Index: llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
+++ llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
@@ -832,9 +832,9 @@
   }
 }
 
-// Convert the V_ADDC_U32_e64 into V_ADDC_U32_e32, and
-// V_ADD_CO_U32_e64 into V_ADD_CO_U32_e32. This allows isConvertibleToSDWA
-// to perform its transformation on V_ADD_CO_U32_e32 into V_ADD_CO_U32_sdwa.
+// Convert the V_ADD_CO_U32_e64 into V_ADD_CO_U32_e32. This allows
+// isConvertibleToSDWA to perform its transformation on V_ADD_CO_U32_e32 into
+// V_ADD_CO_U32_sdwa.
 //
 // We are transforming from a VOP3 into a VOP2 form of the instruction.
 //   %19:vgpr_32 = V_AND_B32_e32 255,
@@ -848,8 +848,8 @@
 //   %47:vgpr_32 = V_ADD_CO_U32_sdwa
 //       0, %26.sub0:vreg_64, 0, killed %16:vgpr_32, 0, 6, 0, 6, 0,
 //       implicit-def $vcc, implicit $exec
-//  %48:vgpr_32 = V_ADDC_U32_e32
-//       0, %26.sub1:vreg_64, implicit-def $vcc, implicit $vcc, implicit $exec
+//  %48:vgpr_32, dead %50:sreg_64_xexec = V_ADDC_U32_e64
+//       %26.sub1:vreg_64, %54:vgpr_32, killed $vcc, implicit $exec
 void SIPeepholeSDWA::pseudoOpConvertToVOP2(MachineInstr &MI,
                                            const GCNSubtarget &ST) const {
   int Opc = MI.getOpcode();
@@ -868,10 +868,7 @@
   if (!NextOp)
     return;
   MachineInstr &MISucc = *NextOp->getParent();
-  // Can the successor be shrunk?
-  if (!TII->canShrink(MISucc, *MRI))
-    return;
-  int SuccOpc = AMDGPU::getVOPe32(MISucc.getOpcode());
+
   // Make sure the carry in/out are subsequently unused.
   MachineOperand *CarryIn = TII->getNamedOperand(MISucc, AMDGPU::OpName::src2);
   if (!CarryIn)
@@ -893,7 +890,6 @@
       return;
   }
 
-  // Make the two new e32 instruction variants.
   // Replace MI with V_{SUB|ADD}_I32_e32
   BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(Opc))
     .add(*TII->getNamedOperand(MI, AMDGPU::OpName::vdst))
@@ -903,14 +899,9 @@
 
   MI.eraseFromParent();
 
-  // Replace MISucc with V_{SUBB|ADDC}_U32_e32
-  BuildMI(MBB, MISucc, MISucc.getDebugLoc(), TII->get(SuccOpc))
-    .add(*TII->getNamedOperand(MISucc, AMDGPU::OpName::vdst))
-    .add(*TII->getNamedOperand(MISucc, AMDGPU::OpName::src0))
-    .add(*TII->getNamedOperand(MISucc, AMDGPU::OpName::src1))
-    .setMIFlags(MISucc.getFlags());
+  // Since the carry outpur of MI is now VCC, update it's use in MISucc
 
-  MISucc.eraseFromParent();
+  MISucc.substituteRegister(CarryIn->getReg(), AMDGPU::VCC, 0, *TRI);
 }
 
 bool SIPeepholeSDWA::isConvertibleToSDWA(MachineInstr &MI,
Index: llvm/test/CodeGen/AMDGPU/sdwa-ops.mir
===================================================================
--- llvm/test/CodeGen/AMDGPU/sdwa-ops.mir
+++ llvm/test/CodeGen/AMDGPU/sdwa-ops.mir
@@ -4,11 +4,11 @@
 # test for 3 consecutive _sdwa's
 # GFX9-LABEL: name:            test1_add_co_sdwa
 # GFX9: = nsw V_ADD_CO_U32_sdwa
-# GFX9-NEXT: = nuw V_ADDC_U32_e32
+# GFX9-NEXT: = nuw V_ADDC_U32_e64
 # GFX9: V_ADD_CO_U32_sdwa
-# GFX9-NEXT: V_ADDC_U32_e32
+# GFX9-NEXT: V_ADDC_U32_e64
 # GFX9: V_ADD_CO_U32_sdwa
-# GFX9-NEXT: V_ADDC_U32_e32
+# GFX9-NEXT: V_ADDC_U32_e64
 ---
 name:            test1_add_co_sdwa
 tracksRegLiveness: true
@@ -48,7 +48,7 @@
 # test for VCC interference on sdwa, should generate 1 xform only
 # GFX9-LABEL: name:            test2_add_co_sdwa
 # GFX9: V_ADD_CO_U32_sdwa
-# GFX9: V_ADDC_U32_e32
+# GFX9: V_ADDC_U32_e64
 # GFX9-NOT: V_ADD_CO_U32_sdwa
 # GFX9-NOT: V_ADDC_U32_e32
 ---
@@ -151,7 +151,7 @@
 # test for simple example, should generate sdwa
 # GFX9-LABEL: name:            test5_add_co_sdwa
 # GFX9: V_ADD_CO_U32_sdwa
-# GFX9: V_ADDC_U32_e32
+# GFX9: V_ADDC_U32_e64
 ---
 name:            test5_add_co_sdwa
 tracksRegLiveness: true
@@ -388,4 +388,3 @@
     %64:vgpr_32, %66:sreg_64_xexec = V_ADDC_U32_e64 %30.sub1, %0, %65, 0, implicit $exec
     %62:vreg_64 = REG_SEQUENCE %63, %subreg.sub0, %64, %subreg.sub1
     GLOBAL_STORE_DWORDX2_SADDR %31.sub0, %62, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
-
Index: llvm/test/CodeGen/AMDGPU/v_add_u64_pseudo_sdwa.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/v_add_u64_pseudo_sdwa.ll
+++ llvm/test/CodeGen/AMDGPU/v_add_u64_pseudo_sdwa.ll
@@ -5,8 +5,7 @@
 ; GFX9:       ; %bb.0: ; %bb
 ; GFX9-NEXT:    v_add_u32_e32 v1, 10, v0
 ; GFX9-NEXT:    v_add_u32_e32 v0, 20, v0
-; GFX9-NEXT:    v_and_b32_e32 v0, 0xff, v0
-; GFX9-NEXT:    v_add_co_u32_e32 v0, vcc, v1, v0
+; GFX9-NEXT:    v_add_co_u32_sdwa v0, vcc, v1, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
 ; GFX9-NEXT:    v_addc_co_u32_e64 v1, s[0:1], 0, 0, vcc
 ; GFX9-NEXT:    global_store_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    s_endpgm
@@ -27,16 +26,13 @@
 ; GFX9-LABEL: test_add_co_sdwa:
 ; GFX9:       ; %bb.0: ; %bb
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
-; GFX9-NEXT:    v_lshlrev_b32_e32 v1, 2, v0
+; GFX9-NEXT:    v_lshlrev_b32_e32 v2, 2, v0
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v3, 3, v0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    global_load_dword v2, v1, s[2:3]
-; GFX9-NEXT:    s_nop 0
+; GFX9-NEXT:    global_load_dword v4, v2, s[2:3]
 ; GFX9-NEXT:    global_load_dwordx2 v[0:1], v3, s[0:1]
-; GFX9-NEXT:    s_waitcnt vmcnt(1)
-; GFX9-NEXT:    v_and_b32_e32 v2, 0xff, v2
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_add_co_u32_e32 v0, vcc, v0, v2
+; GFX9-NEXT:    v_add_co_u32_sdwa v0, vcc, v0, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
 ; GFX9-NEXT:    v_addc_co_u32_e32 v1, vcc, 0, v1, vcc
 ; GFX9-NEXT:    global_store_dwordx2 v3, v[0:1], s[0:1]
 ; GFX9-NEXT:    s_endpgm
Index: llvm/test/CodeGen/AMDGPU/v_sub_u64_pseudo_sdwa.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/v_sub_u64_pseudo_sdwa.ll
+++ llvm/test/CodeGen/AMDGPU/v_sub_u64_pseudo_sdwa.ll
@@ -5,8 +5,7 @@
 ; GFX9:       ; %bb.0: ; %bb
 ; GFX9-NEXT:    v_add_u32_e32 v1, 10, v0
 ; GFX9-NEXT:    v_add_u32_e32 v0, 20, v0
-; GFX9-NEXT:    v_and_b32_e32 v0, 0xff, v0
-; GFX9-NEXT:    v_sub_co_u32_e32 v0, vcc, v1, v0
+; GFX9-NEXT:    v_sub_co_u32_sdwa v0, vcc, v1, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
 ; GFX9-NEXT:    v_subb_co_u32_e64 v1, s[0:1], 0, 0, vcc
 ; GFX9-NEXT:    global_store_dwordx2 v[0:1], v[0:1], off
 ; GFX9-NEXT:    s_endpgm
@@ -27,16 +26,13 @@
 ; GFX9-LABEL: test_sub_co_sdwa:
 ; GFX9:       ; %bb.0: ; %bb
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
-; GFX9-NEXT:    v_lshlrev_b32_e32 v1, 2, v0
+; GFX9-NEXT:    v_lshlrev_b32_e32 v2, 2, v0
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v3, 3, v0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    global_load_dword v2, v1, s[2:3]
-; GFX9-NEXT:    s_nop 0
+; GFX9-NEXT:    global_load_dword v4, v2, s[2:3]
 ; GFX9-NEXT:    global_load_dwordx2 v[0:1], v3, s[0:1]
-; GFX9-NEXT:    s_waitcnt vmcnt(1)
-; GFX9-NEXT:    v_and_b32_e32 v2, 0xff, v2
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_sub_co_u32_e32 v0, vcc, v0, v2
+; GFX9-NEXT:    v_sub_co_u32_sdwa v0, vcc, v0, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
 ; GFX9-NEXT:    v_subbrev_co_u32_e32 v1, vcc, 0, v1, vcc
 ; GFX9-NEXT:    global_store_dwordx2 v3, v[0:1], s[0:1]
 ; GFX9-NEXT:    s_endpgm
Index: llvm/tmp.mir
===================================================================
--- /dev/null
+++ llvm/tmp.mir
@@ -0,0 +1,1465 @@
+--- |
+  ; ModuleID = './test/CodeGen/AMDGPU/sdwa-ops.mir'
+  source_filename = "./test/CodeGen/AMDGPU/sdwa-ops.mir"
+  target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7"
+  target triple = "amdgcn-unknown-unknown"
+  
+  define void @test1_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test2_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test3_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test4_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test5_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test6_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test7_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test8_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test9_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test10_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test11_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  define void @test12_add_co_sdwa() #0 {
+  entry:
+    unreachable
+  }
+  
+  attributes #0 = { "target-cpu"="gfx900" }
+
+...
+---
+name:            test1_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+  - { id: 10, class: vgpr_32, preferred-register: '' }
+  - { id: 11, class: vgpr_32, preferred-register: '' }
+  - { id: 12, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 13, class: vgpr_32, preferred-register: '' }
+  - { id: 14, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 15, class: vreg_64, preferred-register: '' }
+  - { id: 16, class: vgpr_32, preferred-register: '' }
+  - { id: 17, class: vgpr_32, preferred-register: '' }
+  - { id: 18, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 19, class: vgpr_32, preferred-register: '' }
+  - { id: 20, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 21, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32 = nsw V_ADD_CO_U32_sdwa 0, %4.sub0, 0, %0, 0, 6, 0, 6, 0, implicit-def $vcc, implicit $exec
+    %7:vgpr_32, dead %8:sreg_64_xexec = nuw V_ADDC_U32_e64 %4.sub1, %0, killed $vcc, 0, implicit $exec
+    %9:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %7, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %9, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+    %10:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %11:vgpr_32 = V_ADD_CO_U32_sdwa 0, %4.sub0, 0, %0, 0, 6, 0, 6, 0, implicit-def $vcc, implicit $exec
+    %13:vgpr_32, dead %14:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed $vcc, 0, implicit $exec
+    %15:vreg_64 = REG_SEQUENCE %11, %subreg.sub0, %13, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %15, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+    %16:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %17:vgpr_32 = V_ADD_CO_U32_sdwa 0, %4.sub0, 0, %0, 0, 6, 0, 6, 0, implicit-def $vcc, implicit $exec
+    %19:vgpr_32, dead %20:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed $vcc, 0, implicit $exec
+    %21:vreg_64 = REG_SEQUENCE %17, %subreg.sub0, %19, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %21, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test2_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: vgpr_32, preferred-register: '' }
+  - { id: 9, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 10, class: vgpr_32, preferred-register: '' }
+  - { id: 11, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 12, class: vreg_64, preferred-register: '' }
+  - { id: 13, class: vgpr_32, preferred-register: '' }
+  - { id: 14, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 15, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32 = V_ADD_CO_U32_sdwa 0, %4.sub0, 0, %0, 0, 6, 0, 6, 0, implicit-def $vcc, implicit $exec
+    %7:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %8:vgpr_32, %9:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %7, 0, implicit $exec
+    %10:vgpr_32, dead %11:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed %9, 0, implicit $exec
+    %12:vreg_64 = REG_SEQUENCE %8, %subreg.sub0, %10, %subreg.sub1
+    %13:vgpr_32, dead %14:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed $vcc, 0, implicit $exec
+    %15:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %13, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %15, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+    %7:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %8:vgpr_32, %9:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %7, 0, implicit $exec
+    %10:vgpr_32, dead %11:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed %9, 0, implicit $exec
+    %12:vreg_64 = REG_SEQUENCE %8, %subreg.sub0, %10, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %12, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test3_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %3, 0, implicit $exec
+    %7:vgpr_32, %8:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, killed %6, 0, implicit $exec
+    %9:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %8, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %9, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test4_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %3, 0, implicit $exec
+    %7:vgpr_32, %8:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, %6, 0, implicit $exec
+    %9:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %6, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %9, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test5_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32 = V_ADD_CO_U32_sdwa 0, %4.sub0, 0, %0, 0, 6, 0, 6, 0, implicit-def $vcc, implicit $exec
+    %7:vgpr_32, %8:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, $vcc, 0, implicit $exec
+    %9:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %7, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %9, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test6_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %3, 0, implicit $exec
+    %7:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %3, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %4.sub0, %7, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test7_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 5, class: vreg_64, preferred-register: '' }
+  - { id: 6, class: vgpr_32, preferred-register: '' }
+  - { id: 7, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 8, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:sreg_64_xexec = COPY $sgpr0_sgpr1
+    %5:vreg_64 = COPY $sgpr0_sgpr1
+    %6:vgpr_32, %7:sreg_64_xexec = V_ADDC_U32_e64 %5.sub1, %0, %4, 0, implicit $exec
+    %8:vreg_64 = REG_SEQUENCE %3, %subreg.sub0, %3, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %5.sub0, %8, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test8_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vgpr_32, preferred-register: '' }
+  - { id: 4, class: vreg_64, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+  - { id: 10, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %4:vreg_64 = COPY $sgpr0_sgpr1
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %4.sub0, %3, 0, implicit $exec
+    $vcc = COPY %4
+    %7:vgpr_32, %8:sreg_64_xexec = V_ADDC_U32_e64 %4.sub1, %0, %6, 0, implicit $exec
+    %9:vreg_64 = COPY $vcc
+    %10:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %7, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %9.sub0, %10, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test9_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vreg_64, preferred-register: '' }
+  - { id: 4, class: vgpr_32, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 9, class: vreg_64, preferred-register: '' }
+  - { id: 10, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vreg_64 = COPY $sgpr0_sgpr1
+    $vcc = COPY %3
+    %4:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %3.sub0, %4, 0, implicit $exec
+    %7:vgpr_32, %8:sreg_64_xexec = V_ADDC_U32_e64 %3.sub1, %0, %6, 0, implicit $exec
+    %9:vreg_64 = COPY $vcc
+    %10:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %7, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %9.sub0, %10, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test10_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vreg_64, preferred-register: '' }
+  - { id: 4, class: vgpr_32, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: vreg_64, preferred-register: '' }
+  - { id: 9, class: vgpr_32, preferred-register: '' }
+  - { id: 10, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 11, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vreg_64 = COPY $sgpr0_sgpr1
+    $vcc_lo = COPY %3.sub0
+    %4:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %3.sub0, %4, 0, implicit $exec
+    %7:vgpr_32 = COPY $vcc_lo
+    %8:vreg_64 = REG_SEQUENCE %7, %subreg.sub0, %4, %subreg.sub1
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADDC_U32_e64 %3.sub1, %0, %6, 0, implicit $exec
+    %11:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %9, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %8.sub0, %11, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test11_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vreg_64, preferred-register: '' }
+  - { id: 4, class: vgpr_32, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vgpr_32, preferred-register: '' }
+  - { id: 8, class: vreg_64, preferred-register: '' }
+  - { id: 9, class: vgpr_32, preferred-register: '' }
+  - { id: 10, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 11, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vreg_64 = COPY $sgpr0_sgpr1
+    $vcc_hi = COPY %3.sub0
+    %4:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %3.sub0, %4, 0, implicit $exec
+    %7:vgpr_32 = COPY $vcc_hi
+    %8:vreg_64 = REG_SEQUENCE %7, %subreg.sub0, %4, %subreg.sub1
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADDC_U32_e64 %3.sub1, %0, %6, 0, implicit $exec
+    %11:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %9, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %8.sub0, %11, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...
+---
+name:            test12_add_co_sdwa
+alignment:       1
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+hasWinCFI:       false
+callsEHReturn:   false
+callsUnwindInit: false
+hasEHCatchret:   false
+hasEHScopes:     false
+hasEHFunclets:   false
+failsVerification: false
+tracksDebugUserValues: false
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '' }
+  - { id: 1, class: sgpr_64, preferred-register: '' }
+  - { id: 2, class: sreg_32_xm0, preferred-register: '' }
+  - { id: 3, class: vreg_64, preferred-register: '' }
+  - { id: 4, class: vgpr_32, preferred-register: '' }
+  - { id: 5, class: vgpr_32, preferred-register: '' }
+  - { id: 6, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 7, class: vreg_64, preferred-register: '' }
+  - { id: 8, class: vgpr_32, preferred-register: '' }
+  - { id: 9, class: sreg_64_xexec, preferred-register: '' }
+  - { id: 10, class: vreg_64, preferred-register: '' }
+liveins:
+  - { reg: '$vgpr0', virtual-reg: '%0' }
+  - { reg: '$sgpr0_sgpr1', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    1
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  functionContext: ''
+  maxCallFrameSize: 4294967295
+  cvBytesOfCalleeSavedRegisters: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  hasTailCall:     false
+  localFrameSize:  0
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      []
+stack:           []
+callSites:       []
+debugValueSubstitutions: []
+constants:       []
+machineFunctionInfo:
+  explicitKernArgSize: 0
+  maxKernArgAlign: 1
+  ldsSize:         0
+  gdsSize:         0
+  dynLDSAlign:     1
+  isEntryFunction: false
+  noSignedZerosFPMath: false
+  memoryBound:     false
+  waveLimiter:     false
+  hasSpilledSGPRs: false
+  hasSpilledVGPRs: false
+  scratchRSrcReg:  '$private_rsrc_reg'
+  frameOffsetReg:  '$fp_reg'
+  stackPtrOffsetReg: '$sp_reg'
+  bytesInStackArgArea: 0
+  returnsVoid:     true
+  argumentInfo:
+    privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
+    dispatchPtr:     { reg: '$sgpr4_sgpr5' }
+    queuePtr:        { reg: '$sgpr6_sgpr7' }
+    dispatchID:      { reg: '$sgpr10_sgpr11' }
+    workGroupIDX:    { reg: '$sgpr12' }
+    workGroupIDY:    { reg: '$sgpr13' }
+    workGroupIDZ:    { reg: '$sgpr14' }
+    LDSKernelId:     { reg: '$sgpr15' }
+    implicitArgPtr:  { reg: '$sgpr8_sgpr9' }
+    workItemIDX:     { reg: '$vgpr31', mask: 1023 }
+    workItemIDY:     { reg: '$vgpr31', mask: 1047552 }
+    workItemIDZ:     { reg: '$vgpr31', mask: 1072693248 }
+  mode:
+    ieee:            true
+    dx10-clamp:      true
+    fp32-input-denormals: true
+    fp32-output-denormals: true
+    fp64-fp16-input-denormals: true
+    fp64-fp16-output-denormals: true
+  highBitsOf32BitAddress: 0
+  occupancy:       10
+  vgprForAGPRCopy: ''
+body:             |
+  bb.0:
+    liveins: $vgpr0, $sgpr0_sgpr1
+  
+    %1:sgpr_64 = COPY $sgpr0_sgpr1
+    %0:vgpr_32 = COPY $vgpr0
+    %2:sreg_32_xm0 = S_MOV_B32 255
+    %3:vreg_64 = COPY $sgpr0_sgpr1
+    %4:vgpr_32 = V_AND_B32_e32 %2, %0, implicit $exec
+    %5:vgpr_32, %6:sreg_64_xexec = V_ADD_CO_U32_e64 %3.sub0, %4, 0, implicit $exec
+    $vcc = COPY %3
+    %7:vreg_64 = COPY killed $vcc
+    %8:vgpr_32, %9:sreg_64_xexec = V_ADDC_U32_e64 %3.sub1, %0, %6, 0, implicit $exec
+    %10:vreg_64 = REG_SEQUENCE %5, %subreg.sub0, %8, %subreg.sub1
+    GLOBAL_STORE_DWORDX2_SADDR %7.sub0, %10, %1, 0, 0, implicit $exec, implicit $exec :: (store (s64))
+
+...