diff --git a/llvm/test/Analysis/CostModel/AArch64/shuffle-select.ll b/llvm/test/Analysis/CostModel/AArch64/shuffle-select.ll
index 075397afdce791b..9c573c7eb49c790 100644
--- a/llvm/test/Analysis/CostModel/AArch64/shuffle-select.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/shuffle-select.ll
@@ -1,97 +1,112 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
 ; RUN: opt < %s -mtriple=aarch64--linux-gnu -passes="print<cost-model>" 2>&1 -disable-output | FileCheck %s --check-prefix=COST
-; RUN: llc < %s -mtriple=aarch64--linux-gnu | FileCheck %s --check-prefix=CODE
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 
-; COST-LABEL: sel.v8i8
-; COST:       Found an estimated cost of 28 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
-; CODE-LABEL: sel.v8i8
-; CODE:       tbl v0.8b, { v0.16b }, v1.8b
-define <8 x i8> @sel.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
+define <8 x i8> @sel_v8i8(<8 x i8> %v0, <8 x i8> %v1) {
+; COST-LABEL: 'sel_v8i8'
+; COST-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %tmp0
+;
   %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i8> %tmp0
 }
 
-; COST-LABEL: sel.v16i8
-; COST:       Found an estimated cost of 60 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
-; CODE-LABEL: sel.v16i8
-; CODE:       tbl v0.16b, { v0.16b, v1.16b }, v2.16b
-define <16 x i8> @sel.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
+define <16 x i8> @sel_v16i8(<16 x i8> %v0, <16 x i8> %v1) {
+; COST-LABEL: 'sel_v16i8'
+; COST-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %tmp0
+;
   %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
   ret <16 x i8> %tmp0
 }
 
-; COST-LABEL: sel.v4i16
-; COST:       Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CODE-LABEL: sel.v4i16
-; CODE:       rev32 v0.4h, v0.4h
-; CODE:       trn2 v0.4h, v0.4h, v1.4h
-define <4 x i16> @sel.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
+define <4 x i16> @sel_v4i16(<4 x i16> %v0, <4 x i16> %v1) {
+; COST-LABEL: 'sel_v4i16'
+; COST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i16> %tmp0
+;
   %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x i16> %tmp0
 }
 
-; COST-LABEL: sel.v8i16
-; COST:       Found an estimated cost of 28 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
-; CODE-LABEL: sel.v8i16
-; CODE:       tbl v0.16b, { v0.16b, v1.16b }, v2.16b
-define <8 x i16> @sel.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
+define <8 x i16> @sel_v8i16(<8 x i16> %v0, <8 x i16> %v1) {
+; COST-LABEL: 'sel_v8i16'
+; COST-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %tmp0
+;
   %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i16> %tmp0
 }
 
-; COST-LABEL: sel.v2i32
-; COST:        Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>
-; CODE-LABEL: sel.v2i32
-; CODE:       mov v0.s[1], v1.s[1]
-define <2 x i32> @sel.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
+define <2 x i32> @sel_v2i32(<2 x i32> %v0, <2 x i32> %v1) {
+; COST-LABEL: 'sel_v2i32'
+; COST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %tmp0
+;
   %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>
   ret <2 x i32> %tmp0
 }
 
-; COST-LABEL: sel.v4i32
-; COST:       Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CODE-LABEL: sel.v4i32
-; CODE:       rev64 v0.4s, v0.4s
-; CODE:       trn2 v0.4s, v0.4s, v1.4s
-define <4 x i32> @sel.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
+define <4 x i32> @sel_v4i32(<4 x i32> %v0, <4 x i32> %v1) {
+; COST-LABEL: 'sel_v4i32'
+; COST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %tmp0
+;
   %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x i32> %tmp0
 }
 
-; COST-LABEL: sel.v2i64
-; COST:       Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>
-; CODE-LABEL: sel.v2i64
-; CODE:       mov v0.d[1], v1.d[1]
-define <2 x i64> @sel.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
+define <2 x i64> @sel_v2i64(<2 x i64> %v0, <2 x i64> %v1) {
+; COST-LABEL: 'sel_v2i64'
+; COST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %tmp0
+;
   %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>
   ret <2 x i64> %tmp0
 }
 
-; COST-LABEL: sel.v2f32
-; COST:       Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>
-; CODE-LABEL: sel.v2f32
-; CODE:       mov v0.s[1], v1.s[1]
-define <2 x float> @sel.v2f32(<2 x float> %v0, <2 x float> %v1) {
+define <4 x half> @sel_v4f16(<4 x half> %v0, <4 x half> %v1) {
+; COST-LABEL: 'sel_v4f16'
+; COST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x half> %tmp0
+;
+  %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x half> %tmp0
+}
+
+define <8 x half> @sel_v8f16(<8 x half> %v0, <8 x half> %v1) {
+; COST-LABEL: 'sel_v8f16'
+; COST-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x half> %tmp0
+;
+  %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+  ret <8 x half> %tmp0
+}
+
+define <2 x float> @sel_v2f32(<2 x float> %v0, <2 x float> %v1) {
+; COST-LABEL: 'sel_v2f32'
+; COST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %tmp0
+;
   %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>
   ret <2 x float> %tmp0
 }
 
-; COST-LABEL: sel.v4f32
-; COST:       Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
-; CODE-LABEL: sel.v4f32
-; CODE:       rev64 v0.4s, v0.4s
-; CODE:       trn2 v0.4s, v0.4s, v1.4s
-define <4 x float> @sel.v4f32(<4 x float> %v0, <4 x float> %v1) {
+define <4 x float> @sel_v4f32(<4 x float> %v0, <4 x float> %v1) {
+; COST-LABEL: 'sel_v4f32'
+; COST-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %tmp0
+;
   %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x float> %tmp0
 }
 
-; COST-LABEL: sel.v2f64
-; COST:       Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>
-; CODE-LABEL: sel.v2f64
-; CODE:       mov v0.d[1], v1.d[1]
-define <2 x double> @sel.v2f64(<2 x double> %v0, <2 x double> %v1) {
+define <2 x double> @sel_v2f64(<2 x double> %v0, <2 x double> %v1) {
+; COST-LABEL: 'sel_v2f64'
+; COST-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>
+; COST-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %tmp0
+;
   %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>
   ret <2 x double> %tmp0
 }
diff --git a/llvm/test/CodeGen/AArch64/shuffle-select.ll b/llvm/test/CodeGen/AArch64/shuffle-select.ll
new file mode 100644
index 000000000000000..25a935f067bd6c1
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/shuffle-select.ll
@@ -0,0 +1,137 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=aarch64--linux-gnu | FileCheck %s
+
+define <8 x i8> @sel_v8i8(<8 x i8> %v0, <8 x i8> %v1) {
+; CHECK-LABEL: sel_v8i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    adrp x8, .LCPI0_0
+; CHECK-NEXT:    mov v0.d[1], v1.d[0]
+; CHECK-NEXT:    ldr d1, [x8, :lo12:.LCPI0_0]
+; CHECK-NEXT:    tbl v0.8b, { v0.16b }, v1.8b
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+  ret <8 x i8> %tmp0
+}
+
+define <16 x i8> @sel_v16i8(<16 x i8> %v0, <16 x i8> %v1) {
+; CHECK-LABEL: sel_v16i8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI1_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI1_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
+  ret <16 x i8> %tmp0
+}
+
+define <4 x i16> @sel_v4i16(<4 x i16> %v0, <4 x i16> %v1) {
+; CHECK-LABEL: sel_v4i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    rev32 v0.4h, v0.4h
+; CHECK-NEXT:    trn2 v0.4h, v0.4h, v1.4h
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x i16> %tmp0
+}
+
+define <8 x i16> @sel_v8i16(<8 x i16> %v0, <8 x i16> %v1) {
+; CHECK-LABEL: sel_v8i16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI3_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI3_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+  ret <8 x i16> %tmp0
+}
+
+define <2 x i32> @sel_v2i32(<2 x i32> %v0, <2 x i32> %v1) {
+; CHECK-LABEL: sel_v2i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    mov v0.s[1], v1.s[1]
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 0, i32 3>
+  ret <2 x i32> %tmp0
+}
+
+define <4 x i32> @sel_v4i32(<4 x i32> %v0, <4 x i32> %v1) {
+; CHECK-LABEL: sel_v4i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    rev64 v0.4s, v0.4s
+; CHECK-NEXT:    trn2 v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x i32> %tmp0
+}
+
+define <2 x i64> @sel_v2i64(<2 x i64> %v0, <2 x i64> %v1) {
+; CHECK-LABEL: sel_v2i64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov v0.d[1], v1.d[1]
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 0, i32 3>
+  ret <2 x i64> %tmp0
+}
+
+define <4 x half> @sel_v4f16(<4 x half> %v0, <4 x half> %v1) {
+; CHECK-LABEL: sel_v4f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    rev32 v0.4h, v0.4h
+; CHECK-NEXT:    trn2 v0.4h, v0.4h, v1.4h
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x half> %tmp0
+}
+
+define <8 x half> @sel_v8f16(<8 x half> %v0, <8 x half> %v1) {
+; CHECK-LABEL: sel_v8f16:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    adrp x8, .LCPI8_0
+; CHECK-NEXT:    // kill: def $q1 killed $q1 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    ldr q2, [x8, :lo12:.LCPI8_0]
+; CHECK-NEXT:    // kill: def $q0 killed $q0 killed $q0_q1 def $q0_q1
+; CHECK-NEXT:    tbl v0.16b, { v0.16b, v1.16b }, v2.16b
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
+  ret <8 x half> %tmp0
+}
+
+define <2 x float> @sel_v2f32(<2 x float> %v0, <2 x float> %v1) {
+; CHECK-LABEL: sel_v2f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    mov v0.s[1], v1.s[1]
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 0, i32 3>
+  ret <2 x float> %tmp0
+}
+
+define <4 x float> @sel_v4f32(<4 x float> %v0, <4 x float> %v1) {
+; CHECK-LABEL: sel_v4f32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    rev64 v0.4s, v0.4s
+; CHECK-NEXT:    trn2 v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x float> %tmp0
+}
+
+define <2 x double> @sel_v2f64(<2 x double> %v0, <2 x double> %v1) {
+; CHECK-LABEL: sel_v2f64:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    mov v0.d[1], v1.d[1]
+; CHECK-NEXT:    ret
+  %tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 0, i32 3>
+  ret <2 x double> %tmp0
+}