summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/memcmp.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/memcmp.ll')
-rw-r--r--test/CodeGen/X86/memcmp.ll827
1 files changed, 532 insertions, 295 deletions
diff --git a/test/CodeGen/X86/memcmp.ll b/test/CodeGen/X86/memcmp.ll
index 0e09abf73c8c9..2e67827654624 100644
--- a/test/CodeGen/X86/memcmp.ll
+++ b/test/CodeGen/X86/memcmp.ll
@@ -1,8 +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=X86 --check-prefix=X86-NOSSE
+; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=cmov | 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
+; 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
@@ -12,43 +12,21 @@
declare i32 @memcmp(i8*, i8*, i64)
define i32 @length2(i8* %X, i8* %Y) nounwind {
-; 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
+; X86-LABEL: length2:
+; X86: # BB#0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movzwl (%ecx), %ecx
+; X86-NEXT: movzwl (%eax), %eax
+; X86-NEXT: rolw $8, %cx
+; X86-NEXT: rolw $8, %ax
+; X86-NEXT: xorl %edx, %edx
+; X86-NEXT: cmpw %ax, %cx
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: cmovel %edx, %eax
+; X86-NEXT: retl
;
; X64-LABEL: length2:
; X64: # BB#0:
@@ -137,44 +115,90 @@ define i1 @length2_eq_nobuiltin_attr(i8* %X, i8* %Y) nounwind {
define i32 @length3(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movzwl (%eax), %edx
+; X86-NEXT: movzwl (%ecx), %esi
+; X86-NEXT: rolw $8, %dx
+; X86-NEXT: rolw $8, %si
+; X86-NEXT: movzwl %dx, %edx
+; X86-NEXT: movzwl %si, %esi
+; X86-NEXT: cmpl %esi, %edx
+; X86-NEXT: jne .LBB4_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movzbl 2(%eax), %eax
+; X86-NEXT: movzbl 2(%ecx), %ecx
+; X86-NEXT: subl %ecx, %eax
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
+; X86-NEXT: .LBB4_1: # %res_block
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length3:
-; X64: # BB#0:
-; X64-NEXT: movl $3, %edx
-; X64-NEXT: jmp memcmp # TAILCALL
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movzwl (%rdi), %eax
+; X64-NEXT: movzwl (%rsi), %ecx
+; X64-NEXT: rolw $8, %ax
+; X64-NEXT: rolw $8, %cx
+; X64-NEXT: movzwl %ax, %eax
+; X64-NEXT: movzwl %cx, %ecx
+; X64-NEXT: cmpq %rcx, %rax
+; X64-NEXT: jne .LBB4_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movzbl 2(%rdi), %eax
+; X64-NEXT: movzbl 2(%rsi), %ecx
+; X64-NEXT: subl %ecx, %eax
+; X64-NEXT: retq
+; X64-NEXT: .LBB4_1: # %res_block
+; X64-NEXT: movl $-1, %ecx
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: cmovbl %ecx, %eax
+; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
ret i32 %m
}
define i1 @length3_eq(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movzwl (%eax), %edx
+; X86-NEXT: cmpw (%ecx), %dx
+; X86-NEXT: jne .LBB5_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movb 2(%eax), %dl
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpb 2(%ecx), %dl
+; X86-NEXT: je .LBB5_3
+; X86-NEXT: .LBB5_1: # %res_block
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: .LBB5_3: # %endblock
; X86-NEXT: testl %eax, %eax
; X86-NEXT: setne %al
; X86-NEXT: retl
;
; X64-LABEL: length3_eq:
-; X64: # BB#0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $3, %edx
-; X64-NEXT: callq memcmp
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movzwl (%rdi), %eax
+; X64-NEXT: cmpw (%rsi), %ax
+; X64-NEXT: jne .LBB5_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movb 2(%rdi), %cl
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpb 2(%rsi), %cl
+; X64-NEXT: je .LBB5_3
+; X64-NEXT: .LBB5_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB5_3: # %endblock
; X64-NEXT: testl %eax, %eax
; X64-NEXT: setne %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 3) nounwind
%c = icmp ne i32 %m, 0
@@ -182,43 +206,21 @@ define i1 @length3_eq(i8* %X, i8* %Y) nounwind {
}
define i32 @length4(i8* %X, i8* %Y) nounwind {
-; 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
+; X86-LABEL: length4:
+; X86: # BB#0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl (%ecx), %ecx
+; X86-NEXT: movl (%eax), %eax
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %eax
+; X86-NEXT: xorl %edx, %edx
+; X86-NEXT: cmpl %eax, %ecx
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: cmovel %edx, %eax
+; X86-NEXT: retl
;
; X64-LABEL: length4:
; X64: # BB#0:
@@ -278,44 +280,86 @@ define i1 @length4_eq_const(i8* %X) nounwind {
define i32 @length5(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: movl (%ecx), %esi
+; X86-NEXT: bswapl %edx
+; X86-NEXT: bswapl %esi
+; X86-NEXT: cmpl %esi, %edx
+; X86-NEXT: jne .LBB9_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movzbl 4(%eax), %eax
+; X86-NEXT: movzbl 4(%ecx), %ecx
+; X86-NEXT: subl %ecx, %eax
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
+; X86-NEXT: .LBB9_1: # %res_block
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length5:
-; X64: # BB#0:
-; X64-NEXT: movl $5, %edx
-; X64-NEXT: jmp memcmp # TAILCALL
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movl (%rdi), %eax
+; X64-NEXT: movl (%rsi), %ecx
+; X64-NEXT: bswapl %eax
+; X64-NEXT: bswapl %ecx
+; X64-NEXT: cmpq %rcx, %rax
+; X64-NEXT: jne .LBB9_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movzbl 4(%rdi), %eax
+; X64-NEXT: movzbl 4(%rsi), %ecx
+; X64-NEXT: subl %ecx, %eax
+; X64-NEXT: retq
+; X64-NEXT: .LBB9_1: # %res_block
+; X64-NEXT: movl $-1, %ecx
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: cmovbl %ecx, %eax
+; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
ret i32 %m
}
define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: cmpl (%ecx), %edx
+; X86-NEXT: jne .LBB10_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movb 4(%eax), %dl
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpb 4(%ecx), %dl
+; X86-NEXT: je .LBB10_3
+; X86-NEXT: .LBB10_1: # %res_block
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: .LBB10_3: # %endblock
; X86-NEXT: testl %eax, %eax
; X86-NEXT: setne %al
; X86-NEXT: retl
;
; X64-LABEL: length5_eq:
-; X64: # BB#0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $5, %edx
-; X64-NEXT: callq memcmp
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movl (%rdi), %eax
+; X64-NEXT: cmpl (%rsi), %eax
+; X64-NEXT: jne .LBB10_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movb 4(%rdi), %cl
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpb 4(%rsi), %cl
+; X64-NEXT: je .LBB10_3
+; X64-NEXT: .LBB10_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB10_3: # %endblock
; X64-NEXT: testl %eax, %eax
; X64-NEXT: setne %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 5) nounwind
%c = icmp ne i32 %m, 0
@@ -324,13 +368,33 @@ define i1 @length5_eq(i8* %X, i8* %Y) nounwind {
define i32 @length8(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl (%esi), %ecx
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB11_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%esi), %ecx
+; X86-NEXT: movl 4(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB11_1
+; X86-NEXT: # BB#3: # %endblock
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
+; X86-NEXT: .LBB11_1: # %res_block
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length8:
@@ -352,13 +416,20 @@ define i32 @length8(i8* %X, i8* %Y) nounwind {
define i1 @length8_eq(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: cmpl (%ecx), %edx
+; X86-NEXT: jne .LBB12_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%eax), %edx
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpl 4(%ecx), %edx
+; X86-NEXT: je .LBB12_3
+; X86-NEXT: .LBB12_1: # %res_block
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: .LBB12_3: # %endblock
; X86-NEXT: testl %eax, %eax
; X86-NEXT: sete %al
; X86-NEXT: retl
@@ -376,13 +447,17 @@ define i1 @length8_eq(i8* %X, i8* %Y) nounwind {
define i1 @length8_eq_const(i8* %X) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: cmpl $858927408, (%ecx) # imm = 0x33323130
+; X86-NEXT: jne .LBB13_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpl $926299444, 4(%ecx) # imm = 0x37363534
+; X86-NEXT: je .LBB13_3
+; X86-NEXT: .LBB13_1: # %res_block
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: .LBB13_3: # %endblock
; X86-NEXT: testl %eax, %eax
; X86-NEXT: setne %al
; X86-NEXT: retl
@@ -400,25 +475,43 @@ define i1 @length8_eq_const(i8* %X) nounwind {
define i1 @length12_eq(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl (%ecx), %edx
+; X86-NEXT: cmpl (%eax), %edx
+; X86-NEXT: jne .LBB14_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%ecx), %edx
+; X86-NEXT: cmpl 4(%eax), %edx
+; X86-NEXT: jne .LBB14_1
+; X86-NEXT: # BB#3: # %loadbb2
+; X86-NEXT: movl 8(%ecx), %edx
+; X86-NEXT: xorl %ecx, %ecx
+; X86-NEXT: cmpl 8(%eax), %edx
+; X86-NEXT: je .LBB14_4
+; X86-NEXT: .LBB14_1: # %res_block
+; X86-NEXT: movl $1, %ecx
+; X86-NEXT: .LBB14_4: # %endblock
+; X86-NEXT: testl %ecx, %ecx
; X86-NEXT: setne %al
; X86-NEXT: retl
;
; X64-LABEL: length12_eq:
-; X64: # BB#0:
-; X64-NEXT: pushq %rax
-; X64-NEXT: movl $12, %edx
-; X64-NEXT: callq memcmp
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: cmpq (%rsi), %rax
+; X64-NEXT: jne .LBB14_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movl 8(%rdi), %ecx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpl 8(%rsi), %ecx
+; X64-NEXT: je .LBB14_3
+; X64-NEXT: .LBB14_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB14_3: # %endblock
; X64-NEXT: testl %eax, %eax
; X64-NEXT: setne %al
-; X64-NEXT: popq %rcx
; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
%c = icmp ne i32 %m, 0
@@ -427,19 +520,66 @@ define i1 @length12_eq(i8* %X, i8* %Y) nounwind {
define i32 @length12(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl (%esi), %ecx
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB15_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%esi), %ecx
+; X86-NEXT: movl 4(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB15_1
+; X86-NEXT: # BB#3: # %loadbb2
+; X86-NEXT: movl 8(%esi), %ecx
+; X86-NEXT: movl 8(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB15_1
+; X86-NEXT: # BB#4: # %endblock
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
+; X86-NEXT: .LBB15_1: # %res_block
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length12:
-; X64: # BB#0:
-; X64-NEXT: movl $12, %edx
-; X64-NEXT: jmp memcmp # TAILCALL
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rcx
+; X64-NEXT: movq (%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB15_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movl 8(%rdi), %ecx
+; X64-NEXT: movl 8(%rsi), %edx
+; X64-NEXT: bswapl %ecx
+; X64-NEXT: bswapl %edx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB15_1
+; X64-NEXT: # BB#3: # %endblock
+; X64-NEXT: retq
+; X64-NEXT: .LBB15_1: # %res_block
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: movl $-1, %ecx
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: cmovbl %ecx, %eax
+; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 12) nounwind
ret i32 %m
}
@@ -448,111 +588,165 @@ define i32 @length12(i8* %X, i8* %Y) nounwind {
define i32 @length16(i8* %X, i8* %Y) nounwind {
; 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: # BB#0: # %loadbb
+; X86-NEXT: pushl %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl (%esi), %ecx
+; X86-NEXT: movl (%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB16_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%esi), %ecx
+; X86-NEXT: movl 4(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB16_1
+; X86-NEXT: # BB#3: # %loadbb2
+; X86-NEXT: movl 8(%esi), %ecx
+; X86-NEXT: movl 8(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB16_1
+; X86-NEXT: # BB#4: # %loadbb3
+; X86-NEXT: movl 12(%esi), %ecx
+; X86-NEXT: movl 12(%eax), %edx
+; X86-NEXT: bswapl %ecx
+; X86-NEXT: bswapl %edx
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: jne .LBB16_1
+; X86-NEXT: # BB#5: # %endblock
+; X86-NEXT: popl %esi
+; X86-NEXT: retl
+; X86-NEXT: .LBB16_1: # %res_block
+; X86-NEXT: cmpl %edx, %ecx
+; X86-NEXT: movl $-1, %ecx
+; X86-NEXT: movl $1, %eax
+; X86-NEXT: cmovbl %ecx, %eax
+; X86-NEXT: popl %esi
; X86-NEXT: retl
;
; X64-LABEL: length16:
-; X64: # BB#0:
-; X64-NEXT: movl $16, %edx
-; X64-NEXT: jmp memcmp # TAILCALL
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rcx
+; X64-NEXT: movq (%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB16_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movq 8(%rdi), %rcx
+; X64-NEXT: movq 8(%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB16_1
+; X64-NEXT: # BB#3: # %endblock
+; X64-NEXT: retq
+; X64-NEXT: .LBB16_1: # %res_block
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: movl $-1, %ecx
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: cmovbl %ecx, %eax
+; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 16) nounwind
ret i32 %m
}
define i1 @length16_eq(i8* %x, i8* %y) nounwind {
-; 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
+; X86-LABEL: length16_eq:
+; X86: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl (%ecx), %edx
+; X86-NEXT: cmpl (%eax), %edx
+; X86-NEXT: jne .LBB17_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: movl 4(%ecx), %edx
+; X86-NEXT: cmpl 4(%eax), %edx
+; X86-NEXT: jne .LBB17_1
+; X86-NEXT: # BB#3: # %loadbb2
+; X86-NEXT: movl 8(%ecx), %edx
+; X86-NEXT: cmpl 8(%eax), %edx
+; X86-NEXT: jne .LBB17_1
+; X86-NEXT: # BB#4: # %loadbb3
+; X86-NEXT: movl 12(%ecx), %edx
+; X86-NEXT: xorl %ecx, %ecx
+; X86-NEXT: cmpl 12(%eax), %edx
+; X86-NEXT: je .LBB17_5
+; X86-NEXT: .LBB17_1: # %res_block
+; X86-NEXT: movl $1, %ecx
+; X86-NEXT: .LBB17_5: # %endblock
+; X86-NEXT: testl %ecx, %ecx
+; X86-NEXT: setne %al
+; X86-NEXT: retl
;
-; 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
+; X64-LABEL: length16_eq:
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: cmpq (%rsi), %rax
+; X64-NEXT: jne .LBB17_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movq 8(%rdi), %rcx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpq 8(%rsi), %rcx
+; X64-NEXT: je .LBB17_3
+; X64-NEXT: .LBB17_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB17_3: # %endblock
+; X64-NEXT: testl %eax, %eax
+; X64-NEXT: setne %al
+; X64-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 {
-; 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
+; X86-LABEL: length16_eq_const:
+; X86: # BB#0: # %loadbb
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: cmpl $858927408, (%eax) # imm = 0x33323130
+; X86-NEXT: jne .LBB18_1
+; X86-NEXT: # BB#2: # %loadbb1
+; X86-NEXT: cmpl $926299444, 4(%eax) # imm = 0x37363534
+; X86-NEXT: jne .LBB18_1
+; X86-NEXT: # BB#3: # %loadbb2
+; X86-NEXT: cmpl $825243960, 8(%eax) # imm = 0x31303938
+; X86-NEXT: jne .LBB18_1
+; X86-NEXT: # BB#4: # %loadbb3
+; X86-NEXT: xorl %ecx, %ecx
+; X86-NEXT: cmpl $892613426, 12(%eax) # imm = 0x35343332
+; X86-NEXT: je .LBB18_5
+; X86-NEXT: .LBB18_1: # %res_block
+; X86-NEXT: movl $1, %ecx
+; X86-NEXT: .LBB18_5: # %endblock
+; X86-NEXT: testl %ecx, %ecx
+; X86-NEXT: sete %al
+; X86-NEXT: retl
;
-; 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
+; X64-LABEL: length16_eq_const:
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movabsq $3978425819141910832, %rax # imm = 0x3736353433323130
+; X64-NEXT: cmpq %rax, (%rdi)
+; X64-NEXT: jne .LBB18_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: movabsq $3833745473465760056, %rcx # imm = 0x3534333231303938
+; X64-NEXT: cmpq %rcx, 8(%rdi)
+; X64-NEXT: je .LBB18_3
+; X64-NEXT: .LBB18_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB18_3: # %endblock
+; X64-NEXT: testl %eax, %eax
+; X64-NEXT: sete %al
+; X64-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
@@ -570,9 +764,43 @@ define i32 @length32(i8* %X, i8* %Y) nounwind {
; X86-NEXT: retl
;
; X64-LABEL: length32:
-; X64: # BB#0:
-; X64-NEXT: movl $32, %edx
-; X64-NEXT: jmp memcmp # TAILCALL
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rcx
+; X64-NEXT: movq (%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB19_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movq 8(%rdi), %rcx
+; X64-NEXT: movq 8(%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB19_1
+; X64-NEXT: # BB#3: # %loadbb2
+; X64-NEXT: movq 16(%rdi), %rcx
+; X64-NEXT: movq 16(%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB19_1
+; X64-NEXT: # BB#4: # %loadbb3
+; X64-NEXT: movq 24(%rdi), %rcx
+; X64-NEXT: movq 24(%rsi), %rdx
+; X64-NEXT: bswapq %rcx
+; X64-NEXT: bswapq %rdx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: jne .LBB19_1
+; X64-NEXT: # BB#5: # %endblock
+; X64-NEXT: retq
+; X64-NEXT: .LBB19_1: # %res_block
+; X64-NEXT: cmpq %rdx, %rcx
+; X64-NEXT: movl $-1, %ecx
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: cmovbl %ecx, %eax
+; X64-NEXT: retq
%m = tail call i32 @memcmp(i8* %X, i8* %Y, i64 32) nounwind
ret i32 %m
}
@@ -592,25 +820,30 @@ define i1 @length32_eq(i8* %x, i8* %y) nounwind {
; 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
+; X64-LABEL: length32_eq:
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movq (%rdi), %rax
+; X64-NEXT: cmpq (%rsi), %rax
+; X64-NEXT: jne .LBB20_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movq 8(%rdi), %rax
+; X64-NEXT: cmpq 8(%rsi), %rax
+; X64-NEXT: jne .LBB20_1
+; X64-NEXT: # BB#3: # %loadbb2
+; X64-NEXT: movq 16(%rdi), %rax
+; X64-NEXT: cmpq 16(%rsi), %rax
+; X64-NEXT: jne .LBB20_1
+; X64-NEXT: # BB#4: # %loadbb3
+; X64-NEXT: movq 24(%rdi), %rcx
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: cmpq 24(%rsi), %rcx
+; X64-NEXT: je .LBB20_5
+; X64-NEXT: .LBB20_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB20_5: # %endblock
+; X64-NEXT: testl %eax, %eax
+; X64-NEXT: sete %al
+; X64-NEXT: retq
%call = tail call i32 @memcmp(i8* %x, i8* %y, i64 32) nounwind
%cmp = icmp eq i32 %call, 0
ret i1 %cmp
@@ -629,26 +862,30 @@ define i1 @length32_eq_const(i8* %X) nounwind {
; 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
+; X64-LABEL: length32_eq_const:
+; X64: # BB#0: # %loadbb
+; X64-NEXT: movabsq $3978425819141910832, %rax # imm = 0x3736353433323130
+; X64-NEXT: cmpq %rax, (%rdi)
+; X64-NEXT: jne .LBB21_1
+; X64-NEXT: # BB#2: # %loadbb1
+; X64-NEXT: movabsq $3833745473465760056, %rax # imm = 0x3534333231303938
+; X64-NEXT: cmpq %rax, 8(%rdi)
+; X64-NEXT: jne .LBB21_1
+; X64-NEXT: # BB#3: # %loadbb2
+; X64-NEXT: movabsq $3689065127958034230, %rax # imm = 0x3332313039383736
+; X64-NEXT: cmpq %rax, 16(%rdi)
+; X64-NEXT: jne .LBB21_1
+; X64-NEXT: # BB#4: # %loadbb3
+; X64-NEXT: xorl %eax, %eax
+; X64-NEXT: movabsq $3544395820347831604, %rcx # imm = 0x3130393837363534
+; X64-NEXT: cmpq %rcx, 24(%rdi)
+; X64-NEXT: je .LBB21_5
+; X64-NEXT: .LBB21_1: # %res_block
+; X64-NEXT: movl $1, %eax
+; X64-NEXT: .LBB21_5: # %endblock
+; X64-NEXT: testl %eax, %eax
+; X64-NEXT: setne %al
+; X64-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