From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Fri, 30 Jun 2017 11:23:59 +0000 (+0000)
Subject: [X86] Updated 32-bit memcmp tests to run with/without SSE2
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=ec4d81d2021041a16ff2b11790fc40847b93d5c8;p=llvm

[X86] Updated 32-bit memcmp tests to run with/without SSE2

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@306816 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/test/CodeGen/X86/memcmp.ll b/test/CodeGen/X86/memcmp.ll
index 52ef4b0dca5..0e09abf73c8 100644
--- a/test/CodeGen/X86/memcmp.ll
+++ b/test/CodeGen/X86/memcmp.ll
@@ -1,7 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X32
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64 --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=AVX2 | FileCheck %s --check-prefix=X64 --check-prefix=AVX2
+; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X86 --check-prefix=X86-NOSSE
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64 --check-prefix=X64-SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=AVX2 | FileCheck %s --check-prefix=X64 --check-prefix=X64-AVX2
 
 ; This tests codegen time inlining/optimization of memcmp
 ; rdar://6480398
@@ -11,27 +12,43 @@
 declare i32 @memcmp(i8*, i8*, i64)
 
 define i32 @length2(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length2:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movzwl (%ecx), %ecx
-; X32-NEXT:    movzwl (%eax), %eax
-; X32-NEXT:    rolw $8, %cx
-; X32-NEXT:    rolw $8, %ax
-; X32-NEXT:    cmpw %ax, %cx
-; X32-NEXT:    movl $-1, %eax
-; X32-NEXT:    jae .LBB0_1
-; X32-NEXT:  # BB#2:
-; X32-NEXT:    je .LBB0_3
-; X32-NEXT:  .LBB0_4:
-; X32-NEXT:    retl
-; X32-NEXT:  .LBB0_1:
-; X32-NEXT:    movl $1, %eax
-; X32-NEXT:    jne .LBB0_4
-; X32-NEXT:  .LBB0_3:
-; X32-NEXT:    xorl %eax, %eax
-; X32-NEXT:    retl
+; X86-NOSSE-LABEL: length2:
+; X86-NOSSE:       # BB#0:
+; X86-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NOSSE-NEXT:    movzwl (%ecx), %ecx
+; X86-NOSSE-NEXT:    movzwl (%eax), %eax
+; X86-NOSSE-NEXT:    rolw $8, %cx
+; X86-NOSSE-NEXT:    rolw $8, %ax
+; X86-NOSSE-NEXT:    cmpw %ax, %cx
+; X86-NOSSE-NEXT:    movl $-1, %eax
+; X86-NOSSE-NEXT:    jae .LBB0_1
+; X86-NOSSE-NEXT:  # BB#2:
+; X86-NOSSE-NEXT:    je .LBB0_3
+; X86-NOSSE-NEXT:  .LBB0_4:
+; X86-NOSSE-NEXT:    retl
+; X86-NOSSE-NEXT:  .LBB0_1:
+; X86-NOSSE-NEXT:    movl $1, %eax
+; X86-NOSSE-NEXT:    jne .LBB0_4
+; X86-NOSSE-NEXT:  .LBB0_3:
+; X86-NOSSE-NEXT:    xorl %eax, %eax
+; X86-NOSSE-NEXT:    retl
+;
+; X86-SSE2-LABEL: length2:
+; X86-SSE2:       # BB#0:
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE2-NEXT:    movzwl (%ecx), %ecx
+; X86-SSE2-NEXT:    movzwl (%eax), %eax
+; X86-SSE2-NEXT:    rolw $8, %cx
+; X86-SSE2-NEXT:    rolw $8, %ax
+; X86-SSE2-NEXT:    xorl %edx, %edx
+; X86-SSE2-NEXT:    cmpw %ax, %cx
+; X86-SSE2-NEXT:    movl $-1, %ecx
+; X86-SSE2-NEXT:    movl $1, %eax
+; X86-SSE2-NEXT:    cmovbl %ecx, %eax
+; X86-SSE2-NEXT:    cmovel %edx, %eax
+; X86-SSE2-NEXT:    retl
 ;
 ; X64-LABEL: length2:
 ; X64:       # BB#0:
@@ -51,14 +68,14 @@ define i32 @length2(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length2_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length2_eq:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movzwl (%ecx), %ecx
-; X32-NEXT:    cmpw (%eax), %cx
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
+; X86-LABEL: length2_eq:
+; X86:       # BB#0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movzwl (%ecx), %ecx
+; X86-NEXT:    cmpw (%eax), %cx
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length2_eq:
 ; X64:       # BB#0:
@@ -72,13 +89,13 @@ define i1 @length2_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length2_eq_const(i8* %X) nounwind {
-; X32-LABEL: length2_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movzwl (%eax), %eax
-; X32-NEXT:    cmpl $12849, %eax # imm = 0x3231
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length2_eq_const:
+; X86:       # BB#0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movzwl (%eax), %eax
+; X86-NEXT:    cmpl $12849, %eax # imm = 0x3231
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length2_eq_const:
 ; X64:       # BB#0:
@@ -92,17 +109,17 @@ define i1 @length2_eq_const(i8* %X) nounwind {
 }
 
 define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length2_eq_nobuiltin_attr:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $2
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
+; X86-LABEL: length2_eq_nobuiltin_attr:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $2
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length2_eq_nobuiltin_attr:
 ; X64:       # BB#0:
@@ -119,15 +136,15 @@ define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind {
 }
 
 define i32 @length3(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length3:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $3
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length3:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $3
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length3:
 ; X64:       # BB#0:
@@ -138,17 +155,17 @@ define i32 @length3(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length3_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length3_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $3
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length3_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $3
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length3_eq:
 ; X64:       # BB#0:
@@ -165,27 +182,43 @@ define i1 @length3_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i32 @length4(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length4:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movl (%ecx), %ecx
-; X32-NEXT:    movl (%eax), %eax
-; X32-NEXT:    bswapl %ecx
-; X32-NEXT:    bswapl %eax
-; X32-NEXT:    cmpl %eax, %ecx
-; X32-NEXT:    movl $-1, %eax
-; X32-NEXT:    jae .LBB6_1
-; X32-NEXT:  # BB#2:
-; X32-NEXT:    je .LBB6_3
-; X32-NEXT:  .LBB6_4:
-; X32-NEXT:    retl
-; X32-NEXT:  .LBB6_1:
-; X32-NEXT:    movl $1, %eax
-; X32-NEXT:    jne .LBB6_4
-; X32-NEXT:  .LBB6_3:
-; X32-NEXT:    xorl %eax, %eax
-; X32-NEXT:    retl
+; X86-NOSSE-LABEL: length4:
+; X86-NOSSE:       # BB#0:
+; X86-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NOSSE-NEXT:    movl (%ecx), %ecx
+; X86-NOSSE-NEXT:    movl (%eax), %eax
+; X86-NOSSE-NEXT:    bswapl %ecx
+; X86-NOSSE-NEXT:    bswapl %eax
+; X86-NOSSE-NEXT:    cmpl %eax, %ecx
+; X86-NOSSE-NEXT:    movl $-1, %eax
+; X86-NOSSE-NEXT:    jae .LBB6_1
+; X86-NOSSE-NEXT:  # BB#2:
+; X86-NOSSE-NEXT:    je .LBB6_3
+; X86-NOSSE-NEXT:  .LBB6_4:
+; X86-NOSSE-NEXT:    retl
+; X86-NOSSE-NEXT:  .LBB6_1:
+; X86-NOSSE-NEXT:    movl $1, %eax
+; X86-NOSSE-NEXT:    jne .LBB6_4
+; X86-NOSSE-NEXT:  .LBB6_3:
+; X86-NOSSE-NEXT:    xorl %eax, %eax
+; X86-NOSSE-NEXT:    retl
+;
+; X86-SSE2-LABEL: length4:
+; X86-SSE2:       # BB#0:
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE2-NEXT:    movl (%ecx), %ecx
+; X86-SSE2-NEXT:    movl (%eax), %eax
+; X86-SSE2-NEXT:    bswapl %ecx
+; X86-SSE2-NEXT:    bswapl %eax
+; X86-SSE2-NEXT:    xorl %edx, %edx
+; X86-SSE2-NEXT:    cmpl %eax, %ecx
+; X86-SSE2-NEXT:    movl $-1, %ecx
+; X86-SSE2-NEXT:    movl $1, %eax
+; X86-SSE2-NEXT:    cmovbl %ecx, %eax
+; X86-SSE2-NEXT:    cmovel %edx, %eax
+; X86-SSE2-NEXT:    retl
 ;
 ; X64-LABEL: length4:
 ; X64:       # BB#0:
@@ -205,14 +238,14 @@ define i32 @length4(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length4_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length4_eq:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movl (%ecx), %ecx
-; X32-NEXT:    cmpl (%eax), %ecx
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length4_eq:
+; X86:       # BB#0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl (%ecx), %ecx
+; X86-NEXT:    cmpl (%eax), %ecx
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length4_eq:
 ; X64:       # BB#0:
@@ -226,12 +259,12 @@ define i1 @length4_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length4_eq_const(i8* %X) nounwind {
-; X32-LABEL: length4_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    cmpl $875770417, (%eax) # imm = 0x34333231
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
+; X86-LABEL: length4_eq_const:
+; X86:       # BB#0:
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    cmpl $875770417, (%eax) # imm = 0x34333231
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length4_eq_const:
 ; X64:       # BB#0:
@@ -244,15 +277,15 @@ define i1 @length4_eq_const(i8* %X) nounwind {
 }
 
 define i32 @length5(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length5:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $5
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length5:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $5
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length5:
 ; X64:       # BB#0:
@@ -263,17 +296,17 @@ define i32 @length5(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length5_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $5
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length5_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $5
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length5_eq:
 ; X64:       # BB#0:
@@ -290,15 +323,15 @@ define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i32 @length8(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length8:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $8
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length8:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $8
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8:
 ; X64:       # BB#0:
@@ -318,17 +351,17 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length8_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length8_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $8
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
+; X86-LABEL: length8_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $8
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq:
 ; X64:       # BB#0:
@@ -342,17 +375,17 @@ define i1 @length8_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length8_eq_const(i8* %X) nounwind {
-; X32-LABEL: length8_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $8
-; X32-NEXT:    pushl $.L.str
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length8_eq_const:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $8
+; X86-NEXT:    pushl $.L.str
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length8_eq_const:
 ; X64:       # BB#0:
@@ -366,17 +399,17 @@ define i1 @length8_eq_const(i8* %X) nounwind {
 }
 
 define i1 @length12_eq(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length12_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $12
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length12_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $12
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length12_eq:
 ; X64:       # BB#0:
@@ -393,15 +426,15 @@ define i1 @length12_eq(i8* %X, i8* %Y) nounwind {
 }
 
 define i32 @length12(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length12:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $12
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length12:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $12
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length12:
 ; X64:       # BB#0:
@@ -414,15 +447,15 @@ define i32 @length12(i8* %X, i8* %Y) nounwind {
 ; PR33329 - https://bugs.llvm.org/show_bug.cgi?id=33329
 
 define i32 @length16(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length16:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $16
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length16:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $16
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length16:
 ; X64:       # BB#0:
@@ -433,86 +466,108 @@ define i32 @length16(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length16_eq(i8* %x, i8* %y) nounwind {
-; X32-LABEL: length16_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $16
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
-;
-; SSE2-LABEL: length16_eq:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    movdqu (%rsi), %xmm0
-; SSE2-NEXT:    movdqu (%rdi), %xmm1
-; SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
-; SSE2-NEXT:    pmovmskb %xmm1, %eax
-; SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; SSE2-NEXT:    setne %al
-; SSE2-NEXT:    retq
-;
-; AVX2-LABEL: length16_eq:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqu (%rdi), %xmm0
-; AVX2-NEXT:    vpcmpeqb (%rsi), %xmm0, %xmm0
-; AVX2-NEXT:    vpmovmskb %xmm0, %eax
-; AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; AVX2-NEXT:    setne %al
-; AVX2-NEXT:    retq
+; X86-NOSSE-LABEL: length16_eq:
+; X86-NOSSE:       # BB#0:
+; X86-NOSSE-NEXT:    pushl $0
+; X86-NOSSE-NEXT:    pushl $16
+; X86-NOSSE-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT:    calll memcmp
+; X86-NOSSE-NEXT:    addl $16, %esp
+; X86-NOSSE-NEXT:    testl %eax, %eax
+; X86-NOSSE-NEXT:    setne %al
+; X86-NOSSE-NEXT:    retl
+;
+; X86-SSE2-LABEL: length16_eq:
+; X86-SSE2:       # BB#0:
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE2-NEXT:    movdqu (%ecx), %xmm0
+; X86-SSE2-NEXT:    movdqu (%eax), %xmm1
+; X86-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
+; X86-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X86-SSE2-NEXT:    setne %al
+; X86-SSE2-NEXT:    retl
+;
+; X64-SSE2-LABEL: length16_eq:
+; X64-SSE2:       # BB#0:
+; X64-SSE2-NEXT:    movdqu (%rsi), %xmm0
+; X64-SSE2-NEXT:    movdqu (%rdi), %xmm1
+; X64-SSE2-NEXT:    pcmpeqb %xmm0, %xmm1
+; X64-SSE2-NEXT:    pmovmskb %xmm1, %eax
+; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X64-SSE2-NEXT:    setne %al
+; X64-SSE2-NEXT:    retq
+;
+; X64-AVX2-LABEL: length16_eq:
+; X64-AVX2:       # BB#0:
+; X64-AVX2-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %xmm0, %xmm0
+; X64-AVX2-NEXT:    vpmovmskb %xmm0, %eax
+; X64-AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X64-AVX2-NEXT:    setne %al
+; X64-AVX2-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 16) nounwind
   %cmp = icmp ne i32 %call, 0
   ret i1 %cmp
 }
 
 define i1 @length16_eq_const(i8* %X) nounwind {
-; X32-LABEL: length16_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $16
-; X32-NEXT:    pushl $.L.str
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
-;
-; SSE2-LABEL: length16_eq_const:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    movdqu (%rdi), %xmm0
-; SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
-; SSE2-NEXT:    pmovmskb %xmm0, %eax
-; SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; SSE2-NEXT:    sete %al
-; SSE2-NEXT:    retq
-;
-; AVX2-LABEL: length16_eq_const:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqu (%rdi), %xmm0
-; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
-; AVX2-NEXT:    vpmovmskb %xmm0, %eax
-; AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
-; AVX2-NEXT:    sete %al
-; AVX2-NEXT:    retq
+; X86-NOSSE-LABEL: length16_eq_const:
+; X86-NOSSE:       # BB#0:
+; X86-NOSSE-NEXT:    pushl $0
+; X86-NOSSE-NEXT:    pushl $16
+; X86-NOSSE-NEXT:    pushl $.L.str
+; X86-NOSSE-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NOSSE-NEXT:    calll memcmp
+; X86-NOSSE-NEXT:    addl $16, %esp
+; X86-NOSSE-NEXT:    testl %eax, %eax
+; X86-NOSSE-NEXT:    sete %al
+; X86-NOSSE-NEXT:    retl
+;
+; X86-SSE2-LABEL: length16_eq_const:
+; X86-SSE2:       # BB#0:
+; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X86-SSE2-NEXT:    movdqu (%eax), %xmm0
+; X86-SSE2-NEXT:    pcmpeqb {{\.LCPI.*}}, %xmm0
+; X86-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X86-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X86-SSE2-NEXT:    sete %al
+; X86-SSE2-NEXT:    retl
+;
+; X64-SSE2-LABEL: length16_eq_const:
+; X64-SSE2:       # BB#0:
+; X64-SSE2-NEXT:    movdqu (%rdi), %xmm0
+; X64-SSE2-NEXT:    pcmpeqb {{.*}}(%rip), %xmm0
+; X64-SSE2-NEXT:    pmovmskb %xmm0, %eax
+; X64-SSE2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X64-SSE2-NEXT:    sete %al
+; X64-SSE2-NEXT:    retq
+;
+; X64-AVX2-LABEL: length16_eq_const:
+; X64-AVX2:       # BB#0:
+; X64-AVX2-NEXT:    vmovdqu (%rdi), %xmm0
+; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %xmm0, %xmm0
+; X64-AVX2-NEXT:    vpmovmskb %xmm0, %eax
+; X64-AVX2-NEXT:    cmpl $65535, %eax # imm = 0xFFFF
+; X64-AVX2-NEXT:    sete %al
+; X64-AVX2-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 16) nounwind
   %c = icmp eq i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length32(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length32:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $32
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length32:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $32
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length32:
 ; X64:       # BB#0:
@@ -525,90 +580,90 @@ define i32 @length32(i8* %X, i8* %Y) nounwind {
 ; PR33325 - https://bugs.llvm.org/show_bug.cgi?id=33325
 
 define i1 @length32_eq(i8* %x, i8* %y) nounwind {
-; X32-LABEL: length32_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $32
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
-;
-; SSE2-LABEL: length32_eq:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    pushq %rax
-; SSE2-NEXT:    movl $32, %edx
-; SSE2-NEXT:    callq memcmp
-; SSE2-NEXT:    testl %eax, %eax
-; SSE2-NEXT:    sete %al
-; SSE2-NEXT:    popq %rcx
-; SSE2-NEXT:    retq
-;
-; AVX2-LABEL: length32_eq:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqu (%rdi), %ymm0
-; AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
-; AVX2-NEXT:    vpmovmskb %ymm0, %eax
-; AVX2-NEXT:    cmpl $-1, %eax
-; AVX2-NEXT:    sete %al
-; AVX2-NEXT:    vzeroupper
-; AVX2-NEXT:    retq
+; X86-LABEL: length32_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $32
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
+;
+; X64-SSE2-LABEL: length32_eq:
+; X64-SSE2:       # BB#0:
+; X64-SSE2-NEXT:    pushq %rax
+; X64-SSE2-NEXT:    movl $32, %edx
+; X64-SSE2-NEXT:    callq memcmp
+; X64-SSE2-NEXT:    testl %eax, %eax
+; X64-SSE2-NEXT:    sete %al
+; X64-SSE2-NEXT:    popq %rcx
+; X64-SSE2-NEXT:    retq
+;
+; X64-AVX2-LABEL: length32_eq:
+; X64-AVX2:       # BB#0:
+; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vpcmpeqb (%rsi), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
+; X64-AVX2-NEXT:    cmpl $-1, %eax
+; X64-AVX2-NEXT:    sete %al
+; X64-AVX2-NEXT:    vzeroupper
+; X64-AVX2-NEXT:    retq
   %call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind
   %cmp = icmp eq i32 %call, 0
   ret i1 %cmp
 }
 
 define i1 @length32_eq_const(i8* %X) nounwind {
-; X32-LABEL: length32_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $32
-; X32-NEXT:    pushl $.L.str
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
-;
-; SSE2-LABEL: length32_eq_const:
-; SSE2:       # BB#0:
-; SSE2-NEXT:    pushq %rax
-; SSE2-NEXT:    movl $.L.str, %esi
-; SSE2-NEXT:    movl $32, %edx
-; SSE2-NEXT:    callq memcmp
-; SSE2-NEXT:    testl %eax, %eax
-; SSE2-NEXT:    setne %al
-; SSE2-NEXT:    popq %rcx
-; SSE2-NEXT:    retq
-;
-; AVX2-LABEL: length32_eq_const:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqu (%rdi), %ymm0
-; AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vpmovmskb %ymm0, %eax
-; AVX2-NEXT:    cmpl $-1, %eax
-; AVX2-NEXT:    setne %al
-; AVX2-NEXT:    vzeroupper
-; AVX2-NEXT:    retq
+; X86-LABEL: length32_eq_const:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $32
+; X86-NEXT:    pushl $.L.str
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
+;
+; X64-SSE2-LABEL: length32_eq_const:
+; X64-SSE2:       # BB#0:
+; X64-SSE2-NEXT:    pushq %rax
+; X64-SSE2-NEXT:    movl $.L.str, %esi
+; X64-SSE2-NEXT:    movl $32, %edx
+; X64-SSE2-NEXT:    callq memcmp
+; X64-SSE2-NEXT:    testl %eax, %eax
+; X64-SSE2-NEXT:    setne %al
+; X64-SSE2-NEXT:    popq %rcx
+; X64-SSE2-NEXT:    retq
+;
+; X64-AVX2-LABEL: length32_eq_const:
+; X64-AVX2:       # BB#0:
+; X64-AVX2-NEXT:    vmovdqu (%rdi), %ymm0
+; X64-AVX2-NEXT:    vpcmpeqb {{.*}}(%rip), %ymm0, %ymm0
+; X64-AVX2-NEXT:    vpmovmskb %ymm0, %eax
+; X64-AVX2-NEXT:    cmpl $-1, %eax
+; X64-AVX2-NEXT:    setne %al
+; X64-AVX2-NEXT:    vzeroupper
+; X64-AVX2-NEXT:    retq
   %m = tail call i32 @memcmp(i8* %X, i8* getelementptr inbounds ([65 x i8], [65 x i8]* @.str, i32 0, i32 0), i64 32) nounwind
   %c = icmp ne i32 %m, 0
   ret i1 %c
 }
 
 define i32 @length64(i8* %X, i8* %Y) nounwind {
-; X32-LABEL: length64:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $64
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    retl
+; X86-LABEL: length64:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $64
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length64:
 ; X64:       # BB#0:
@@ -619,17 +674,17 @@ define i32 @length64(i8* %X, i8* %Y) nounwind {
 }
 
 define i1 @length64_eq(i8* %x, i8* %y) nounwind {
-; X32-LABEL: length64_eq:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $64
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    setne %al
-; X32-NEXT:    retl
+; X86-LABEL: length64_eq:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $64
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    setne %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length64_eq:
 ; X64:       # BB#0:
@@ -646,17 +701,17 @@ define i1 @length64_eq(i8* %x, i8* %y) nounwind {
 }
 
 define i1 @length64_eq_const(i8* %X) nounwind {
-; X32-LABEL: length64_eq_const:
-; X32:       # BB#0:
-; X32-NEXT:    pushl $0
-; X32-NEXT:    pushl $64
-; X32-NEXT:    pushl $.L.str
-; X32-NEXT:    pushl {{[0-9]+}}(%esp)
-; X32-NEXT:    calll memcmp
-; X32-NEXT:    addl $16, %esp
-; X32-NEXT:    testl %eax, %eax
-; X32-NEXT:    sete %al
-; X32-NEXT:    retl
+; X86-LABEL: length64_eq_const:
+; X86:       # BB#0:
+; X86-NEXT:    pushl $0
+; X86-NEXT:    pushl $64
+; X86-NEXT:    pushl $.L.str
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll memcmp
+; X86-NEXT:    addl $16, %esp
+; X86-NEXT:    testl %eax, %eax
+; X86-NEXT:    sete %al
+; X86-NEXT:    retl
 ;
 ; X64-LABEL: length64_eq_const:
 ; X64:       # BB#0: