diff --git a/test/CodeGen/X86/bitcast-and-setcc-128.ll b/test/CodeGen/X86/bitcast-and-setcc-128.ll
index 092b139fca2..1d78ee26a0b 100644
--- a/test/CodeGen/X86/bitcast-and-setcc-128.ll
+++ b/test/CodeGen/X86/bitcast-and-setcc-128.ll
@@ -1,48 +1,48 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+sse2 < %s | FileCheck %s --check-prefixes=SSE2-SSSE3,SSE2
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+ssse3 < %s | FileCheck %s --check-prefixes=SSE2-SSSE3,SSSE3
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx < %s | FileCheck %s --check-prefixes=AVX12,AVX1
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx2 < %s | FileCheck %s --check-prefixes=AVX12,AVX2
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx512f,+avx512vl,+avx512bw < %s | FileCheck %s --check-prefixes=AVX512
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE2-SSSE3,SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE2-SSSE3,SSSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX12,AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX12,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl,+avx512bw | FileCheck %s --check-prefixes=AVX512
 
 define i8 @v8i16(<8 x i16> %a, <8 x i16> %b, <8 x i16> %c, <8 x i16> %d) {
 ; SSE2-LABEL: v8i16:
-; SSE2:       ## BB#0:
+; SSE2:       # BB#0:
 ; SSE2-NEXT:    pcmpgtw %xmm1, %xmm0
 ; SSE2-NEXT:    pcmpgtw %xmm3, %xmm2
 ; SSE2-NEXT:    pand %xmm0, %xmm2
 ; SSE2-NEXT:    pand {{.*}}(%rip), %xmm2
 ; SSE2-NEXT:    packuswb %xmm2, %xmm2
 ; SSE2-NEXT:    pmovmskb %xmm2, %eax
-; SSE2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: v8i16:
-; SSSE3:       ## BB#0:
+; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    pcmpgtw %xmm1, %xmm0
 ; SSSE3-NEXT:    pcmpgtw %xmm3, %xmm2
 ; SSSE3-NEXT:    pand %xmm0, %xmm2
 ; SSSE3-NEXT:    pshufb {{.*#+}} xmm2 = xmm2[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; SSSE3-NEXT:    pmovmskb %xmm2, %eax
-; SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v8i16:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpcmpgtw %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpcmpgtw %xmm3, %xmm2, %xmm1
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; AVX12-NEXT:    vpmovmskb %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v8i16:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtw %xmm1, %xmm0, %k1
 ; AVX512-NEXT:    vpcmpgtw %xmm3, %xmm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX512-NEXT:    retq
   %x0 = icmp sgt <8 x i16> %a, %b
   %x1 = icmp sgt <8 x i16> %c, %d
@@ -53,25 +53,25 @@ define i8 @v8i16(<8 x i16> %a, <8 x i16> %b, <8 x i16> %c, <8 x i16> %d) {
 
 define i4 @v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) {
 ; SSE2-SSSE3-LABEL: v4i32:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    pcmpgtd %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    pcmpgtd %xmm3, %xmm2
 ; SSE2-SSSE3-NEXT:    pand %xmm0, %xmm2
 ; SSE2-SSSE3-NEXT:    movmskps %xmm2, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v4i32:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpcmpgtd %xmm3, %xmm2, %xmm1
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskps %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v4i32:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtd %xmm1, %xmm0, %k1
 ; AVX512-NEXT:    vpcmpgtd %xmm3, %xmm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -87,25 +87,25 @@ define i4 @v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) {
 
 define i4 @v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d) {
 ; SSE2-SSSE3-LABEL: v4f32:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    cmpltps %xmm0, %xmm1
 ; SSE2-SSSE3-NEXT:    cmpltps %xmm2, %xmm3
 ; SSE2-SSSE3-NEXT:    andps %xmm1, %xmm3
 ; SSE2-SSSE3-NEXT:    movmskps %xmm3, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v4f32:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vcmpltps %xmm0, %xmm1, %xmm0
 ; AVX12-NEXT:    vcmpltps %xmm2, %xmm3, %xmm1
 ; AVX12-NEXT:    vandps %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskps %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v4f32:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vcmpltps %xmm0, %xmm1, %k1
 ; AVX512-NEXT:    vcmpltps %xmm2, %xmm3, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -121,29 +121,29 @@ define i4 @v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d)
 
 define i16 @v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) {
 ; SSE2-SSSE3-LABEL: v16i8:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    pcmpgtb %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    pcmpgtb %xmm3, %xmm2
 ; SSE2-SSSE3-NEXT:    pand %xmm0, %xmm2
 ; SSE2-SSSE3-NEXT:    pmovmskb %xmm2, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v16i8:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpcmpgtb %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpcmpgtb %xmm3, %xmm2, %xmm1
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpmovmskb %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v16i8:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtb %xmm1, %xmm0, %k1
 ; AVX512-NEXT:    vpcmpgtb %xmm3, %xmm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; AVX512-NEXT:    retq
   %x0 = icmp sgt <16 x i8> %a, %b
   %x1 = icmp sgt <16 x i8> %c, %d
@@ -154,7 +154,7 @@ define i16 @v16i8(<16 x i8> %a, <16 x i8> %b, <16 x i8> %c, <16 x i8> %d) {
 
 define i2 @v2i8(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d) {
 ; SSE2-SSSE3-LABEL: v2i8:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    psllq $56, %xmm2
 ; SSE2-SSSE3-NEXT:    movdqa %xmm2, %xmm4
 ; SSE2-SSSE3-NEXT:    psrad $31, %xmm4
@@ -206,11 +206,11 @@ define i2 @v2i8(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d) {
 ; SSE2-SSSE3-NEXT:    por %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskpd %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v2i8:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpsllq $56, %xmm3, %xmm3
 ; AVX1-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX1-NEXT:    vpsrad $24, %xmm3, %xmm3
@@ -235,11 +235,11 @@ define i2 @v2i8(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d) {
 ; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vmovmskpd %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v2i8:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpsllq $56, %xmm3, %xmm3
 ; AVX2-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX2-NEXT:    vpsrad $24, %xmm3, %xmm3
@@ -264,11 +264,11 @@ define i2 @v2i8(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d) {
 ; AVX2-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vmovmskpd %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v2i8:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpsllq $56, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsraq $56, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsllq $56, %xmm2, %xmm2
@@ -292,7 +292,7 @@ define i2 @v2i8(<2 x i8> %a, <2 x i8> %b, <2 x i8> %c, <2 x i8> %d) {
 
 define i2 @v2i16(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c, <2 x i16> %d) {
 ; SSE2-SSSE3-LABEL: v2i16:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    psllq $48, %xmm2
 ; SSE2-SSSE3-NEXT:    movdqa %xmm2, %xmm4
 ; SSE2-SSSE3-NEXT:    psrad $31, %xmm4
@@ -344,11 +344,11 @@ define i2 @v2i16(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c, <2 x i16> %d) {
 ; SSE2-SSSE3-NEXT:    por %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskpd %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v2i16:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpsllq $48, %xmm3, %xmm3
 ; AVX1-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX1-NEXT:    vpsrad $16, %xmm3, %xmm3
@@ -373,11 +373,11 @@ define i2 @v2i16(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c, <2 x i16> %d) {
 ; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vmovmskpd %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v2i16:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpsllq $48, %xmm3, %xmm3
 ; AVX2-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX2-NEXT:    vpsrad $16, %xmm3, %xmm3
@@ -402,11 +402,11 @@ define i2 @v2i16(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c, <2 x i16> %d) {
 ; AVX2-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vmovmskpd %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v2i16:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpsllq $48, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsraq $48, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsllq $48, %xmm2, %xmm2
@@ -430,7 +430,7 @@ define i2 @v2i16(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c, <2 x i16> %d) {
 
 define i2 @v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c, <2 x i32> %d) {
 ; SSE2-SSSE3-LABEL: v2i32:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    psllq $32, %xmm2
 ; SSE2-SSSE3-NEXT:    pshufd {{.*#+}} xmm4 = xmm2[1,3,2,3]
 ; SSE2-SSSE3-NEXT:    psrad $31, %xmm2
@@ -474,11 +474,11 @@ define i2 @v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c, <2 x i32> %d) {
 ; SSE2-SSSE3-NEXT:    por %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm3, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskpd %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v2i32:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpsllq $32, %xmm3, %xmm3
 ; AVX1-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
@@ -499,11 +499,11 @@ define i2 @v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c, <2 x i32> %d) {
 ; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vmovmskpd %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v2i32:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpsllq $32, %xmm3, %xmm3
 ; AVX2-NEXT:    vpsrad $31, %xmm3, %xmm4
 ; AVX2-NEXT:    vpshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
@@ -524,11 +524,11 @@ define i2 @v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c, <2 x i32> %d) {
 ; AVX2-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX2-NEXT:    vmovmskpd %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v2i32:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpsllq $32, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsraq $32, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsllq $32, %xmm2, %xmm2
@@ -552,7 +552,7 @@ define i2 @v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c, <2 x i32> %d) {
 
 define i2 @v2i64(<2 x i64> %a, <2 x i64> %b, <2 x i64> %c, <2 x i64> %d) {
 ; SSE2-SSSE3-LABEL: v2i64:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    movdqa {{.*#+}} xmm4 = [2147483648,0,2147483648,0]
 ; SSE2-SSSE3-NEXT:    pxor %xmm4, %xmm1
 ; SSE2-SSSE3-NEXT:    pxor %xmm4, %xmm0
@@ -576,20 +576,20 @@ define i2 @v2i64(<2 x i64> %a, <2 x i64> %b, <2 x i64> %c, <2 x i64> %d) {
 ; SSE2-SSSE3-NEXT:    por %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskpd %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v2i64:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpcmpgtq %xmm3, %xmm2, %xmm1
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskpd %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v2i64:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtq %xmm1, %xmm0, %k1
 ; AVX512-NEXT:    vpcmpgtq %xmm3, %xmm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -605,25 +605,25 @@ define i2 @v2i64(<2 x i64> %a, <2 x i64> %b, <2 x i64> %c, <2 x i64> %d) {
 
 define i2 @v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %d) {
 ; SSE2-SSSE3-LABEL: v2f64:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    cmpltpd %xmm0, %xmm1
 ; SSE2-SSSE3-NEXT:    cmpltpd %xmm2, %xmm3
 ; SSE2-SSSE3-NEXT:    andpd %xmm1, %xmm3
 ; SSE2-SSSE3-NEXT:    movmskpd %xmm3, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v2f64:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vcmpltpd %xmm0, %xmm1, %xmm0
 ; AVX12-NEXT:    vcmpltpd %xmm2, %xmm3, %xmm1
 ; AVX12-NEXT:    vandpd %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskpd %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v2f64:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vcmpltpd %xmm0, %xmm1, %k1
 ; AVX512-NEXT:    vcmpltpd %xmm2, %xmm3, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -639,7 +639,7 @@ define i2 @v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double>
 
 define i4 @v4i8(<4 x i8> %a, <4 x i8> %b, <4 x i8> %c, <4 x i8> %d) {
 ; SSE2-SSSE3-LABEL: v4i8:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    pslld $24, %xmm3
 ; SSE2-SSSE3-NEXT:    psrad $24, %xmm3
 ; SSE2-SSSE3-NEXT:    pslld $24, %xmm2
@@ -652,11 +652,11 @@ define i4 @v4i8(<4 x i8> %a, <4 x i8> %b, <4 x i8> %c, <4 x i8> %d) {
 ; SSE2-SSSE3-NEXT:    pcmpgtd %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskps %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v4i8:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpslld $24, %xmm3, %xmm3
 ; AVX12-NEXT:    vpsrad $24, %xmm3, %xmm3
 ; AVX12-NEXT:    vpslld $24, %xmm2, %xmm2
@@ -669,11 +669,11 @@ define i4 @v4i8(<4 x i8> %a, <4 x i8> %b, <4 x i8> %c, <4 x i8> %d) {
 ; AVX12-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskps %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v4i8:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpslld $24, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsrad $24, %xmm3, %xmm3
 ; AVX512-NEXT:    vpslld $24, %xmm2, %xmm2
@@ -697,7 +697,7 @@ define i4 @v4i8(<4 x i8> %a, <4 x i8> %b, <4 x i8> %c, <4 x i8> %d) {
 
 define i4 @v4i16(<4 x i16> %a, <4 x i16> %b, <4 x i16> %c, <4 x i16> %d) {
 ; SSE2-SSSE3-LABEL: v4i16:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    pslld $16, %xmm3
 ; SSE2-SSSE3-NEXT:    psrad $16, %xmm3
 ; SSE2-SSSE3-NEXT:    pslld $16, %xmm2
@@ -710,11 +710,11 @@ define i4 @v4i16(<4 x i16> %a, <4 x i16> %b, <4 x i16> %c, <4 x i16> %d) {
 ; SSE2-SSSE3-NEXT:    pcmpgtd %xmm1, %xmm0
 ; SSE2-SSSE3-NEXT:    pand %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    movmskps %xmm0, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v4i16:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpslld $16, %xmm3, %xmm3
 ; AVX12-NEXT:    vpsrad $16, %xmm3, %xmm3
 ; AVX12-NEXT:    vpslld $16, %xmm2, %xmm2
@@ -727,11 +727,11 @@ define i4 @v4i16(<4 x i16> %a, <4 x i16> %b, <4 x i16> %c, <4 x i16> %d) {
 ; AVX12-NEXT:    vpcmpgtd %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskps %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v4i16:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpslld $16, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsrad $16, %xmm3, %xmm3
 ; AVX512-NEXT:    vpslld $16, %xmm2, %xmm2
@@ -755,7 +755,7 @@ define i4 @v4i16(<4 x i16> %a, <4 x i16> %b, <4 x i16> %c, <4 x i16> %d) {
 
 define i8 @v8i8(<8 x i8> %a, <8 x i8> %b, <8 x i8> %c, <8 x i8> %d) {
 ; SSE2-LABEL: v8i8:
-; SSE2:       ## BB#0:
+; SSE2:       # BB#0:
 ; SSE2-NEXT:    psllw $8, %xmm3
 ; SSE2-NEXT:    psraw $8, %xmm3
 ; SSE2-NEXT:    psllw $8, %xmm2
@@ -770,11 +770,11 @@ define i8 @v8i8(<8 x i8> %a, <8 x i8> %b, <8 x i8> %c, <8 x i8> %d) {
 ; SSE2-NEXT:    pand {{.*}}(%rip), %xmm0
 ; SSE2-NEXT:    packuswb %xmm0, %xmm0
 ; SSE2-NEXT:    pmovmskb %xmm0, %eax
-; SSE2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: v8i8:
-; SSSE3:       ## BB#0:
+; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    psllw $8, %xmm3
 ; SSSE3-NEXT:    psraw $8, %xmm3
 ; SSSE3-NEXT:    psllw $8, %xmm2
@@ -788,11 +788,11 @@ define i8 @v8i8(<8 x i8> %a, <8 x i8> %b, <8 x i8> %c, <8 x i8> %d) {
 ; SSSE3-NEXT:    pand %xmm2, %xmm0
 ; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; SSSE3-NEXT:    pmovmskb %xmm0, %eax
-; SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v8i8:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vpsllw $8, %xmm3, %xmm3
 ; AVX12-NEXT:    vpsraw $8, %xmm3, %xmm3
 ; AVX12-NEXT:    vpsllw $8, %xmm2, %xmm2
@@ -806,11 +806,11 @@ define i8 @v8i8(<8 x i8> %a, <8 x i8> %b, <8 x i8> %c, <8 x i8> %d) {
 ; AVX12-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; AVX12-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; AVX12-NEXT:    vpmovmskb %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v8i8:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpsllw $8, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsraw $8, %xmm3, %xmm3
 ; AVX512-NEXT:    vpsllw $8, %xmm2, %xmm2
@@ -822,7 +822,7 @@ define i8 @v8i8(<8 x i8> %a, <8 x i8> %b, <8 x i8> %c, <8 x i8> %d) {
 ; AVX512-NEXT:    vpcmpgtw %xmm1, %xmm0, %k1
 ; AVX512-NEXT:    vpcmpgtw %xmm3, %xmm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX512-NEXT:    retq
   %x0 = icmp sgt <8 x i8> %a, %b
   %x1 = icmp sgt <8 x i8> %c, %d
diff --git a/test/CodeGen/X86/bitcast-and-setcc-256.ll b/test/CodeGen/X86/bitcast-and-setcc-256.ll
index a6d6ca15530..95529686a58 100644
--- a/test/CodeGen/X86/bitcast-and-setcc-256.ll
+++ b/test/CodeGen/X86/bitcast-and-setcc-256.ll
@@ -1,13 +1,13 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+SSE2 < %s | FileCheck %s --check-prefixes=SSE2-SSSE3,SSE2
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+SSSE3 < %s | FileCheck %s --check-prefixes=SSE2-SSSE3,SSSE3
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx < %s | FileCheck %s --check-prefixes=AVX12,AVX1
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx2 < %s | FileCheck %s --check-prefixes=AVX12,AVX2
-; RUN: llc -mtriple=x86_64-apple-darwin -mcpu=x86-64 -mattr=+avx512f,+avx512vl,+avx512bw < %s | FileCheck %s --check-prefix=AVX512
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+SSE2 | FileCheck %s --check-prefixes=SSE2-SSSE3,SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+SSSE3 | FileCheck %s --check-prefixes=SSE2-SSSE3,SSSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX12,AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX12,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl,+avx512bw | FileCheck %s --check-prefix=AVX512
 
 define i4 @v4i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
 ; SSE2-SSSE3-LABEL: v4i64:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    movdqa {{.*#+}} xmm8 = [2147483648,0,2147483648,0]
 ; SSE2-SSSE3-NEXT:    pxor %xmm8, %xmm3
 ; SSE2-SSSE3-NEXT:    pxor %xmm8, %xmm1
@@ -57,11 +57,11 @@ define i4 @v4i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
 ; SSE2-SSSE3-NEXT:    psrad $31, %xmm2
 ; SSE2-SSSE3-NEXT:    pand %xmm0, %xmm2
 ; SSE2-SSSE3-NEXT:    movmskps %xmm2, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v4i64:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
 ; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm5, %xmm4
@@ -74,12 +74,12 @@ define i4 @v4i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
 ; AVX1-NEXT:    vpacksswb %xmm1, %xmm2, %xmm1
 ; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vmovmskps %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v4i64:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
@@ -88,12 +88,12 @@ define i4 @v4i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
 ; AVX2-NEXT:    vpacksswb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vmovmskps %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v4i64:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtq %ymm1, %ymm0, %k1
 ; AVX512-NEXT:    vpcmpgtq %ymm3, %ymm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -110,7 +110,7 @@ define i4 @v4i64(<4 x i64> %a, <4 x i64> %b, <4 x i64> %c, <4 x i64> %d) {
 
 define i4 @v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double> %d) {
 ; SSE2-SSSE3-LABEL: v4f64:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    cmpltpd %xmm1, %xmm3
 ; SSE2-SSSE3-NEXT:    cmpltpd %xmm0, %xmm2
 ; SSE2-SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
@@ -123,11 +123,11 @@ define i4 @v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double>
 ; SSE2-SSSE3-NEXT:    psrad $31, %xmm6
 ; SSE2-SSSE3-NEXT:    pand %xmm2, %xmm6
 ; SSE2-SSSE3-NEXT:    movmskps %xmm6, %eax
-; SSE2-SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v4f64:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vcmpltpd %ymm0, %ymm1, %ymm0
 ; AVX12-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX12-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
@@ -136,12 +136,12 @@ define i4 @v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double>
 ; AVX12-NEXT:    vpacksswb %xmm2, %xmm1, %xmm1
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vmovmskps %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    vzeroupper
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v4f64:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vcmpltpd %ymm0, %ymm1, %k1
 ; AVX512-NEXT:    vcmpltpd %ymm2, %ymm3, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
@@ -158,7 +158,7 @@ define i4 @v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double>
 
 define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 ; SSE2-LABEL: v16i16:
-; SSE2:       ## BB#0:
+; SSE2:       # BB#0:
 ; SSE2-NEXT:    pcmpgtw %xmm3, %xmm1
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
 ; SSE2-NEXT:    pand %xmm3, %xmm1
@@ -181,11 +181,11 @@ define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 ; SSE2-NEXT:    pcmpgtb %xmm4, %xmm2
 ; SSE2-NEXT:    pand %xmm1, %xmm2
 ; SSE2-NEXT:    pmovmskb %xmm2, %eax
-; SSE2-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; SSE2-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: v16i16:
-; SSSE3:       ## BB#0:
+; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    pcmpgtw %xmm3, %xmm1
 ; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; SSSE3-NEXT:    pshufb %xmm3, %xmm1
@@ -208,11 +208,11 @@ define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 ; SSSE3-NEXT:    pcmpgtb %xmm4, %xmm2
 ; SSSE3-NEXT:    pand %xmm1, %xmm2
 ; SSSE3-NEXT:    pmovmskb %xmm2, %eax
-; SSSE3-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; SSSE3-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v16i16:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
 ; AVX1-NEXT:    vpcmpgtw %xmm4, %xmm5, %xmm4
@@ -225,12 +225,12 @@ define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 ; AVX1-NEXT:    vpacksswb %xmm1, %xmm2, %xmm1
 ; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpmovmskb %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v16i16:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpcmpgtw %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
@@ -239,16 +239,16 @@ define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 ; AVX2-NEXT:    vpacksswb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpmovmskb %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v16i16:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtw %ymm1, %ymm0, %k1
 ; AVX512-NEXT:    vpcmpgtw %ymm3, %ymm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AX<def> %AX<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AX<def> %AX<kill> %EAX<kill>
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %x0 = icmp sgt <16 x i16> %a, %b
@@ -260,7 +260,7 @@ define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
 
 define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 ; SSE2-LABEL: v8i32:
-; SSE2:       ## BB#0:
+; SSE2:       # BB#0:
 ; SSE2-NEXT:    pcmpgtd %xmm3, %xmm1
 ; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
 ; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
@@ -287,11 +287,11 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 ; SSE2-NEXT:    pand {{.*}}(%rip), %xmm2
 ; SSE2-NEXT:    packuswb %xmm2, %xmm2
 ; SSE2-NEXT:    pmovmskb %xmm2, %eax
-; SSE2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: v8i32:
-; SSSE3:       ## BB#0:
+; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    pcmpgtd %xmm3, %xmm1
 ; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
 ; SSSE3-NEXT:    pshufb %xmm3, %xmm1
@@ -310,11 +310,11 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 ; SSSE3-NEXT:    pand %xmm0, %xmm4
 ; SSSE3-NEXT:    pshufb {{.*#+}} xmm4 = xmm4[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; SSSE3-NEXT:    pmovmskb %xmm4, %eax
-; SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v8i32:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
 ; AVX1-NEXT:    vpcmpgtd %xmm4, %xmm5, %xmm4
@@ -328,12 +328,12 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 ; AVX1-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; AVX1-NEXT:    vpmovmskb %xmm0, %eax
-; AVX1-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX1-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v8i32:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpcmpgtd %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
 ; AVX2-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
@@ -343,16 +343,16 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 ; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; AVX2-NEXT:    vpmovmskb %xmm0, %eax
-; AVX2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v8i32:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtd %ymm1, %ymm0, %k1
 ; AVX512-NEXT:    vpcmpgtd %ymm3, %ymm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %x0 = icmp sgt <8 x i32> %a, %b
@@ -364,7 +364,7 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
 
 define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d) {
 ; SSE2-LABEL: v8f32:
-; SSE2:       ## BB#0:
+; SSE2:       # BB#0:
 ; SSE2-NEXT:    cmpltps %xmm1, %xmm3
 ; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm3[0,2,2,3,4,5,6,7]
 ; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
@@ -391,11 +391,11 @@ define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d)
 ; SSE2-NEXT:    pand {{.*}}(%rip), %xmm2
 ; SSE2-NEXT:    packuswb %xmm2, %xmm2
 ; SSE2-NEXT:    pmovmskb %xmm2, %eax
-; SSE2-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSE2-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: v8f32:
-; SSSE3:       ## BB#0:
+; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    cmpltps %xmm1, %xmm3
 ; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
 ; SSSE3-NEXT:    pshufb %xmm1, %xmm3
@@ -414,11 +414,11 @@ define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d)
 ; SSSE3-NEXT:    pand %xmm2, %xmm6
 ; SSSE3-NEXT:    pshufb {{.*#+}} xmm6 = xmm6[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; SSSE3-NEXT:    pmovmskb %xmm6, %eax
-; SSSE3-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; SSSE3-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; SSSE3-NEXT:    retq
 ;
 ; AVX12-LABEL: v8f32:
-; AVX12:       ## BB#0:
+; AVX12:       # BB#0:
 ; AVX12-NEXT:    vcmpltps %ymm0, %ymm1, %ymm0
 ; AVX12-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX12-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0
@@ -428,16 +428,16 @@ define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d)
 ; AVX12-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX12-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
 ; AVX12-NEXT:    vpmovmskb %xmm0, %eax
-; AVX12-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX12-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX12-NEXT:    vzeroupper
 ; AVX12-NEXT:    retq
 ;
 ; AVX512-LABEL: v8f32:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vcmpltps %ymm0, %ymm1, %k1
 ; AVX512-NEXT:    vcmpltps %ymm2, %ymm3, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax
-; AVX512-NEXT:    ## kill: %AL<def> %AL<kill> %EAX<kill>
+; AVX512-NEXT:    # kill: %AL<def> %AL<kill> %EAX<kill>
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %x0 = fcmp ogt <8 x float> %a, %b
@@ -449,7 +449,7 @@ define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d)
 
 define i32 @v32i8(<32 x i8> %a, <32 x i8> %b, <32 x i8> %c, <32 x i8> %d) {
 ; SSE2-SSSE3-LABEL: v32i8:
-; SSE2-SSSE3:       ## BB#0:
+; SSE2-SSSE3:       # BB#0:
 ; SSE2-SSSE3-NEXT:    pcmpgtb %xmm2, %xmm0
 ; SSE2-SSSE3-NEXT:    pcmpgtb %xmm3, %xmm1
 ; SSE2-SSSE3-NEXT:    pcmpgtb %xmm6, %xmm4
@@ -561,14 +561,14 @@ define i32 @v32i8(<32 x i8> %a, <32 x i8> %b, <32 x i8> %c, <32 x i8> %d) {
 ; SSE2-SSSE3-NEXT:    retq
 ;
 ; AVX1-LABEL: v32i8:
-; AVX1:       ## BB#0:
+; AVX1:       # BB#0:
 ; AVX1-NEXT:    pushq %rbp
-; AVX1-NEXT:  Lcfi0:
+; AVX1-NEXT:  .Lcfi0:
 ; AVX1-NEXT:    .cfi_def_cfa_offset 16
-; AVX1-NEXT:  Lcfi1:
+; AVX1-NEXT:  .Lcfi1:
 ; AVX1-NEXT:    .cfi_offset %rbp, -16
 ; AVX1-NEXT:    movq %rsp, %rbp
-; AVX1-NEXT:  Lcfi2:
+; AVX1-NEXT:  .Lcfi2:
 ; AVX1-NEXT:    .cfi_def_cfa_register %rbp
 ; AVX1-NEXT:    andq $-32, %rsp
 ; AVX1-NEXT:    subq $32, %rsp
@@ -687,7 +687,7 @@ define i32 @v32i8(<32 x i8> %a, <32 x i8> %b, <32 x i8> %c, <32 x i8> %d) {
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: v32i8:
-; AVX2:       ## BB#0:
+; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpcmpgtb %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    vpcmpgtb %ymm3, %ymm2, %ymm1
 ; AVX2-NEXT:    vpand %ymm1, %ymm0, %ymm0
@@ -696,7 +696,7 @@ define i32 @v32i8(<32 x i8> %a, <32 x i8> %b, <32 x i8> %c, <32 x i8> %d) {
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: v32i8:
-; AVX512:       ## BB#0:
+; AVX512:       # BB#0:
 ; AVX512-NEXT:    vpcmpgtb %ymm1, %ymm0, %k1
 ; AVX512-NEXT:    vpcmpgtb %ymm3, %ymm2, %k0 {%k1}
 ; AVX512-NEXT:    kmovd %k0, %eax