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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
; RUN: llc -mtriple=aarch64-unknown-linux-gnu -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
; BIT Bitwise Insert if True
;
; 8-bit vectors tests
define <1 x i8> @test_bit_v1i8(<1 x i8> %A, <1 x i8> %B, <1 x i8> %C) {
; CHECK-SD-LABEL: test_bit_v1i8:
; CHECK-SD: // %bb.0:
; CHECK-SD-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_bit_v1i8:
; CHECK-GI: // %bb.0:
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-GI-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-GI-NEXT: // kill: def $d2 killed $d2 def $q2
; CHECK-GI-NEXT: umov w8, v2.b[0]
; CHECK-GI-NEXT: umov w9, v1.b[0]
; CHECK-GI-NEXT: umov w10, v0.b[0]
; CHECK-GI-NEXT: and w9, w8, w9
; CHECK-GI-NEXT: bic w8, w10, w8
; CHECK-GI-NEXT: orr w8, w9, w8
; CHECK-GI-NEXT: fmov s0, w8
; CHECK-GI-NEXT: ret
%and = and <1 x i8> %C, %B
%neg = xor <1 x i8> %C, <i8 -1>
%and1 = and <1 x i8> %neg, %A
%or = or <1 x i8> %and, %and1
ret <1 x i8> %or
}
; 16-bit vectors tests
define <1 x i16> @test_bit_v1i16(<1 x i16> %A, <1 x i16> %B, <1 x i16> %C) {
; CHECK-SD-LABEL: test_bit_v1i16:
; CHECK-SD: // %bb.0:
; CHECK-SD-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_bit_v1i16:
; CHECK-GI: // %bb.0:
; CHECK-GI-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-GI-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-GI-NEXT: // kill: def $d2 killed $d2 def $q2
; CHECK-GI-NEXT: umov w8, v2.h[0]
; CHECK-GI-NEXT: umov w9, v1.h[0]
; CHECK-GI-NEXT: umov w10, v0.h[0]
; CHECK-GI-NEXT: and w9, w8, w9
; CHECK-GI-NEXT: bic w8, w10, w8
; CHECK-GI-NEXT: orr w8, w9, w8
; CHECK-GI-NEXT: fmov s0, w8
; CHECK-GI-NEXT: ret
%and = and <1 x i16> %C, %B
%neg = xor <1 x i16> %C, <i16 -1>
%and1 = and <1 x i16> %neg, %A
%or = or <1 x i16> %and, %and1
ret <1 x i16> %or
}
; 32-bit vectors tests
define <1 x i32> @test_bit_v1i32(<1 x i32> %A, <1 x i32> %B, <1 x i32> %C) {
; CHECK-SD-LABEL: test_bit_v1i32:
; CHECK-SD: // %bb.0:
; CHECK-SD-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_bit_v1i32:
; CHECK-GI: // %bb.0:
; CHECK-GI-NEXT: fmov w8, s2
; CHECK-GI-NEXT: fmov w9, s1
; CHECK-GI-NEXT: fmov w10, s0
; CHECK-GI-NEXT: and w9, w8, w9
; CHECK-GI-NEXT: bic w8, w10, w8
; CHECK-GI-NEXT: orr w8, w9, w8
; CHECK-GI-NEXT: fmov s0, w8
; CHECK-GI-NEXT: ret
%and = and <1 x i32> %C, %B
%neg = xor <1 x i32> %C, <i32 -1>
%and1 = and <1 x i32> %neg, %A
%or = or <1 x i32> %and, %and1
ret <1 x i32> %or
}
; 64-bit vectors tests
define <1 x i64> @test_bit_v1i64(<1 x i64> %A, <1 x i64> %B, <1 x i64> %C) {
; CHECK-SD-LABEL: test_bit_v1i64:
; CHECK-SD: // %bb.0:
; CHECK-SD-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_bit_v1i64:
; CHECK-GI: // %bb.0:
; CHECK-GI-NEXT: fmov x8, d2
; CHECK-GI-NEXT: fmov x9, d1
; CHECK-GI-NEXT: fmov x10, d0
; CHECK-GI-NEXT: and x9, x8, x9
; CHECK-GI-NEXT: bic x8, x10, x8
; CHECK-GI-NEXT: orr x8, x9, x8
; CHECK-GI-NEXT: fmov d0, x8
; CHECK-GI-NEXT: ret
%and = and <1 x i64> %C, %B
%neg = xor <1 x i64> %C, <i64 -1>
%and1 = and <1 x i64> %neg, %A
%or = or <1 x i64> %and, %and1
ret <1 x i64> %or
}
define <2 x i32> @test_bit_v2i32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
; CHECK-LABEL: test_bit_v2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT: ret
%and = and <2 x i32> %C, %B
%neg = xor <2 x i32> %C, <i32 -1, i32 -1>
%and1 = and <2 x i32> %neg, %A
%or = or <2 x i32> %and, %and1
ret <2 x i32> %or
}
define <4 x i16> @test_bit_v4i16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
; CHECK-LABEL: test_bit_v4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT: ret
%and = and <4 x i16> %C, %B
%neg = xor <4 x i16> %C, <i16 -1, i16 -1, i16 -1, i16 -1>
%and1 = and <4 x i16> %neg, %A
%or = or <4 x i16> %and, %and1
ret <4 x i16> %or
}
define <8 x i8> @test_bit_v8i8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
; CHECK-LABEL: test_bit_v8i8:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT: ret
%and = and <8 x i8> %C, %B
%neg = xor <8 x i8> %C, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%and1 = and <8 x i8> %neg, %A
%or = or <8 x i8> %and, %and1
ret <8 x i8> %or
}
; 128-bit vectors tests
define <2 x i64> @test_bit_v2i64(<2 x i64> %A, <2 x i64> %B, <2 x i64> %C) {
; CHECK-LABEL: test_bit_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT: ret
%and = and <2 x i64> %C, %B
%neg = xor <2 x i64> %C, <i64 -1, i64 -1>
%and1 = and <2 x i64> %neg, %A
%or = or <2 x i64> %and, %and1
ret <2 x i64> %or
}
define <4 x i32> @test_bit_v4i32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
; CHECK-LABEL: test_bit_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT: ret
%and = and <4 x i32> %C, %B
%neg = xor <4 x i32> %C, <i32 -1, i32 -1, i32 -1, i32 -1>
%and1 = and <4 x i32> %neg, %A
%or = or <4 x i32> %and, %and1
ret <4 x i32> %or
}
define <8 x i16> @test_bit_v8i16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
; CHECK-LABEL: test_bit_v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT: ret
%and = and <8 x i16> %C, %B
%neg = xor <8 x i16> %C, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%and1 = and <8 x i16> %neg, %A
%or = or <8 x i16> %and, %and1
ret <8 x i16> %or
}
define <16 x i8> @test_bit_v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
; CHECK-LABEL: test_bit_v16i8:
; CHECK: // %bb.0:
; CHECK-NEXT: bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT: ret
%and = and <16 x i8> %C, %B
%neg = xor <16 x i8> %C, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%and1 = and <16 x i8> %neg, %A
%or = or <16 x i8> %and, %and1
ret <16 x i8> %or
}
define <4 x i32> @test_bit_sink_operand(<4 x i32> %src, <4 x i32> %dst, <4 x i32> %mask, i32 %scratch) {
; CHECK-SD-LABEL: test_bit_sink_operand:
; CHECK-SD: // %bb.0: // %entry
; CHECK-SD-NEXT: sub sp, sp, #32
; CHECK-SD-NEXT: .cfi_def_cfa_offset 32
; CHECK-SD-NEXT: add w8, w0, w0, lsr #31
; CHECK-SD-NEXT: mov w9, wzr
; CHECK-SD-NEXT: asr w8, w8, #1
; CHECK-SD-NEXT: .LBB11_1: // %do.body
; CHECK-SD-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-SD-NEXT: bit v1.16b, v0.16b, v2.16b
; CHECK-SD-NEXT: add x10, sp, #16
; CHECK-SD-NEXT: mov x11, sp
; CHECK-SD-NEXT: bfi x10, x9, #2, #2
; CHECK-SD-NEXT: bfi x11, x9, #2, #2
; CHECK-SD-NEXT: add w9, w9, #1
; CHECK-SD-NEXT: cmp w9, #5
; CHECK-SD-NEXT: str q1, [sp, #16]
; CHECK-SD-NEXT: str w0, [x10]
; CHECK-SD-NEXT: ldr q1, [sp, #16]
; CHECK-SD-NEXT: str q0, [sp]
; CHECK-SD-NEXT: str w8, [x11]
; CHECK-SD-NEXT: ldr q0, [sp]
; CHECK-SD-NEXT: b.ne .LBB11_1
; CHECK-SD-NEXT: // %bb.2: // %do.end
; CHECK-SD-NEXT: mov v0.16b, v1.16b
; CHECK-SD-NEXT: add sp, sp, #32
; CHECK-SD-NEXT: ret
;
; CHECK-GI-LABEL: test_bit_sink_operand:
; CHECK-GI: // %bb.0: // %entry
; CHECK-GI-NEXT: sub sp, sp, #32
; CHECK-GI-NEXT: .cfi_def_cfa_offset 32
; CHECK-GI-NEXT: asr w9, w0, #31
; CHECK-GI-NEXT: mov w8, wzr
; CHECK-GI-NEXT: add x10, sp, #16
; CHECK-GI-NEXT: mov x11, sp
; CHECK-GI-NEXT: add w9, w0, w9, lsr #31
; CHECK-GI-NEXT: asr w9, w9, #1
; CHECK-GI-NEXT: .LBB11_1: // %do.body
; CHECK-GI-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-GI-NEXT: bit v1.16b, v0.16b, v2.16b
; CHECK-GI-NEXT: mov w12, w8
; CHECK-GI-NEXT: add w8, w8, #1
; CHECK-GI-NEXT: and x12, x12, #0x3
; CHECK-GI-NEXT: cmp w8, #5
; CHECK-GI-NEXT: str q1, [sp, #16]
; CHECK-GI-NEXT: str w0, [x10, x12, lsl #2]
; CHECK-GI-NEXT: ldr q1, [sp, #16]
; CHECK-GI-NEXT: str q0, [sp]
; CHECK-GI-NEXT: str w9, [x11, x12, lsl #2]
; CHECK-GI-NEXT: ldr q0, [sp]
; CHECK-GI-NEXT: b.ne .LBB11_1
; CHECK-GI-NEXT: // %bb.2: // %do.end
; CHECK-GI-NEXT: mov v0.16b, v1.16b
; CHECK-GI-NEXT: add sp, sp, #32
; CHECK-GI-NEXT: ret
entry:
%0 = xor <4 x i32> %mask, <i32 -1, i32 -1, i32 -1, i32 -1>
%div = sdiv i32 %scratch, 2
br label %do.body
do.body:
%dst.addr.0 = phi <4 x i32> [ %dst, %entry ], [ %vecins, %do.body ]
%src.addr.0 = phi <4 x i32> [ %src, %entry ], [ %vecins1, %do.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
%vbsl3.i = and <4 x i32> %src.addr.0, %mask
%vbsl4.i = and <4 x i32> %dst.addr.0, %0
%vbsl5.i = or <4 x i32> %vbsl3.i, %vbsl4.i
%vecins = insertelement <4 x i32> %vbsl5.i, i32 %scratch, i32 %i.0
%vecins1 = insertelement <4 x i32> %src.addr.0, i32 %div, i32 %i.0
%inc = add nuw nsw i32 %i.0, 1
%exitcond.not = icmp eq i32 %inc, 5
br i1 %exitcond.not, label %do.end, label %do.body
do.end:
ret <4 x i32> %vecins
}
|
