GlobalISel: Fix artifact combiner constant legality checks for vectors

[arsenm]

Summary

Since G_CONSTANT is illegal for vectors, this needs to check
what buildConstant will produce for a splat vector.

[arsenm]

Include actual change

[aditya_nandakumar]

test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-sext.mir

17

Is this correct ? We're shifting a 32 bit source by 32 into 32 bit destination.

[arsenm]

Fix using getSizeInBits instead of getScalarSizeInBits

[aditya_nandakumar]

Thanks. LGTM.

[arsenm]

r353449

test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-sext.mir

17

Thanks, I have another patch where I've been auditing all the getSizeInBits which should be getScalarSizeInBits

include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h

bool tryCombineZExt(MachineInstr &MI,
     unsigned DstReg = MI.getOperand(0).getReg();
     unsigned SrcReg = lookThroughCopyInstrs(MI.getOperand(1).getReg());
 
     // zext(trunc x) - > and (aext/copy/trunc x), mask
     unsigned TruncSrc;
     if (mi_match(SrcReg, MRI, m_GTrunc(m_Reg(TruncSrc)))) {
       LLT DstTy = MRI.getType(DstReg);
       if (isInstUnsupported({TargetOpcode::G_AND, {DstTy}}) ||
-          isInstUnsupported({TargetOpcode::G_CONSTANT, {DstTy}}))
+          isConstantUnsupported(DstTy))
         return false;
       LLVM_DEBUG(dbgs() << ".. Combine MI: " << MI;);
       LLT SrcTy = MRI.getType(SrcReg);
-      APInt Mask = APInt::getAllOnesValue(SrcTy.getSizeInBits());
+      APInt Mask = APInt::getAllOnesValue(SrcTy.getScalarSizeInBits());
       auto MIBMask = Builder.buildConstant(DstTy, Mask.getZExtValue());
       Builder.buildAnd(DstReg, Builder.buildAnyExtOrTrunc(DstTy, TruncSrc),
                        MIBMask);
       markInstAndDefDead(MI, *MRI.getVRegDef(SrcReg), DeadInsts);
       return true;
     }
     return tryFoldImplicitDef(MI, DeadInsts);
   }
bool tryCombineSExt(MachineInstr &MI,
     // sext(trunc x) - > ashr (shl (aext/copy/trunc x), c), c
     unsigned TruncSrc;
     if (mi_match(SrcReg, MRI, m_GTrunc(m_Reg(TruncSrc)))) {
       LLT DstTy = MRI.getType(DstReg);
       // Guess on the RHS shift amount type, which should be re-legalized if
       // applicable.
       if (isInstUnsupported({TargetOpcode::G_SHL, {DstTy, DstTy}}) ||
           isInstUnsupported({TargetOpcode::G_ASHR, {DstTy, DstTy}}) ||
-          isInstUnsupported({TargetOpcode::G_CONSTANT, {DstTy}}))
+          isConstantUnsupported(DstTy))
         return false;
       LLVM_DEBUG(dbgs() << ".. Combine MI: " << MI;);
       LLT SrcTy = MRI.getType(SrcReg);
-      unsigned ShAmt = DstTy.getSizeInBits() - SrcTy.getSizeInBits();
+      unsigned ShAmt = DstTy.getScalarSizeInBits() - SrcTy.getScalarSizeInBits();
       auto MIBShAmt = Builder.buildConstant(DstTy, ShAmt);
       auto MIBShl = Builder.buildInstr(
           TargetOpcode::G_SHL, {DstTy},
           {Builder.buildAnyExtOrTrunc(DstTy, TruncSrc), MIBShAmt});
       Builder.buildInstr(TargetOpcode::G_ASHR, {DstReg}, {MIBShl, MIBShAmt});
       markInstAndDefDead(MI, *MRI.getVRegDef(SrcReg), DeadInsts);
       return true;
     }
if (MachineInstr *DefMI = getOpcodeDef(TargetOpcode::G_IMPLICIT_DEF,
         // G_ANYEXT (G_IMPLICIT_DEF) -> G_IMPLICIT_DEF
         if (isInstUnsupported({TargetOpcode::G_IMPLICIT_DEF, {DstTy}}))
           return false;
         LLVM_DEBUG(dbgs() << ".. Combine G_ANYEXT(G_IMPLICIT_DEF): " << MI;);
         Builder.buildInstr(TargetOpcode::G_IMPLICIT_DEF, {DstReg}, {});
       } else {
         // G_[SZ]EXT (G_IMPLICIT_DEF) -> G_CONSTANT 0 because the top
         // bits will be 0 for G_ZEXT and 0/1 for the G_SEXT.
-        if (isInstUnsupported({TargetOpcode::G_CONSTANT, {DstTy}}))
+        if (isConstantUnsupported(DstTy))
           return false;
         LLVM_DEBUG(dbgs() << ".. Combine G_[SZ]EXT(G_IMPLICIT_DEF): " << MI;);
         Builder.buildConstant(DstReg, 0);
       }
 
       markInstAndDefDead(MI, *DefMI, DeadInsts);
       return true;
     }
private:
   /// Checks if the target legalizer info has specified anything about the
   /// instruction, or if unsupported.
   bool isInstUnsupported(const LegalityQuery &Query) const {
     using namespace LegalizeActions;
     auto Step = LI.getAction(Query);
     return Step.Action == Unsupported || Step.Action == NotFound;
   }
 
+  bool isConstantUnsupported(LLT Ty) const {
+    if (!Ty.isVector())
+      return isInstUnsupported({TargetOpcode::G_CONSTANT, {Ty}});
+
+    LLT EltTy = Ty.getElementType();
+    return isInstUnsupported({TargetOpcode::G_CONSTANT, {EltTy}}) ||
+           isInstUnsupported({TargetOpcode::G_BUILD_VECTOR, {Ty, EltTy}});
+  }
+
   /// Looks through copy instructions and returns the actual
   /// source register.
   unsigned lookThroughCopyInstrs(unsigned Reg) {
     unsigned TmpReg;
     while (mi_match(Reg, MRI, m_Copy(m_Reg(TmpReg)))) {
       if (MRI.getType(TmpReg).isValid())
         Reg = TmpReg;
       else
         break;
     }
     return Reg;
   }
 };
 
 } // namespace llvm

test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-anyext.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer  -global-isel-abort=0 %s -o - | FileCheck %s
+# FIXME: Remove -global-isel-abort=0 when G_TRUNC legality handled
+
+---
+name: test_anyext_trunc_v2s32_to_v2s16_to_v2s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_anyext_trunc_v2s32_to_v2s16_to_v2s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY [[COPY]](<2 x s32>)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[COPY1]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s32>) = G_ANYEXT %1
+    $vgpr0_vgpr1 = COPY %2
+...
+
+---
+name: test_anyext_trunc_v2s32_to_v2s16_to_v2s64
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_anyext_trunc_v2s32_to_v2s16_to_v2s64
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32)
+    ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32)
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[ANYEXT]](s64), [[ANYEXT1]](s64)
+    ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s64>) = G_ANYEXT %1
+    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
+...
+
+---
+name: test_anyext_trunc_v2s32_to_v2s8_to_v2s16
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_anyext_trunc_v2s32_to_v2s8_to_v2s16
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[COPY]](<2 x s32>)
+    ; CHECK: $vgpr0 = COPY [[TRUNC]](<2 x s16>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s8>) = G_TRUNC %0
+    %2:_(<2 x s16>) = G_ANYEXT %1
+    $vgpr0 = COPY %2
+...
+
+---
+name: test_anyext_trunc_v3s32_to_v3s16_to_v3s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1_vgpr2
+
+    ; CHECK-LABEL: name: test_anyext_trunc_v3s32_to_v3s16_to_v3s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY [[COPY]](<3 x s32>)
+    ; CHECK: $vgpr0_vgpr1_vgpr2 = COPY [[COPY1]](<3 x s32>)
+    %0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    %1:_(<3 x s16>) = G_TRUNC %0
+    %2:_(<3 x s32>) = G_ANYEXT %1
+    $vgpr0_vgpr1_vgpr2 = COPY %2
+...
+

test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-sext.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer  -global-isel-abort=0 %s -o - | FileCheck %s
+# FIXME: Remove -global-isel-abort=0 when G_TRUNC legality handled
+
+---
+name: test_sext_trunc_v2s32_to_v2s16_to_v2s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_sext_trunc_v2s32_to_v2s16_to_v2s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY [[COPY]](<2 x s32>)
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
+    ; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[UV]], [[C]](s32)
+    ; CHECK: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[UV1]], [[C]](s32)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
+    ; CHECK: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[ASHR]](s32), [[ASHR1]](s32)
+    ; CHECK: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s32>) = G_SEXT %1
+    $vgpr0_vgpr1 = COPY %2
+...
+
+---
+name: test_sext_trunc_v2s32_to_v2s16_to_v2s64
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_sext_trunc_v2s32_to_v2s16_to_v2s64
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32)
+    ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32)
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[C]](s64)
+    ; CHECK: [[SHL:%[0-9]+]]:_(s64) = G_SHL [[ANYEXT]], [[TRUNC]](s32)
+    ; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[C]](s64)
+    ; CHECK: [[SHL1:%[0-9]+]]:_(s64) = G_SHL [[ANYEXT1]], [[TRUNC1]](s32)
+    ; CHECK: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[C]](s64)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s64) = G_ASHR [[SHL]], [[TRUNC2]](s32)
+    ; CHECK: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[C]](s64)
+    ; CHECK: [[ASHR1:%[0-9]+]]:_(s64) = G_ASHR [[SHL1]], [[TRUNC3]](s32)
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[ASHR]](s64), [[ASHR1]](s64)
+    ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s64>) = G_SEXT %1
+    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
+...
+
+---
+name: test_sext_trunc_v2s32_to_v2s8_to_v2s16
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_sext_trunc_v2s32_to_v2s8_to_v2s16
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[C]](s16), [[C]](s16)
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[COPY]](<2 x s32>)
+    ; CHECK: [[SHL:%[0-9]+]]:_(<2 x s16>) = G_SHL [[TRUNC]], [[BUILD_VECTOR]](<2 x s16>)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(<2 x s16>) = G_ASHR [[SHL]], [[BUILD_VECTOR]](<2 x s16>)
+    ; CHECK: $vgpr0 = COPY [[ASHR]](<2 x s16>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s8>) = G_TRUNC %0
+    %2:_(<2 x s16>) = G_SEXT %1
+    $vgpr0 = COPY %2
+...
+
+---
+name: test_sext_trunc_v3s32_to_v3s16_to_v3s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1_vgpr2
+
+    ; CHECK-LABEL: name: test_sext_trunc_v3s32_to_v3s16_to_v3s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY [[COPY]](<3 x s32>)
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
+    ; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[UV]], [[C]](s32)
+    ; CHECK: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[UV1]], [[C]](s32)
+    ; CHECK: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[UV2]], [[C]](s32)
+    ; CHECK: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
+    ; CHECK: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
+    ; CHECK: [[ASHR2:%[0-9]+]]:_(s32) = G_ASHR [[SHL2]], [[C]](s32)
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ASHR]](s32), [[ASHR1]](s32), [[ASHR2]](s32)
+    ; CHECK: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
+    %0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    %1:_(<3 x s16>) = G_TRUNC %0
+    %2:_(<3 x s32>) = G_SEXT %1
+    $vgpr0_vgpr1_vgpr2 = COPY %2
+...
+

test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-zext.mir

+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -O0 -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer  -global-isel-abort=0 %s -o - | FileCheck %s
+# FIXME: Remove -global-isel-abort=0 when G_TRUNC legality handled
+
+---
+name: test_zext_trunc_v2s32_to_v2s16_to_v2s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_zext_trunc_v2s32_to_v2s16_to_v2s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32)
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY [[COPY]](<2 x s32>)
+    ; CHECK: [[AND:%[0-9]+]]:_(<2 x s32>) = G_AND [[COPY1]], [[BUILD_VECTOR]]
+    ; CHECK: $vgpr0_vgpr1 = COPY [[AND]](<2 x s32>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s32>) = G_ZEXT %1
+    $vgpr0_vgpr1 = COPY %2
+...
+
+---
+name: test_zext_trunc_v2s32_to_v2s16_to_v2s64
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_zext_trunc_v2s32_to_v2s16_to_v2s64
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 65535
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
+    ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32)
+    ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32)
+    ; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[ANYEXT]], [[C]]
+    ; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[ANYEXT1]], [[C]]
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[AND]](s64), [[AND1]](s64)
+    ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s16>) = G_TRUNC %0
+    %2:_(<2 x s64>) = G_ZEXT %1
+    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
+...
+
+---
+name: test_zext_trunc_v2s32_to_v2s8_to_v2s16
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+
+    ; CHECK-LABEL: name: test_zext_trunc_v2s32_to_v2s8_to_v2s16
+    ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[C]](s16), [[C]](s16)
+    ; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[COPY]](<2 x s32>)
+    ; CHECK: [[AND:%[0-9]+]]:_(<2 x s16>) = G_AND [[TRUNC]], [[BUILD_VECTOR]]
+    ; CHECK: $vgpr0 = COPY [[AND]](<2 x s16>)
+    %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:_(<2 x s8>) = G_TRUNC %0
+    %2:_(<2 x s16>) = G_ZEXT %1
+    $vgpr0 = COPY %2
+...
+
+---
+name: test_zext_trunc_v3s32_to_v3s16_to_v3s32
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1_vgpr2
+
+    ; CHECK-LABEL: name: test_zext_trunc_v3s32_to_v3s16_to_v3s32
+    ; CHECK: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+    ; CHECK: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY [[COPY]](<3 x s32>)
+    ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
+    ; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[UV]], [[C]]
+    ; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[UV1]], [[C]]
+    ; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[UV2]], [[C]]
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32), [[AND2]](s32)
+    ; CHECK: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
+    %0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
+    %1:_(<3 x s16>) = G_TRUNC %0
+    %2:_(<3 x s32>) = G_ZEXT %1
+    $vgpr0_vgpr1_vgpr2 = COPY %2
+...
+