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
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
define <4 x double> @andpd256(<4 x double> %y, <4 x double> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: andpd256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %x to <4 x i64>
%1 = bitcast <4 x double> %y to <4 x i64>
%and.i = and <4 x i64> %0, %1
%2 = bitcast <4 x i64> %and.i to <4 x double>
; add forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3
}
define <4 x double> @andpd256fold(<4 x double> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: andpd256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandpd {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %y to <4 x i64>
%and.i = and <4 x i64> %0, <i64 4616752568008179712, i64 4614838538166547251, i64 4612361558371493478, i64 4608083138725491507>
%1 = bitcast <4 x i64> %and.i to <4 x double>
; add forces execution domain
%2 = fadd <4 x double> %1, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %2
}
define <8 x float> @andps256(<8 x float> %y, <8 x float> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: andps256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %x to <8 x i32>
%1 = bitcast <8 x float> %y to <8 x i32>
%and.i = and <8 x i32> %0, %1
%2 = bitcast <8 x i32> %and.i to <8 x float>
ret <8 x float> %2
}
define <8 x float> @andps256fold(<8 x float> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: andps256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %y to <8 x i32>
%and.i = and <8 x i32> %0, <i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938, i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938>
%1 = bitcast <8 x i32> %and.i to <8 x float>
ret <8 x float> %1
}
define <4 x double> @xorpd256(<4 x double> %y, <4 x double> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: xorpd256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vxorpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %x to <4 x i64>
%1 = bitcast <4 x double> %y to <4 x i64>
%xor.i = xor <4 x i64> %0, %1
%2 = bitcast <4 x i64> %xor.i to <4 x double>
; add forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3
}
define <4 x double> @xorpd256fold(<4 x double> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: xorpd256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vxorpd {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %y to <4 x i64>
%xor.i = xor <4 x i64> %0, <i64 4616752568008179712, i64 4614838538166547251, i64 4612361558371493478, i64 4608083138725491507>
%1 = bitcast <4 x i64> %xor.i to <4 x double>
; add forces execution domain
%2 = fadd <4 x double> %1, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %2
}
define <8 x float> @xorps256(<8 x float> %y, <8 x float> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: xorps256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vxorps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %x to <8 x i32>
%1 = bitcast <8 x float> %y to <8 x i32>
%xor.i = xor <8 x i32> %0, %1
%2 = bitcast <8 x i32> %xor.i to <8 x float>
ret <8 x float> %2
}
define <8 x float> @xorps256fold(<8 x float> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: xorps256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vxorps {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %y to <8 x i32>
%xor.i = xor <8 x i32> %0, <i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938, i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938>
%1 = bitcast <8 x i32> %xor.i to <8 x float>
ret <8 x float> %1
}
define <4 x double> @orpd256(<4 x double> %y, <4 x double> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: orpd256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vorpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %x to <4 x i64>
%1 = bitcast <4 x double> %y to <4 x i64>
%or.i = or <4 x i64> %0, %1
%2 = bitcast <4 x i64> %or.i to <4 x double>
; add forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3
}
define <4 x double> @orpd256fold(<4 x double> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: orpd256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vorpd {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %y to <4 x i64>
%or.i = or <4 x i64> %0, <i64 4616752568008179712, i64 4614838538166547251, i64 4612361558371493478, i64 4608083138725491507>
%1 = bitcast <4 x i64> %or.i to <4 x double>
; add forces execution domain
%2 = fadd <4 x double> %1, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %2
}
define <8 x float> @orps256(<8 x float> %y, <8 x float> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: orps256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vorps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %x to <8 x i32>
%1 = bitcast <8 x float> %y to <8 x i32>
%or.i = or <8 x i32> %0, %1
%2 = bitcast <8 x i32> %or.i to <8 x float>
ret <8 x float> %2
}
define <8 x float> @orps256fold(<8 x float> %y) nounwind uwtable readnone ssp {
; CHECK-LABEL: orps256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vorps {{.*}}(%rip), %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %y to <8 x i32>
%or.i = or <8 x i32> %0, <i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938, i32 1083179008, i32 1079613850, i32 1075000115, i32 1067030938>
%1 = bitcast <8 x i32> %or.i to <8 x float>
ret <8 x float> %1
}
define <4 x double> @andnotpd256(<4 x double> %y, <4 x double> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: andnotpd256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandnpd %ymm0, %ymm1, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <4 x double> %x to <4 x i64>
%neg.i = xor <4 x i64> %0, <i64 -1, i64 -1, i64 -1, i64 -1>
%1 = bitcast <4 x double> %y to <4 x i64>
%and.i = and <4 x i64> %1, %neg.i
%2 = bitcast <4 x i64> %and.i to <4 x double>
; add forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3
}
define <4 x double> @andnotpd256fold(<4 x double> %y, <4 x double>* nocapture %x) nounwind uwtable readonly ssp {
; CHECK-LABEL: andnotpd256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandnpd (%rdi), %ymm0, %ymm0
; CHECK-NEXT: vxorpd %ymm1, %ymm1, %ymm1
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%tmp2 = load <4 x double>, <4 x double>* %x, align 32
%0 = bitcast <4 x double> %y to <4 x i64>
%neg.i = xor <4 x i64> %0, <i64 -1, i64 -1, i64 -1, i64 -1>
%1 = bitcast <4 x double> %tmp2 to <4 x i64>
%and.i = and <4 x i64> %1, %neg.i
%2 = bitcast <4 x i64> %and.i to <4 x double>
; add forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3
}
define <8 x float> @andnotps256(<8 x float> %y, <8 x float> %x) nounwind uwtable readnone ssp {
; CHECK-LABEL: andnotps256:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandnps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
entry:
%0 = bitcast <8 x float> %x to <8 x i32>
%neg.i = xor <8 x i32> %0, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%1 = bitcast <8 x float> %y to <8 x i32>
%and.i = and <8 x i32> %1, %neg.i
%2 = bitcast <8 x i32> %and.i to <8 x float>
ret <8 x float> %2
}
define <8 x float> @andnotps256fold(<8 x float> %y, <8 x float>* nocapture %x) nounwind uwtable readonly ssp {
; CHECK-LABEL: andnotps256fold:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vandnps (%rdi), %ymm0, %ymm0
; CHECK-NEXT: retq
entry:
%tmp2 = load <8 x float>, <8 x float>* %x, align 32
%0 = bitcast <8 x float> %y to <8 x i32>
%neg.i = xor <8 x i32> %0, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%1 = bitcast <8 x float> %tmp2 to <8 x i32>
%and.i = and <8 x i32> %1, %neg.i
%2 = bitcast <8 x i32> %and.i to <8 x float>
ret <8 x float> %2
}
;;; Test that basic 2 x i64 logic use the integer version on AVX
define <2 x i64> @vpandn(<2 x i64> %a, <2 x i64> %b) nounwind uwtable readnone ssp {
; CHECK-LABEL: vpandn:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm1
; CHECK-NEXT: vpandn %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
entry:
; Force the execution domain with an add.
%a2 = add <2 x i64> %a, <i64 1, i64 1>
%y = xor <2 x i64> %a2, <i64 -1, i64 -1>
%x = and <2 x i64> %a, %y
ret <2 x i64> %x
}
define <2 x i64> @vpand(<2 x i64> %a, <2 x i64> %b) nounwind uwtable readnone ssp {
; CHECK-LABEL: vpand:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: vpaddq {{.*}}(%rip), %xmm0, %xmm0
; CHECK-NEXT: vpand %xmm1, %xmm0, %xmm0
; CHECK-NEXT: retq
entry:
; Force the execution domain with an add.
%a2 = add <2 x i64> %a, <i64 1, i64 1>
%x = and <2 x i64> %a2, %b
ret <2 x i64> %x
}
|
