memory() #1 {
+  call void asm sideeffect "; clobber nonpreserved SGPRs",
+    "~{s4},~{s5},~{s6},~{s7},~{s8},~{s9}
+    ,~{s10},~{s11},~{s12},~{s13},~{s14},~{s15},~{s16},~{s17},~{s18},~{s19}
+    ,~{s20},~{s21},~{s22},~{s23},~{s24},~{s25},~{s26},~{s27},~{s28},~{s29}
+    ,~{vcc}"()
+
+  call void asm sideeffect "; clobber all VGPRs",
+    "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
+    ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}
+    ,~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}
+    ,~{v30},~{v31},~{v32},~{v33},~{v34},~{v35},~{v36},~{v37},~{v38},~{v39}
+    ,~{v40},~{v41},~{v42},~{v43},~{v44},~{v45},~{v46},~{v47},~{v48},~{v49}
+    ,~{v50},~{v51},~{v52},~{v53},~{v54},~{v55},~{v56},~{v57},~{v58},~{v59}
+    ,~{v60},~{v61},~{v62},~{v63},~{v64},~{v65},~{v66},~{v67},~{v68},~{v69}
+    ,~{v70},~{v71},~{v72},~{v73},~{v74},~{v75},~{v76},~{v77},~{v78},~{v79}
+    ,~{v80},~{v81},~{v82},~{v83},~{v84},~{v85},~{v86},~{v87},~{v88},~{v89}
+    ,~{v90},~{v91},~{v92},~{v93},~{v94},~{v95},~{v96},~{v97},~{v98},~{v99}
+    ,~{v100},~{v101},~{v102},~{v103},~{v104},~{v105},~{v106},~{v107},~{v108},~{v109}
+    ,~{v110},~{v111},~{v112},~{v113},~{v114},~{v115},~{v116},~{v117},~{v118},~{v119}
+    ,~{v120},~{v121},~{v122},~{v123},~{v124},~{v125},~{v126},~{v127},~{v128},~{v129}
+    ,~{v130},~{v131},~{v132},~{v133},~{v134},~{v135},~{v136},~{v137},~{v138},~{v139}
+    ,~{v140},~{v141},~{v142},~{v143},~{v144},~{v145},~{v146},~{v147},~{v148},~{v149}
+    ,~{v150},~{v151},~{v152},~{v153},~{v154},~{v155},~{v156},~{v157},~{v158},~{v159}
+    ,~{v160},~{v161},~{v162},~{v163},~{v164},~{v165},~{v166},~{v167},~{v168},~{v169}
+    ,~{v170},~{v171},~{v172},~{v173},~{v174},~{v175},~{v176},~{v177},~{v178},~{v179}
+    ,~{v180},~{v181},~{v182},~{v183},~{v184},~{v185},~{v186},~{v187},~{v188},~{v189}
+    ,~{v190},~{v191},~{v192},~{v193},~{v194},~{v195},~{v196},~{v197},~{v198},~{v199}
+    ,~{v200},~{v201},~{v202},~{v203},~{v204},~{v205},~{v206},~{v207},~{v208},~{v209}
+    ,~{v210},~{v211},~{v212},~{v213},~{v214},~{v215},~{v216},~{v217},~{v218},~{v219}
+    ,~{v220},~{v221},~{v222},~{v223},~{v224},~{v225},~{v226},~{v227},~{v228},~{v229}
+    ,~{v230},~{v231},~{v232},~{v233},~{v234},~{v235},~{v236},~{v237},~{v238},~{v239}
+    ,~{v240},~{v241},~{v242},~{v243},~{v244},~{v245},~{v246},~{v247},~{v248},~{v249}
+    ,~{v250},~{v251},~{v252},~{v253},~{v254},~{v255}"()
+  ret void
+}
+
+declare hidden void @ex() #0
+
+; CHECK-LABEL: func_call_clobber:
+; CHECK: .cfi_startproc
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: %bb.0:
+; CHECK-NEXT: .cfi_llvm_def_aspace_cfa 64, 0, 6
+; CHECK-NEXT: .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
+
+; VGPR0_wave64 = 2560
+; WAVE64-NEXT: .cfi_undefined 2560
+; WAVE64-NEXT: .cfi_undefined 2561
+; WAVE64-NEXT: .cfi_undefined 2562
+; WAVE64-NEXT: .cfi_undefined 2563
+; WAVE64-NEXT: .cfi_undefined 2564
+; WAVE64-NEXT: .cfi_undefined 2565
+; WAVE64-NEXT: .cfi_undefined 2566
+; WAVE64-NEXT: .cfi_undefined 2567
+; WAVE64-NEXT: .cfi_undefined 2568
+; WAVE64-NEXT: .cfi_undefined 2569
+; WAVE64-NEXT: .cfi_undefined 2570
+; WAVE64-NEXT: .cfi_undefined 2571
+; WAVE64-NEXT: .cfi_undefined 2572
+; WAVE64-NEXT: .cfi_undefined 2573
+; WAVE64-NEXT: .cfi_undefined 2574
+; WAVE64-NEXT: .cfi_undefined 2575
+; WAVE64-NEXT: .cfi_undefined 2576
+; WAVE64-NEXT: .cfi_undefined 2577
+; WAVE64-NEXT: .cfi_undefined 2578
+; WAVE64-NEXT: .cfi_undefined 2579
+; WAVE64-NEXT: .cfi_undefined 2580
+; WAVE64-NEXT: .cfi_undefined 2581
+; WAVE64-NEXT: .cfi_undefined 2582
+; WAVE64-NEXT: .cfi_undefined 2583
+; WAVE64-NEXT: .cfi_undefined 2584
+; WAVE64-NEXT: .cfi_undefined 2585
+; WAVE64-NEXT: .cfi_undefined 2586
+; WAVE64-NEXT: .cfi_undefined 2587
+; WAVE64-NEXT: .cfi_undefined 2588
+; WAVE64-NEXT: .cfi_undefined 2589
+; WAVE64-NEXT: .cfi_undefined 2590
+; WAVE64-NEXT: .cfi_undefined 2591
+; WAVE64-NEXT: .cfi_undefined 2592
+; WAVE64-NEXT: .cfi_undefined 2593
+; WAVE64-NEXT: .cfi_undefined 2594
+; WAVE64-NEXT: .cfi_undefined 2595
+; WAVE64-NEXT: .cfi_undefined 2596
+; WAVE64-NEXT: .cfi_undefined 2597
+; WAVE64-NEXT: .cfi_undefined 2598
+; WAVE64-NEXT: .cfi_undefined 2599
+
+; VPGR48_wave64 = 2608
+; WAVE64-NEXT: .cfi_undefined 2608
+; WAVE64-NEXT: .cfi_undefined 2609
+; WAVE64-NEXT: .cfi_undefined 2610
+; WAVE64-NEXT: .cfi_undefined 2611
+; WAVE64-NEXT: .cfi_undefined 2612
+; WAVE64-NEXT: .cfi_undefined 2613
+; WAVE64-NEXT: .cfi_undefined 2614
+; WAVE64-NEXT: .cfi_undefined 2615
+
+; WAVE64-NEXT: .cfi_undefined 2624
+; WAVE64-NEXT: .cfi_undefined 2625
+; WAVE64-NEXT: .cfi_undefined 2626
+; WAVE64-NEXT: .cfi_undefined 2627
+; WAVE64-NEXT: .cfi_undefined 2628
+; WAVE64-NEXT: .cfi_undefined 2629
+; WAVE64-NEXT: .cfi_undefined 2630
+; WAVE64-NEXT: .cfi_undefined 2631
+
+; WAVE64-NEXT: .cfi_undefined 2640
+; WAVE64-NEXT: .cfi_undefined 2641
+; WAVE64-NEXT: .cfi_undefined 2642
+; WAVE64-NEXT: .cfi_undefined 2643
+; WAVE64-NEXT: .cfi_undefined 2644
+; WAVE64-NEXT: .cfi_undefined 2645
+; WAVE64-NEXT: .cfi_undefined 2646
+; WAVE64-NEXT: .cfi_undefined 2647
+
+; WAVE64-NEXT: .cfi_undefined 2656
+; WAVE64-NEXT: .cfi_undefined 2657
+; WAVE64-NEXT: .cfi_undefined 2658
+; WAVE64-NEXT: .cfi_undefined 2659
+; WAVE64-NEXT: .cfi_undefined 2660
+; WAVE64-NEXT: .cfi_undefined 2661
+; WAVE64-NEXT: .cfi_undefined 2662
+; WAVE64-NEXT: .cfi_undefined 2663
+
+; WAVE64-NEXT: .cfi_undefined 2672
+; WAVE64-NEXT: .cfi_undefined 2673
+; WAVE64-NEXT: .cfi_undefined 2674
+; WAVE64-NEXT: .cfi_undefined 2675
+; WAVE64-NEXT: .cfi_undefined 2676
+; WAVE64-NEXT: .cfi_undefined 2677
+; WAVE64-NEXT: .cfi_undefined 2678
+; WAVE64-NEXT: .cfi_undefined 2679
+
+; WAVE64-NEXT: .cfi_undefined 2688
+; WAVE64-NEXT: .cfi_undefined 2689
+; WAVE64-NEXT: .cfi_undefined 2690
+; WAVE64-NEXT: .cfi_undefined 2691
+; WAVE64-NEXT: .cfi_undefined 2692
+; WAVE64-NEXT: .cfi_undefined 2693
+; WAVE64-NEXT: .cfi_undefined 2694
+; WAVE64-NEXT: .cfi_undefined 2695
+
+; WAVE64-NEXT: .cfi_undefined 2704
+; WAVE64-NEXT: .cfi_undefined 2705
+; WAVE64-NEXT: .cfi_undefined 2706
+; WAVE64-NEXT: .cfi_undefined 2707
+; WAVE64-NEXT: .cfi_undefined 2708
+; WAVE64-NEXT: .cfi_undefined 2709
+; WAVE64-NEXT: .cfi_undefined 2710
+; WAVE64-NEXT: .cfi_undefined 2711
+
+; WAVE64-NEXT: .cfi_undefined 2720
+; WAVE64-NEXT: .cfi_undefined 2721
+; WAVE64-NEXT: .cfi_undefined 2722
+; WAVE64-NEXT: .cfi_undefined 2723
+; WAVE64-NEXT: .cfi_undefined 2724
+; WAVE64-NEXT: .cfi_undefined 2725
+; WAVE64-NEXT: .cfi_undefined 2726
+; WAVE64-NEXT: .cfi_undefined 2727
+
+; WAVE64-NEXT: .cfi_undefined 2736
+; WAVE64-NEXT: .cfi_undefined 2737
+; WAVE64-NEXT: .cfi_undefined 2738
+; WAVE64-NEXT: .cfi_undefined 2739
+; WAVE64-NEXT: .cfi_undefined 2740
+; WAVE64-NEXT: .cfi_undefined 2741
+; WAVE64-NEXT: .cfi_undefined 2742
+; WAVE64-NEXT: .cfi_undefined 2743
+
+; WAVE64-NEXT: .cfi_undefined 2752
+; WAVE64-NEXT: .cfi_undefined 2753
+; WAVE64-NEXT: .cfi_undefined 2754
+; WAVE64-NEXT: .cfi_undefined 2755
+; WAVE64-NEXT: .cfi_undefined 2756
+; WAVE64-NEXT: .cfi_undefined 2757
+; WAVE64-NEXT: .cfi_undefined 2758
+; WAVE64-NEXT: .cfi_undefined 2759
+
+; WAVE64-NEXT: .cfi_undefined 2768
+; WAVE64-NEXT: .cfi_undefined 2769
+; WAVE64-NEXT: .cfi_undefined 2770
+; WAVE64-NEXT: .cfi_undefined 2771
+; WAVE64-NEXT: .cfi_undefined 2772
+; WAVE64-NEXT: .cfi_undefined 2773
+; WAVE64-NEXT: .cfi_undefined 2774
+; WAVE64-NEXT: .cfi_undefined 2775
+
+; WAVE64-NEXT: .cfi_undefined 2784
+; WAVE64-NEXT: .cfi_undefined 2785
+; WAVE64-NEXT: .cfi_undefined 2786
+; WAVE64-NEXT: .cfi_undefined 2787
+; WAVE64-NEXT: .cfi_undefined 2788
+; WAVE64-NEXT: .cfi_undefined 2789
+; WAVE64-NEXT: .cfi_undefined 2790
+; WAVE64-NEXT: .cfi_undefined 2791
+
+; WAVE64-NEXT: .cfi_undefined 2800
+; WAVE64-NEXT: .cfi_undefined 2801
+; WAVE64-NEXT: .cfi_undefined 2802
+; WAVE64-NEXT: .cfi_undefined 2803
+; WAVE64-NEXT: .cfi_undefined 2804
+; WAVE64-NEXT: .cfi_undefined 2805
+; WAVE64-NEXT: .cfi_undefined 2806
+; WAVE64-NEXT: .cfi_undefined 2807
+
+
+; VGPR0_wave32 = 1536
+; WAVE32-NEXT: .cfi_undefined 1536
+; WAVE32-NEXT: .cfi_undefined 1537
+; WAVE32-NEXT: .cfi_undefined 1538
+; WAVE32-NEXT: .cfi_undefined 1539
+; WAVE32-NEXT: .cfi_undefined 1540
+; WAVE32-NEXT: .cfi_undefined 1541
+; WAVE32-NEXT: .cfi_undefined 1542
+; WAVE32-NEXT: .cfi_undefined 1543
+; WAVE32-NEXT: .cfi_undefined 1544
+; WAVE32-NEXT: .cfi_undefined 1545
+; WAVE32-NEXT: .cfi_undefined 1546
+; WAVE32-NEXT: .cfi_undefined 1547
+; WAVE32-NEXT: .cfi_undefined 1548
+; WAVE32-NEXT: .cfi_undefined 1549
+; WAVE32-NEXT: .cfi_undefined 1550
+; WAVE32-NEXT: .cfi_undefined 1551
+; WAVE32-NEXT: .cfi_undefined 1552
+; WAVE32-NEXT: .cfi_undefined 1553
+; WAVE32-NEXT: .cfi_undefined 1554
+; WAVE32-NEXT: .cfi_undefined 1555
+; WAVE32-NEXT: .cfi_undefined 1556
+; WAVE32-NEXT: .cfi_undefined 1557
+; WAVE32-NEXT: .cfi_undefined 1558
+; WAVE32-NEXT: .cfi_undefined 1559
+; WAVE32-NEXT: .cfi_undefined 1560
+; WAVE32-NEXT: .cfi_undefined 1561
+; WAVE32-NEXT: .cfi_undefined 1562
+; WAVE32-NEXT: .cfi_undefined 1563
+; WAVE32-NEXT: .cfi_undefined 1564
+; WAVE32-NEXT: .cfi_undefined 1565
+; WAVE32-NEXT: .cfi_undefined 1566
+; WAVE32-NEXT: .cfi_undefined 1567
+; WAVE32-NEXT: .cfi_undefined 1568
+; WAVE32-NEXT: .cfi_undefined 1569
+; WAVE32-NEXT: .cfi_undefined 1570
+; WAVE32-NEXT: .cfi_undefined 1571
+; WAVE32-NEXT: .cfi_undefined 1572
+; WAVE32-NEXT: .cfi_undefined 1573
+; WAVE32-NEXT: .cfi_undefined 1574
+; WAVE32-NEXT: .cfi_undefined 1575
+
+; VPGR48_wave64 = 1584
+; WAVE32-NEXT: .cfi_undefined 1584
+; WAVE32-NEXT: .cfi_undefined 1585
+; WAVE32-NEXT: .cfi_undefined 1586
+; WAVE32-NEXT: .cfi_undefined 1587
+; WAVE32-NEXT: .cfi_undefined 1588
+; WAVE32-NEXT: .cfi_undefined 1589
+; WAVE32-NEXT: .cfi_undefined 1590
+; WAVE32-NEXT: .cfi_undefined 1591
+
+; WAVE32-NEXT: .cfi_undefined 1600
+; WAVE32-NEXT: .cfi_undefined 1601
+; WAVE32-NEXT: .cfi_undefined 1602
+; WAVE32-NEXT: .cfi_undefined 1603
+; WAVE32-NEXT: .cfi_undefined 1604
+; WAVE32-NEXT: .cfi_undefined 1605
+; WAVE32-NEXT: .cfi_undefined 1606
+; WAVE32-NEXT: .cfi_undefined 1607
+
+; WAVE32-NEXT: .cfi_undefined 1616
+; WAVE32-NEXT: .cfi_undefined 1617
+; WAVE32-NEXT: .cfi_undefined 1618
+; WAVE32-NEXT: .cfi_undefined 1619
+; WAVE32-NEXT: .cfi_undefined 1620
+; WAVE32-NEXT: .cfi_undefined 1621
+; WAVE32-NEXT: .cfi_undefined 1622
+; WAVE32-NEXT: .cfi_undefined 1623
+
+; WAVE32-NEXT: .cfi_undefined 1632
+; WAVE32-NEXT: .cfi_undefined 1633
+; WAVE32-NEXT: .cfi_undefined 1634
+; WAVE32-NEXT: .cfi_undefined 1635
+; WAVE32-NEXT: .cfi_undefined 1636
+; WAVE32-NEXT: .cfi_undefined 1637
+; WAVE32-NEXT: .cfi_undefined 1638
+; WAVE32-NEXT: .cfi_undefined 1639
+
+; WAVE32-NEXT: .cfi_undefined 1648
+; WAVE32-NEXT: .cfi_undefined 1649
+; WAVE32-NEXT: .cfi_undefined 1650
+; WAVE32-NEXT: .cfi_undefined 1651
+; WAVE32-NEXT: .cfi_undefined 1652
+; WAVE32-NEXT: .cfi_undefined 1653
+; WAVE32-NEXT: .cfi_undefined 1654
+; WAVE32-NEXT: .cfi_undefined 1655
+
+; WAVE32-NEXT: .cfi_undefined 1664
+; WAVE32-NEXT: .cfi_undefined 1665
+; WAVE32-NEXT: .cfi_undefined 1666
+; WAVE32-NEXT: .cfi_undefined 1667
+; WAVE32-NEXT: .cfi_undefined 1668
+; WAVE32-NEXT: .cfi_undefined 1669
+; WAVE32-NEXT: .cfi_undefined 1670
+; WAVE32-NEXT: .cfi_undefined 1671
+
+; WAVE32-NEXT: .cfi_undefined 1680
+; WAVE32-NEXT: .cfi_undefined 1681
+; WAVE32-NEXT: .cfi_undefined 1682
+; WAVE32-NEXT: .cfi_undefined 1683
+; WAVE32-NEXT: .cfi_undefined 1684
+; WAVE32-NEXT: .cfi_undefined 1685
+; WAVE32-NEXT: .cfi_undefined 1686
+; WAVE32-NEXT: .cfi_undefined 1687
+
+; WAVE32-NEXT: .cfi_undefined 1696
+; WAVE32-NEXT: .cfi_undefined 1697
+; WAVE32-NEXT: .cfi_undefined 1698
+; WAVE32-NEXT: .cfi_undefined 1699
+; WAVE32-NEXT: .cfi_undefined 1700
+; WAVE32-NEXT: .cfi_undefined 1701
+; WAVE32-NEXT: .cfi_undefined 1702
+; WAVE32-NEXT: .cfi_undefined 1703
+
+; WAVE32-NEXT: .cfi_undefined 1712
+; WAVE32-NEXT: .cfi_undefined 1713
+; WAVE32-NEXT: .cfi_undefined 1714
+; WAVE32-NEXT: .cfi_undefined 1715
+; WAVE32-NEXT: .cfi_undefined 1716
+; WAVE32-NEXT: .cfi_undefined 1717
+; WAVE32-NEXT: .cfi_undefined 1718
+; WAVE32-NEXT: .cfi_undefined 1719
+
+; WAVE32-NEXT: .cfi_undefined 1728
+; WAVE32-NEXT: .cfi_undefined 1729
+; WAVE32-NEXT: .cfi_undefined 1730
+; WAVE32-NEXT: .cfi_undefined 1731
+; WAVE32-NEXT: .cfi_undefined 1732
+; WAVE32-NEXT: .cfi_undefined 1733
+; WAVE32-NEXT: .cfi_undefined 1734
+; WAVE32-NEXT: .cfi_undefined 1735
+
+; WAVE32-NEXT: .cfi_undefined 1744
+; WAVE32-NEXT: .cfi_undefined 1745
+; WAVE32-NEXT: .cfi_undefined 1746
+; WAVE32-NEXT: .cfi_undefined 1747
+; WAVE32-NEXT: .cfi_undefined 1748
+; WAVE32-NEXT: .cfi_undefined 1749
+; WAVE32-NEXT: .cfi_undefined 1750
+; WAVE32-NEXT: .cfi_undefined 1751
+
+; WAVE32-NEXT: .cfi_undefined 1760
+; WAVE32-NEXT: .cfi_undefined 1761
+; WAVE32-NEXT: .cfi_undefined 1762
+; WAVE32-NEXT: .cfi_undefined 1763
+; WAVE32-NEXT: .cfi_undefined 1764
+; WAVE32-NEXT: .cfi_undefined 1765
+; WAVE32-NEXT: .cfi_undefined 1766
+; WAVE32-NEXT: .cfi_undefined 1767
+
+; WAVE32-NEXT: .cfi_undefined 1776
+; WAVE32-NEXT: .cfi_undefined 1777
+; WAVE32-NEXT: .cfi_undefined 1778
+; WAVE32-NEXT: .cfi_undefined 1779
+; WAVE32-NEXT: .cfi_undefined 1780
+; WAVE32-NEXT: .cfi_undefined 1781
+; WAVE32-NEXT: .cfi_undefined 1782
+; WAVE32-NEXT: .cfi_undefined 1783
+
+
+; SGPR0 = 32
+; CHECK-NEXT: .cfi_undefined 32
+; CHECK-NEXT: .cfi_undefined 33
+; CHECK-NEXT: .cfi_undefined 34
+; CHECK-NEXT: .cfi_undefined 35
+; CHECK-NEXT: .cfi_undefined 36
+; CHECK-NEXT: .cfi_undefined 37
+; CHECK-NEXT: .cfi_undefined 38
+; CHECK-NEXT: .cfi_undefined 39
+; CHECK-NEXT: .cfi_undefined 40
+; CHECK-NEXT: .cfi_undefined 41
+; CHECK-NEXT: .cfi_undefined 42
+; CHECK-NEXT: .cfi_undefined 43
+; CHECK-NEXT: .cfi_undefined 44
+; CHECK-NEXT: .cfi_undefined 45
+; CHECK-NEXT: .cfi_undefined 46
+; CHECK-NEXT: .cfi_undefined 47
+; CHECK-NEXT: .cfi_undefined 48
+; CHECK-NEXT: .cfi_undefined 49
+; CHECK-NEXT: .cfi_undefined 50
+; CHECK-NEXT: .cfi_undefined 51
+; CHECK-NEXT: .cfi_undefined 52
+; CHECK-NEXT: .cfi_undefined 53
+; CHECK-NEXT: .cfi_undefined 54
+; CHECK-NEXT: .cfi_undefined 55
+; CHECK-NEXT: .cfi_undefined 56
+; CHECK-NEXT: .cfi_undefined 57
+; CHECK-NEXT: .cfi_undefined 58
+; CHECK-NEXT: .cfi_undefined 59
+; CHECK-NEXT: .cfi_undefined 60
+; CHECK-NEXT: .cfi_undefined 61
+; CHECK-NEXT: .cfi_undefined 62
+; CHECK-NEXT: .cfi_undefined 63
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; WAVE64: s_or_saveexec_b64 s[4:5], -1
+; WAVE32: s_or_saveexec_b32 s4, -1
+; CHECK-NEXT: buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
+; VGPR40_wave64 = 2600
+; WAVE64-NEXT: .cfi_offset 2600, 0
+; VGPR40_wave32 = 1576
+; WAVE32-NEXT: .cfi_offset 1576, 0
+; CHECK-NOT: .cfi_{{.*}}
+; WAVE64: s_mov_b64 exec, s[4:5]
+; WAVE32: s_mov_b32 exec_lo, s4
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: v_writelane_b32 v40, s33, 2
+
+; DW_CFA_expression [0x10] SGPR33 ULEB128(65)=[0x41]
+;   BLOCK_LENGTH ULEB128(5)=[0x05]
+;     DW_OP_regx [0x90]
+;       VGPR40_wave64 ULEB128(2600)=[0xa8, 0x14]
+;     DW_OP_LLVM_offset_uconst [0xe4]
+;       OFFSET ULEB128(0x08) [0x08]
+; WAVE64-NEXT: .cfi_escape 0x10, 0x41, 0x05, 0x90, 0xa8, 0x14, 0xe4, 0x08
+
+; DW_CFA_expression [0x10] SGPR33 ULEB128(65)=[0x41]
+;   BLOCK_LENGTH ULEB128(5)=[0x05]
+;     DW_OP_regx [0x90]
+;       VGPR40_wave32 ULEB128(1576)=[0xa8, 0x0c]
+;     DW_OP_LLVM_offset_uconst [0xe4]
+;       OFFSET ULEB128(0x08) [0x08]
+; WAVE32-NEXT: .cfi_escape 0x10, 0x41, 0x05, 0x90, 0xa8, 0x0c, 0xe4, 0x08
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: s_mov_b32 s33, s32
+; SGPR33 = 65
+; CHECK-NEXT: .cfi_def_cfa_register 65
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: s_sub_u32 s32, s32,
+; CHECK-NEXT: v_readlane_b32 s33, v40, 2
+; SGPR32 = 64
+; CHECK-NEXT: .cfi_def_cfa_register 64
+
+; CHECK-NOT: .cfi_{{.*}}
+
+; CHECK: .cfi_endproc
+define hidden void @func_call_clobber() #0 {
+entry:
+  call void @ex() #0
+  ret void
+}
+
+; NOTE: Number of VGPRs available to kernel, and in turn number of corresponding CFIs generated,
+; is dependent on waves/WG size. Since the intent here is to check whether we generate the correct
+; CFIs, doing it for any one set of details is sufficient which also makes the test insensitive to
+; changes in those details.
+attributes #0 = { nounwind "amdgpu-waves-per-eu"="1,1" "amdgpu-flat-work-group-size"="128,128" }
+attributes #1 = { nounwind "amdgpu-waves-per-eu"="1,1" "amdgpu-flat-work-group-size"="128,128" "frame-pointer"="all" }
 
 !llvm.dbg.cu = !{!0}
 !llvm.module.flags = !{!2, !3}
diff --git a/llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll b/llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
--- a/llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
+++ b/llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
@@ -99,8 +99,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -128,15 +128,15 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i1@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i1@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX10-NEXT:    v_readlane_b32 s5, v40, 1
@@ -159,11 +159,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_ubyte v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i1_signext@rel32@lo+4
@@ -190,15 +190,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i1_signext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i1_signext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    v_and_b32_e32 v0, 1, v0
 ; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
@@ -225,11 +225,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_ubyte v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i1_zeroext@rel32@lo+4
@@ -256,15 +256,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i1_zeroext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i1_zeroext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    v_and_b32_e32 v0, 1, v0
 ; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
@@ -292,8 +292,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -320,13 +320,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i8@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i8@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -350,11 +350,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_sbyte v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i8_signext@rel32@lo+4
@@ -379,15 +379,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_sbyte v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_sbyte v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i8_signext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i8_signext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -412,11 +412,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_ubyte v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i8_zeroext@rel32@lo+4
@@ -441,15 +441,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_ubyte v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i8_zeroext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i8_zeroext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -475,8 +475,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -503,13 +503,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -533,11 +533,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_ushort v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i16_signext@rel32@lo+4
@@ -562,15 +562,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_ushort v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_ushort v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i16_signext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i16_signext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -595,11 +595,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    global_load_ushort v0, v[0:1], off glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_i16_zeroext@rel32@lo+4
@@ -624,15 +624,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_ushort v0, v[0:1], off glc dlc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_ushort v0, v[0:1], off glc dlc
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i16_zeroext@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i16_zeroext@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -658,8 +658,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 42
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -686,13 +686,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 42
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 42
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i32@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -717,8 +717,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0
@@ -746,11 +746,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i64@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i64@rel32@hi+12
@@ -777,12 +777,12 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v2i64@rel32@lo+4
@@ -807,16 +807,16 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0
-; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2i64@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2i64@rel32@hi+12
 ; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -842,8 +842,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2
@@ -873,12 +873,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2i64@rel32@lo+4
@@ -906,12 +906,12 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v4, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v5, 2
@@ -938,15 +938,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
+; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0
-; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v5, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3i64@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v3i64@rel32@hi+12
@@ -976,12 +976,12 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v4, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v5, 2
@@ -1010,16 +1010,16 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
+; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0
-; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v5, 2
 ; GFX10-NEXT:    v_mov_b32_e32 v6, 3
 ; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v7, 4
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v4i64@rel32@lo+4
@@ -1050,8 +1050,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x4400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -1078,13 +1078,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0x4400
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0x4400
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_f16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_f16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1109,8 +1109,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 4.0
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -1137,13 +1137,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 4.0
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 4.0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_f32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_f32@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1168,8 +1168,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2.0
@@ -1197,11 +1197,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2.0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2f32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2f32@rel32@hi+12
@@ -1229,8 +1229,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2.0
@@ -1259,11 +1259,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2.0
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 4.0
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3f32@rel32@lo+4
@@ -1292,8 +1292,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2.0
@@ -1324,13 +1324,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1.0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2.0
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 4.0
 ; GFX10-NEXT:    v_mov_b32_e32 v3, -1.0
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 0.5
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v5f32@rel32@lo+4
@@ -1359,8 +1359,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0x40100000
@@ -1388,11 +1388,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0x40100000
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_f64@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_f64@rel32@hi+12
@@ -1420,8 +1420,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2.0
@@ -1451,12 +1451,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2.0
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 0x40100000
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2f64@rel32@lo+4
@@ -1485,8 +1485,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2.0
@@ -1518,14 +1518,14 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2.0
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 0x40100000
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v5, 0x40200000
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3f64@rel32@lo+4
@@ -1553,10 +1553,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dword v0, v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dword v0, v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v2i16@rel32@lo+4
@@ -1581,14 +1581,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dword v0, v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dword v0, v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2i16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1613,10 +1613,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v3i16@rel32@lo+4
@@ -1641,14 +1641,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v3i16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1673,10 +1673,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v3f16@rel32@lo+4
@@ -1701,14 +1701,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3f16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v3f16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1734,8 +1734,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x20001
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 3
@@ -1763,11 +1763,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0x20001
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 3
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v3i16@rel32@hi+12
@@ -1795,8 +1795,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x40003c00
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0x4400
@@ -1824,11 +1824,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0x40003c00
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0x4400
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3f16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v3f16@rel32@hi+12
@@ -1855,10 +1855,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v4i16@rel32@lo+4
@@ -1883,14 +1883,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v4i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v4i16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -1916,8 +1916,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0x20001
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 0x40003
@@ -1945,11 +1945,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0x20001
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0x40003
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v4i16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v4i16@rel32@hi+12
@@ -1976,10 +1976,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dword v0, v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dword v0, v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v2f16@rel32@lo+4
@@ -2004,14 +2004,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dword v0, v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dword v0, v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2f16@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2f16@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -2036,10 +2036,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v2i32@rel32@lo+4
@@ -2064,14 +2064,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dwordx2 v[0:1], v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2i32@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -2097,8 +2097,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2
@@ -2126,11 +2126,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v2i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v2i32@rel32@hi+12
@@ -2158,8 +2158,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 3
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 4
@@ -2188,11 +2188,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 4
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 5
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3i32@rel32@lo+4
@@ -2221,8 +2221,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 3
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 4
@@ -2252,12 +2252,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 4
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 5
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 6
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v3i32_i32@rel32@lo+4
@@ -2285,10 +2285,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v4i32@rel32@lo+4
@@ -2313,14 +2313,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    global_load_dwordx4 v[0:3], v[0:1], off
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v4i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_v4i32@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -2346,8 +2346,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2
@@ -2377,12 +2377,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v4i32@rel32@lo+4
@@ -2411,8 +2411,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2
@@ -2443,13 +2443,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 5
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v5i32@rel32@lo+4
@@ -2477,19 +2477,19 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v8, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v8, s[4:5]
 ; GFX9-NEXT:    global_load_dwordx4 v[4:7], v8, s[4:5] offset:16
-; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v8i32@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, external_void_func_v8i32@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -2509,12 +2509,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v8, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v8, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_clause 0x1
@@ -2549,8 +2549,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    v_mov_b32_e32 v1, 2
@@ -2584,16 +2584,16 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 2
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v4, 5
 ; GFX10-NEXT:    v_mov_b32_e32 v5, 6
 ; GFX10-NEXT:    v_mov_b32_e32 v6, 7
 ; GFX10-NEXT:    v_mov_b32_e32 v7, 8
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_v8i32@rel32@lo+4
@@ -2621,21 +2621,21 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v16, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v16, s[4:5]
 ; GFX9-NEXT:    global_load_dwordx4 v[4:7], v16, s[4:5] offset:16
 ; GFX9-NEXT:    global_load_dwordx4 v[8:11], v16, s[4:5] offset:32
 ; GFX9-NEXT:    global_load_dwordx4 v[12:15], v16, s[4:5] offset:48
-; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v16i32@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, external_void_func_v16i32@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -2655,12 +2655,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v16, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v16, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_clause 0x3
@@ -2696,11 +2696,13 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v28, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v28, s[4:5]
 ; GFX9-NEXT:    global_load_dwordx4 v[4:7], v28, s[4:5] offset:16
@@ -2709,12 +2711,11 @@
 ; GFX9-NEXT:    global_load_dwordx4 v[16:19], v28, s[4:5] offset:64
 ; GFX9-NEXT:    global_load_dwordx4 v[20:23], v28, s[4:5] offset:80
 ; GFX9-NEXT:    global_load_dwordx4 v[24:27], v28, s[4:5] offset:96
-; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    s_nop 0
 ; GFX9-NEXT:    global_load_dwordx4 v[28:31], v28, s[4:5] offset:112
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v32i32@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, external_void_func_v32i32@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -2734,12 +2735,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v32, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v32, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_clause 0x7
@@ -2779,11 +2780,13 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v28, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dwordx4 v[0:3], v28, s[4:5]
 ; GFX9-NEXT:    global_load_dwordx4 v[4:7], v28, s[4:5] offset:16
@@ -2792,8 +2795,7 @@
 ; GFX9-NEXT:    global_load_dwordx4 v[16:19], v28, s[4:5] offset:64
 ; GFX9-NEXT:    global_load_dwordx4 v[20:23], v28, s[4:5] offset:80
 ; GFX9-NEXT:    global_load_dwordx4 v[24:27], v28, s[4:5] offset:96
-; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX9-NEXT:    s_nop 0
 ; GFX9-NEXT:    global_load_dwordx4 v[28:31], v28, s[4:5] offset:112
 ; GFX9-NEXT:    s_waitcnt vmcnt(7)
 ; GFX9-NEXT:    global_load_dword v32, v[0:1], off
@@ -2821,12 +2823,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v32, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v32, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    global_load_dword v33, v[0:1], off
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
@@ -2908,17 +2910,17 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v42, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    v_writelane_b32 v42, s30, 0
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
 ; GFX10-NEXT:    buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX10-NEXT:    v_mov_b32_e32 v40, v0
-; GFX10-NEXT:    v_writelane_b32 v42, s30, 0
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 42
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_i32_func_i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_i32_func_i32@rel32@hi+12
-; GFX10-NEXT:    v_mov_b32_e32 v41, v1
 ; GFX10-NEXT:    v_writelane_b32 v42, s31, 1
+; GFX10-NEXT:    v_mov_b32_e32 v41, v1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    global_store_dword v[40:41], v0, off
 ; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
@@ -2947,19 +2949,19 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v2, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v2, s[4:5] offset:4
 ; GFX9-NEXT:    global_load_ubyte v0, v2, s[4:5]
-; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_struct_i8_i32@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, external_void_func_struct_i8_i32@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -2979,12 +2981,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_clause 0x1
@@ -3051,17 +3053,17 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 3
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 8
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s33
-; GFX10-NEXT:    buffer_store_dword v1, off, s[0:3], s33 offset:4
-; GFX10-NEXT:    v_lshrrev_b32_e64 v0, 5, s33
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_byval_struct_i8_i32@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_byval_struct_i8_i32@rel32@hi+12
+; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s33
+; GFX10-NEXT:    buffer_store_dword v1, off, s[0:3], s33 offset:4
+; GFX10-NEXT:    v_lshrrev_b32_e64 v0, 5, s33
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3131,21 +3133,21 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    v_mov_b32_e32 v0, 3
-; GFX10-NEXT:    v_mov_b32_e32 v1, 8
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_mov_b32_e32 v0, 3
+; GFX10-NEXT:    v_mov_b32_e32 v1, 8
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x400
+; GFX10-NEXT:    s_getpc_b64 s[4:5]
+; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_sret_struct_i8_i32_byval_struct_i8_i32@rel32@lo+4
+; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_sret_struct_i8_i32_byval_struct_i8_i32@rel32@hi+12
 ; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s33
 ; GFX10-NEXT:    buffer_store_dword v1, off, s[0:3], s33 offset:4
 ; GFX10-NEXT:    v_lshrrev_b32_e64 v0, 5, s33
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_lshrrev_b32_e64 v1, 5, s33
-; GFX10-NEXT:    s_getpc_b64 s[4:5]
-; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_sret_struct_i8_i32_byval_struct_i8_i32@rel32@lo+4
-; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_sret_struct_i8_i32_byval_struct_i8_i32@rel32@hi+12
-; GFX10-NEXT:    v_add_nc_u32_e32 v0, 8, v0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX10-NEXT:    v_add_nc_u32_e32 v0, 8, v0
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    buffer_load_ubyte v0, off, s[0:3], s33 offset:8
@@ -3164,6 +3166,7 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s6
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-NEXT:    s_setpc_b64 s[4:5]
   %in.val = alloca { i8, i32 }, align 4, addrspace(5)
   %out.val = alloca { i8, i32 }, align 4, addrspace(5)
@@ -3189,15 +3192,15 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
-; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    global_load_dwordx4 v[0:3], v0, s[4:5]
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    global_load_dwordx4 v[0:3], v0, s[4:5]
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_v16i8@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, external_void_func_v16i8@rel32@hi+12
@@ -3239,12 +3242,12 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dwordx4 v[0:3], v0, s[4:5]
@@ -3329,14 +3332,14 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    buffer_load_dword v32, off, s[0:3], s33 offset:12
 ; GFX10-NEXT:    buffer_load_dword v33, off, s[0:3], s33 offset:8
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, byval_align16_f64_arg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, byval_align16_f64_arg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt vmcnt(1)
 ; GFX10-NEXT:    buffer_store_dword v32, off, s[0:3], s32 offset:4
@@ -3368,8 +3371,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -3397,15 +3400,15 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 1
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_i1_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_i1_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX10-NEXT:    buffer_store_byte v0, off, s[0:3], s32
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX10-NEXT:    v_readlane_b32 s5, v40, 1
@@ -3429,8 +3432,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
@@ -3457,13 +3460,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_i8_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_i8_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3488,8 +3491,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
@@ -3516,13 +3519,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_i16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3547,8 +3550,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 42
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
@@ -3575,13 +3578,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_mov_b32 s4, 42
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_mov_b32 s4, 42
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_i32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3606,8 +3609,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX9-NEXT:    s_mov_b32 s5, 0
@@ -3635,11 +3638,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_movk_i32 s4, 0x7b
 ; GFX10-NEXT:    s_mov_b32 s5, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_i64_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_i64_inreg@rel32@hi+12
@@ -3666,11 +3669,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[8:9]
 ; GFX9-NEXT:    s_add_u32 s8, s8, external_void_func_v2i64_inreg@rel32@lo+4
@@ -3695,15 +3698,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_mov_b64 s[4:5], 0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v2i64_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s9, s9, external_void_func_v2i64_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[8:9]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3729,8 +3732,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1
 ; GFX9-NEXT:    s_mov_b32 s5, 2
@@ -3760,12 +3763,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1
 ; GFX10-NEXT:    s_mov_b32 s5, 2
 ; GFX10-NEXT:    s_mov_b32 s6, 3
 ; GFX10-NEXT:    s_mov_b32 s7, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v2i64_inreg@rel32@lo+4
@@ -3793,11 +3796,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s8, 1
 ; GFX9-NEXT:    s_mov_b32 s9, 2
@@ -3824,13 +3827,13 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_mov_b64 s[4:5], 0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX10-NEXT:    s_mov_b32 s8, 1
 ; GFX10-NEXT:    s_mov_b32 s9, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[10:11]
 ; GFX10-NEXT:    s_add_u32 s10, s10, external_void_func_v3i64_inreg@rel32@lo+4
@@ -3861,11 +3864,11 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
+; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
-; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s8, 1
 ; GFX9-NEXT:    s_mov_b32 s9, 2
@@ -3894,15 +3897,15 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_mov_b64 s[4:5], 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_mov_b64 s[4:5], 0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX10-NEXT:    s_mov_b32 s8, 1
 ; GFX10-NEXT:    s_mov_b32 s9, 2
 ; GFX10-NEXT:    s_mov_b32 s10, 3
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s11, 4
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[12:13]
 ; GFX10-NEXT:    s_add_u32 s12, s12, external_void_func_v4i64_inreg@rel32@lo+4
@@ -3933,8 +3936,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_movk_i32 s4, 0x4400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
@@ -3961,13 +3964,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_movk_i32 s4, 0x4400
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_movk_i32 s4, 0x4400
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_f16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_f16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -3992,8 +3995,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 4.0
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
@@ -4020,13 +4023,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_mov_b32 s4, 4.0
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_mov_b32 s4, 4.0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_f32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_f32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4051,8 +4054,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1.0
 ; GFX9-NEXT:    s_mov_b32 s5, 2.0
@@ -4080,11 +4083,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1.0
 ; GFX10-NEXT:    s_mov_b32 s5, 2.0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v2f32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v2f32_inreg@rel32@hi+12
@@ -4112,8 +4115,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1.0
 ; GFX9-NEXT:    s_mov_b32 s5, 2.0
@@ -4142,11 +4145,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1.0
 ; GFX10-NEXT:    s_mov_b32 s5, 2.0
 ; GFX10-NEXT:    s_mov_b32 s6, 4.0
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v3f32_inreg@rel32@lo+4
@@ -4175,8 +4178,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1.0
 ; GFX9-NEXT:    s_mov_b32 s5, 2.0
@@ -4207,13 +4210,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1.0
 ; GFX10-NEXT:    s_mov_b32 s5, 2.0
 ; GFX10-NEXT:    s_mov_b32 s6, 4.0
 ; GFX10-NEXT:    s_mov_b32 s7, -1.0
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s8, 0.5
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[10:11]
 ; GFX10-NEXT:    s_add_u32 s10, s10, external_void_func_v5f32_inreg@rel32@lo+4
@@ -4242,8 +4245,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0
 ; GFX9-NEXT:    s_mov_b32 s5, 0x40100000
@@ -4271,11 +4274,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0
 ; GFX10-NEXT:    s_mov_b32 s5, 0x40100000
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_f64_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_f64_inreg@rel32@hi+12
@@ -4303,8 +4306,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0
 ; GFX9-NEXT:    s_mov_b32 s5, 2.0
@@ -4334,12 +4337,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0
 ; GFX10-NEXT:    s_mov_b32 s5, 2.0
 ; GFX10-NEXT:    s_mov_b32 s6, 0
 ; GFX10-NEXT:    s_mov_b32 s7, 0x40100000
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v2f64_inreg@rel32@lo+4
@@ -4368,8 +4371,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0
 ; GFX9-NEXT:    s_mov_b32 s5, 2.0
@@ -4401,14 +4404,14 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0
 ; GFX10-NEXT:    s_mov_b32 s5, 2.0
 ; GFX10-NEXT:    s_mov_b32 s6, 0
 ; GFX10-NEXT:    s_mov_b32 s7, 0x40100000
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s8, 0
 ; GFX10-NEXT:    s_mov_b32 s9, 0x40200000
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[10:11]
 ; GFX10-NEXT:    s_add_u32 s10, s10, external_void_func_v3f64_inreg@rel32@lo+4
@@ -4436,10 +4439,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dword s4, s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dword s4, s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v2i16_inreg@rel32@lo+4
@@ -4464,14 +4467,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dword s4, s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dword s4, s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v2i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v2i16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4496,10 +4499,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v3i16_inreg@rel32@lo+4
@@ -4524,14 +4527,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v3i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v3i16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4556,10 +4559,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v3f16_inreg@rel32@lo+4
@@ -4584,14 +4587,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v3f16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v3f16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4617,8 +4620,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0x20001
 ; GFX9-NEXT:    s_mov_b32 s5, 3
@@ -4646,11 +4649,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0x20001
 ; GFX10-NEXT:    s_mov_b32 s5, 3
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v3i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v3i16_inreg@rel32@hi+12
@@ -4678,8 +4681,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0x40003c00
 ; GFX9-NEXT:    s_movk_i32 s5, 0x4400
@@ -4707,11 +4710,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0x40003c00
 ; GFX10-NEXT:    s_movk_i32 s5, 0x4400
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v3f16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v3f16_inreg@rel32@hi+12
@@ -4738,10 +4741,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v4i16_inreg@rel32@lo+4
@@ -4766,14 +4769,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v4i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v4i16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4799,8 +4802,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 0x20001
 ; GFX9-NEXT:    s_mov_b32 s5, 0x40003
@@ -4828,11 +4831,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 0x20001
 ; GFX10-NEXT:    s_mov_b32 s5, 0x40003
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v4i16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v4i16_inreg@rel32@hi+12
@@ -4859,10 +4862,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dword s4, s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dword s4, s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v2f16_inreg@rel32@lo+4
@@ -4887,14 +4890,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dword s4, s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dword s4, s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v2f16_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v2f16_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4919,10 +4922,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[6:7]
 ; GFX9-NEXT:    s_add_u32 s6, s6, external_void_func_v2i32_inreg@rel32@lo+4
@@ -4947,14 +4950,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v2i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v2i32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[6:7]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -4980,8 +4983,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1
 ; GFX9-NEXT:    s_mov_b32 s5, 2
@@ -5009,11 +5012,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1
 ; GFX10-NEXT:    s_mov_b32 s5, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[6:7]
 ; GFX10-NEXT:    s_add_u32 s6, s6, external_void_func_v2i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s7, s7, external_void_func_v2i32_inreg@rel32@hi+12
@@ -5041,8 +5044,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 3
 ; GFX9-NEXT:    s_mov_b32 s5, 4
@@ -5071,11 +5074,11 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 3
 ; GFX10-NEXT:    s_mov_b32 s5, 4
 ; GFX10-NEXT:    s_mov_b32 s6, 5
-; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v3i32_inreg@rel32@lo+4
@@ -5104,8 +5107,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 3
 ; GFX9-NEXT:    s_mov_b32 s5, 4
@@ -5135,12 +5138,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 3
 ; GFX10-NEXT:    s_mov_b32 s5, 4
 ; GFX10-NEXT:    s_mov_b32 s6, 5
 ; GFX10-NEXT:    s_mov_b32 s7, 6
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v3i32_i32_inreg@rel32@lo+4
@@ -5168,10 +5171,10 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[8:9]
 ; GFX9-NEXT:    s_add_u32 s8, s8, external_void_func_v4i32_inreg@rel32@lo+4
@@ -5196,14 +5199,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v4i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s9, s9, external_void_func_v4i32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[8:9]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -5229,8 +5232,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1
 ; GFX9-NEXT:    s_mov_b32 s5, 2
@@ -5260,12 +5263,12 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1
 ; GFX10-NEXT:    s_mov_b32 s5, 2
 ; GFX10-NEXT:    s_mov_b32 s6, 3
 ; GFX10-NEXT:    s_mov_b32 s7, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[8:9]
 ; GFX10-NEXT:    s_add_u32 s8, s8, external_void_func_v4i32_inreg@rel32@lo+4
@@ -5294,8 +5297,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1
 ; GFX9-NEXT:    s_mov_b32 s5, 2
@@ -5326,13 +5329,13 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1
 ; GFX10-NEXT:    s_mov_b32 s5, 2
 ; GFX10-NEXT:    s_mov_b32 s6, 3
 ; GFX10-NEXT:    s_mov_b32 s7, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s8, 5
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[10:11]
 ; GFX10-NEXT:    s_add_u32 s10, s10, external_void_func_v5i32_inreg@rel32@lo+4
@@ -5360,17 +5363,17 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
-; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    s_load_dwordx8 s[4:11], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_getpc_b64 s[12:13]
 ; GFX9-NEXT:    s_add_u32 s12, s12, external_void_func_v8i32_inreg@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s13, s13, external_void_func_v8i32_inreg@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    s_load_dwordx8 s[4:11], s[4:5], 0x0
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[12:13]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -5390,14 +5393,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[12:13]
 ; GFX10-NEXT:    s_add_u32 s12, s12, external_void_func_v8i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s13, s13, external_void_func_v8i32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_load_dwordx8 s[4:11], s[4:5], 0x0
@@ -5426,8 +5429,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_mov_b32 s4, 1
 ; GFX9-NEXT:    s_mov_b32 s5, 2
@@ -5461,16 +5464,16 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s4, 1
 ; GFX10-NEXT:    s_mov_b32 s5, 2
 ; GFX10-NEXT:    s_mov_b32 s6, 3
 ; GFX10-NEXT:    s_mov_b32 s7, 4
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_mov_b32 s8, 5
 ; GFX10-NEXT:    s_mov_b32 s9, 6
 ; GFX10-NEXT:    s_mov_b32 s10, 7
 ; GFX10-NEXT:    s_mov_b32 s11, 8
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[12:13]
 ; GFX10-NEXT:    s_add_u32 s12, s12, external_void_func_v8i32_inreg@rel32@lo+4
@@ -5498,17 +5501,17 @@
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
-; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    s_load_dwordx16 s[4:19], s[4:5], 0x0
+; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX9-NEXT:    s_getpc_b64 s[20:21]
 ; GFX9-NEXT:    s_add_u32 s20, s20, external_void_func_v16i32_inreg@rel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s21, s21, external_void_func_v16i32_inreg@rel32@hi+12
-; GFX9-NEXT:    v_writelane_b32 v40, s31, 1
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    s_load_dwordx16 s[4:19], s[4:5], 0x0
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[20:21]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 0
 ; GFX9-NEXT:    v_readlane_b32 s5, v40, 1
@@ -5528,14 +5531,14 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
-; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[20:21]
 ; GFX10-NEXT:    s_add_u32 s20, s20, external_void_func_v16i32_inreg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s21, s21, external_void_func_v16i32_inreg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_load_dwordx16 s[4:19], s[4:5], 0x0
@@ -5564,6 +5567,7 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 18
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s36, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s37, 1
 ; GFX9-NEXT:    v_writelane_b32 v40, s38, 2
@@ -5584,10 +5588,12 @@
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    s_load_dwordx16 s[4:19], s[20:21], 0x0
 ; GFX9-NEXT:    s_load_dwordx16 s[36:51], s[20:21], 0x40
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 16
 ; GFX9-NEXT:    v_writelane_b32 v40, s31, 17
+; GFX9-NEXT:    s_getpc_b64 s[30:31]
+; GFX9-NEXT:    s_add_u32 s30, s30, external_void_func_v32i32_inreg@rel32@lo+4
+; GFX9-NEXT:    s_addc_u32 s31, s31, external_void_func_v32i32_inreg@rel32@hi+12
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s46
 ; GFX9-NEXT:    v_mov_b32_e32 v1, s47
@@ -5610,9 +5616,6 @@
 ; GFX9-NEXT:    s_mov_b32 s27, s43
 ; GFX9-NEXT:    s_mov_b32 s28, s44
 ; GFX9-NEXT:    s_mov_b32 s29, s45
-; GFX9-NEXT:    s_getpc_b64 s[30:31]
-; GFX9-NEXT:    s_add_u32 s30, s30, external_void_func_v32i32_inreg@rel32@lo+4
-; GFX9-NEXT:    s_addc_u32 s31, s31, external_void_func_v32i32_inreg@rel32@hi+12
 ; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], s32 offset:20
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[30:31]
 ; GFX9-NEXT:    v_readlane_b32 s4, v40, 16
@@ -5650,10 +5653,10 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 18
-; GFX10-NEXT:    s_load_dwordx2 s[20:21], s[4:5], 0x0
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s36, 0
+; GFX10-NEXT:    s_load_dwordx2 s[20:21], s[4:5], 0x0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s37, 1
 ; GFX10-NEXT:    v_writelane_b32 v40, s38, 2
 ; GFX10-NEXT:    v_writelane_b32 v40, s39, 3
@@ -5742,6 +5745,7 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 18
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s36, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s37, 1
 ; GFX9-NEXT:    v_writelane_b32 v40, s38, 2
@@ -5763,10 +5767,10 @@
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    s_load_dwordx16 s[4:19], s[20:21], 0x0
 ; GFX9-NEXT:    s_load_dwordx16 s[36:51], s[20:21], 0x40
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s22
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], s32 offset:24
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 16
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s46
 ; GFX9-NEXT:    v_mov_b32_e32 v1, s47
@@ -5777,7 +5781,6 @@
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s49
 ; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], s32 offset:12
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s50
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 16
 ; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], s32 offset:16
 ; GFX9-NEXT:    v_mov_b32_e32 v0, s51
 ; GFX9-NEXT:    s_mov_b32 s20, s36
@@ -5831,18 +5834,18 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 18
+; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s36, 0
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    s_load_dwordx2 s[20:21], s[4:5], 0x0
 ; GFX10-NEXT:    s_load_dword s22, s[4:5], 0x0
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    v_writelane_b32 v40, s36, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s37, 1
 ; GFX10-NEXT:    v_writelane_b32 v40, s38, 2
 ; GFX10-NEXT:    v_writelane_b32 v40, s39, 3
+; GFX10-NEXT:    v_writelane_b32 v40, s40, 4
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    v_mov_b32_e32 v0, s22
-; GFX10-NEXT:    v_writelane_b32 v40, s40, 4
 ; GFX10-NEXT:    v_writelane_b32 v40, s41, 5
 ; GFX10-NEXT:    v_writelane_b32 v40, s42, 6
 ; GFX10-NEXT:    v_writelane_b32 v40, s43, 7
@@ -5962,14 +5965,14 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    buffer_load_dword v32, off, s[0:3], s33
 ; GFX10-NEXT:    buffer_load_dword v33, off, s[0:3], s33 offset:4
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, stack_passed_f64_arg@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, stack_passed_f64_arg@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_waitcnt vmcnt(1)
 ; GFX10-NEXT:    buffer_store_dword v32, off, s[0:3], s32
@@ -6066,10 +6069,10 @@
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 12
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 13
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 14
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 15
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
@@ -6223,11 +6226,11 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
+; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 8
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 9
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 10
-; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 14
 ; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], s32
@@ -6385,11 +6388,11 @@
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
+; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
+; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    v_mov_b32_e32 v0, 0x41000000
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0x41100000
 ; GFX10-NEXT:    v_mov_b32_e32 v2, 0x41200000
-; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX10-NEXT:    s_mov_b32 s33, s32
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_mov_b32_e32 v3, 0x41600000
 ; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], s32
diff --git a/llvm/test/CodeGen/AMDGPU/gfx-callable-preserved-registers.ll b/llvm/test/CodeGen/AMDGPU/gfx-callable-preserved-registers.ll
--- a/llvm/test/CodeGen/AMDGPU/gfx-callable-preserved-registers.ll
+++ b/llvm/test/CodeGen/AMDGPU/gfx-callable-preserved-registers.ll
@@ -12,10 +12,10 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 4
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s35, 1
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 2
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[34:35]
 ; GFX9-NEXT:    s_add_u32 s34, s34, external_void_func_void@rel32@lo+4
@@ -47,8 +47,8 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 4
 ; GFX10-NEXT:    s_mov_b32 s33, s32
-; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s34, 0
+; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    v_writelane_b32 v40, s35, 1
 ; GFX10-NEXT:    s_getpc_b64 s[34:35]
 ; GFX10-NEXT:    s_add_u32 s34, s34, external_void_func_void@rel32@lo+4
@@ -108,9 +108,9 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 3
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 1
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    v_writelane_b32 v40, s31, 2
 ; GFX9-NEXT:    ;;#ASMSTART
@@ -146,11 +146,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 3
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s30, 1
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 2
 ; GFX10-NEXT:    ;;#ASMSTART
@@ -187,8 +187,8 @@
 ; GFX9-NEXT:    buffer_store_dword v41, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v41, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX9-NEXT:    ;;#ASMSTART
@@ -225,17 +225,17 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v41, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def v31
 ; GFX10-NEXT:    ;;#ASMEND
-; GFX10-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_mov_b32_e32 v40, v31
 ; GFX10-NEXT:    v_writelane_b32 v41, s31, 1
+; GFX10-NEXT:    v_mov_b32_e32 v40, v31
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_mov_b32_e32 v31, v40
 ; GFX10-NEXT:    ;;#ASMSTART
@@ -303,11 +303,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 3
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s33, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s33, 0
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def s33
 ; GFX10-NEXT:    ;;#ASMEND
@@ -342,9 +342,9 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 3
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 1
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
@@ -378,11 +378,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 3
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s34, 0
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def s34
 ; GFX10-NEXT:    ;;#ASMEND
@@ -417,8 +417,8 @@
 ; GFX9-NEXT:    buffer_store_dword v41, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v41, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
@@ -453,12 +453,12 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v41, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v41, s30, 0
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def v40
 ; GFX10-NEXT:    ;;#ASMEND
@@ -576,8 +576,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, void_func_void_clobber_s33@rel32@lo+4
@@ -604,11 +604,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, void_func_void_clobber_s33@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, void_func_void_clobber_s33@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -633,8 +633,8 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 2
-; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, void_func_void_clobber_s34@rel32@lo+4
@@ -661,11 +661,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 2
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, void_func_void_clobber_s34@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, void_func_void_clobber_s34@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s30, 0
 ; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    v_readlane_b32 s4, v40, 0
@@ -690,9 +690,9 @@
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v40, s33, 3
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v40, s40, 0
 ; GFX9-NEXT:    v_writelane_b32 v40, s30, 1
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
@@ -726,11 +726,11 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v40, s33, 3
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v40, s40, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
 ; GFX10-NEXT:    s_getpc_b64 s[4:5]
 ; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
-; GFX10-NEXT:    v_writelane_b32 v40, s40, 0
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def s40
 ; GFX10-NEXT:    ;;#ASMEND
@@ -765,9 +765,9 @@
 ; GFX9-NEXT:    buffer_store_dword v41, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
 ; GFX9-NEXT:    v_writelane_b32 v41, s33, 3
+; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    v_writelane_b32 v41, s40, 0
 ; GFX9-NEXT:    v_writelane_b32 v41, s30, 1
-; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x400
 ; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GFX9-NEXT:    ;;#ASMSTART
@@ -810,20 +810,20 @@
 ; GFX10-NEXT:    s_mov_b32 exec_lo, s4
 ; GFX10-NEXT:    v_writelane_b32 v41, s33, 3
 ; GFX10-NEXT:    s_mov_b32 s33, s32
+; GFX10-NEXT:    v_writelane_b32 v41, s40, 0
 ; GFX10-NEXT:    s_add_u32 s32, s32, 0x200
-; GFX10-NEXT:    s_getpc_b64 s[4:5]
-; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
-; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
 ; GFX10-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
-; GFX10-NEXT:    v_writelane_b32 v41, s40, 0
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def s40
 ; GFX10-NEXT:    ;;#ASMEND
 ; GFX10-NEXT:    ;;#ASMSTART
 ; GFX10-NEXT:    ; def v32
 ; GFX10-NEXT:    ;;#ASMEND
-; GFX10-NEXT:    v_mov_b32_e32 v40, v32
 ; GFX10-NEXT:    v_writelane_b32 v41, s30, 1
+; GFX10-NEXT:    s_getpc_b64 s[4:5]
+; GFX10-NEXT:    s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
+; GFX10-NEXT:    s_addc_u32 s5, s5, external_void_func_void@rel32@hi+12
+; GFX10-NEXT:    v_mov_b32_e32 v40, v32
 ; GFX10-NEXT:    v_writelane_b32 v41, s31, 2
 ; GFX10-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GFX10-NEXT:    ;;#ASMSTART
diff --git a/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll b/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
--- a/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
+++ b/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
@@ -147,6 +147,7 @@
 ; MUBUF-NEXT:    v_addc_co_u32_e32 v3, vcc, v5, v7, vcc
 ; MUBUF-NEXT:    global_store_dwordx2 v[0:1], v[2:3], off
 ; MUBUF-NEXT:    s_waitcnt vmcnt(0)
+; MUBUF-NEXT:    s_waitcnt vmcnt(0)
 ; MUBUF-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; FLATSCR-LABEL: func_local_stack_offset_uses_sp:
@@ -184,6 +185,7 @@
 ; FLATSCR-NEXT:    v_addc_co_u32_e32 v3, vcc, v3, v5, vcc
 ; FLATSCR-NEXT:    global_store_dwordx2 v[0:1], v[2:3], off
 ; FLATSCR-NEXT:    s_waitcnt vmcnt(0)
+; FLATSCR-NEXT:    s_waitcnt vmcnt(0)
 ; FLATSCR-NEXT:    s_setpc_b64 s[30:31]
 entry:
   %pin.low = alloca i32, align 8192, addrspace(5)
diff --git a/llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll b/llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll
--- a/llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll
+++ b/llvm/test/CodeGen/AMDGPU/non-entry-alloca.ll
@@ -220,8 +220,8 @@
 ; MUBUF:       ; %bb.0: ; %entry
 ; MUBUF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; MUBUF-NEXT:    s_mov_b32 s7, s33
-; MUBUF-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; MUBUF-NEXT:    s_mov_b32 s33, s32
+; MUBUF-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; MUBUF-NEXT:    s_add_u32 s32, s32, 0x400
 ; MUBUF-NEXT:    s_and_saveexec_b64 s[4:5], vcc
 ; MUBUF-NEXT:    s_cbranch_execz BB2_3
@@ -256,8 +256,8 @@
 ; FLATSCR:       ; %bb.0: ; %entry
 ; FLATSCR-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; FLATSCR-NEXT:    s_mov_b32 s5, s33
-; FLATSCR-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; FLATSCR-NEXT:    s_mov_b32 s33, s32
+; FLATSCR-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v2
 ; FLATSCR-NEXT:    s_add_u32 s32, s32, 16
 ; FLATSCR-NEXT:    s_and_saveexec_b64 s[0:1], vcc
 ; FLATSCR-NEXT:    s_cbranch_execz BB2_3
diff --git a/llvm/test/CodeGen/AMDGPU/split-arg-dbg-value.ll b/llvm/test/CodeGen/AMDGPU/split-arg-dbg-value.ll
--- a/llvm/test/CodeGen/AMDGPU/split-arg-dbg-value.ll
+++ b/llvm/test/CodeGen/AMDGPU/split-arg-dbg-value.ll
@@ -13,6 +13,8 @@
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp0:
 ; GCN-NEXT:    .loc 0 4 5 prologue_end ; /tmp/dbg.cl:4:5
@@ -35,6 +37,12 @@
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f32_multi_arg:arg0 <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
+; GCN-NEXT:    .cfi_undefined 2560
+; GCN-NEXT:    .cfi_undefined 2561
+; GCN-NEXT:    .cfi_undefined 2562
+; GCN-NEXT:    .cfi_undefined 2563
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp2:
 ; GCN-NEXT:    .loc 0 8 17 prologue_end ; /tmp/dbg.cl:8:17
@@ -65,6 +73,8 @@
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f16_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v4f16_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp8:
 ; GCN-NEXT:    .loc 0 12 5 prologue_end ; /tmp/dbg.cl:12:5
@@ -83,6 +93,8 @@
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp10:
 ; GCN-NEXT:    .loc 0 16 5 prologue_end ; /tmp/dbg.cl:16:5
@@ -103,6 +115,8 @@
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 64 32] $vgpr2
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_v2f64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp12:
 ; GCN-NEXT:    .loc 0 20 5 prologue_end ; /tmp/dbg.cl:20:5
@@ -121,6 +135,8 @@
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_i64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_i64_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp14:
 ; GCN-NEXT:    .loc 0 24 5 prologue_end ; /tmp/dbg.cl:24:5
@@ -139,6 +155,8 @@
 ; GCN-NEXT:  ; %bb.0:
 ; GCN-NEXT:    ;DEBUG_VALUE: split_ptr_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 32 32] $vgpr1
 ; GCN-NEXT:    ;DEBUG_VALUE: split_ptr_arg:arg <- [DW_OP_constu 1, DW_OP_swap, DW_OP_xderef, DW_OP_LLVM_fragment 0 32] $vgpr0
+; GCN-NEXT:    .cfi_llvm_def_aspace_cfa 64, 0, 6
+; GCN-NEXT:    .cfi_escape 0x10, 0x10, 0x08, 0x90, 0x3e, 0x93, 0x04, 0x90, 0x3f, 0x93, 0x04
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:  .Ltmp16:
 ; GCN-NEXT:    .loc 0 28 5 prologue_end ; /tmp/dbg.cl:28:5
diff --git a/llvm/test/CodeGen/AMDGPU/stack-realign.ll b/llvm/test/CodeGen/AMDGPU/stack-realign.ll
--- a/llvm/test/CodeGen/AMDGPU/stack-realign.ll
+++ b/llvm/test/CodeGen/AMDGPU/stack-realign.ll
@@ -125,13 +125,13 @@
 
 ; GCN-LABEL: {{^}}default_realign_align128:
 ; GCN: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
-; GCN-NEXT: s_add_u32 s33, s32, 0x1fc0
-; GCN-NEXT: s_and_b32 s33, s33, 0xffffe000
-; GCN-NEXT: s_add_u32 s32, s32, 0x4000
-; GCN-NOT: s33
+; GCN-NEXT: s_add_u32 [[TMP:s[0-9]+]], s32, 0x1fc0
+; GCN-NEXT: s_and_b32 s33, [[TMP]], 0xffffe000
+; GCN: s_add_u32 s32, s32, 0x4000
 ; GCN: buffer_store_dword v0, off, s[0:3], s33{{$}}
 ; GCN: s_sub_u32 s32, s32, 0x4000
 ; GCN: s_mov_b32 s33, [[FP_COPY]]
+; GCN-NOT: s33
 define void @default_realign_align128(i32 %idx) #0 {
   %alloca.align = alloca i32, align 128, addrspace(5)
   store volatile i32 9, i32 addrspace(5)* %alloca.align, align 128
@@ -194,10 +194,10 @@
 
 ; GCN-LABEL: needs_align1024_stack_args_used_inside_loop:
 ; GCN: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
-; GCN-NEXT: s_add_u32 s33, s32, 0xffc0
 ; GCN-NEXT: s_mov_b32 [[BP_COPY:s[0-9]+]], s34
+; GCN-NEXT: s_add_u32 [[SCRATCH_REG:s[0-9]+]], s32, 0xffc0
+; GCN-NEXT: s_and_b32 s33, [[SCRATCH_REG]], 0xffff0000
 ; GCN-NEXT: s_mov_b32 s34, s32
-; GCN-NEXT: s_and_b32 s33, s33, 0xffff0000
 ; GCN-NEXT: v_mov_b32_e32 v{{[0-9]+}}, 0
 ; GCN-NEXT: v_lshrrev_b32_e64 [[VGPR_REG:v[0-9]+]], 6, s34
 ; GCN: s_add_u32 s32, s32, 0x30000
@@ -234,9 +234,8 @@
 ; GCN-LABEL: no_free_scratch_sgpr_for_bp_copy:
 ; GCN: ; %bb.0:
 ; GCN: v_writelane_b32 [[VGPR_REG:v[0-9]+]], s34, 0
-; GCN-NEXT: s_mov_b32 s34, s32
+; GCN: s_mov_b32 s34, s32
 ; GCN-NEXT: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s34
-; GCN: v_readlane_b32 s34, [[VGPR_REG:v[0-9]+]], 0
 ; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s33 offset:128
 ; GCN-NEXT: s_waitcnt vmcnt(0)
 ; GCN-NEXT: ;;#ASMSTART
diff --git a/llvm/test/DebugInfo/AMDGPU/cfi.ll b/llvm/test/DebugInfo/AMDGPU/cfi.ll
--- a/llvm/test/DebugInfo/AMDGPU/cfi.ll
+++ b/llvm/test/DebugInfo/AMDGPU/cfi.ll
@@ -21,6 +21,11 @@
 ; CHECK-EMPTY:
 ; CHECK-NEXT: 00000020 {{[0-9]+}} 00000000 FDE cie=00000000 pc=00000000...{{[0-9]+}}
 ; CHECK-NEXT: Format:       DWARF32
+; CHECK-NEXT: DW_CFA_LLVM_def_aspace_cfa: SGPR32_LO16 +0 as6
+; CHECK-NEXT: DW_CFA_expression: PC_REG DW_OP_regx SGPR30_LO16, DW_OP_piece 0x4, DW_OP_regx SGPR31_LO16, DW_OP_piece 0x4
+; CHECK-NEXT: DW_CFA_nop
+; CHECK-EMPTY:
+; CHECK-NEXT: 0x0: CFA=SGPR32_LO16 as6: PC_REG=[DW_OP_regx SGPR30_LO16, DW_OP_piece 0x4, DW_OP_regx SGPR31_LO16, DW_OP_piece 0x4]
 ; CHECK-EMPTY:
 ; CHECK: .eh_frame contents:
 ; CHECK-NOT: CIE