diff --git a/llvm/test/CodeGen/AArch64/arm64-neon-select_cc.ll b/llvm/test/CodeGen/AArch64/arm64-neon-select_cc.ll
--- a/llvm/test/CodeGen/AArch64/arm64-neon-select_cc.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-neon-select_cc.ll
@@ -1,13 +1,17 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc  -mtriple=arm64-none-linux-gnu -mattr=+neon -fp-contract=fast \
-; RUN:        < %s -verify-machineinstrs -asm-verbose=false | FileCheck %s
+; RUN:        < %s -verify-machineinstrs | FileCheck %s
 
 define <8x i8> @test_select_cc_v8i8_i8(i8 %a, i8 %b, <8x i8> %c, <8x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v8i8_i8:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].8b, v[[LHS]].8b, v[[RHS]].8b
-; CHECK: dup [[DUPMASK:v[0-9]+]].8b, [[MASK]].b[0]
-; CHECK: bsl [[DUPMASK]].8b, v0.8b, v1.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.8b, v3.8b, v2.8b
+; CHECK-NEXT:    dup v2.8b, v2.b[0]
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i8 %a, %b
   %e = select i1 %cmp31, <8x i8> %c, <8x i8> %d
   ret <8x i8> %e
@@ -15,9 +19,13 @@
 
 define <8x i8> @test_select_cc_v8i8_f32(float %a, float %b, <8x i8> %c, <8x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v8i8_f32:
-; CHECK: fcmeq [[MASK:v[0-9]+]].2s, v0.2s, v1.2s
-; CHECK-NEXT: dup [[DUPMASK:v[0-9]+]].2s, [[MASK]].s[0]
-; CHECK-NEXT: bsl [[DUPMASK]].8b, v2.8b, v3.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $d0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $d1
+; CHECK-NEXT:    fcmeq v0.2s, v0.2s, v1.2s
+; CHECK-NEXT:    dup v0.2s, v0.s[0]
+; CHECK-NEXT:    bsl v0.8b, v2.8b, v3.8b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq float %a, %b
   %e = select i1 %cmp31, <8x i8> %c, <8x i8> %d
   ret <8x i8> %e
@@ -25,8 +33,10 @@
 
 define <8x i8> @test_select_cc_v8i8_f64(double %a, double %b, <8x i8> %c, <8x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v8i8_f64:
-; CHECK: fcmeq d[[MASK:[0-9]+]], d0, d1
-; CHECK-NEXT: bsl v[[MASK]].8b, v2.8b, v3.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fcmeq d0, d0, d1
+; CHECK-NEXT:    bsl v0.8b, v2.8b, v3.8b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq double %a, %b
   %e = select i1 %cmp31, <8x i8> %c, <8x i8> %d
   ret <8x i8> %e
@@ -34,11 +44,14 @@
 
 define <16x i8> @test_select_cc_v16i8_i8(i8 %a, i8 %b, <16x i8> %c, <16x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v16i8_i8:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].16b, v[[LHS]].16b, v[[RHS]].16b
-; CHECK: dup [[DUPMASK:v[0-9]+]].16b, [[MASK]].b[0]
-; CHECK: bsl [[DUPMASK]].16b, v0.16b, v1.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.16b, v3.16b, v2.16b
+; CHECK-NEXT:    dup v2.16b, v2.b[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i8 %a, %b
   %e = select i1 %cmp31, <16x i8> %c, <16x i8> %d
   ret <16x i8> %e
@@ -46,9 +59,13 @@
 
 define <16x i8> @test_select_cc_v16i8_f32(float %a, float %b, <16x i8> %c, <16x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v16i8_f32:
-; CHECK: fcmeq [[MASK:v[0-9]+]].4s, v0.4s, v1.4s
-; CHECK-NEXT: dup [[DUPMASK:v[0-9]+]].4s, [[MASK]].s[0]
-; CHECK-NEXT: bsl [[DUPMASK]].16b, v2.16b, v3.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $q1
+; CHECK-NEXT:    fcmeq v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    dup v0.4s, v0.s[0]
+; CHECK-NEXT:    bsl v0.16b, v2.16b, v3.16b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq float %a, %b
   %e = select i1 %cmp31, <16x i8> %c, <16x i8> %d
   ret <16x i8> %e
@@ -56,9 +73,13 @@
 
 define <16x i8> @test_select_cc_v16i8_f64(double %a, double %b, <16x i8> %c, <16x i8> %d ) {
 ; CHECK-LABEL: test_select_cc_v16i8_f64:
-; CHECK: fcmeq [[MASK:v[0-9]+]].2d, v0.2d, v1.2d
-; CHECK-NEXT: dup [[DUPMASK:v[0-9]+]].2d, [[MASK]].d[0]
-; CHECK-NEXT: bsl [[DUPMASK]].16b, v2.16b, v3.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    fcmeq v0.2d, v0.2d, v1.2d
+; CHECK-NEXT:    dup v0.2d, v0.d[0]
+; CHECK-NEXT:    bsl v0.16b, v2.16b, v3.16b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq double %a, %b
   %e = select i1 %cmp31, <16x i8> %c, <16x i8> %d
   ret <16x i8> %e
@@ -66,11 +87,14 @@
 
 define <4x i16> @test_select_cc_v4i16(i16 %a, i16 %b, <4x i16> %c, <4x i16> %d ) {
 ; CHECK-LABEL: test_select_cc_v4i16:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].4h, v[[LHS]].4h, v[[RHS]].4h
-; CHECK: dup [[DUPMASK:v[0-9]+]].4h, [[MASK]].h[0]
-; CHECK: bsl [[DUPMASK]].8b, v0.8b, v1.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.4h, v3.4h, v2.4h
+; CHECK-NEXT:    dup v2.4h, v2.h[0]
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i16 %a, %b
   %e = select i1 %cmp31, <4x i16> %c, <4x i16> %d
   ret <4x i16> %e
@@ -78,11 +102,14 @@
 
 define <8x i16> @test_select_cc_v8i16(i16 %a, i16 %b, <8x i16> %c, <8x i16> %d ) {
 ; CHECK-LABEL: test_select_cc_v8i16:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].8h, v[[LHS]].8h, v[[RHS]].8h
-; CHECK: dup [[DUPMASK:v[0-9]+]].8h, [[MASK]].h[0]
-; CHECK: bsl [[DUPMASK]].16b, v0.16b, v1.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.8h, v3.8h, v2.8h
+; CHECK-NEXT:    dup v2.8h, v2.h[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i16 %a, %b
   %e = select i1 %cmp31, <8x i16> %c, <8x i16> %d
   ret <8x i16> %e
@@ -90,11 +117,14 @@
 
 define <2x i32> @test_select_cc_v2i32(i32 %a, i32 %b, <2x i32> %c, <2x i32> %d ) {
 ; CHECK-LABEL: test_select_cc_v2i32:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].2s, v[[LHS]].2s, v[[RHS]].2s
-; CHECK: dup [[DUPMASK:v[0-9]+]].2s, [[MASK]].s[0]
-; CHECK: bsl [[DUPMASK]].8b, v0.8b, v1.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.2s, v3.2s, v2.2s
+; CHECK-NEXT:    dup v2.2s, v2.s[0]
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i32 %a, %b
   %e = select i1 %cmp31, <2x i32> %c, <2x i32> %d
   ret <2x i32> %e
@@ -102,11 +132,14 @@
 
 define <4x i32> @test_select_cc_v4i32(i32 %a, i32 %b, <4x i32> %c, <4x i32> %d ) {
 ; CHECK-LABEL: test_select_cc_v4i32:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].4s, v[[LHS]].4s, v[[RHS]].4s
-; CHECK: dup [[DUPMASK:v[0-9]+]].4s, [[MASK]].s[0]
-; CHECK: bsl [[DUPMASK]].16b, v0.16b, v1.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.4s, v3.4s, v2.4s
+; CHECK-NEXT:    dup v2.4s, v2.s[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i32 %a, %b
   %e = select i1 %cmp31, <4x i32> %c, <4x i32> %d
   ret <4x i32> %e
@@ -114,10 +147,13 @@
 
 define <1x i64> @test_select_cc_v1i64(i64 %a, i64 %b, <1x i64> %c, <1x i64> %d ) {
 ; CHECK-LABEL: test_select_cc_v1i64:
-; CHECK-DAG: fmov d[[LHS:[0-9]+]], x0
-; CHECK-DAG: fmov d[[RHS:[0-9]+]], x1
-; CHECK: cmeq d[[MASK:[0-9]+]], d[[LHS]], d[[RHS]]
-; CHECK: bsl v[[MASK]].8b, v0.8b, v1.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov d2, x1
+; CHECK-NEXT:    fmov d3, x0
+; CHECK-NEXT:    cmeq d2, d3, d2
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i64 %a, %b
   %e = select i1 %cmp31, <1x i64> %c, <1x i64> %d
   ret <1x i64> %e
@@ -125,11 +161,14 @@
 
 define <2x i64> @test_select_cc_v2i64(i64 %a, i64 %b, <2x i64> %c, <2x i64> %d ) {
 ; CHECK-LABEL: test_select_cc_v2i64:
-; CHECK-DAG: fmov d[[LHS:[0-9]+]], x0
-; CHECK-DAG: fmov d[[RHS:[0-9]+]], x1
-; CHECK: cmeq [[MASK:v[0-9]+]].2d, v[[LHS]].2d, v[[RHS]].2d
-; CHECK: dup [[DUPMASK:v[0-9]+]].2d, [[MASK]].d[0]
-; CHECK: bsl [[DUPMASK]].16b, v0.16b, v1.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov d2, x1
+; CHECK-NEXT:    fmov d3, x0
+; CHECK-NEXT:    cmeq v2.2d, v3.2d, v2.2d
+; CHECK-NEXT:    dup v2.2d, v2.d[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i64 %a, %b
   %e = select i1 %cmp31, <2x i64> %c, <2x i64> %d
   ret <2x i64> %e
@@ -137,8 +176,12 @@
 
 define <1 x float> @test_select_cc_v1f32(float %a, float %b, <1 x float> %c, <1 x float> %d ) {
 ; CHECK-LABEL: test_select_cc_v1f32:
-; CHECK: fcmeq [[MASK:v[0-9]+]].2s, v0.2s, v1.2s
-; CHECK-NEXT: bsl [[MASK]].8b, v2.8b, v3.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $d0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $d1
+; CHECK-NEXT:    fcmeq v0.2s, v0.2s, v1.2s
+; CHECK-NEXT:    bsl v0.8b, v2.8b, v3.8b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq float %a, %b
   %e = select i1 %cmp31, <1 x float> %c, <1 x float> %d
   ret <1 x float> %e
@@ -146,9 +189,13 @@
 
 define <2 x float> @test_select_cc_v2f32(float %a, float %b, <2 x float> %c, <2 x float> %d ) {
 ; CHECK-LABEL: test_select_cc_v2f32:
-; CHECK: fcmeq [[MASK:v[0-9]+]].2s, v0.2s, v1.2s
-; CHECK: dup [[DUPMASK:v[0-9]+]].2s, [[MASK]].s[0]
-; CHECK: bsl [[DUPMASK]].8b, v2.8b, v3.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $d0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $d1
+; CHECK-NEXT:    fcmeq v0.2s, v0.2s, v1.2s
+; CHECK-NEXT:    dup v0.2s, v0.s[0]
+; CHECK-NEXT:    bsl v0.8b, v2.8b, v3.8b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq float %a, %b
   %e = select i1 %cmp31, <2 x float> %c, <2 x float> %d
   ret <2 x float> %e
@@ -156,9 +203,13 @@
 
 define <4x float> @test_select_cc_v4f32(float %a, float %b, <4x float> %c, <4x float> %d ) {
 ; CHECK-LABEL: test_select_cc_v4f32:
-; CHECK: fcmeq [[MASK:v[0-9]+]].4s, v0.4s, v1.4s
-; CHECK: dup [[DUPMASK:v[0-9]+]].4s, [[MASK]].s[0]
-; CHECK: bsl [[DUPMASK]].16b, v2.16b, v3.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-NEXT:    // kill: def $s1 killed $s1 def $q1
+; CHECK-NEXT:    fcmeq v0.4s, v0.4s, v1.4s
+; CHECK-NEXT:    dup v0.4s, v0.s[0]
+; CHECK-NEXT:    bsl v0.16b, v2.16b, v3.16b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq float %a, %b
   %e = select i1 %cmp31, <4x float> %c, <4x float> %d
   ret <4x float> %e
@@ -166,11 +217,14 @@
 
 define <4x float> @test_select_cc_v4f32_icmp(i32 %a, i32 %b, <4x float> %c, <4x float> %d ) {
 ; CHECK-LABEL: test_select_cc_v4f32_icmp:
-; CHECK-DAG: fmov s[[LHS:[0-9]+]], w0
-; CHECK-DAG: fmov s[[RHS:[0-9]+]], w1
-; CHECK: cmeq [[MASK:v[0-9]+]].4s, v[[LHS]].4s, v[[RHS]].4s
-; CHECK: dup [[DUPMASK:v[0-9]+]].4s, [[MASK]].s[0]
-; CHECK: bsl [[DUPMASK]].16b, v0.16b, v1.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov s2, w1
+; CHECK-NEXT:    fmov s3, w0
+; CHECK-NEXT:    cmeq v2.4s, v3.4s, v2.4s
+; CHECK-NEXT:    dup v2.4s, v2.s[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i32 %a, %b
   %e = select i1 %cmp31, <4x float> %c, <4x float> %d
   ret <4x float> %e
@@ -178,8 +232,10 @@
 
 define <1 x double> @test_select_cc_v1f64(double %a, double %b, <1 x double> %c, <1 x double> %d ) {
 ; CHECK-LABEL: test_select_cc_v1f64:
-; CHECK: fcmeq d[[MASK:[0-9]+]], d0, d1
-; CHECK: bsl v[[MASK]].8b, v2.8b, v3.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fcmeq d0, d0, d1
+; CHECK-NEXT:    bsl v0.8b, v2.8b, v3.8b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq double %a, %b
   %e = select i1 %cmp31, <1 x double> %c, <1 x double> %d
   ret <1 x double> %e
@@ -187,10 +243,13 @@
 
 define <1 x double> @test_select_cc_v1f64_icmp(i64 %a, i64 %b, <1 x double> %c, <1 x double> %d ) {
 ; CHECK-LABEL: test_select_cc_v1f64_icmp:
-; CHECK-DAG: fmov [[LHS:d[0-9]+]], x0
-; CHECK-DAG: fmov [[RHS:d[0-9]+]], x1
-; CHECK: cmeq d[[MASK:[0-9]+]], [[LHS]], [[RHS]]
-; CHECK: bsl v[[MASK]].8b, v0.8b, v1.8b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov d2, x1
+; CHECK-NEXT:    fmov d3, x0
+; CHECK-NEXT:    cmeq d2, d3, d2
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp31 = icmp eq i64 %a, %b
   %e = select i1 %cmp31, <1 x double> %c, <1 x double> %d
   ret <1 x double> %e
@@ -198,9 +257,13 @@
 
 define <2 x double> @test_select_cc_v2f64(double %a, double %b, <2 x double> %c, <2 x double> %d ) {
 ; CHECK-LABEL: test_select_cc_v2f64:
-; CHECK: fcmeq [[MASK:v[0-9]+]].2d, v0.2d, v1.2d
-; CHECK: dup [[DUPMASK:v[0-9]+]].2d, [[MASK]].d[0]
-; CHECK: bsl [[DUPMASK]].16b, v2.16b, v3.16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    fcmeq v0.2d, v0.2d, v1.2d
+; CHECK-NEXT:    dup v0.2d, v0.d[0]
+; CHECK-NEXT:    bsl v0.16b, v2.16b, v3.16b
+; CHECK-NEXT:    ret
   %cmp31 = fcmp oeq double %a, %b
   %e = select i1 %cmp31, <2 x double> %c, <2 x double> %d
   ret <2 x double> %e
@@ -211,11 +274,13 @@
 ; Part of PR21549.
 define <2 x i32> @test_select_cc_v2i32_icmpi1(i1 %cc, <2 x i32> %a, <2 x i32> %b) {
 ; CHECK-LABEL: test_select_cc_v2i32_icmpi1:
-; CHECK: tst   w0, #0x1
-; CHECK: csetm [[MASK:w[0-9]+]], ne
-; CHECK: dup   [[DUPMASK:v[0-9]+]].2s, [[MASK]]
-; CHECK: bsl   [[DUPMASK]].8b, v0.8b, v1.8b
-; CHECK: mov   v0.16b, [[DUPMASK]].16b
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    tst w0, #0x1
+; CHECK-NEXT:    csetm w8, ne
+; CHECK-NEXT:    dup v2.2s, w8
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cmp = icmp ne i1 %cc, 0
   %e = select i1 %cmp, <2 x i32> %a, <2 x i32> %b
   ret <2 x i32> %e
@@ -224,11 +289,14 @@
 ; Also make sure we support irregular/non-power-of-2 types such as v3f32.
 define <3 x float> @test_select_cc_v3f32_fcmp_f32(<3 x float> %a, <3 x float> %b, float %c1, float %c2) #0 {
 ; CHECK-LABEL: test_select_cc_v3f32_fcmp_f32:
-; CHECK-NEXT: fcmeq [[MASK:v[0-9]+]].4s, v2.4s, v3.4s
-; CHECK-NEXT: dup [[DUPMASK:v[0-9]+]].4s, [[MASK]].s[0]
-; CHECK-NEXT: bsl [[DUPMASK:v[0-9]+]].16b, v0.16b, v1.16b
-; CHECK-NEXT: mov v0.16b, [[DUPMASK]].16b
-; CHECK-NEXT: ret
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $s2 killed $s2 def $q2
+; CHECK-NEXT:    // kill: def $s3 killed $s3 def $q3
+; CHECK-NEXT:    fcmeq v2.4s, v2.4s, v3.4s
+; CHECK-NEXT:    dup v2.4s, v2.s[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cc = fcmp oeq float %c1, %c2
   %r = select i1 %cc, <3 x float> %a, <3 x float> %b
   ret <3 x float> %r
@@ -236,11 +304,14 @@
 
 define <3 x float> @test_select_cc_v3f32_fcmp_f64(<3 x float> %a, <3 x float> %b, double %c1, double %c2) #0 {
 ; CHECK-LABEL: test_select_cc_v3f32_fcmp_f64:
-; CHECK-NEXT: fcmeq [[MASK:v[0-9]+]].2d, v2.2d, v3.2d
-; CHECK-NEXT: dup [[DUPMASK:v[0-9]+]].2d, [[MASK]].d[0]
-; CHECK-NEXT: bsl [[DUPMASK:v[0-9]+]].16b, v0.16b, v1.16b
-; CHECK-NEXT: mov v0.16b, [[DUPMASK]].16b
-; CHECK-NEXT: ret
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // kill: def $d2 killed $d2 def $q2
+; CHECK-NEXT:    // kill: def $d3 killed $d3 def $q3
+; CHECK-NEXT:    fcmeq v2.2d, v2.2d, v3.2d
+; CHECK-NEXT:    dup v2.2d, v2.d[0]
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
   %cc = fcmp oeq double %c1, %c2
   %r = select i1 %cc, <3 x float> %a, <3 x float> %b
   ret <3 x float> %r
diff --git a/llvm/test/CodeGen/AArch64/fp16-vector-shuffle.ll b/llvm/test/CodeGen/AArch64/fp16-vector-shuffle.ll
--- a/llvm/test/CodeGen/AArch64/fp16-vector-shuffle.ll
+++ b/llvm/test/CodeGen/AArch64/fp16-vector-shuffle.ll
@@ -1,9 +1,13 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=aarch64-none-eabi | FileCheck %s
 
 ; float16x4_t select_64(float16x4_t a, float16x4_t b, uint16x4_t c) { return vbsl_u16(c, a, b); }
 define <4 x half> @select_64(<4 x half> %a, <4 x half> %b, <4 x i16> %c) #0 {
 ; CHECK-LABEL: select_64:
-; CHECK: bsl
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    bsl v2.8b, v0.8b, v1.8b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <4 x half> %a to <4 x i16>
   %1 = bitcast <4 x half> %b to <4 x i16>
@@ -18,7 +22,10 @@
 ; float16x8_t select_128(float16x8_t a, float16x8_t b, uint16x8_t c) { return vbslq_u16(c, a, b); }
 define <8 x half> @select_128(<8 x half> %a, <8 x half> %b, <8 x i16> %c) #0 {
 ; CHECK-LABEL: select_128:
-; CHECK: bsl
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v1.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <8 x half> %a to <8 x i16>
   %1 = bitcast <8 x half> %b to <8 x i16>
@@ -35,7 +42,12 @@
 ; }
 define <4 x half> @lane_64_64(<4 x half> %a, <4 x half> %b) #0 {
 ; CHECK-LABEL: lane_64_64:
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    mov v0.h[1], v1.h[2]
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <4 x half> %a, <4 x half> %b, <4 x i32> <i32 0, i32 6, i32 2, i32 3>
   ret <4 x half> %0
@@ -46,7 +58,10 @@
 ; }
 define <8 x half> @lane_128_64(<8 x half> %a, <4 x half> %b) #0 {
 ; CHECK-LABEL: lane_128_64:
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    mov v0.h[1], v1.h[2]
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <4 x half> %b to <4 x i16>
   %vget_lane = extractelement <4 x i16> %0, i32 2
@@ -61,7 +76,11 @@
 ; }
 define <4 x half> @lane_64_128(<4 x half> %a, <8 x half> %b) #0 {
 ; CHECK-LABEL: lane_64_128:
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    mov v0.h[3], v1.h[5]
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <8 x half> %b to <8 x i16>
   %vgetq_lane = extractelement <8 x i16> %0, i32 5
@@ -76,7 +95,9 @@
 ; }
 define <8 x half> @lane_128_128(<8 x half> %a, <8 x half> %b) #0 {
 ; CHECK-LABEL: lane_128_128:
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    mov v0.h[3], v1.h[5]
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <8 x half> %a, <8 x half> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 13, i32 4, i32 5, i32 6, i32 7>
   ret <8 x half> %0
@@ -87,7 +108,9 @@
 ; }
 define <4 x half> @ext_64(<4 x half> %a, <4 x half> %b) #0 {
 ; CHECK-LABEL: ext_64:
-; CHECK: ext
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ext v0.8b, v0.8b, v1.8b, #6
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <4 x half> %a, <4 x half> %b, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
   ret <4 x half> %0
@@ -98,7 +121,9 @@
 ; }
 define <8 x half> @ext_128(<8 x half> %a, <8 x half> %b) #0 {
 ; CHECK-LABEL: ext_128:
-; CHECK: ext
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ext v0.16b, v0.16b, v1.16b, #6
+; CHECK-NEXT:    ret
 entry:
   %0 = shufflevector <8 x half> %a, <8 x half> %b, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10>
   ret <8 x half> %0
@@ -108,9 +133,11 @@
 ;   return vrev32_s16(a);
 ; }
 define <4 x half> @rev32_64(<4 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: rev32_64:
-; CHECK: rev32
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    rev32 v0.4h, v0.4h
+; CHECK-NEXT:    ret
+entry:
   %0 = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   ret <4 x half> %0
 }
@@ -119,9 +146,11 @@
 ;   return vrev64_s16(a);
 ; }
 define <4 x half> @rev64_64(<4 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: rev64_64:
-; CHECK: rev64
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    rev64 v0.4h, v0.4h
+; CHECK-NEXT:    ret
+entry:
   %0 = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   ret <4 x half> %0
 }
@@ -130,9 +159,11 @@
 ;   return vrev32q_s16(a);
 ; }
 define <8 x half> @rev32_128(<8 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: rev32_128:
-; CHECK: rev32
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    rev32 v0.8h, v0.8h
+; CHECK-NEXT:    ret
+entry:
   %0 = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
   ret <8 x half> %0
 }
@@ -141,9 +172,11 @@
 ;   return vrev64q_s16(a);
 ; }
 define <8 x half> @rev64_128(<8 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: rev64_128:
-; CHECK: rev64
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    rev64 v0.8h, v0.8h
+; CHECK-NEXT:    ret
+entry:
   %0 = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   ret <8 x half> %0
 }
@@ -151,7 +184,9 @@
 ; float16x4_t create_64(long long a) { return vcreate_f16(a); }
 define <4 x half> @create_64(i64 %a) #0 {
 ; CHECK-LABEL: create_64:
-; CHECK: fmov
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    fmov d0, x0
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast i64 %a to <4 x half>
   ret <4 x half> %0
@@ -160,7 +195,10 @@
 ; float16x4_t dup_64(__fp16 a) { return vdup_n_f16(a); }
 define <4 x half> @dup_64(half %a) #0 {
 ; CHECK-LABEL: dup_64:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $h0 killed $h0 def $q0
+; CHECK-NEXT:    dup v0.4h, v0.h[0]
+; CHECK-NEXT:    ret
 entry:
   %vecinit = insertelement <4 x half> undef, half %a, i32 0
   %vecinit1 = insertelement <4 x half> %vecinit, half %a, i32 1
@@ -171,9 +209,12 @@
 
 ; float16x8_t dup_128(__fp16 a) { return vdupq_n_f16(a); }
 define <8 x half> @dup_128(half %a) #0 {
-entry:
 ; CHECK-LABEL: dup_128:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $h0 killed $h0 def $q0
+; CHECK-NEXT:    dup v0.8h, v0.h[0]
+; CHECK-NEXT:    ret
+entry:
   %vecinit = insertelement <8 x half> undef, half %a, i32 0
   %vecinit1 = insertelement <8 x half> %vecinit, half %a, i32 1
   %vecinit2 = insertelement <8 x half> %vecinit1, half %a, i32 2
@@ -187,45 +228,59 @@
 
 ; float16x4_t dup_lane_64(float16x4_t a) { return vdup_lane_f16(a, 2); }
 define <4 x half> @dup_lane_64(<4 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: dup_lane_64:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    dup v0.4h, v0.h[2]
+; CHECK-NEXT:    ret
+entry:
   %shuffle = shufflevector <4 x half> %a, <4 x half> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
   ret <4 x half> %shuffle
 }
 
 ; float16x8_t dup_lane_128(float16x4_t a) { return vdupq_lane_f16(a, 2); }
 define <8 x half> @dup_lane_128(<4 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: dup_lane_128:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    dup v0.8h, v0.h[2]
+; CHECK-NEXT:    ret
+entry:
   %shuffle = shufflevector <4 x half> %a, <4 x half> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
   ret <8 x half> %shuffle
 }
 
 ; float16x4_t dup_laneq_64(float16x8_t a) { return vdup_laneq_f16(a, 2); }
 define <4 x half> @dup_laneq_64(<8 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: dup_laneq_64:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup v0.4h, v0.h[2]
+; CHECK-NEXT:    ret
+entry:
   %shuffle = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
   ret <4 x half> %shuffle
 }
 
 ; float16x8_t dup_laneq_128(float16x8_t a) { return vdupq_laneq_f16(a, 2); }
 define <8 x half> @dup_laneq_128(<8 x half> %a) #0 {
-entry:
 ; CHECK-LABEL: dup_laneq_128:
-; CHECK: dup
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    dup v0.8h, v0.h[2]
+; CHECK-NEXT:    ret
+entry:
   %shuffle = shufflevector <8 x half> %a, <8 x half> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
   ret <8 x half> %shuffle
 }
 
 ; float16x8_t vcombine(float16x4_t a, float16x4_t b) { return vcombine_f16(a, b); }
 define <8 x half> @vcombine(<4 x half> %a, <4 x half> %b) #0 {
-entry:
 ; CHECK-LABEL: vcombine:
-; CHECK: mov v0.d[1], v1.d[0]
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT:    mov v0.d[1], v1.d[0]
+; CHECK-NEXT:    ret
+entry:
   %shuffle.i = shufflevector <4 x half> %a, <4 x half> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   ret <8 x half> %shuffle.i
 }
@@ -233,7 +288,10 @@
 ; float16x4_t get_high(float16x8_t a) { return vget_high_f16(a); }
 define <4 x half> @get_high(<8 x half> %a) #0 {
 ; CHECK-LABEL: get_high:
-; CHECK: ext
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ext v0.16b, v0.16b, v0.16b, #8
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
 entry:
   %shuffle.i = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
   ret <4 x half> %shuffle.i
@@ -243,7 +301,9 @@
 ; float16x4_t get_low(float16x8_t a) { return vget_low_f16(a); }
 define <4 x half> @get_low(<8 x half> %a) #0 {
 ; CHECK-LABEL: get_low:
-; CHECK-NOT: ext
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
 entry:
   %shuffle.i = shufflevector <8 x half> %a, <8 x half> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
   ret <4 x half> %shuffle.i
@@ -252,8 +312,13 @@
 ; float16x4_t set_lane_64(float16x4_t a, __fp16 b) { return vset_lane_f16(b, a, 2); }
 define <4 x half> @set_lane_64(<4 x half> %a, half %b) #0 {
 ; CHECK-LABEL: set_lane_64:
-; CHECK: fmov
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $h1 killed $h1 def $s1
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    fmov w8, s1
+; CHECK-NEXT:    mov v0.h[2], w8
+; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast half %b to i16
   %1 = bitcast <4 x half> %a to <4 x i16>
@@ -266,8 +331,11 @@
 ; float16x8_t set_lane_128(float16x8_t a, __fp16 b) { return vsetq_lane_f16(b, a, 2); }
 define <8 x half> @set_lane_128(<8 x half> %a, half %b) #0 {
 ; CHECK-LABEL: set_lane_128:
-; CHECK: fmov
-; CHECK: mov v{{[0-9]+}}.h
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $h1 killed $h1 def $s1
+; CHECK-NEXT:    fmov w8, s1
+; CHECK-NEXT:    mov v0.h[2], w8
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast half %b to i16
   %1 = bitcast <8 x half> %a to <8 x i16>
@@ -279,8 +347,12 @@
 ; __fp16 get_lane_64(float16x4_t a) { return vget_lane_f16(a, 2); }
 define half @get_lane_64(<4 x half> %a) #0 {
 ; CHECK-LABEL: get_lane_64:
-; CHECK: umov
-; CHECK: fmov
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT:    umov w8, v0.h[2]
+; CHECK-NEXT:    fmov s0, w8
+; CHECK-NEXT:    // kill: def $h0 killed $h0 killed $s0
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <4 x half> %a to <4 x i16>
   %vget_lane = extractelement <4 x i16> %0, i32 2
@@ -291,8 +363,11 @@
 ; __fp16 get_lane_128(float16x8_t a) { return vgetq_lane_f16(a, 2); }
 define half @get_lane_128(<8 x half> %a) #0 {
 ; CHECK-LABEL: get_lane_128:
-; CHECK: umov
-; CHECK: fmov
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    umov w8, v0.h[2]
+; CHECK-NEXT:    fmov s0, w8
+; CHECK-NEXT:    // kill: def $h0 killed $h0 killed $s0
+; CHECK-NEXT:    ret
 entry:
   %0 = bitcast <8 x half> %a to <8 x i16>
   %vgetq_lane = extractelement <8 x i16> %0, i32 2