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
287
288
289
290
291
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=-sse2 | FileCheck %s --check-prefix=SSE1
define <4 x float> @shuffle_v4f32_0001(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0001:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,0,1]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0020(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0020:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,2,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0300(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0300:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,3,0,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_1000(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_1000:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0,0,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_2200(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_2200:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,2,0,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_3330(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_3330:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3,3,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_3210(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_3210:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0011(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0011:
; SSE1: # %bb.0:
; SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0,0,1,1]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 1, i32 1>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_2233(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_2233:
; SSE1: # %bb.0:
; SSE1-NEXT: unpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 2, i32 3, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0022(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0022:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,2,2]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_1133(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_1133:
; SSE1: # %bb.0:
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,3,3]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0145(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0145:
; SSE1: # %bb.0:
; SSE1-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_0101(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_0101:
; SSE1: # %bb.0:
; SSE1-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0,0]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_2323(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_2323:
; SSE1: # %bb.0:
; SSE1-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 3, i32 2, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_6723(<4 x float> %a, <4 x float> %b) {
; SSE1-LABEL: shuffle_v4f32_6723:
; SSE1: # %bb.0:
; SSE1-NEXT: movhlps {{.*#+}} xmm0 = xmm1[1],xmm0[1]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 6, i32 7, i32 2, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_4zzz(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_4zzz:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
; SSE1-NEXT: movaps %xmm1, %xmm0
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 4, i32 1, i32 2, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_z4zz(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_z4zz:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm1[2,3]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 2, i32 4, i32 3, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_zz4z(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_zz4z:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[3,0]
; SSE1-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm0[0,2]
; SSE1-NEXT: movaps %xmm1, %xmm0
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 0, i32 0, i32 4, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_zuu4(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_zuu4:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
; SSE1-NEXT: movaps %xmm1, %xmm0
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 0, i32 undef, i32 undef, i32 4>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_zzz7(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_zzz7:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,0],xmm1[2,0]
; SSE1-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm0[2,0]
; SSE1-NEXT: movaps %xmm1, %xmm0
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_v4f32_z6zz(<4 x float> %a) {
; SSE1-LABEL: shuffle_v4f32_z6zz:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm1[0,0]
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm1[2,3]
; SSE1-NEXT: retq
%shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 0, i32 6, i32 2, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @insert_reg_and_zero_v4f32(float %a) {
; SSE1-LABEL: insert_reg_and_zero_v4f32:
; SSE1: # %bb.0:
; SSE1-NEXT: xorps %xmm1, %xmm1
; SSE1-NEXT: movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
; SSE1-NEXT: movaps %xmm1, %xmm0
; SSE1-NEXT: retq
%v = insertelement <4 x float> undef, float %a, i32 0
%shuffle = shufflevector <4 x float> %v, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuffle
}
define <4 x float> @insert_mem_and_zero_v4f32(ptr %ptr) {
; SSE1-LABEL: insert_mem_and_zero_v4f32:
; SSE1: # %bb.0:
; SSE1-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE1-NEXT: retq
%a = load float, ptr %ptr
%v = insertelement <4 x float> undef, float %a, i32 0
%shuffle = shufflevector <4 x float> %v, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
ret <4 x float> %shuffle
}
define <4 x float> @insert_mem_lo_v4f32(ptr %ptr, <4 x float> %b) {
; SSE1-LABEL: insert_mem_lo_v4f32:
; SSE1: # %bb.0:
; SSE1-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSE1-NEXT: retq
%a = load <2 x float>, ptr %ptr
%v = shufflevector <2 x float> %a, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x float> %v, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
ret <4 x float> %shuffle
}
define <4 x float> @insert_mem_hi_v4f32(ptr %ptr, <4 x float> %b) {
; SSE1-LABEL: insert_mem_hi_v4f32:
; SSE1: # %bb.0:
; SSE1-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
; SSE1-NEXT: retq
%a = load <2 x float>, ptr %ptr
%v = shufflevector <2 x float> %a, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%shuffle = shufflevector <4 x float> %v, <4 x float> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_mem_v4f32_3210(ptr %ptr) {
; SSE1-LABEL: shuffle_mem_v4f32_3210:
; SSE1: # %bb.0:
; SSE1-NEXT: movaps (%rdi), %xmm0
; SSE1-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; SSE1-NEXT: retq
%a = load <4 x float>, ptr %ptr
%shuffle = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_mem_v4f32_0145(<4 x float> %a, ptr %pb) {
; SSE1-LABEL: shuffle_mem_v4f32_0145:
; SSE1: # %bb.0:
; SSE1-NEXT: movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
; SSE1-NEXT: retq
%b = load <4 x float>, ptr %pb, align 1
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_mem_v4f32_6723(<4 x float> %a, ptr %pb) {
; SSE1-LABEL: shuffle_mem_v4f32_6723:
; SSE1: # %bb.0:
; SSE1-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSE1-NEXT: retq
%b = load <4 x float>, ptr %pb, align 16
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 6, i32 7, i32 2, i32 3>
ret <4 x float> %shuffle
}
define <4 x float> @shuffle_mem_v4f32_4523(<4 x float> %a, ptr %pb) {
; SSE1-LABEL: shuffle_mem_v4f32_4523:
; SSE1: # %bb.0:
; SSE1-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSE1-NEXT: retq
%b = load <4 x float>, ptr %pb, align 1
%shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
ret <4 x float> %shuffle
}
|
