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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefixes=SSE,SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse3 | FileCheck %s --check-prefixes=SSE,SSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,avx512bw | FileCheck %s --check-prefixes=AVX,AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX,AVX512
define <2 x i64> @insert_v2i64_x1(<2 x i64> %a) {
; SSE2-LABEL: insert_v2i64_x1:
; SSE2: # %bb.0:
; SSE2-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v2i64_x1:
; SSE3: # %bb.0:
; SSE3-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v2i64_x1:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v2i64_x1:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v2i64_x1:
; AVX1: # %bb.0:
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v2i64_x1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v2i64_x1:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX512-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512-NEXT: retq
%1 = insertelement <2 x i64> %a, i64 -1, i32 0
ret <2 x i64> %1
}
define <4 x i64> @insert_v4i64_01x3(<4 x i64> %a) {
; SSE2-LABEL: insert_v4i64_01x3:
; SSE2: # %bb.0:
; SSE2-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v4i64_01x3:
; SSE3: # %bb.0:
; SSE3-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v4i64_01x3:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movlps {{.*#+}} xmm1 = mem[0,1],xmm1[2,3]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v4i64_01x3:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm2[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v4i64_01x3:
; AVX1: # %bb.0:
; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vcmptrueps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v4i64_01x3:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v4i64_01x3:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX512-NEXT: retq
%1 = insertelement <4 x i64> %a, i64 -1, i32 2
ret <4 x i64> %1
}
define <4 x i32> @insert_v4i32_01x3(<4 x i32> %a) {
; SSE2-LABEL: insert_v4i32_01x3:
; SSE2: # %bb.0:
; SSE2-NEXT: movl $-1, %eax
; SSE2-NEXT: movd %eax, %xmm1
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v4i32_01x3:
; SSE3: # %bb.0:
; SSE3-NEXT: movl $-1, %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v4i32_01x3:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movl $-1, %eax
; SSSE3-NEXT: movd %eax, %xmm1
; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v4i32_01x3:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v4i32_01x3:
; AVX1: # %bb.0:
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v4i32_01x3:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v4i32_01x3:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX512-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
; AVX512-NEXT: retq
%1 = insertelement <4 x i32> %a, i32 -1, i32 2
ret <4 x i32> %1
}
define <8 x i32> @insert_v8i32_x12345x7(<8 x i32> %a) {
; SSE-LABEL: insert_v8i32_x12345x7:
; SSE: # %bb.0:
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE-NEXT: retq
;
; AVX-LABEL: insert_v8i32_x12345x7:
; AVX: # %bb.0:
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX-NEXT: retq
%1 = insertelement <8 x i32> %a, i32 -1, i32 0
%2 = insertelement <8 x i32> %1, i32 -1, i32 6
ret <8 x i32> %2
}
define <8 x i16> @insert_v8i16_x12345x7(<8 x i16> %a) {
; SSE-LABEL: insert_v8i16_x12345x7:
; SSE: # %bb.0:
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: insert_v8i16_x12345x7:
; AVX: # %bb.0:
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = insertelement <8 x i16> %a, i16 -1, i32 0
%2 = insertelement <8 x i16> %1, i16 -1, i32 6
ret <8 x i16> %2
}
define <16 x i16> @insert_v16i16_x12345x789ABCDEx(<16 x i16> %a) {
; SSE-LABEL: insert_v16i16_x12345x789ABCDEx:
; SSE: # %bb.0:
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE-NEXT: retq
;
; AVX-LABEL: insert_v16i16_x12345x789ABCDEx:
; AVX: # %bb.0:
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX-NEXT: retq
%1 = insertelement <16 x i16> %a, i16 -1, i32 0
%2 = insertelement <16 x i16> %1, i16 -1, i32 6
%3 = insertelement <16 x i16> %2, i16 -1, i32 15
ret <16 x i16> %3
}
define <16 x i8> @insert_v16i8_x123456789ABCDEx(<16 x i8> %a) {
; SSE-LABEL: insert_v16i8_x123456789ABCDEx:
; SSE: # %bb.0:
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: insert_v16i8_x123456789ABCDEx:
; AVX: # %bb.0:
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = insertelement <16 x i8> %a, i8 -1, i32 0
%2 = insertelement <16 x i8> %1, i8 -1, i32 15
ret <16 x i8> %2
}
define <32 x i8> @insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx(<32 x i8> %a) {
; SSE-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; SSE: # %bb.0:
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; SSE-NEXT: orps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
; SSE-NEXT: retq
;
; AVX-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; AVX: # %bb.0:
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
; AVX-NEXT: retq
%1 = insertelement <32 x i8> %a, i8 -1, i32 0
%2 = insertelement <32 x i8> %1, i8 -1, i32 15
%3 = insertelement <32 x i8> %2, i8 -1, i32 30
%4 = insertelement <32 x i8> %3, i8 -1, i32 31
ret <32 x i8> %4
}
|
