[GlobalISel][AMDGPU] Lower G_UMULO/G_SMULO

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D93963

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
index d8e79d5..8a96e37 100644 (file)
--- a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
@@ -174,6 +174,8 @@ private:
                                            LLT WideTy);
   LegalizeResult widenScalarAddSubShlSat(MachineInstr &MI, unsigned TypeIdx,
                                          LLT WideTy);
+  LegalizeResult widenScalarMulo(MachineInstr &MI, unsigned TypeIdx,
+                                 LLT WideTy);
 
   /// Helper function to split a wide generic register into bitwise blocks with
   /// the given Type (which implies the number of blocks needed). The generic
@@ -295,6 +297,9 @@ public:
                                                            unsigned TypeIdx,
                                                            LLT NarrowTy);
 
+  LegalizeResult fewerElementsVectorMulo(MachineInstr &MI, unsigned TypeIdx,
+                                         LLT NarrowTy);
+
   LegalizeResult
   reduceLoadStoreWidth(MachineInstr &MI, unsigned TypeIdx, LLT NarrowTy);
 

diff --git a/llvm/include/llvm/CodeGen/GlobalISel/MachineIRBuilder.h b/llvm/include/llvm/CodeGen/GlobalISel/MachineIRBuilder.h
index 2812890..9cb86db 100644 (file)
--- a/llvm/include/llvm/CodeGen/GlobalISel/MachineIRBuilder.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/MachineIRBuilder.h
@@ -712,6 +712,12 @@ public:
   MachineInstrBuilder buildExtOrTrunc(unsigned ExtOpc, const DstOp &Res,
                                       const SrcOp &Op);
 
+  /// Build and inserts \p Res = \p G_AND \p Op, \p LowBitsSet(ImmOp)
+  /// Since there is no G_ZEXT_INREG like G_SEXT_INREG, the instruction is
+  /// emulated using G_AND.
+  MachineInstrBuilder buildZExtInReg(const DstOp &Res, const SrcOp &Op,
+                                     int64_t ImmOp);
+
   /// Build and insert an appropriate cast between two registers of equal size.
   MachineInstrBuilder buildCast(const DstOp &Dst, const SrcOp &Src);
 

diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index f74ef8e..97a5c64 100644 (file)
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -1824,6 +1824,62 @@ LegalizerHelper::widenScalarAddSubShlSat(MachineInstr &MI, unsigned TypeIdx,
 }
 
 LegalizerHelper::LegalizeResult
+LegalizerHelper::widenScalarMulo(MachineInstr &MI, unsigned TypeIdx,
+                                 LLT WideTy) {
+  if (TypeIdx == 1)
+    return UnableToLegalize;
+
+  bool IsSigned = MI.getOpcode() == TargetOpcode::G_SMULO;
+  Register Result = MI.getOperand(0).getReg();
+  Register OriginalOverflow = MI.getOperand(1).getReg();
+  Register LHS = MI.getOperand(2).getReg();
+  Register RHS = MI.getOperand(3).getReg();
+  LLT SrcTy = MRI.getType(LHS);
+  LLT OverflowTy = MRI.getType(OriginalOverflow);
+  unsigned SrcBitWidth = SrcTy.getScalarSizeInBits();
+
+  // To determine if the result overflowed in the larger type, we extend the
+  // input to the larger type, do the multiply (checking if it overflows),
+  // then also check the high bits of the result to see if overflow happened
+  // there.
+  unsigned ExtOp = IsSigned ? TargetOpcode::G_SEXT : TargetOpcode::G_ZEXT;
+  auto LeftOperand = MIRBuilder.buildInstr(ExtOp, {WideTy}, {LHS});
+  auto RightOperand = MIRBuilder.buildInstr(ExtOp, {WideTy}, {RHS});
+
+  auto Mulo = MIRBuilder.buildInstr(MI.getOpcode(), {WideTy, OverflowTy},
+                                    {LeftOperand, RightOperand});
+  auto Mul = Mulo->getOperand(0);
+  MIRBuilder.buildTrunc(Result, Mul);
+
+  MachineInstrBuilder ExtResult;
+  // Overflow occurred if it occurred in the larger type, or if the high part
+  // of the result does not zero/sign-extend the low part.  Check this second
+  // possibility first.
+  if (IsSigned) {
+    // For signed, overflow occurred when the high part does not sign-extend
+    // the low part.
+    ExtResult = MIRBuilder.buildSExtInReg(WideTy, Mul, SrcBitWidth);
+  } else {
+    // Unsigned overflow occurred when the high part does not zero-extend the
+    // low part.
+    ExtResult = MIRBuilder.buildZExtInReg(WideTy, Mul, SrcBitWidth);
+  }
+
+  // Multiplication cannot overflow if the WideTy is >= 2 * original width,
+  // so we don't need to check the overflow result of larger type Mulo.
+  if (WideTy.getScalarSizeInBits() < 2 * SrcBitWidth) {
+    auto Overflow =
+        MIRBuilder.buildICmp(CmpInst::ICMP_NE, OverflowTy, Mul, ExtResult);
+    // Finally check if the multiplication in the larger type itself overflowed.
+    MIRBuilder.buildOr(OriginalOverflow, Mulo->getOperand(1), Overflow);
+  } else {
+    MIRBuilder.buildICmp(CmpInst::ICMP_NE, OriginalOverflow, Mul, ExtResult);
+  }
+  MI.eraseFromParent();
+  return Legalized;
+}
+
+LegalizerHelper::LegalizeResult
 LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
   switch (MI.getOpcode()) {
   default:
@@ -1845,6 +1901,9 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
   case TargetOpcode::G_UADDE:
   case TargetOpcode::G_USUBE:
     return widenScalarAddSubOverflow(MI, TypeIdx, WideTy);
+  case TargetOpcode::G_UMULO:
+  case TargetOpcode::G_SMULO:
+    return widenScalarMulo(MI, TypeIdx, WideTy);
   case TargetOpcode::G_SADDSAT:
   case TargetOpcode::G_SSUBSAT:
   case TargetOpcode::G_SSHLSAT:
@@ -3619,6 +3678,55 @@ LegalizerHelper::fewerElementsVectorUnmergeValues(MachineInstr &MI,
   return Legalized;
 }
 
+LegalizerHelper::LegalizeResult
+LegalizerHelper::fewerElementsVectorMulo(MachineInstr &MI, unsigned TypeIdx,
+                                         LLT NarrowTy) {
+  Register Result = MI.getOperand(0).getReg();
+  Register Overflow = MI.getOperand(1).getReg();
+  Register LHS = MI.getOperand(2).getReg();
+  Register RHS = MI.getOperand(3).getReg();
+
+  LLT SrcTy = MRI.getType(LHS);
+  if (!SrcTy.isVector())
+    return UnableToLegalize;
+
+  LLT ElementType = SrcTy.getElementType();
+  LLT OverflowElementTy = MRI.getType(Overflow).getElementType();
+  const int NumResult = SrcTy.getNumElements();
+  LLT GCDTy = getGCDType(SrcTy, NarrowTy);
+
+  // Unmerge the operands to smaller parts of GCD type.
+  auto UnmergeLHS = MIRBuilder.buildUnmerge(GCDTy, LHS);
+  auto UnmergeRHS = MIRBuilder.buildUnmerge(GCDTy, RHS);
+
+  const int NumOps = UnmergeLHS->getNumOperands() - 1;
+  const int PartsPerUnmerge = NumResult / NumOps;
+  LLT OverflowTy = LLT::scalarOrVector(PartsPerUnmerge, OverflowElementTy);
+  LLT ResultTy = LLT::scalarOrVector(PartsPerUnmerge, ElementType);
+
+  // Perform the operation over unmerged parts.
+  SmallVector<Register, 8> ResultParts;
+  SmallVector<Register, 8> OverflowParts;
+  for (int I = 0; I != NumOps; ++I) {
+    Register Operand1 = UnmergeLHS->getOperand(I).getReg();
+    Register Operand2 = UnmergeRHS->getOperand(I).getReg();
+    auto PartMul = MIRBuilder.buildInstr(MI.getOpcode(), {ResultTy, OverflowTy},
+                                         {Operand1, Operand2});
+    ResultParts.push_back(PartMul->getOperand(0).getReg());
+    OverflowParts.push_back(PartMul->getOperand(1).getReg());
+  }
+
+  LLT ResultLCMTy = buildLCMMergePieces(SrcTy, NarrowTy, GCDTy, ResultParts);
+  LLT OverflowLCMTy =
+      LLT::scalarOrVector(ResultLCMTy.getNumElements(), OverflowElementTy);
+
+  // Recombine the pieces to the original result and overflow registers.
+  buildWidenedRemergeToDst(Result, ResultLCMTy, ResultParts);
+  buildWidenedRemergeToDst(Overflow, OverflowLCMTy, OverflowParts);
+  MI.eraseFromParent();
+  return Legalized;
+}
+
 // Handle FewerElementsVector a G_BUILD_VECTOR or G_CONCAT_VECTORS that produces
 // a vector
 //
@@ -4026,6 +4134,9 @@ LegalizerHelper::fewerElementsVector(MachineInstr &MI, unsigned TypeIdx,
   case G_UADDSAT:
   case G_USUBSAT:
     return reduceOperationWidth(MI, TypeIdx, NarrowTy);
+  case G_UMULO:
+  case G_SMULO:
+    return fewerElementsVectorMulo(MI, TypeIdx, NarrowTy);
   case G_SHL:
   case G_LSHR:
   case G_ASHR:

diff --git a/llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp b/llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp
index df8b799..bde442a 100644 (file)
--- a/llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp
@@ -486,6 +486,15 @@ MachineInstrBuilder MachineIRBuilder::buildAnyExtOrTrunc(const DstOp &Res,
   return buildExtOrTrunc(TargetOpcode::G_ANYEXT, Res, Op);
 }
 
+MachineInstrBuilder MachineIRBuilder::buildZExtInReg(const DstOp &Res,
+                                                     const SrcOp &Op,
+                                                     int64_t ImmOp) {
+  LLT ResTy = Res.getLLTTy(*getMRI());
+  auto Mask = buildConstant(
+      ResTy, APInt::getLowBitsSet(ResTy.getScalarSizeInBits(), ImmOp));
+  return buildAnd(ResTy, Op, Mask);
+}
+
 MachineInstrBuilder MachineIRBuilder::buildCast(const DstOp &Dst,
                                                 const SrcOp &Src) {
   LLT SrcTy = Src.getLLTTy(*getMRI());

diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
index 2925f70..7c50e17 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -1606,6 +1606,11 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
   getActionDefinitionsBuilder(G_FENCE)
     .alwaysLegal();
 
+  getActionDefinitionsBuilder({G_SMULO, G_UMULO})
+      .scalarize(0)
+      .minScalar(0, S32)
+      .lower();
+
   getActionDefinitionsBuilder({
       // TODO: Verify V_BFI_B32 is generated from expanded bit ops
       G_FCOPYSIGN,

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulo.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulo.mir
new file mode 100644 (file)
index 0000000..87b0c5b
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulo.mir
@@ -0,0 +1,578 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX8
+# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx906 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX9
+
+---
+name: test_smulo_s32
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_smulo_s32
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[COPY]], [[COPY1]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[MUL]](s32)
+    ; GFX8: $vgpr1 = COPY [[SEXT]](s32)
+    ; GFX9-LABEL: name: test_smulo_s32
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[COPY]], [[COPY1]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[MUL]](s32)
+    ; GFX9: $vgpr1 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s32), %3:_(s1) = G_SMULO %0, %1
+    %4:_(s32) = G_SEXT %3
+    $vgpr0 = COPY %2
+    $vgpr1 = COPY %4
+...
+
+---
+name: test_smulo_v2s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; GFX8-LABEL: name: test_smulo_v2s32
+    ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[UV]], [[UV2]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX8: [[SMULH1:%[0-9]+]]:_(s32) = G_SMULH [[UV1]], [[UV3]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX8: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[MUL1]], [[C]](s32)
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH1]](s32), [[ASHR1]]
+    ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 1
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 1
+    ; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG]](s32), [[SEXT_INREG1]](s32)
+    ; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX9-LABEL: name: test_smulo_v2s32
+    ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX9: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[UV]], [[UV2]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX9: [[SMULH1:%[0-9]+]]:_(s32) = G_SMULH [[UV1]], [[UV3]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX9: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[MUL1]], [[C]](s32)
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH1]](s32), [[ASHR1]]
+    ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
+    ; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG]](s32), [[SEXT_INREG1]](s32)
+    ; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    %2:_(<2 x s32>), %3:_(<2 x s1>) = G_SMULO %0, %1
+    %4:_(<2 x s32>) = G_SEXT %3
+    $vgpr0_vgpr1 = COPY %2
+    $vgpr2_vgpr3 = COPY %4
+...
+
+---
+name: test_smulo_s16
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_smulo_s16
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 16
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 16
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 16
+    ; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX8: $vgpr1 = COPY [[SEXT]](s32)
+    ; GFX9-LABEL: name: test_smulo_s16
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 16
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 16
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 16
+    ; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX9: $vgpr1 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s16) = G_TRUNC %0
+    %3:_(s16) = G_TRUNC %1
+    %4:_(s16), %6:_(s1) = G_SMULO %2, %3
+    %5:_(s32) = G_SEXT %4
+    %7:_(s32) = G_SEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+
+---
+name: test_smulo_s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_smulo_s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX8: $vgpr1 = COPY [[SEXT]](s32)
+    ; GFX9-LABEL: name: test_smulo_s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX9: $vgpr1 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8) = G_TRUNC %0
+    %3:_(s8) = G_TRUNC %1
+    %4:_(s8), %6:_(s1) = G_SMULO %2, %3
+    %5:_(s32) = G_SEXT %4
+    %7:_(s32) = G_SEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+
+---
+name: test_smulo_v2s16
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+    ; GFX8-LABEL: name: test_smulo_v2s16
+    ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 16
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 16
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[UV1]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 16
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
+    ; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 16
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 16
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C]]
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C]]
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C1]](s32)
+    ; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
+    ; GFX8: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: [[COPY8:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
+    ; GFX8: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY8]], 1
+    ; GFX8: [[COPY9:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
+    ; GFX8: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY9]], 1
+    ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG6]](s32), [[SEXT_INREG7]](s32)
+    ; GFX8: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[BITCAST]](<2 x s16>)
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
+    ; GFX8: [[COPY10:%[0-9]+]]:_(s32) = COPY [[BITCAST1]](s32)
+    ; GFX8: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY10]], 16
+    ; GFX8: [[COPY11:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX8: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY11]], 16
+    ; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG8]](s32), [[SEXT_INREG9]](s32)
+    ; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX9-LABEL: name: test_smulo_v2s16
+    ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 16
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 16
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[UV1]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 16
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
+    ; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 16
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 16
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY6]](s32), [[COPY7]](s32)
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
+    ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG6]](s32), [[SEXT_INREG7]](s32)
+    ; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[BUILD_VECTOR_TRUNC]](<2 x s16>)
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
+    ; GFX9: [[COPY8:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
+    ; GFX9: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY8]], 16
+    ; GFX9: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX9: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY9]], 16
+    ; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG8]](s32), [[SEXT_INREG9]](s32)
+    ; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    %2:_(<2 x s16>) = G_TRUNC %0
+    %3:_(<2 x s16>) = G_TRUNC %1
+    %4:_(<2 x s16>), %6:_(<2 x s1>) = G_SMULO %2, %3
+    %7:_(<2 x s32>) = G_SEXT %6
+    %5:_(<2 x s32>) = G_SEXT %4
+    $vgpr0_vgpr1 = COPY %5
+    $vgpr2_vgpr3 = COPY %7
+...
+
+
+---
+name: test_smulo_v2s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+    ; GFX8-LABEL: name: test_smulo_v2s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[COPY2]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 8
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY6]], 8
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[COPY3]](s32)
+    ; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY7]], 8
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; GFX8: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
+    ; GFX8: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C]]
+    ; GFX8: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND1]], [[C1]](s16)
+    ; GFX8: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND]], [[SHL]]
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: $vgpr1 = COPY [[ANYEXT1]](s32)
+    ; GFX8: $vgpr2 = COPY [[ANYEXT2]](s32)
+    ; GFX9-LABEL: name: test_smulo_v2s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[COPY2]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 8
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY6]], 8
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[COPY3]](s32)
+    ; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY7]], 8
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
+    ; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C]]
+    ; GFX9: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND1]], [[C1]](s16)
+    ; GFX9: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND]], [[SHL]]
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: $vgpr1 = COPY [[ANYEXT1]](s32)
+    ; GFX9: $vgpr2 = COPY [[ANYEXT2]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s32) = COPY $vgpr2
+    %3:_(s32) = COPY $vgpr3
+    %5:_(s8) = G_TRUNC %0
+    %6:_(s8) = G_TRUNC %1
+    %7:_(s8) = G_TRUNC %2
+    %8:_(s8) = G_TRUNC %3
+    %11:_(<2 x s8>) = G_BUILD_VECTOR %5, %6
+    %12:_(<2 x s8>) = G_BUILD_VECTOR %7, %8
+    %13:_(<2 x s8>), %19:_(<2 x s1>) = G_SMULO %11, %12
+    %20:_(<2 x s32>) = G_SEXT %19
+    %14:_(s8), %15:_(s8) = G_UNMERGE_VALUES %13
+    %21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %19
+    %17:_(s16) = G_MERGE_VALUES %14, %15
+    %18:_(s32) = G_ANYEXT %17
+    %23:_(s32) = G_ANYEXT %21
+    %24:_(s32) = G_ANYEXT %22
+    $vgpr0 = COPY %18
+    $vgpr1 = COPY %23
+    $vgpr2 = COPY %24
+...
+
+---
+name: test_smulo_v4s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    ; GFX8-LABEL: name: test_smulo_v4s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX8: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
+    ; GFX8: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
+    ; GFX8: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
+    ; GFX8: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
+    ; GFX8: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
+    ; GFX8: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[LSHR3]](s32)
+    ; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 8
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
+    ; GFX8: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY6]], 8
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[LSHR4]](s32)
+    ; GFX8: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY7]], 8
+    ; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG6]], [[SEXT_INREG7]]
+    ; GFX8: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL2]], 8
+    ; GFX8: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL2]](s32), [[SEXT_INREG8]]
+    ; GFX8: [[COPY8:%[0-9]+]]:_(s32) = COPY [[LSHR2]](s32)
+    ; GFX8: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY8]], 8
+    ; GFX8: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR5]](s32)
+    ; GFX8: [[SEXT_INREG10:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY9]], 8
+    ; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG9]], [[SEXT_INREG10]]
+    ; GFX8: [[SEXT_INREG11:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL3]], 8
+    ; GFX8: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL3]](s32), [[SEXT_INREG11]]
+    ; GFX8: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX8: [[COPY10:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY10]], [[C3]]
+    ; GFX8: [[COPY11:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY11]], [[C3]]
+    ; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+    ; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
+    ; GFX8: [[COPY12:%[0-9]+]]:_(s32) = COPY [[MUL2]](s32)
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[COPY12]], [[C3]]
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND2]], [[C1]](s32)
+    ; GFX8: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
+    ; GFX8: [[COPY13:%[0-9]+]]:_(s32) = COPY [[MUL3]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY13]], [[C3]]
+    ; GFX8: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C2]](s32)
+    ; GFX8: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[OR2]](s32)
+    ; GFX8: $vgpr1 = COPY [[ANYEXT]](s32)
+    ; GFX9-LABEL: name: test_smulo_v4s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
+    ; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
+    ; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
+    ; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
+    ; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
+    ; GFX9: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
+    ; GFX9: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 8
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[LSHR3]](s32)
+    ; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY5]], 8
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
+    ; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
+    ; GFX9: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY6]], 8
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[LSHR4]](s32)
+    ; GFX9: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY7]], 8
+    ; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG6]], [[SEXT_INREG7]]
+    ; GFX9: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL2]], 8
+    ; GFX9: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL2]](s32), [[SEXT_INREG8]]
+    ; GFX9: [[COPY8:%[0-9]+]]:_(s32) = COPY [[LSHR2]](s32)
+    ; GFX9: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY8]], 8
+    ; GFX9: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR5]](s32)
+    ; GFX9: [[SEXT_INREG10:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY9]], 8
+    ; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG9]], [[SEXT_INREG10]]
+    ; GFX9: [[SEXT_INREG11:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL3]], 8
+    ; GFX9: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL3]](s32), [[SEXT_INREG11]]
+    ; GFX9: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX9: [[COPY10:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY10]], [[C3]]
+    ; GFX9: [[COPY11:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY11]], [[C3]]
+    ; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+    ; GFX9: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
+    ; GFX9: [[COPY12:%[0-9]+]]:_(s32) = COPY [[MUL2]](s32)
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[COPY12]], [[C3]]
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND2]], [[C1]](s32)
+    ; GFX9: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
+    ; GFX9: [[COPY13:%[0-9]+]]:_(s32) = COPY [[MUL3]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY13]], [[C3]]
+    ; GFX9: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C2]](s32)
+    ; GFX9: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[OR2]](s32)
+    ; GFX9: $vgpr1 = COPY [[ANYEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8) = G_UNMERGE_VALUES %0
+    %6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8) = G_UNMERGE_VALUES %1
+    %10:_(<4 x s8>) = G_BUILD_VECTOR %2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8)
+    %11:_(<4 x s8>) = G_BUILD_VECTOR %6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8)
+    %12:_(<4 x s8>), %18:_(<4 x s1>) = G_SMULO %10:_, %11:_
+    %13:_(s8), %14:_(s8), %15:_(s8), %16:_(s8) = G_UNMERGE_VALUES %12:_(<4 x s8>)
+    %19:_(s1), %20:_(s1), %21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %18:_(<4 x s1>)
+    %17:_(s32) = G_MERGE_VALUES %13, %14, %15, %16
+    %23:_(s32) = G_ANYEXT %19
+    $vgpr0 = COPY %17
+    $vgpr1 = COPY %23
+...
+---
+name: test_smulo_s24
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_smulo_s24
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 24
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 24
+    ; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX8: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 24
+    ; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[OR]](s1)
+    ; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX8: $vgpr1 = COPY [[SEXT]](s32)
+    ; GFX9-LABEL: name: test_smulo_s24
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 24
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 24
+    ; GFX9: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
+    ; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
+    ; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
+    ; GFX9: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY4]], 24
+    ; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[OR]](s1)
+    ; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
+    ; GFX9: $vgpr1 = COPY [[SEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s24) = G_TRUNC %0
+    %3:_(s24) = G_TRUNC %1
+    %4:_(s24), %6:_(s1) = G_SMULO %2, %3
+    %5:_(s32) = G_SEXT %4
+    %7:_(s32) = G_SEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir
new file mode 100644 (file)
index 0000000..c3e1309
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir
@@ -0,0 +1,680 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX8
+# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx906 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX9
+
+---
+name: test_umulo_s32
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_umulo_s32
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[COPY]], [[COPY1]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C]]
+    ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[MUL]](s32)
+    ; GFX8: $vgpr1 = COPY [[ZEXT]](s32)
+    ; GFX9-LABEL: name: test_umulo_s32
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[COPY]], [[COPY1]]
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C]]
+    ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[MUL]](s32)
+    ; GFX9: $vgpr1 = COPY [[ZEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s32), %3:_(s1) = G_UMULO %0, %1
+    %4:_(s32) = G_ZEXT %3
+    $vgpr0 = COPY %2
+    $vgpr1 = COPY %4
+...
+
+---
+name: test_umulo_v2s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; GFX8-LABEL: name: test_umulo_v2s32
+    ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV2]]
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C]]
+    ; GFX8: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV3]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH1]](s32), [[C]]
+    ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C1]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C1]]
+    ; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32)
+    ; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX9-LABEL: name: test_umulo_v2s32
+    ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV2]]
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C]]
+    ; GFX9: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV3]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH1]](s32), [[C]]
+    ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
+    ; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[ANYEXT]], [[C1]]
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[ANYEXT1]], [[C1]]
+    ; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32)
+    ; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    %2:_(<2 x s32>), %3:_(<2 x s1>) = G_UMULO %0, %1
+    %4:_(<2 x s32>) = G_ZEXT %3
+    $vgpr0_vgpr1 = COPY %2
+    $vgpr2_vgpr3 = COPY %4
+...
+
+---
+name: test_umulo_s64
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+
+    ; GFX8-LABEL: name: test_umulo_s64
+    ; GFX8: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
+    ; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+    ; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV2]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV3]]
+    ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV2]]
+    ; GFX8: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]]
+    ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1)
+    ; GFX8: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]]
+    ; GFX8: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1)
+    ; GFX8: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]]
+    ; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX8: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV2]]
+    ; GFX8: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV3]]
+    ; GFX8: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]]
+    ; GFX8: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1)
+    ; GFX8: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]]
+    ; GFX8: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1)
+    ; GFX8: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]]
+    ; GFX8: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]]
+    ; GFX8: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1)
+    ; GFX8: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]]
+    ; GFX8: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV3]]
+    ; GFX8: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]]
+    ; GFX8: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32)
+    ; GFX8: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+    ; GFX8: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+    ; GFX8: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
+    ; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV6]]
+    ; GFX8: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]]
+    ; GFX8: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]]
+    ; GFX8: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]]
+    ; GFX8: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[MUL4]], [[MUL5]]
+    ; GFX8: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ADD4]], [[UMULH4]]
+    ; GFX8: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL3]](s32), [[ADD5]](s32)
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV]](s64), [[C]]
+    ; GFX8: [[ZEXT5:%[0-9]+]]:_(s64) = G_ZEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0_vgpr1 = COPY [[MV1]](s64)
+    ; GFX8: $vgpr2_vgpr3 = COPY [[ZEXT5]](s64)
+    ; GFX9-LABEL: name: test_umulo_s64
+    ; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
+    ; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+    ; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV2]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV3]]
+    ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV2]]
+    ; GFX9: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]]
+    ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1)
+    ; GFX9: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]]
+    ; GFX9: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1)
+    ; GFX9: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]]
+    ; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
+    ; GFX9: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV2]]
+    ; GFX9: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV]], [[UV3]]
+    ; GFX9: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]]
+    ; GFX9: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1)
+    ; GFX9: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]]
+    ; GFX9: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1)
+    ; GFX9: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]]
+    ; GFX9: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]]
+    ; GFX9: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1)
+    ; GFX9: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]]
+    ; GFX9: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV1]], [[UV3]]
+    ; GFX9: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]]
+    ; GFX9: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32)
+    ; GFX9: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+    ; GFX9: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
+    ; GFX9: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
+    ; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV6]]
+    ; GFX9: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]]
+    ; GFX9: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]]
+    ; GFX9: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]]
+    ; GFX9: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[MUL4]], [[MUL5]]
+    ; GFX9: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ADD4]], [[UMULH4]]
+    ; GFX9: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL3]](s32), [[ADD5]](s32)
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV]](s64), [[C]]
+    ; GFX9: [[ZEXT5:%[0-9]+]]:_(s64) = G_ZEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0_vgpr1 = COPY [[MV1]](s64)
+    ; GFX9: $vgpr2_vgpr3 = COPY [[ZEXT5]](s64)
+    %0:_(s64) = COPY $vgpr0_vgpr1
+    %1:_(s64) = COPY $vgpr2_vgpr3
+    %2:_(s64), %3:_(s1) = G_UMULO %0, %1
+    %4:_(s64) = G_ZEXT %3
+    $vgpr0_vgpr1 = COPY %2
+    $vgpr2_vgpr3 = COPY %4
+...
+
+---
+name: test_umulo_s24
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_umulo_s24
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16777215
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[AND]], [[AND1]]
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[OR]](s1)
+    ; GFX8: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX8: $vgpr1 = COPY [[ZEXT]](s32)
+    ; GFX9-LABEL: name: test_umulo_s24
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16777215
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[AND]], [[AND1]]
+    ; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[UMULH]](s32), [[C1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[OR]](s1)
+    ; GFX9: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX9: $vgpr1 = COPY [[ZEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s24) = G_TRUNC %0
+    %3:_(s24) = G_TRUNC %1
+    %4:_(s24), %6:_(s1) = G_UMULO %2, %3
+    %5:_(s32) = G_ZEXT %4
+    %7:_(s32) = G_ZEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+
+
+---
+name: test_umulo_s16
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_umulo_s16
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX8: $vgpr1 = COPY [[ZEXT]](s32)
+    ; GFX9-LABEL: name: test_umulo_s16
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX9: $vgpr1 = COPY [[ZEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s16) = G_TRUNC %0
+    %3:_(s16) = G_TRUNC %1
+    %4:_(s16), %6:_(s1) = G_UMULO %2, %3
+    %5:_(s32) = G_ZEXT %4
+    %7:_(s32) = G_ZEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+
+---
+name: test_umulo_s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+
+    ; GFX8-LABEL: name: test_umulo_s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX8: $vgpr1 = COPY [[ZEXT]](s32)
+    ; GFX9-LABEL: name: test_umulo_s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[AND3]](s32)
+    ; GFX9: $vgpr1 = COPY [[ZEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8) = G_TRUNC %0
+    %3:_(s8) = G_TRUNC %1
+    %4:_(s8), %6:_(s1) = G_UMULO %2, %3
+    %5:_(s32) = G_ZEXT %4
+    %7:_(s32) = G_ZEXT %6
+    $vgpr0 = COPY %5
+    $vgpr1 = COPY %7
+...
+
+---
+name: test_umulo_v2s16
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
+    ; GFX8-LABEL: name: test_umulo_v2s16
+    ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[UV1]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
+    ; GFX8: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX8: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C]]
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND6:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C]]
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX8: [[AND7:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C]]
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND7]], [[C1]](s32)
+    ; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND6]], [[SHL]]
+    ; GFX8: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; GFX8: [[COPY8:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
+    ; GFX8: [[AND8:%[0-9]+]]:_(s32) = G_AND [[COPY8]], [[C2]]
+    ; GFX8: [[COPY9:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
+    ; GFX8: [[AND9:%[0-9]+]]:_(s32) = G_AND [[COPY9]], [[C2]]
+    ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND8]](s32), [[AND9]](s32)
+    ; GFX8: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[BITCAST]](<2 x s16>)
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
+    ; GFX8: [[COPY10:%[0-9]+]]:_(s32) = COPY [[BITCAST1]](s32)
+    ; GFX8: [[AND10:%[0-9]+]]:_(s32) = G_AND [[COPY10]], [[C]]
+    ; GFX8: [[COPY11:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX8: [[AND11:%[0-9]+]]:_(s32) = G_AND [[COPY11]], [[C]]
+    ; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND10]](s32), [[AND11]](s32)
+    ; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    ; GFX9-LABEL: name: test_umulo_v2s16
+    ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    ; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[UV1]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
+    ; GFX9: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX9: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C]]
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[COPY6]](s32), [[COPY7]](s32)
+    ; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[AND6:%[0-9]+]]:_(s32) = G_AND [[ANYEXT]], [[C1]]
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: [[AND7:%[0-9]+]]:_(s32) = G_AND [[ANYEXT1]], [[C1]]
+    ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND6]](s32), [[AND7]](s32)
+    ; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[BUILD_VECTOR_TRUNC]](<2 x s16>)
+    ; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C2]](s32)
+    ; GFX9: [[COPY8:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
+    ; GFX9: [[AND8:%[0-9]+]]:_(s32) = G_AND [[COPY8]], [[C]]
+    ; GFX9: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX9: [[AND9:%[0-9]+]]:_(s32) = G_AND [[COPY9]], [[C]]
+    ; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND8]](s32), [[AND9]](s32)
+    ; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
+    ; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
+    %2:_(<2 x s16>) = G_TRUNC %0
+    %3:_(<2 x s16>) = G_TRUNC %1
+    %4:_(<2 x s16>), %6:_(<2 x s1>) = G_UMULO %2, %3
+    %7:_(<2 x s32>) = G_ZEXT %6
+    %5:_(<2 x s32>) = G_ZEXT %4
+    $vgpr0_vgpr1 = COPY %5
+    $vgpr2_vgpr3 = COPY %7
+...
+
+
+---
+name: test_umulo_v2s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+    ; GFX8-LABEL: name: test_umulo_v2s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[COPY2]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C]]
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[COPY3]](s32)
+    ; GFX8: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX8: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C]]
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX8: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; GFX8: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
+    ; GFX8: [[AND6:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C1]]
+    ; GFX8: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
+    ; GFX8: [[AND7:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C1]]
+    ; GFX8: [[C2:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND7]], [[C2]](s16)
+    ; GFX8: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND6]], [[SHL]]
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
+    ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX8: $vgpr1 = COPY [[ANYEXT1]](s32)
+    ; GFX8: $vgpr2 = COPY [[ANYEXT2]](s32)
+    ; GFX9-LABEL: name: test_umulo_v2s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[COPY2]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C]]
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[COPY3]](s32)
+    ; GFX9: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX9: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C]]
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX9: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
+    ; GFX9: [[AND6:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C1]]
+    ; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
+    ; GFX9: [[AND7:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C1]]
+    ; GFX9: [[C2:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND7]], [[C2]](s16)
+    ; GFX9: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND6]], [[SHL]]
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
+    ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
+    ; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
+    ; GFX9: $vgpr1 = COPY [[ANYEXT1]](s32)
+    ; GFX9: $vgpr2 = COPY [[ANYEXT2]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s32) = COPY $vgpr2
+    %3:_(s32) = COPY $vgpr3
+    %5:_(s8) = G_TRUNC %0
+    %6:_(s8) = G_TRUNC %1
+    %7:_(s8) = G_TRUNC %2
+    %8:_(s8) = G_TRUNC %3
+    %11:_(<2 x s8>) = G_BUILD_VECTOR %5, %6
+    %12:_(<2 x s8>) = G_BUILD_VECTOR %7, %8
+    %13:_(<2 x s8>), %19:_(<2 x s1>) = G_UMULO %11, %12
+    %20:_(<2 x s32>) = G_ZEXT %19
+    %14:_(s8), %15:_(s8) = G_UNMERGE_VALUES %13
+    %21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %19
+    %17:_(s16) = G_MERGE_VALUES %14, %15
+    %18:_(s32) = G_ANYEXT %17
+    %23:_(s32) = G_ANYEXT %21
+    %24:_(s32) = G_ANYEXT %22
+    $vgpr0 = COPY %18
+    $vgpr1 = COPY %23
+    $vgpr2 = COPY %24
+...
+
+---
+name: test_umulo_v4s8
+body: |
+  bb.0:
+    liveins: $vgpr0, $vgpr1
+    ; GFX8-LABEL: name: test_umulo_v4s8
+    ; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+    ; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
+    ; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX8: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
+    ; GFX8: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
+    ; GFX8: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
+    ; GFX8: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
+    ; GFX8: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
+    ; GFX8: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
+    ; GFX8: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C3]]
+    ; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C3]]
+    ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C3]]
+    ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX8: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C3]]
+    ; GFX8: [[COPY5:%[0-9]+]]:_(s32) = COPY [[LSHR3]](s32)
+    ; GFX8: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C3]]
+    ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX8: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C3]]
+    ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX8: [[COPY6:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
+    ; GFX8: [[AND6:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C3]]
+    ; GFX8: [[COPY7:%[0-9]+]]:_(s32) = COPY [[LSHR4]](s32)
+    ; GFX8: [[AND7:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C3]]
+    ; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[AND6]], [[AND7]]
+    ; GFX8: [[AND8:%[0-9]+]]:_(s32) = G_AND [[MUL2]], [[C3]]
+    ; GFX8: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL2]](s32), [[AND8]]
+    ; GFX8: [[COPY8:%[0-9]+]]:_(s32) = COPY [[LSHR2]](s32)
+    ; GFX8: [[AND9:%[0-9]+]]:_(s32) = G_AND [[COPY8]], [[C3]]
+    ; GFX8: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR5]](s32)
+    ; GFX8: [[AND10:%[0-9]+]]:_(s32) = G_AND [[COPY9]], [[C3]]
+    ; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[AND9]], [[AND10]]
+    ; GFX8: [[AND11:%[0-9]+]]:_(s32) = G_AND [[MUL3]], [[C3]]
+    ; GFX8: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL3]](s32), [[AND11]]
+    ; GFX8: [[COPY10:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX8: [[AND12:%[0-9]+]]:_(s32) = G_AND [[COPY10]], [[C3]]
+    ; GFX8: [[COPY11:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX8: [[AND13:%[0-9]+]]:_(s32) = G_AND [[COPY11]], [[C3]]
+    ; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND13]], [[C]](s32)
+    ; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND12]], [[SHL]]
+    ; GFX8: [[COPY12:%[0-9]+]]:_(s32) = COPY [[MUL2]](s32)
+    ; GFX8: [[AND14:%[0-9]+]]:_(s32) = G_AND [[COPY12]], [[C3]]
+    ; GFX8: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND14]], [[C1]](s32)
+    ; GFX8: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
+    ; GFX8: [[COPY13:%[0-9]+]]:_(s32) = COPY [[MUL3]](s32)
+    ; GFX8: [[AND15:%[0-9]+]]:_(s32) = G_AND [[COPY13]], [[C3]]
+    ; GFX8: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND15]], [[C2]](s32)
+    ; GFX8: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
+    ; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX8: $vgpr0 = COPY [[OR2]](s32)
+    ; GFX8: $vgpr1 = COPY [[ANYEXT]](s32)
+    ; GFX9-LABEL: name: test_umulo_v4s8
+    ; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
+    ; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
+    ; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
+    ; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
+    ; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
+    ; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
+    ; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
+    ; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
+    ; GFX9: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
+    ; GFX9: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
+    ; GFX9: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+    ; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
+    ; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C3]]
+    ; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
+    ; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C3]]
+    ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[AND]], [[AND1]]
+    ; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C3]]
+    ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[AND2]]
+    ; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
+    ; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C3]]
+    ; GFX9: [[COPY5:%[0-9]+]]:_(s32) = COPY [[LSHR3]](s32)
+    ; GFX9: [[AND4:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C3]]
+    ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[AND3]], [[AND4]]
+    ; GFX9: [[AND5:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C3]]
+    ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[AND5]]
+    ; GFX9: [[COPY6:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
+    ; GFX9: [[AND6:%[0-9]+]]:_(s32) = G_AND [[COPY6]], [[C3]]
+    ; GFX9: [[COPY7:%[0-9]+]]:_(s32) = COPY [[LSHR4]](s32)
+    ; GFX9: [[AND7:%[0-9]+]]:_(s32) = G_AND [[COPY7]], [[C3]]
+    ; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[AND6]], [[AND7]]
+    ; GFX9: [[AND8:%[0-9]+]]:_(s32) = G_AND [[MUL2]], [[C3]]
+    ; GFX9: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL2]](s32), [[AND8]]
+    ; GFX9: [[COPY8:%[0-9]+]]:_(s32) = COPY [[LSHR2]](s32)
+    ; GFX9: [[AND9:%[0-9]+]]:_(s32) = G_AND [[COPY8]], [[C3]]
+    ; GFX9: [[COPY9:%[0-9]+]]:_(s32) = COPY [[LSHR5]](s32)
+    ; GFX9: [[AND10:%[0-9]+]]:_(s32) = G_AND [[COPY9]], [[C3]]
+    ; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[AND9]], [[AND10]]
+    ; GFX9: [[AND11:%[0-9]+]]:_(s32) = G_AND [[MUL3]], [[C3]]
+    ; GFX9: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL3]](s32), [[AND11]]
+    ; GFX9: [[COPY10:%[0-9]+]]:_(s32) = COPY [[MUL]](s32)
+    ; GFX9: [[AND12:%[0-9]+]]:_(s32) = G_AND [[COPY10]], [[C3]]
+    ; GFX9: [[COPY11:%[0-9]+]]:_(s32) = COPY [[MUL1]](s32)
+    ; GFX9: [[AND13:%[0-9]+]]:_(s32) = G_AND [[COPY11]], [[C3]]
+    ; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND13]], [[C]](s32)
+    ; GFX9: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND12]], [[SHL]]
+    ; GFX9: [[COPY12:%[0-9]+]]:_(s32) = COPY [[MUL2]](s32)
+    ; GFX9: [[AND14:%[0-9]+]]:_(s32) = G_AND [[COPY12]], [[C3]]
+    ; GFX9: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND14]], [[C1]](s32)
+    ; GFX9: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
+    ; GFX9: [[COPY13:%[0-9]+]]:_(s32) = COPY [[MUL3]](s32)
+    ; GFX9: [[AND15:%[0-9]+]]:_(s32) = G_AND [[COPY13]], [[C3]]
+    ; GFX9: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND15]], [[C2]](s32)
+    ; GFX9: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
+    ; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
+    ; GFX9: $vgpr0 = COPY [[OR2]](s32)
+    ; GFX9: $vgpr1 = COPY [[ANYEXT]](s32)
+    %0:_(s32) = COPY $vgpr0
+    %1:_(s32) = COPY $vgpr1
+    %2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8) = G_UNMERGE_VALUES %0
+    %6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8) = G_UNMERGE_VALUES %1
+    %10:_(<4 x s8>) = G_BUILD_VECTOR %2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8)
+    %11:_(<4 x s8>) = G_BUILD_VECTOR %6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8)
+    %12:_(<4 x s8>), %18:_(<4 x s1>) = G_UMULO %10:_, %11:_
+    %13:_(s8), %14:_(s8), %15:_(s8), %16:_(s8) = G_UNMERGE_VALUES %12:_(<4 x s8>)
+    %19:_(s1), %20:_(s1), %21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %18:_(<4 x s1>)
+    %17:_(s32) = G_MERGE_VALUES %13, %14, %15, %16
+    %23:_(s32) = G_ANYEXT %19
+    $vgpr0 = COPY %17
+    $vgpr1 = COPY %23
+...