diff --git a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h
index 637c2c71b0241..6afaea3f3fc5c 100644
--- a/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h
+++ b/llvm/include/llvm/CodeGen/GlobalISel/LegalizerInfo.h
@@ -908,6 +908,18 @@ class LegalizeRuleSet {
         LegalizeMutations::widenScalarOrEltToNextPow2(TypeIdx, MinSize));
   }
 
+  /// Widen the scalar or vector element type to the next power of two that is
+  /// at least MinSize.  No effect if the scalar size is a power of two.
+  LegalizeRuleSet &widenScalarOrEltToNextPow2OrMinSize(unsigned TypeIdx,
+                                                       unsigned MinSize = 0) {
+    using namespace LegalityPredicates;
+    return actionIf(
+        LegalizeAction::WidenScalar,
+        any(scalarOrEltNarrowerThan(TypeIdx, MinSize),
+            scalarOrEltSizeNotPow2(typeIdx(TypeIdx))),
+        LegalizeMutations::widenScalarOrEltToNextPow2(TypeIdx, MinSize));
+  }
+
   LegalizeRuleSet &narrowScalar(unsigned TypeIdx, LegalizeMutation Mutation) {
     using namespace LegalityPredicates;
     return actionIf(LegalizeAction::NarrowScalar, isScalar(typeIdx(TypeIdx)),
diff --git a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
index 8079f853aef85..1d016e684c48f 100644
--- a/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
@@ -2495,6 +2495,7 @@ LegalizerHelper::widenScalar(MachineInstr &MI, unsigned TypeIdx, LLT WideTy) {
   case TargetOpcode::G_OR:
   case TargetOpcode::G_XOR:
   case TargetOpcode::G_SUB:
+  case TargetOpcode::G_SHUFFLE_VECTOR:
     // Perform operation at larger width (any extension is fines here, high bits
     // don't affect the result) and then truncate the result back to the
     // original type.
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index 117c4004d41df..33f04e6ad0c76 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -956,6 +956,9 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
           },
           changeTo(1, 0))
       .moreElementsToNextPow2(0)
+      .widenScalarOrEltToNextPow2OrMinSize(0, 8)
+      .clampNumElements(0, v8s8, v16s8)
+      .clampNumElements(0, v4s16, v8s16)
       .clampNumElements(0, v4s32, v4s32)
       .clampNumElements(0, v2s64, v2s64)
       .moreElementsIf(
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp b/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
index 5a8031641ae09..3cee2de4f5df8 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerLowering.cpp
@@ -780,6 +780,8 @@ bool matchScalarizeVectorUnmerge(MachineInstr &MI, MachineRegisterInfo &MRI) {
   auto &Unmerge = cast<GUnmerge>(MI);
   Register Src1Reg = Unmerge.getReg(Unmerge.getNumOperands() - 1);
   const LLT SrcTy = MRI.getType(Src1Reg);
+  if (SrcTy.getSizeInBits() != 128 && SrcTy.getSizeInBits() != 64)
+    return false;
   return SrcTy.isVector() && !SrcTy.isScalable() &&
          Unmerge.getNumOperands() == (unsigned)SrcTy.getNumElements() + 1;
 }
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
index 4879ffd28784c..63a26dcfea476 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-select.mir
@@ -287,39 +287,47 @@ body:             |
     ; CHECK-NEXT: %q0:_(<4 x s32>) = COPY $q0
     ; CHECK-NEXT: %q1:_(<4 x s32>) = COPY $q1
     ; CHECK-NEXT: %q2:_(<4 x s32>) = COPY $q2
-    ; CHECK-NEXT: %vec_cond0:_(<4 x s1>) = G_ICMP intpred(eq), %q0(<4 x s32>), %q1
-    ; CHECK-NEXT: %vec_cond1:_(<4 x s1>) = G_ICMP intpred(eq), %q0(<4 x s32>), %q2
+    ; CHECK-NEXT: [[ICMP:%[0-9]+]]:_(<4 x s32>) = G_ICMP intpred(eq), %q0(<4 x s32>), %q1
+    ; CHECK-NEXT: [[ICMP1:%[0-9]+]]:_(<4 x s32>) = G_ICMP intpred(eq), %q0(<4 x s32>), %q2
     ; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 4100
-    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 0.000000e+00
-    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C1]](s32), [[C1]](s32), [[C1]](s32), [[C1]](s32)
-    ; CHECK-NEXT: %cmp:_(s1) = G_ICMP intpred(eq), %w0(s32), [[C]]
-    ; CHECK-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT %cmp(s1)
-    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ZEXT]], 1
-    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[SEXT_INREG]](s32)
-    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(<4 x s1>) = G_IMPLICIT_DEF
-    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
-    ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s1>) = G_INSERT_VECTOR_ELT [[DEF]], [[TRUNC]](s1), [[C2]](s64)
-    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<4 x s1>) = G_SHUFFLE_VECTOR [[IVEC]](<4 x s1>), [[DEF]], shufflemask(0, 0, 0, 0)
-    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s8) = G_CONSTANT i8 1
-    ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s1) = G_TRUNC [[C3]](s8)
-    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<4 x s1>) = G_BUILD_VECTOR [[TRUNC1]](s1), [[TRUNC1]](s1), [[TRUNC1]](s1), [[TRUNC1]](s1)
-    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[SHUF]](<4 x s1>)
-    ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[BUILD_VECTOR1]](<4 x s1>)
-    ; CHECK-NEXT: [[XOR:%[0-9]+]]:_(<4 x s16>) = G_XOR [[ANYEXT]], [[ANYEXT1]]
-    ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(<4 x s1>) = G_TRUNC [[XOR]](<4 x s16>)
-    ; CHECK-NEXT: [[ANYEXT2:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT %vec_cond0(<4 x s1>)
-    ; CHECK-NEXT: [[ANYEXT3:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[SHUF]](<4 x s1>)
-    ; CHECK-NEXT: [[AND:%[0-9]+]]:_(<4 x s16>) = G_AND [[ANYEXT2]], [[ANYEXT3]]
-    ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(<4 x s1>) = G_TRUNC [[AND]](<4 x s16>)
-    ; CHECK-NEXT: [[ANYEXT4:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT %vec_cond1(<4 x s1>)
-    ; CHECK-NEXT: [[ANYEXT5:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[TRUNC2]](<4 x s1>)
-    ; CHECK-NEXT: [[AND1:%[0-9]+]]:_(<4 x s16>) = G_AND [[ANYEXT4]], [[ANYEXT5]]
-    ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(<4 x s1>) = G_TRUNC [[AND1]](<4 x s16>)
-    ; CHECK-NEXT: [[ANYEXT6:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[TRUNC3]](<4 x s1>)
-    ; CHECK-NEXT: [[ANYEXT7:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[TRUNC4]](<4 x s1>)
-    ; CHECK-NEXT: [[OR:%[0-9]+]]:_(<4 x s16>) = G_OR [[ANYEXT6]], [[ANYEXT7]]
-    ; CHECK-NEXT: %select:_(<4 x s1>) = G_TRUNC [[OR]](<4 x s16>)
-    ; CHECK-NEXT: %zext_select:_(<4 x s32>) = G_ZEXT %select(<4 x s1>)
+    ; CHECK-NEXT: [[ICMP2:%[0-9]+]]:_(s32) = G_ICMP intpred(eq), %w0(s32), [[C]]
+    ; CHECK-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ICMP2]], 1
+    ; CHECK-NEXT: [[DEF:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[DEF1:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
+    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
+    ; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s16) = COPY [[DEF1]](s16)
+    ; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY]](s16), [[COPY1]](s16), [[COPY2]](s16), [[DEF1]](s16)
+    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
+    ; CHECK-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+    ; CHECK-NEXT: [[IVEC:%[0-9]+]]:_(<4 x s16>) = G_INSERT_VECTOR_ELT [[BUILD_VECTOR]], [[TRUNC]](s16), [[C1]](s64)
+    ; CHECK-NEXT: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[IVEC]](<4 x s16>)
+    ; CHECK-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[UV]](s16)
+    ; CHECK-NEXT: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[UV1]](s16)
+    ; CHECK-NEXT: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s16)
+    ; CHECK-NEXT: [[TRUNC4:%[0-9]+]]:_(s8) = G_TRUNC [[UV3]](s16)
+    ; CHECK-NEXT: [[DEF2:%[0-9]+]]:_(s8) = G_IMPLICIT_DEF
+    ; CHECK-NEXT: [[BUILD_VECTOR1:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[TRUNC1]](s8), [[TRUNC2]](s8), [[TRUNC3]](s8), [[TRUNC4]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8)
+    ; CHECK-NEXT: [[BUILD_VECTOR2:%[0-9]+]]:_(<8 x s8>) = G_BUILD_VECTOR [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8), [[DEF2]](s8)
+    ; CHECK-NEXT: [[SHUF:%[0-9]+]]:_(<8 x s8>) = G_SHUFFLE_VECTOR [[BUILD_VECTOR1]](<8 x s8>), [[BUILD_VECTOR2]], shufflemask(0, 0, 0, 0, undef, undef, undef, undef)
+    ; CHECK-NEXT: [[UV4:%[0-9]+]]:_(<4 x s8>), [[UV5:%[0-9]+]]:_(<4 x s8>) = G_UNMERGE_VALUES [[SHUF]](<8 x s8>)
+    ; CHECK-NEXT: [[C2:%[0-9]+]]:_(s16) = G_CONSTANT i16 1
+    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
+    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
+    ; CHECK-NEXT: [[COPY5:%[0-9]+]]:_(s16) = COPY [[C2]](s16)
+    ; CHECK-NEXT: [[BUILD_VECTOR3:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[COPY3]](s16), [[COPY4]](s16), [[COPY5]](s16), [[C2]](s16)
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[UV4]](<4 x s8>)
+    ; CHECK-NEXT: [[XOR:%[0-9]+]]:_(<4 x s16>) = G_XOR [[ANYEXT]], [[BUILD_VECTOR3]]
+    ; CHECK-NEXT: [[TRUNC5:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[ICMP]](<4 x s32>)
+    ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(<4 x s16>) = G_ANYEXT [[UV4]](<4 x s8>)
+    ; CHECK-NEXT: [[AND:%[0-9]+]]:_(<4 x s16>) = G_AND [[TRUNC5]], [[ANYEXT1]]
+    ; CHECK-NEXT: [[TRUNC6:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[ICMP1]](<4 x s32>)
+    ; CHECK-NEXT: [[AND1:%[0-9]+]]:_(<4 x s16>) = G_AND [[TRUNC6]], [[XOR]]
+    ; CHECK-NEXT: [[OR:%[0-9]+]]:_(<4 x s16>) = G_OR [[AND]], [[AND1]]
+    ; CHECK-NEXT: [[ANYEXT2:%[0-9]+]]:_(<4 x s32>) = G_ANYEXT [[OR]](<4 x s16>)
+    ; CHECK-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; CHECK-NEXT: [[BUILD_VECTOR4:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C3]](s32), [[C3]](s32), [[C3]](s32), [[C3]](s32)
+    ; CHECK-NEXT: %zext_select:_(<4 x s32>) = G_AND [[ANYEXT2]], [[BUILD_VECTOR4]]
     ; CHECK-NEXT: $q0 = COPY %zext_select(<4 x s32>)
     ; CHECK-NEXT: RET_ReallyLR implicit $q0
     %w0:_(s32) = COPY $w0
diff --git a/llvm/test/CodeGen/AArch64/shufflevector.ll b/llvm/test/CodeGen/AArch64/shufflevector.ll
index df59eb8e629f4..b408bc1c38976 100644
--- a/llvm/test/CodeGen/AArch64/shufflevector.ll
+++ b/llvm/test/CodeGen/AArch64/shufflevector.ll
@@ -3,17 +3,7 @@
 ; RUN: llc -mtriple=aarch64-none-linux-gnu -global-isel -global-isel-abort=2 %s -o - 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-GI
 
 ; CHECK-GI:         warning: Instruction selection used fallback path for shufflevector_v2i1
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v4i8
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v32i8
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v2i16
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v16i16
 ; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v2i1_zeroes
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v4i8_zeroes
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v32i8_zeroes
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v2i16_zeroes
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v16i16_zeroes
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v3i8
-; CHECK-GI-NEXT:    warning: Instruction selection used fallback path for shufflevector_v3i8_zeroes
 
 ; ===== Legal Vector Types =====
 
@@ -205,68 +195,142 @@ define <2 x i1> @shufflevector_v2i1(<2 x i1> %a, <2 x i1> %b){
 }
 
 define i32 @shufflevector_v4i8(<4 x i8> %a, <4 x i8> %b){
-; CHECK-LABEL: shufflevector_v4i8:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    ext v0.8b, v1.8b, v0.8b, #6
-; CHECK-NEXT:    zip1 v1.4h, v1.4h, v0.4h
-; CHECK-NEXT:    ext v0.8b, v0.8b, v1.8b, #4
-; CHECK-NEXT:    xtn v0.8b, v0.8h
-; CHECK-NEXT:    fmov w0, s0
-; CHECK-NEXT:    add sp, sp, #16
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v4i8:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    sub sp, sp, #16
+; CHECK-SD-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-SD-NEXT:    ext v0.8b, v1.8b, v0.8b, #6
+; CHECK-SD-NEXT:    zip1 v1.4h, v1.4h, v0.4h
+; CHECK-SD-NEXT:    ext v0.8b, v0.8b, v1.8b, #4
+; CHECK-SD-NEXT:    xtn v0.8b, v0.8h
+; CHECK-SD-NEXT:    fmov w0, s0
+; CHECK-SD-NEXT:    add sp, sp, #16
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v4i8:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT:    mov h2, v0.h[1]
+; CHECK-GI-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-GI-NEXT:    mov h3, v1.h[1]
+; CHECK-GI-NEXT:    adrp x8, .LCPI15_0
+; CHECK-GI-NEXT:    mov h4, v0.h[2]
+; CHECK-GI-NEXT:    mov h5, v0.h[3]
+; CHECK-GI-NEXT:    mov h6, v1.h[3]
+; CHECK-GI-NEXT:    mov v0.b[1], v2.b[0]
+; CHECK-GI-NEXT:    mov h2, v1.h[2]
+; CHECK-GI-NEXT:    mov v1.b[1], v3.b[0]
+; CHECK-GI-NEXT:    mov v0.b[2], v4.b[0]
+; CHECK-GI-NEXT:    mov v1.b[2], v2.b[0]
+; CHECK-GI-NEXT:    mov v0.b[3], v5.b[0]
+; CHECK-GI-NEXT:    mov v1.b[3], v6.b[0]
+; CHECK-GI-NEXT:    mov v0.b[4], v0.b[0]
+; CHECK-GI-NEXT:    mov v1.b[4], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[5], v0.b[0]
+; CHECK-GI-NEXT:    mov v1.b[5], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[6], v0.b[0]
+; CHECK-GI-NEXT:    mov v1.b[6], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[7], v0.b[0]
+; CHECK-GI-NEXT:    mov v1.b[7], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.d[1], v1.d[0]
+; CHECK-GI-NEXT:    ldr d1, [x8, :lo12:.LCPI15_0]
+; CHECK-GI-NEXT:    tbl v0.16b, { v0.16b }, v1.16b
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <4 x i8> %a, <4 x i8> %b, <4 x i32> <i32 1, i32 2, i32 4, i32 7>
     %d = bitcast <4 x i8> %c to i32
     ret i32 %d
 }
 
 define <32 x i8> @shufflevector_v32i8(<32 x i8> %a, <32 x i8> %b){
-; CHECK-LABEL: shufflevector_v32i8:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    // kill: def $q2 killed $q2 def $q1_q2
-; CHECK-NEXT:    adrp x8, .LCPI16_0
-; CHECK-NEXT:    adrp x9, .LCPI16_1
-; CHECK-NEXT:    mov v1.16b, v0.16b
-; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI16_0]
-; CHECK-NEXT:    ldr q4, [x9, :lo12:.LCPI16_1]
-; CHECK-NEXT:    tbl v0.16b, { v1.16b, v2.16b }, v3.16b
-; CHECK-NEXT:    tbl v1.16b, { v1.16b, v2.16b }, v4.16b
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v32i8:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    // kill: def $q2 killed $q2 def $q1_q2
+; CHECK-SD-NEXT:    adrp x8, .LCPI16_0
+; CHECK-SD-NEXT:    adrp x9, .LCPI16_1
+; CHECK-SD-NEXT:    mov v1.16b, v0.16b
+; CHECK-SD-NEXT:    ldr q3, [x8, :lo12:.LCPI16_0]
+; CHECK-SD-NEXT:    ldr q4, [x9, :lo12:.LCPI16_1]
+; CHECK-SD-NEXT:    tbl v0.16b, { v1.16b, v2.16b }, v3.16b
+; CHECK-SD-NEXT:    tbl v1.16b, { v1.16b, v2.16b }, v4.16b
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v32i8:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    mov v3.16b, v0.16b
+; CHECK-GI-NEXT:    adrp x8, .LCPI16_1
+; CHECK-GI-NEXT:    adrp x9, .LCPI16_0
+; CHECK-GI-NEXT:    mov v4.16b, v2.16b
+; CHECK-GI-NEXT:    ldr q0, [x8, :lo12:.LCPI16_1]
+; CHECK-GI-NEXT:    ldr q1, [x9, :lo12:.LCPI16_0]
+; CHECK-GI-NEXT:    tbl v0.16b, { v3.16b, v4.16b }, v0.16b
+; CHECK-GI-NEXT:    tbl v1.16b, { v3.16b, v4.16b }, v1.16b
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 32, i32 32, i32 32, i32 1, i32 32, i32 32, i32 32, i32 2, i32 32, i32 32, i32 32, i32 3, i32 32, i32 32, i32 32, i32 4, i32 32, i32 32, i32 32, i32 5, i32 32, i32 32, i32 32, i32 6, i32 32, i32 32, i32 32, i32 7, i32 32, i32 32, i32 32>
     ret <32 x i8> %c
 }
 
 define i32 @shufflevector_v2i16(<2 x i16> %a, <2 x i16> %b){
-; CHECK-LABEL: shufflevector_v2i16:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    ext v0.8b, v0.8b, v1.8b, #4
-; CHECK-NEXT:    mov w8, v0.s[1]
-; CHECK-NEXT:    fmov w9, s0
-; CHECK-NEXT:    strh w9, [sp, #12]
-; CHECK-NEXT:    strh w8, [sp, #14]
-; CHECK-NEXT:    ldr w0, [sp, #12]
-; CHECK-NEXT:    add sp, sp, #16
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v2i16:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    sub sp, sp, #16
+; CHECK-SD-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-SD-NEXT:    ext v0.8b, v0.8b, v1.8b, #4
+; CHECK-SD-NEXT:    mov w8, v0.s[1]
+; CHECK-SD-NEXT:    fmov w9, s0
+; CHECK-SD-NEXT:    strh w9, [sp, #12]
+; CHECK-SD-NEXT:    strh w8, [sp, #14]
+; CHECK-SD-NEXT:    ldr w0, [sp, #12]
+; CHECK-SD-NEXT:    add sp, sp, #16
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v2i16:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT:    mov s2, v0.s[1]
+; CHECK-GI-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-GI-NEXT:    mov s3, v1.s[1]
+; CHECK-GI-NEXT:    adrp x8, .LCPI17_0
+; CHECK-GI-NEXT:    mov v0.h[1], v2.h[0]
+; CHECK-GI-NEXT:    mov v1.h[1], v3.h[0]
+; CHECK-GI-NEXT:    mov v0.h[2], v0.h[0]
+; CHECK-GI-NEXT:    mov v1.h[2], v0.h[0]
+; CHECK-GI-NEXT:    mov v0.h[3], v0.h[0]
+; CHECK-GI-NEXT:    mov v1.h[3], v0.h[0]
+; CHECK-GI-NEXT:    mov v0.d[1], v1.d[0]
+; CHECK-GI-NEXT:    ldr d1, [x8, :lo12:.LCPI17_0]
+; CHECK-GI-NEXT:    tbl v0.16b, { v0.16b }, v1.16b
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <2 x i16> %a, <2 x i16> %b, <2 x i32> <i32 1, i32 2>
     %d = bitcast <2 x i16> %c to i32
     ret i32 %d
 }
 
 define <16 x i16> @shufflevector_v16i16(<16 x i16> %a, <16 x i16> %b){
-; CHECK-LABEL: shufflevector_v16i16:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    // kill: def $q2 killed $q2 def $q1_q2
-; CHECK-NEXT:    adrp x8, .LCPI18_0
-; CHECK-NEXT:    adrp x9, .LCPI18_1
-; CHECK-NEXT:    mov v1.16b, v0.16b
-; CHECK-NEXT:    ldr q3, [x8, :lo12:.LCPI18_0]
-; CHECK-NEXT:    ldr q4, [x9, :lo12:.LCPI18_1]
-; CHECK-NEXT:    tbl v0.16b, { v1.16b, v2.16b }, v3.16b
-; CHECK-NEXT:    tbl v1.16b, { v1.16b, v2.16b }, v4.16b
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v16i16:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    // kill: def $q2 killed $q2 def $q1_q2
+; CHECK-SD-NEXT:    adrp x8, .LCPI18_0
+; CHECK-SD-NEXT:    adrp x9, .LCPI18_1
+; CHECK-SD-NEXT:    mov v1.16b, v0.16b
+; CHECK-SD-NEXT:    ldr q3, [x8, :lo12:.LCPI18_0]
+; CHECK-SD-NEXT:    ldr q4, [x9, :lo12:.LCPI18_1]
+; CHECK-SD-NEXT:    tbl v0.16b, { v1.16b, v2.16b }, v3.16b
+; CHECK-SD-NEXT:    tbl v1.16b, { v1.16b, v2.16b }, v4.16b
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v16i16:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    mov v3.16b, v0.16b
+; CHECK-GI-NEXT:    adrp x8, .LCPI18_1
+; CHECK-GI-NEXT:    adrp x9, .LCPI18_0
+; CHECK-GI-NEXT:    mov v4.16b, v2.16b
+; CHECK-GI-NEXT:    ldr q0, [x8, :lo12:.LCPI18_1]
+; CHECK-GI-NEXT:    ldr q1, [x9, :lo12:.LCPI18_0]
+; CHECK-GI-NEXT:    tbl v0.16b, { v3.16b, v4.16b }, v0.16b
+; CHECK-GI-NEXT:    tbl v1.16b, { v3.16b, v4.16b }, v1.16b
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 16, i32 16, i32 16, i32 1, i32 16, i32 16, i32 16, i32 1, i32 16, i32 16, i32 16, i32 3, i32 16, i32 16, i32 16>
     ret <16 x i16> %c
 }
@@ -332,16 +396,23 @@ define <2 x i1> @shufflevector_v2i1_zeroes(<2 x i1> %a, <2 x i1> %b){
 }
 
 define i32 @shufflevector_v4i8_zeroes(<4 x i8> %a, <4 x i8> %b){
-; CHECK-LABEL: shufflevector_v4i8_zeroes:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    dup v0.4h, v0.h[0]
-; CHECK-NEXT:    xtn v0.8b, v0.8h
-; CHECK-NEXT:    fmov w0, s0
-; CHECK-NEXT:    add sp, sp, #16
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v4i8_zeroes:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    sub sp, sp, #16
+; CHECK-SD-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-SD-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-SD-NEXT:    dup v0.4h, v0.h[0]
+; CHECK-SD-NEXT:    xtn v0.8b, v0.8h
+; CHECK-SD-NEXT:    fmov w0, s0
+; CHECK-SD-NEXT:    add sp, sp, #16
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v4i8_zeroes:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    fmov w8, s0
+; CHECK-GI-NEXT:    dup v0.8b, w8
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <4 x i8> %a, <4 x i8> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
     %d = bitcast <4 x i8> %c to i32
     ret i32 %d
@@ -358,19 +429,26 @@ define <32 x i8> @shufflevector_v32i8_zeroes(<32 x i8> %a, <32 x i8> %b){
 }
 
 define i32 @shufflevector_v2i16_zeroes(<2 x i16> %a, <2 x i16> %b){
-; CHECK-LABEL: shufflevector_v2i16_zeroes:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    sub sp, sp, #16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
-; CHECK-NEXT:    dup v1.2s, v0.s[0]
-; CHECK-NEXT:    fmov w9, s0
-; CHECK-NEXT:    strh w9, [sp, #12]
-; CHECK-NEXT:    mov w8, v1.s[1]
-; CHECK-NEXT:    strh w8, [sp, #14]
-; CHECK-NEXT:    ldr w0, [sp, #12]
-; CHECK-NEXT:    add sp, sp, #16
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v2i16_zeroes:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    sub sp, sp, #16
+; CHECK-SD-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-SD-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-SD-NEXT:    dup v1.2s, v0.s[0]
+; CHECK-SD-NEXT:    fmov w9, s0
+; CHECK-SD-NEXT:    strh w9, [sp, #12]
+; CHECK-SD-NEXT:    mov w8, v1.s[1]
+; CHECK-SD-NEXT:    strh w8, [sp, #14]
+; CHECK-SD-NEXT:    ldr w0, [sp, #12]
+; CHECK-SD-NEXT:    add sp, sp, #16
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v2i16_zeroes:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    fmov w8, s0
+; CHECK-GI-NEXT:    dup v0.4h, w8
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <2 x i16> %a, <2 x i16> %b, <2 x i32> <i32 0, i32 0>
     %d = bitcast <2 x i16> %c to i32
     ret i32 %d
@@ -417,12 +495,45 @@ define <4 x i64> @shufflevector_v4i64_zeroes(<4 x i64> %a, <4 x i64> %b) {
 ; ===== Vectors with Non-Pow 2 Widths =====
 
 define <3 x i8> @shufflevector_v3i8(<3 x i8> %a, <3 x i8> %b) {
-; CHECK-LABEL: shufflevector_v3i8:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov w0, w1
-; CHECK-NEXT:    mov w1, w2
-; CHECK-NEXT:    mov w2, w4
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v3i8:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    mov w0, w1
+; CHECK-SD-NEXT:    mov w1, w2
+; CHECK-SD-NEXT:    mov w2, w4
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v3i8:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    fmov s0, w0
+; CHECK-GI-NEXT:    fmov s1, w1
+; CHECK-GI-NEXT:    adrp x8, .LCPI30_0
+; CHECK-GI-NEXT:    fmov s2, w3
+; CHECK-GI-NEXT:    fmov s3, w4
+; CHECK-GI-NEXT:    mov v0.b[1], v1.b[0]
+; CHECK-GI-NEXT:    fmov s1, w2
+; CHECK-GI-NEXT:    mov v2.b[1], v3.b[0]
+; CHECK-GI-NEXT:    fmov s3, w5
+; CHECK-GI-NEXT:    mov v0.b[2], v1.b[0]
+; CHECK-GI-NEXT:    ldr d1, [x8, :lo12:.LCPI30_0]
+; CHECK-GI-NEXT:    mov v2.b[2], v3.b[0]
+; CHECK-GI-NEXT:    mov v0.b[3], v0.b[0]
+; CHECK-GI-NEXT:    mov v2.b[3], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[4], v0.b[0]
+; CHECK-GI-NEXT:    mov v2.b[4], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[5], v0.b[0]
+; CHECK-GI-NEXT:    mov v2.b[5], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[6], v0.b[0]
+; CHECK-GI-NEXT:    mov v2.b[6], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.b[7], v0.b[0]
+; CHECK-GI-NEXT:    mov v2.b[7], v0.b[0]
+; CHECK-GI-NEXT:    mov v0.d[1], v2.d[0]
+; CHECK-GI-NEXT:    tbl v0.16b, { v0.16b }, v1.16b
+; CHECK-GI-NEXT:    mov b1, v0.b[1]
+; CHECK-GI-NEXT:    mov b2, v0.b[2]
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    fmov w1, s1
+; CHECK-GI-NEXT:    fmov w2, s2
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <3 x i8> %a, <3 x i8> %b, <3 x i32> <i32 1, i32 2, i32 4>
     ret <3 x i8> %c
 }
@@ -517,11 +628,21 @@ define <3 x i32> @shufflevector_v3i32(<3 x i32> %a, <3 x i32> %b) {
 ; ===== Vectors with Non-Pow 2 Widths with Zero Masks =====
 
 define <3 x i8> @shufflevector_v3i8_zeroes(<3 x i8> %a, <3 x i8> %b) {
-; CHECK-LABEL: shufflevector_v3i8_zeroes:
-; CHECK:       // %bb.0:
-; CHECK-NEXT:    mov w1, w0
-; CHECK-NEXT:    mov w2, w0
-; CHECK-NEXT:    ret
+; CHECK-SD-LABEL: shufflevector_v3i8_zeroes:
+; CHECK-SD:       // %bb.0:
+; CHECK-SD-NEXT:    mov w1, w0
+; CHECK-SD-NEXT:    mov w2, w0
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: shufflevector_v3i8_zeroes:
+; CHECK-GI:       // %bb.0:
+; CHECK-GI-NEXT:    dup v0.8b, w0
+; CHECK-GI-NEXT:    mov b1, v0.b[1]
+; CHECK-GI-NEXT:    mov b2, v0.b[2]
+; CHECK-GI-NEXT:    fmov w0, s0
+; CHECK-GI-NEXT:    fmov w1, s1
+; CHECK-GI-NEXT:    fmov w2, s2
+; CHECK-GI-NEXT:    ret
     %c = shufflevector <3 x i8> %a, <3 x i8> %b, <3 x i32> <i32 0, i32 0, i32 0>
     ret <3 x i8> %c
 }