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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=corei7-avx -mattr=+avx | FileCheck %s
declare i32 @llvm.x86.avx.ptestz.256(<4 x i64> %p1, <4 x i64> %p2) nounwind
declare i32 @llvm.x86.avx.ptestc.256(<4 x i64> %p1, <4 x i64> %p2) nounwind
define <4 x float> @test1(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test1:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: jne LBB0_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI0_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB0_2: ## %bb2
; CHECK-NEXT: vdivps LCPI0_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %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> @test3(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test3:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: jne LBB1_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI1_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB1_2: ## %bb2
; CHECK-NEXT: vdivps LCPI1_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %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> @test4(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test4:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: jae LBB2_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI2_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB2_2: ## %bb2
; CHECK-NEXT: vdivps LCPI2_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %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> @test6(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test6:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: jae LBB3_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI3_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB3_2: ## %bb2
; CHECK-NEXT: vdivps LCPI3_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %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> @test7(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test7:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: jne LBB4_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI4_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB4_2: ## %bb2
; CHECK-NEXT: vdivps LCPI4_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %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> @test8(<4 x i64> %a, <4 x float> %b) nounwind {
; CHECK-LABEL: test8:
; CHECK: ## %bb.0: ## %entry
; CHECK-NEXT: vptest %ymm0, %ymm0
; CHECK-NEXT: je LBB5_2
; CHECK-NEXT: ## %bb.1: ## %bb1
; CHECK-NEXT: vaddps LCPI5_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
; CHECK-NEXT: LBB5_2: ## %bb2
; CHECK-NEXT: vdivps LCPI5_0, %xmm1, %xmm0
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retl
entry:
%res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %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
}
|