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
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
; RUN: llc < %s -mattr=+sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Darwin
; RUN: llc < %s -mattr=+sse2 -mtriple=i686-pc-mingw32 -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Mingw32
; RUN: llc < %s -mattr=+sse,-sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE1
; RUN: llc < %s -mattr=-sse -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=NOSSE
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=X86-64
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=nehalem | FileCheck %s -check-prefix=NHM_64
@.str = internal constant [25 x i8] c"image\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00"
@.str2 = internal constant [30 x i8] c"xxxxxxxxxxxxxxxxxxxxxxxxxxxxx\00", align 4
define void @t1(i32 %argc, ptr %argv) nounwind {
entry:
; SSE2-Darwin-LABEL: t1:
; SSE2-Darwin: movsd _.str+16, %xmm0
; SSE2-Darwin: movsd %xmm0, 16(%esp)
; SSE2-Darwin: movaps _.str, %xmm0
; SSE2-Darwin: movaps %xmm0
; SSE2-Darwin: movb $0, 24(%esp)
; SSE2-Mingw32-LABEL: t1:
; SSE2-Mingw32: movsd _.str+16, %xmm0
; SSE2-Mingw32: movsd %xmm0, 16(%esp)
; SSE2-Mingw32: movaps _.str, %xmm0
; SSE2-Mingw32: movups %xmm0
; SSE2-Mingw32: movb $0, 24(%esp)
; SSE1-LABEL: t1:
; SSE1: movaps _.str, %xmm0
; SSE1: movaps %xmm0
; SSE1: movb $0, 24(%esp)
; SSE1: movl $0, 20(%esp)
; SSE1: movl $0, 16(%esp)
; NOSSE-LABEL: t1:
; NOSSE: movb $0
; NOSSE: movl $0
; NOSSE: movl $0
; NOSSE: movl $0
; NOSSE: movl $0
; NOSSE: movl $101
; NOSSE: movl $1734438249
; X86-64-LABEL: t1:
; X86-64: movaps _.str(%rip), %xmm0
; X86-64: movaps %xmm0
; X86-64: movb $0
; X86-64: movq $0
%tmp1 = alloca [25 x i8]
call void @llvm.memcpy.p0.p0.i32(ptr align 1 %tmp1, ptr align 1 @.str, i32 25, i1 false)
unreachable
}
;rdar://7774704
%struct.s0 = type { [2 x double] }
define void @t2(ptr nocapture %a, ptr nocapture %b) nounwind ssp {
entry:
; SSE2-Darwin-LABEL: t2:
; SSE2-Darwin: movaps (%ecx), %xmm0
; SSE2-Darwin: movaps %xmm0, (%eax)
; SSE2-Mingw32-LABEL: t2:
; SSE2-Mingw32: movaps (%ecx), %xmm0
; SSE2-Mingw32: movaps %xmm0, (%eax)
; SSE1-LABEL: t2:
; SSE1: movaps (%ecx), %xmm0
; SSE1: movaps %xmm0, (%eax)
; NOSSE-LABEL: t2:
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; X86-64-LABEL: t2:
; X86-64: movaps (%rsi), %xmm0
; X86-64: movaps %xmm0, (%rdi)
tail call void @llvm.memcpy.p0.p0.i32(ptr align 16 %a, ptr align 16 %b, i32 16, i1 false)
ret void
}
define void @t3(ptr nocapture %a, ptr nocapture %b) nounwind ssp {
entry:
; SSE2-Darwin-LABEL: t3:
; SSE2-Darwin: movsd (%ecx), %xmm0
; SSE2-Darwin: movsd 8(%ecx), %xmm1
; SSE2-Darwin: movsd %xmm1, 8(%eax)
; SSE2-Darwin: movsd %xmm0, (%eax)
; SSE2-Mingw32-LABEL: t3:
; SSE2-Mingw32: movsd (%ecx), %xmm0
; SSE2-Mingw32: movsd 8(%ecx), %xmm1
; SSE2-Mingw32: movsd %xmm1, 8(%eax)
; SSE2-Mingw32: movsd %xmm0, (%eax)
; SSE1-LABEL: t3:
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; SSE1: movl
; NOSSE-LABEL: t3:
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; NOSSE: movl
; X86-64-LABEL: t3:
; X86-64: movq (%rsi), %rax
; X86-64: movq 8(%rsi), %rcx
; X86-64: movq %rcx, 8(%rdi)
; X86-64: movq %rax, (%rdi)
tail call void @llvm.memcpy.p0.p0.i32(ptr align 8 %a, ptr align 8 %b, i32 16, i1 false)
ret void
}
define void @t4() nounwind {
entry:
; SSE2-Darwin-LABEL: t4:
; SSE2-Darwin: movw $120
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Darwin: movl $2021161080
; SSE2-Mingw32-LABEL: t4:
; SSE2-Mingw32: movw $120
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE2-Mingw32: movl $2021161080
; SSE1-LABEL: t4:
; SSE1: movw $120
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; SSE1: movl $2021161080
; NOSSE-LABEL: t4:
; NOSSE: movw $120
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
; NOSSE: movl $2021161080
;;; TODO: (1) Some of the loads and stores are certainly unaligned and (2) the first load and first
;;; store overlap with the second load and second store respectively.
;;;
;;; Is either of the sequences ideal?
; X86-64-LABEL: t4:
; X86-64: movabsq $33909456017848440, %rax ## imm = 0x78787878787878
; X86-64: movq %rax, -10(%rsp)
; X86-64: movabsq $8680820740569200760, %rax ## imm = 0x7878787878787878
; X86-64: movq %rax, -16(%rsp)
; X86-64: movq %rax, -24(%rsp)
; X86-64: movq %rax, -32(%rsp)
; NHM_64-LABEL: t4:
; NHM_64: movups _.str2+14(%rip), %xmm0
; NHM_64: movups %xmm0, -26(%rsp)
; NHM_64: movups _.str2(%rip), %xmm0
; NHM_64: movaps %xmm0, -40(%rsp)
%tmp1 = alloca [30 x i8]
call void @llvm.memcpy.p0.p0.i32(ptr align 1 %tmp1, ptr align 1 @.str2, i32 30, i1 false)
unreachable
}
declare void @llvm.memcpy.p0.p0.i32(ptr nocapture, ptr nocapture, i32, i1) nounwind
|
