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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+sse2 < %s | FileCheck %s --check-prefixes=CHECK-SSE,CHECK-SSE2
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+sse4.1 < %s | FileCheck %s --check-prefixes=CHECK-SSE,CHECK-SSE41
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx < %s | FileCheck %s --check-prefixes=CHECK-AVX,CHECK-AVX1
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2 < %s | FileCheck %s --check-prefixes=CHECK-AVX,CHECK-AVX2
; RUN: llc -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f,+avx512vl < %s | FileCheck %s --check-prefixes=CHECK-AVX,CHECK-AVX512VL
define <4 x i1> @t0_all_tautological(<4 x i32> %X) nounwind {
; CHECK-SSE-LABEL: t0_all_tautological:
; CHECK-SSE: # %bb.0:
; CHECK-SSE-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE-NEXT: pcmpeqd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE-NEXT: retq
;
; CHECK-AVX-LABEL: t0_all_tautological:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX-NEXT: vpcmpeqd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX-NEXT: retq
%urem = urem <4 x i32> %X, <i32 1, i32 1, i32 2, i32 2>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 1, i32 2, i32 3>
ret <4 x i1> %cmp
}
define <4 x i1> @t1_all_odd_eq(<4 x i32> %X) nounwind {
; CHECK-SSE2-LABEL: t1_all_odd_eq:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: movdqa {{.*#+}} xmm1 = [2863311531,2863311531,2863311531,2863311531]
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; CHECK-SSE2-NEXT: pmuludq %xmm1, %xmm0
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; CHECK-SSE2-NEXT: pmuludq %xmm1, %xmm2
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; CHECK-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-SSE2-NEXT: pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: pcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: pandn {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: retq
;
; CHECK-SSE41-LABEL: t1_all_odd_eq:
; CHECK-SSE41: # %bb.0:
; CHECK-SSE41-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE41-NEXT: movdqa {{.*#+}} xmm1 = [1431655765,4294967295,4294967295,4294967295]
; CHECK-SSE41-NEXT: pminud %xmm0, %xmm1
; CHECK-SSE41-NEXT: pcmpeqd %xmm1, %xmm0
; CHECK-SSE41-NEXT: pxor %xmm1, %xmm1
; CHECK-SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-SSE41-NEXT: retq
;
; CHECK-AVX1-LABEL: t1_all_odd_eq:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vpmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX2-LABEL: t1_all_odd_eq:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vpbroadcastd {{.*#+}} xmm1 = [2863311531,2863311531,2863311531,2863311531]
; CHECK-AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX512VL-LABEL: t1_all_odd_eq:
; CHECK-AVX512VL: # %bb.0:
; CHECK-AVX512VL-NEXT: vpmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX512VL-NEXT: retq
%urem = urem <4 x i32> %X, <i32 3, i32 1, i32 1, i32 9>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 42, i32 0, i32 42>
ret <4 x i1> %cmp
}
define <4 x i1> @t1_all_odd_ne(<4 x i32> %X) nounwind {
; CHECK-SSE2-LABEL: t1_all_odd_ne:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: movdqa {{.*#+}} xmm1 = [2863311531,2863311531,2863311531,2863311531]
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; CHECK-SSE2-NEXT: pmuludq %xmm1, %xmm0
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; CHECK-SSE2-NEXT: pmuludq %xmm1, %xmm2
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; CHECK-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-SSE2-NEXT: pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: pcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; CHECK-SSE2-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-SSE2-NEXT: retq
;
; CHECK-SSE41-LABEL: t1_all_odd_ne:
; CHECK-SSE41: # %bb.0:
; CHECK-SSE41-NEXT: pmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE41-NEXT: movdqa {{.*#+}} xmm1 = [1431655765,4294967295,4294967295,4294967295]
; CHECK-SSE41-NEXT: pminud %xmm0, %xmm1
; CHECK-SSE41-NEXT: pcmpeqd %xmm1, %xmm0
; CHECK-SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-SSE41-NEXT: pxor %xmm1, %xmm0
; CHECK-SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-SSE41-NEXT: retq
;
; CHECK-AVX1-LABEL: t1_all_odd_ne:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vpmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX2-LABEL: t1_all_odd_ne:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vpbroadcastd {{.*#+}} xmm1 = [2863311531,2863311531,2863311531,2863311531]
; CHECK-AVX2-NEXT: vpmulld %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX512VL-LABEL: t1_all_odd_ne:
; CHECK-AVX512VL: # %bb.0:
; CHECK-AVX512VL-NEXT: vpmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpternlogq $15, %xmm0, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX512VL-NEXT: retq
%urem = urem <4 x i32> %X, <i32 3, i32 1, i32 1, i32 9>
%cmp = icmp ne <4 x i32> %urem, <i32 0, i32 42, i32 0, i32 42>
ret <4 x i1> %cmp
}
define <8 x i1> @t2_narrow(<8 x i16> %X) nounwind {
; CHECK-SSE2-LABEL: t2_narrow:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: psubusw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: pxor %xmm1, %xmm1
; CHECK-SSE2-NEXT: pcmpeqw %xmm1, %xmm0
; CHECK-SSE2-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE2-NEXT: retq
;
; CHECK-SSE41-LABEL: t2_narrow:
; CHECK-SSE41: # %bb.0:
; CHECK-SSE41-NEXT: pmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE41-NEXT: movdqa {{.*#+}} xmm1 = [21845,65535,65535,65535,21845,65535,65535,65535]
; CHECK-SSE41-NEXT: pminuw %xmm0, %xmm1
; CHECK-SSE41-NEXT: pcmpeqw %xmm1, %xmm0
; CHECK-SSE41-NEXT: pxor %xmm1, %xmm1
; CHECK-SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-SSE41-NEXT: retq
;
; CHECK-AVX1-LABEL: t2_narrow:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vpmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpminuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX1-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX2-LABEL: t2_narrow:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vpmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpminuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX2-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX512VL-LABEL: t2_narrow:
; CHECK-AVX512VL: # %bb.0:
; CHECK-AVX512VL-NEXT: vpmullw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpminuw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX512VL-NEXT: vpcmpeqw %xmm1, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
; CHECK-AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
; CHECK-AVX512VL-NEXT: retq
%urem = urem <8 x i16> %X, <i16 3, i16 1, i16 1, i16 9, i16 3, i16 1, i16 1, i16 9>
%cmp = icmp eq <8 x i16> %urem, <i16 0, i16 0, i16 42, i16 42, i16 0, i16 0, i16 42, i16 42>
ret <8 x i1> %cmp
}
define <2 x i1> @t3_wide(<2 x i64> %X) nounwind {
; CHECK-SSE-LABEL: t3_wide:
; CHECK-SSE: # %bb.0:
; CHECK-SSE-NEXT: movdqa {{.*#+}} xmm1 = [12297829382473034411,12297829382473034411]
; CHECK-SSE-NEXT: movdqa %xmm0, %xmm2
; CHECK-SSE-NEXT: pmuludq %xmm1, %xmm2
; CHECK-SSE-NEXT: movdqa %xmm0, %xmm3
; CHECK-SSE-NEXT: psrlq $32, %xmm3
; CHECK-SSE-NEXT: pmuludq %xmm1, %xmm3
; CHECK-SSE-NEXT: pmuludq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE-NEXT: paddq %xmm3, %xmm0
; CHECK-SSE-NEXT: psllq $32, %xmm0
; CHECK-SSE-NEXT: paddq %xmm2, %xmm0
; CHECK-SSE-NEXT: pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-SSE-NEXT: movdqa {{.*#+}} xmm1 = [15372286730238776661,9223372034707292159]
; CHECK-SSE-NEXT: movdqa %xmm0, %xmm2
; CHECK-SSE-NEXT: pcmpgtd %xmm1, %xmm2
; CHECK-SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2]
; CHECK-SSE-NEXT: pcmpeqd %xmm1, %xmm0
; CHECK-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
; CHECK-SSE-NEXT: pand %xmm3, %xmm0
; CHECK-SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm2[1,1,3,3]
; CHECK-SSE-NEXT: por %xmm0, %xmm1
; CHECK-SSE-NEXT: pcmpeqd %xmm0, %xmm0
; CHECK-SSE-NEXT: pxor %xmm1, %xmm0
; CHECK-SSE-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-SSE-NEXT: retq
;
; CHECK-AVX1-LABEL: t3_wide:
; CHECK-AVX1: # %bb.0:
; CHECK-AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [12297829382473034411,12297829382473034411]
; CHECK-AVX1-NEXT: vpmuludq %xmm1, %xmm0, %xmm2
; CHECK-AVX1-NEXT: vpsrlq $32, %xmm0, %xmm3
; CHECK-AVX1-NEXT: vpmuludq %xmm1, %xmm3, %xmm1
; CHECK-AVX1-NEXT: vpmuludq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpaddq %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpsllq $32, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpaddq %xmm0, %xmm2, %xmm0
; CHECK-AVX1-NEXT: vpxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-AVX1-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-AVX1-NEXT: retq
;
; CHECK-AVX2-LABEL: t3_wide:
; CHECK-AVX2: # %bb.0:
; CHECK-AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [12297829382473034411,12297829382473034411]
; CHECK-AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm2
; CHECK-AVX2-NEXT: vpsrlq $32, %xmm0, %xmm3
; CHECK-AVX2-NEXT: vpmuludq %xmm1, %xmm3, %xmm1
; CHECK-AVX2-NEXT: vpmuludq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpaddq %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpsllq $32, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpaddq %xmm0, %xmm2, %xmm0
; CHECK-AVX2-NEXT: vpxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; CHECK-AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
; CHECK-AVX2-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-AVX2-NEXT: retq
;
; CHECK-AVX512VL-LABEL: t3_wide:
; CHECK-AVX512VL: # %bb.0:
; CHECK-AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [12297829382473034411,12297829382473034411]
; CHECK-AVX512VL-NEXT: vpmuludq %xmm1, %xmm0, %xmm2
; CHECK-AVX512VL-NEXT: vpsrlq $32, %xmm0, %xmm3
; CHECK-AVX512VL-NEXT: vpmuludq %xmm1, %xmm3, %xmm1
; CHECK-AVX512VL-NEXT: vpmuludq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpaddq %xmm1, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpsllq $32, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vpaddq %xmm0, %xmm2, %xmm0
; CHECK-AVX512VL-NEXT: vpminuq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
; CHECK-AVX512VL-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0
; CHECK-AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-AVX512VL-NEXT: retq
%urem = urem <2 x i64> %X, <i64 3, i64 1>
%cmp = icmp eq <2 x i64> %urem, <i64 0, i64 42>
ret <2 x i1> %cmp
}
|
