1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mcpu=corei7 -mtriple=i686-- -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=SSE42
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=NOSSE
; 64-bit load/store on x86-32
; FIXME: The generated code can be substantially improved.
define void @test1(ptr %ptr, i64 %val1) {
; SSE42-LABEL: test1:
; SSE42: # %bb.0:
; SSE42-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE42-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE42-NEXT: movlps %xmm0, (%eax)
; SSE42-NEXT: lock orl $0, (%esp)
; SSE42-NEXT: retl
;
; NOSSE-LABEL: test1:
; NOSSE: # %bb.0:
; NOSSE-NEXT: pushl %ebp
; NOSSE-NEXT: .cfi_def_cfa_offset 8
; NOSSE-NEXT: .cfi_offset %ebp, -8
; NOSSE-NEXT: movl %esp, %ebp
; NOSSE-NEXT: .cfi_def_cfa_register %ebp
; NOSSE-NEXT: andl $-8, %esp
; NOSSE-NEXT: subl $8, %esp
; NOSSE-NEXT: movl 8(%ebp), %eax
; NOSSE-NEXT: movl 12(%ebp), %ecx
; NOSSE-NEXT: movl 16(%ebp), %edx
; NOSSE-NEXT: movl %edx, {{[0-9]+}}(%esp)
; NOSSE-NEXT: movl %ecx, (%esp)
; NOSSE-NEXT: fildll (%esp)
; NOSSE-NEXT: fistpll (%eax)
; NOSSE-NEXT: lock orl $0, (%esp)
; NOSSE-NEXT: movl %ebp, %esp
; NOSSE-NEXT: popl %ebp
; NOSSE-NEXT: .cfi_def_cfa %esp, 4
; NOSSE-NEXT: retl
store atomic i64 %val1, ptr %ptr seq_cst, align 8
ret void
}
define i64 @test2(ptr %ptr) {
; SSE42-LABEL: test2:
; SSE42: # %bb.0:
; SSE42-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE42-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; SSE42-NEXT: movd %xmm0, %eax
; SSE42-NEXT: pextrd $1, %xmm0, %edx
; SSE42-NEXT: retl
;
; NOSSE-LABEL: test2:
; NOSSE: # %bb.0:
; NOSSE-NEXT: pushl %ebp
; NOSSE-NEXT: .cfi_def_cfa_offset 8
; NOSSE-NEXT: .cfi_offset %ebp, -8
; NOSSE-NEXT: movl %esp, %ebp
; NOSSE-NEXT: .cfi_def_cfa_register %ebp
; NOSSE-NEXT: andl $-8, %esp
; NOSSE-NEXT: subl $8, %esp
; NOSSE-NEXT: movl 8(%ebp), %eax
; NOSSE-NEXT: fildll (%eax)
; NOSSE-NEXT: fistpll (%esp)
; NOSSE-NEXT: movl (%esp), %eax
; NOSSE-NEXT: movl {{[0-9]+}}(%esp), %edx
; NOSSE-NEXT: movl %ebp, %esp
; NOSSE-NEXT: popl %ebp
; NOSSE-NEXT: .cfi_def_cfa %esp, 4
; NOSSE-NEXT: retl
%val = load atomic i64, ptr %ptr seq_cst, align 8
ret i64 %val
}
; Same as test2, but with noimplicitfloat.
define i64 @test3(ptr %ptr) noimplicitfloat {
; CHECK-LABEL: test3:
; CHECK: # %bb.0:
; CHECK-NEXT: pushl %ebx
; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: pushl %esi
; CHECK-NEXT: .cfi_def_cfa_offset 12
; CHECK-NEXT: .cfi_offset %esi, -12
; CHECK-NEXT: .cfi_offset %ebx, -8
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %esi
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: xorl %ebx, %ebx
; CHECK-NEXT: lock cmpxchg8b (%esi)
; CHECK-NEXT: popl %esi
; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: popl %ebx
; CHECK-NEXT: .cfi_def_cfa_offset 4
; CHECK-NEXT: retl
%val = load atomic i64, ptr %ptr seq_cst, align 8
ret i64 %val
}
define i64 @test4(ptr %ptr) {
; SSE42-LABEL: test4:
; SSE42: # %bb.0:
; SSE42-NEXT: movl {{[0-9]+}}(%esp), %eax
; SSE42-NEXT: movq {{.*#+}} xmm0 = mem[0],zero
; SSE42-NEXT: movd %xmm0, %eax
; SSE42-NEXT: pextrd $1, %xmm0, %edx
; SSE42-NEXT: retl
;
; NOSSE-LABEL: test4:
; NOSSE: # %bb.0:
; NOSSE-NEXT: pushl %ebp
; NOSSE-NEXT: .cfi_def_cfa_offset 8
; NOSSE-NEXT: .cfi_offset %ebp, -8
; NOSSE-NEXT: movl %esp, %ebp
; NOSSE-NEXT: .cfi_def_cfa_register %ebp
; NOSSE-NEXT: andl $-8, %esp
; NOSSE-NEXT: subl $8, %esp
; NOSSE-NEXT: movl 8(%ebp), %eax
; NOSSE-NEXT: fildll (%eax)
; NOSSE-NEXT: fistpll (%esp)
; NOSSE-NEXT: movl (%esp), %eax
; NOSSE-NEXT: movl {{[0-9]+}}(%esp), %edx
; NOSSE-NEXT: movl %ebp, %esp
; NOSSE-NEXT: popl %ebp
; NOSSE-NEXT: .cfi_def_cfa %esp, 4
; NOSSE-NEXT: retl
%val = load atomic volatile i64, ptr %ptr seq_cst, align 8
ret i64 %val
}
|
