diff --git a/llvm/include/llvm/CodeGen/GlobalISel/MIPatternMatch.h b/llvm/include/llvm/CodeGen/GlobalISel/MIPatternMatch.h
--- a/llvm/include/llvm/CodeGen/GlobalISel/MIPatternMatch.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/MIPatternMatch.h
@@ -681,6 +681,41 @@
       Src0, Src1, Src2);
 }
 
+// TODO: We could just use TernaryOp_match if we allow match() functions to
+//   optionally take a MachineOperand instead of always taking registers.
+//   We could then just have a m_ShuffleMask matcher like m_Reg for instance.
+template <typename Src0Ty, typename Src1Ty> struct GShuffleVector_match {
+  Src0Ty Src0;
+  Src1Ty Src1;
+  ArrayRef<int> &ShuffleMask;
+
+  GShuffleVector_match(const Src0Ty &Src0, const Src1Ty &Src1,
+                       ArrayRef<int> &ShuffleMask)
+      : Src0(Src0), Src1(Src1), ShuffleMask(ShuffleMask) {}
+
+  template <typename OpTy>
+  bool match(const MachineRegisterInfo &MRI, OpTy &&Op) {
+    MachineInstr *TmpMI;
+    if (mi_match(Op, MRI, m_MInstr(TmpMI))) {
+      if (TmpMI->getOpcode() == TargetOpcode::G_SHUFFLE_VECTOR &&
+          TmpMI->getNumOperands() == 4) {
+        ShuffleMask = TmpMI->getOperand(3).getShuffleMask();
+        return Src0.match(MRI, TmpMI->getOperand(1).getReg()) &&
+               Src1.match(MRI, TmpMI->getOperand(2).getReg());
+      }
+    }
+
+    return false;
+  }
+};
+
+template <typename Src0Ty, typename Src1Ty>
+inline GShuffleVector_match<Src0Ty, Src1Ty>
+m_GShuffleVector(const Src0Ty &Src0, const Src1Ty &Src1,
+                 ArrayRef<int> &ShuffleMask) {
+  return GShuffleVector_match<Src0Ty, Src1Ty>(Src0, Src1, ShuffleMask);
+}
+
 /// Matches a register negated by a G_SUB.
 /// G_SUB 0, %negated_reg
 template <typename SrcTy>
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
--- a/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCombine.td
@@ -88,6 +88,12 @@
          [{ return RegBankHelper.matchFPMed3ToClamp(*${fmed3}, ${matchinfo}); }]),
   (apply [{ RegBankHelper.applyClamp(*${fmed3}, ${matchinfo}); }])>;
 
+def trunc_shift_shufflevector_fold : GICombineRule<
+  (defs root:$trunc, register_matchinfo:$matchinfo),
+  (match (wip_match_opcode G_TRUNC):$trunc,
+         [{ return RegBankHelper.matchTruncShiftShuffleVectorFold(*${trunc}, ${matchinfo}); }]),
+  (apply [{ RegBankHelper.applyTruncShiftShuffleVectorFold(*${trunc}, ${matchinfo}); }])>;
+
 def remove_fcanonicalize_matchinfo : GIDefMatchData<"Register">;
 
 def remove_fcanonicalize : GICombineRule<
@@ -128,7 +134,8 @@
 def AMDGPURegBankCombinerHelper : GICombinerHelper<
   "AMDGPUGenRegBankCombinerHelper",
   [zext_trunc_fold, int_minmax_to_med3, ptr_add_immed_chain,
-   fp_minmax_to_clamp, fp_minmax_to_med3, fmed3_intrinsic_to_clamp]> {
+   fp_minmax_to_clamp, fp_minmax_to_med3, fmed3_intrinsic_to_clamp,
+   trunc_shift_shufflevector_fold]> {
   let DisableRuleOption = "amdgpuregbankcombiner-disable-rule";
   let StateClass = "AMDGPURegBankCombinerHelperState";
   let AdditionalArguments = [];
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
@@ -74,6 +74,9 @@
   void applyMed3(MachineInstr &MI, Med3MatchInfo &MatchInfo);
   void applyClamp(MachineInstr &MI, Register &Reg);
 
+  bool matchTruncShiftShuffleVectorFold(MachineInstr &MI, Register &Reg);
+  void applyTruncShiftShuffleVectorFold(MachineInstr &MI, Register &Reg);
+
 private:
   AMDGPU::SIModeRegisterDefaults getMode();
   bool getIEEE();
@@ -328,6 +331,67 @@
   MI.eraseFromParent();
 }
 
+bool AMDGPURegBankCombinerHelper::matchTruncShiftShuffleVectorFold(
+    MachineInstr &MI, Register &Reg) {
+  // Fold (G_TRUNC (G_LSHR (G_BITCAST (G_SHUFFLE_VECTOR %a, %b, shufflemask(1,
+  // ?))), K)) into a simple (G_TRUNC (G_BITCAST(%a)) if the shift amount (K) is
+  // 1/2 of the destination type and the vector types have 2 elements.
+
+  assert(MI.getOpcode() == AMDGPU::G_TRUNC);
+
+  Register TruncSrc = MI.getOperand(1).getReg();
+  const LLT TruncSrcTy = MRI.getType(TruncSrc);
+  const unsigned TruncSrcSize = TruncSrcTy.getSizeInBits();
+
+  Register LHS, RHS;
+  ArrayRef<int> ShuffleMask;
+  Optional<ValueAndVReg> ShiftAmount;
+  if (!mi_match(TruncSrc, MRI,
+                m_GLShr(m_GBitcast(m_GShuffleVector(m_Reg(LHS), m_Reg(RHS),
+                                                    ShuffleMask)),
+                        m_GCst(ShiftAmount)))) {
+    return false;
+  }
+
+  // The shift amount is 1/2 of the scalar type.
+  if (ShiftAmount->Value != (TruncSrcSize / 2))
+    return false;
+
+  // The operands of the SHUFFLE_VECTOR must be the same size as its
+  // destination. This limitation could be lifted if needed, but
+  // applyTruncShiftShuffleVectorFold will need to take it into account and
+  // generate additional operations to trunc the input instead of just
+  // generating a bitcast.
+  if (MRI.getType(LHS).getSizeInBits() != TruncSrcSize ||
+      MRI.getType(RHS).getSizeInBits() != TruncSrcSize)
+    return false;
+
+  // The SHUFFLE_VECTOR's dest is a 2-element vector
+  // and the first element is 1 (2nd element from first vector).
+  if (ShuffleMask.size() != 2 || ShuffleMask[0] != 1)
+    return false;
+
+  // We can just replace the trunc src with a bitcast of the LHS of the
+  // G_SHUFFLE_VECTOR.
+  Reg = LHS;
+  return true;
+}
+
+void AMDGPURegBankCombinerHelper::applyTruncShiftShuffleVectorFold(
+    MachineInstr &MI, Register &Reg) {
+  B.setInstrAndDebugLoc(MI);
+
+  Register TruncSrc = MI.getOperand(1).getReg();
+  const RegisterBank *TruncSrcRB = MRI.getRegBankOrNull(TruncSrc);
+  assert(TruncSrcRB && "TruncSrc has no RegBank assigned");
+
+  Register NewSrc = MRI.createGenericVirtualRegister(MRI.getType(TruncSrc));
+  MRI.setRegBank(NewSrc, *TruncSrcRB);
+
+  B.buildBitcast(NewSrc, Reg);
+  MI.getOperand(1).setReg(NewSrc);
+}
+
 AMDGPU::SIModeRegisterDefaults AMDGPURegBankCombinerHelper::getMode() {
   return MF.getInfo<SIMachineFunctionInfo>()->getMode();
 }
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-shift-shufflevector.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-shift-shufflevector.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/combine-trunc-shift-shufflevector.mir
@@ -0,0 +1,272 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -run-pass=amdgpu-regbank-combiner -verify-machineinstrs %s -o - | FileCheck %s
+
+---
+name:            lshr16_v2s16_mask10
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: lshr16_v2s16_mask10
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[COPY]](<2 x s16>)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[BITCAST]](s32)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
+    %0:vgpr(<2 x s16>) = COPY $vgpr0
+    %1:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 16
+    %5:vgpr(s32) = G_LSHR %3, %4
+    %6:vgpr(s16) = G_TRUNC %5
+    %7:vgpr(s32) = G_ANYEXT %6
+    $vgpr0 = COPY %7
+...
+
+---
+name:            lshr16_v2s16_mask10_notrunc_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: lshr16_v2s16_mask10_notrunc_nofold
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s16>), [[DEF]], shufflemask(1, 0)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[SHUF]](<2 x s16>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 16
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s32) = G_LSHR [[BITCAST]], [[C]](s32)
+    ; CHECK-NEXT: $vgpr0 = COPY [[LSHR]](s32)
+    %0:vgpr(<2 x s16>) = COPY $vgpr0
+    %1:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 16
+    %5:vgpr(s32) = G_LSHR %3, %4
+    $vgpr0 = COPY %5
+...
+
+---
+name:            lshr16_v2s16_v4s16_mask10_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; CHECK-LABEL: name: lshr16_v2s16_v4s16_mask10_nofold
+    ; CHECK: liveins: $vgpr0_vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<4 x s16>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<4 x s16>), [[DEF]], shufflemask(1, 0)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[SHUF]](<2 x s16>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 16
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s32) = G_LSHR [[BITCAST]], [[C]](s32)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[LSHR]](s32)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
+    %0:vgpr(<4 x s16>) = COPY $vgpr0_vgpr1
+    %1:vgpr(<4 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 16
+    %5:vgpr(s32) = G_LSHR %3, %4
+    %6:vgpr(s16) = G_TRUNC %5
+    %7:vgpr(s32) = G_ANYEXT %6
+    $vgpr0 = COPY %7
+...
+
+---
+name:            lshr8_v2s16_mask10_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: lshr8_v2s16_mask10_nofold
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s16>), [[DEF]], shufflemask(1, 0)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[SHUF]](<2 x s16>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 8
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s32) = G_LSHR [[BITCAST]], [[C]](s32)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[LSHR]](s32)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
+    %0:vgpr(<2 x s16>) = COPY $vgpr0
+    %1:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 8
+    %5:vgpr(s32) = G_LSHR %3, %4
+    %6:vgpr(s16) = G_TRUNC %5
+    %7:vgpr(s32) = G_ANYEXT %6
+    $vgpr0 = COPY %7
+...
+
+---
+name:            lshr16_v2s16_mask11
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: lshr16_v2s16_mask11
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[COPY]](<2 x s16>)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[BITCAST]](s32)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
+    %0:vgpr(<2 x s16>) = COPY $vgpr0
+    %1:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 1)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 16
+    %5:vgpr(s32) = G_LSHR %3, %4
+    %6:vgpr(s16) = G_TRUNC %5
+    %7:vgpr(s32) = G_ANYEXT %6
+    $vgpr0 = COPY %7
+...
+
+---
+name:            lshr16_v2s16_mask01_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+    ; CHECK-LABEL: name: lshr16_v2s16_mask01_nofold
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s16>) = COPY $vgpr0
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s16>), [[DEF]], shufflemask(0, 1)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s32) = G_BITCAST [[SHUF]](<2 x s16>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s32) = G_CONSTANT i32 16
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s32) = G_LSHR [[BITCAST]], [[C]](s32)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s16) = G_TRUNC [[LSHR]](s32)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s32) = G_ANYEXT [[TRUNC]](s16)
+    ; CHECK-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
+    %0:vgpr(<2 x s16>) = COPY $vgpr0
+    %1:vgpr(<2 x s16>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s16>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(0, 1)
+    %3:vgpr(s32) = G_BITCAST %2
+    %4:vgpr(s32) = G_CONSTANT i32 16
+    %5:vgpr(s32) = G_LSHR %3, %4
+    %6:vgpr(s16) = G_TRUNC %5
+    %7:vgpr(s32) = G_ANYEXT %6
+    $vgpr0 = COPY %7
+...
+
+---
+name:            lshr32_v2s32_mask10
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; CHECK-LABEL: name: lshr32_v2s32_mask10
+    ; CHECK: liveins: $vgpr0_vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s64) = G_BITCAST [[COPY]](<2 x s32>)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s32) = G_TRUNC [[BITCAST]](s64)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s64) = G_ANYEXT [[TRUNC]](s32)
+    ; CHECK-NEXT: $vgpr0_vgpr1 = COPY [[ANYEXT]](s64)
+    %0:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s64) = G_BITCAST %2
+    %4:vgpr(s64) = G_CONSTANT i64 32
+    %5:vgpr(s64) = G_LSHR %3, %4
+    %6:vgpr(s32) = G_TRUNC %5
+    %7:vgpr(s64) = G_ANYEXT %6
+    $vgpr0_vgpr1 = COPY %7
+...
+
+---
+name:            lshr16_v2s32_mask10_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; CHECK-LABEL: name: lshr16_v2s32_mask10_nofold
+    ; CHECK: liveins: $vgpr0_vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s32>), [[DEF]], shufflemask(1, 0)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s64) = G_BITCAST [[SHUF]](<2 x s32>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 16
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s64) = G_LSHR [[BITCAST]], [[C]](s64)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s32) = G_TRUNC [[LSHR]](s64)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s64) = G_ANYEXT [[TRUNC]](s32)
+    ; CHECK-NEXT: $vgpr0_vgpr1 = COPY [[ANYEXT]](s64)
+    %0:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 0)
+    %3:vgpr(s64) = G_BITCAST %2
+    %4:vgpr(s64) = G_CONSTANT i64 16
+    %5:vgpr(s64) = G_LSHR %3, %4
+    %6:vgpr(s32) = G_TRUNC %5
+    %7:vgpr(s64) = G_ANYEXT %6
+    $vgpr0_vgpr1 = COPY %7
+...
+
+---
+name:            lshr32_v2s32_mask11
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; CHECK-LABEL: name: lshr32_v2s32_mask11
+    ; CHECK: liveins: $vgpr0_vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s64) = G_BITCAST [[COPY]](<2 x s32>)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s32) = G_TRUNC [[BITCAST]](s64)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s64) = G_ANYEXT [[TRUNC]](s32)
+    ; CHECK-NEXT: $vgpr0_vgpr1 = COPY [[ANYEXT]](s64)
+    %0:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(1, 1)
+    %3:vgpr(s64) = G_BITCAST %2
+    %4:vgpr(s64) = G_CONSTANT i64 32
+    %5:vgpr(s64) = G_LSHR %3, %4
+    %6:vgpr(s32) = G_TRUNC %5
+    %7:vgpr(s64) = G_ANYEXT %6
+    $vgpr0_vgpr1 = COPY %7
+...
+
+---
+name:            lshr32_v2s32_mask01_nofold
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0_vgpr1
+    ; CHECK-LABEL: name: lshr32_v2s32_mask01_nofold
+    ; CHECK: liveins: $vgpr0_vgpr1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR [[COPY]](<2 x s32>), [[DEF]], shufflemask(0, 1)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:vgpr(s64) = G_BITCAST [[SHUF]](<2 x s32>)
+    ; CHECK-NEXT: [[C:%[0-9]+]]:vgpr(s64) = G_CONSTANT i64 32
+    ; CHECK-NEXT: [[LSHR:%[0-9]+]]:vgpr(s64) = G_LSHR [[BITCAST]], [[C]](s64)
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:vgpr(s32) = G_TRUNC [[LSHR]](s64)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:vgpr(s64) = G_ANYEXT [[TRUNC]](s32)
+    ; CHECK-NEXT: $vgpr0_vgpr1 = COPY [[ANYEXT]](s64)
+    %0:vgpr(<2 x s32>) = COPY $vgpr0_vgpr1
+    %1:vgpr(<2 x s32>) = G_IMPLICIT_DEF
+    %2:vgpr(<2 x s32>) = G_SHUFFLE_VECTOR %0:vgpr, %1:vgpr, shufflemask(0, 1)
+    %3:vgpr(s64) = G_BITCAST %2
+    %4:vgpr(s64) = G_CONSTANT i64 32
+    %5:vgpr(s64) = G_LSHR %3, %4
+    %6:vgpr(s32) = G_TRUNC %5
+    %7:vgpr(s64) = G_ANYEXT %6
+    $vgpr0_vgpr1 = COPY %7
+...