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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=penryn | FileCheck %s
; rdar://7475489
define i32 @test1(i32 %a, i32 %b) nounwind ssp {
; CHECK-LABEL: test1:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: movb {{[0-9]+}}(%esp), %al
; CHECK-NEXT: xorb {{[0-9]+}}(%esp), %al
; CHECK-NEXT: testb $64, %al
; CHECK-NEXT: je LBB0_1
; CHECK-NEXT: ## %bb.2: ## %bb1
; CHECK-NEXT: jmp _bar ## TAILCALL
; CHECK-NEXT: LBB0_1: ## %bb
; CHECK-NEXT: jmp _foo ## TAILCALL
entry:
%0 = and i32 %a, 16384
%1 = icmp ne i32 %0, 0
%2 = and i32 %b, 16384
%3 = icmp ne i32 %2, 0
%4 = xor i1 %1, %3
br i1 %4, label %bb1, label %bb
bb: ; preds = %entry
%5 = tail call i32 (...) @foo() nounwind ; <i32> [#uses=1]
ret i32 %5
bb1: ; preds = %entry
%6 = tail call i32 (...) @bar() nounwind ; <i32> [#uses=1]
ret i32 %6
}
declare i32 @foo(...)
declare i32 @bar(...)
; <rdar://problem/7598384>:
;
; jCC L1
; jmp L2
; L1:
; ...
; L2:
; ...
;
; to:
;
; jnCC L2
; L1:
; ...
; L2:
; ...
define float @test4(float %x, float %y) nounwind readnone optsize ssp {
; CHECK-LABEL: test4:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: pushl %eax
; CHECK-NEXT: cvtss2sd {{[0-9]+}}(%esp), %xmm1
; CHECK-NEXT: cvtss2sd {{[0-9]+}}(%esp), %xmm0
; CHECK-NEXT: mulsd %xmm1, %xmm0
; CHECK-NEXT: xorpd %xmm1, %xmm1
; CHECK-NEXT: ucomisd %xmm1, %xmm0
; CHECK-NEXT: jne LBB1_1
; CHECK-NEXT: jnp LBB1_2
; CHECK-NEXT: LBB1_1: ## %bb1
; CHECK-NEXT: addsd LCPI1_0, %xmm0
; CHECK-NEXT: LBB1_2: ## %bb2
; CHECK-NEXT: cvtsd2ss %xmm0, %xmm0
; CHECK-NEXT: movss %xmm0, (%esp)
; CHECK-NEXT: flds (%esp)
; CHECK-NEXT: popl %eax
; CHECK-NEXT: retl
entry:
%0 = fpext float %x to double ; <double> [#uses=1]
%1 = fpext float %y to double ; <double> [#uses=1]
%2 = fmul double %0, %1 ; <double> [#uses=3]
%3 = fcmp oeq double %2, 0.000000e+00 ; <i1> [#uses=1]
br i1 %3, label %bb2, label %bb1
bb1: ; preds = %entry
%4 = fadd double %2, -1.000000e+00 ; <double> [#uses=1]
br label %bb2
bb2: ; preds = %entry, %bb1
%.0.in = phi double [ %4, %bb1 ], [ %2, %entry ] ; <double> [#uses=1]
%.0 = fptrunc double %.0.in to float ; <float> [#uses=1]
ret float %.0
}
declare i32 @llvm.x86.sse41.ptestz(<4 x float> %p1, <4 x float> %p2) nounwind
declare i32 @llvm.x86.sse41.ptestc(<4 x float> %p1, <4 x float> %p2) nounwind
define <4 x float> @test5(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test5:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: jne LBB2_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI2_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB2_2: ## %bb2
; CHECK-NEXT: divps LCPI2_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind
%one = icmp ne i32 %res, 0
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
define <4 x float> @test7(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test7:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: jne LBB3_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI3_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB3_2: ## %bb2
; CHECK-NEXT: divps LCPI3_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind
%one = trunc i32 %res to i1
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
define <4 x float> @test8(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test8:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: jae LBB4_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI4_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB4_2: ## %bb2
; CHECK-NEXT: divps LCPI4_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind
%one = icmp ne i32 %res, 0
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
define <4 x float> @test10(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test10:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: jae LBB5_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI5_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB5_2: ## %bb2
; CHECK-NEXT: divps LCPI5_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind
%one = trunc i32 %res to i1
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
define <4 x float> @test11(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test11:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: jne LBB6_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI6_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB6_2: ## %bb2
; CHECK-NEXT: divps LCPI6_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind
%one = icmp eq i32 %res, 1
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
define <4 x float> @test12(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test12:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: ptest %xmm0, %xmm0
; CHECK-NEXT: je LBB7_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: addps LCPI7_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
; CHECK-NEXT: LBB7_2: ## %bb2
; CHECK-NEXT: divps LCPI7_0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind
%one = icmp ne i32 %res, 1
br i1 %one, label %bb1, label %bb2
bb1:
%c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
bb2:
%d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 >
br label %return
return:
%e = phi <4 x float> [%c, %bb1], [%d, %bb2]
ret <4 x float> %e
}
|