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=aarch64-- | FileCheck %s
; logic shift reg pattern: and
; already optimized by another pattern
define i64 @and_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: and_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: and x8, x1, x0, asr #23
; CHECK-NEXT: and x0, x8, #0xffffffffff000000
; CHECK-NEXT: ret
%ashr = ashr i64 %a, 23
%and = and i64 %ashr, -16777216
%r = and i64 %b, %and
ret i64 %r
}
; TODO: logic shift reg pattern: bic
define i64 @bic_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: bic_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #16777215 // =0xffffff
; CHECK-NEXT: orn x8, x8, x0, asr #23
; CHECK-NEXT: and x0, x1, x8
; CHECK-NEXT: ret
%ashr = ashr i64 %a, 23
%and = and i64 %ashr, -16777216
%not = xor i64 %and, -1
%r = and i64 %b, %not
ret i64 %r
}
; logic shift reg pattern: eon
define i64 @eon_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: eon_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #17
; CHECK-NEXT: eon x0, x1, x8, lsl #53
; CHECK-NEXT: ret
%shl = shl i64 %a, 36
%and = and i64 %shl, -9007199254740992
%xor = xor i64 %and, -1
%r = xor i64 %b, %xor
ret i64 %r
}
; logic shift reg pattern: eor
define i64 @eor_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: eor_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #47
; CHECK-NEXT: eor x0, x1, x8, lsl #24
; CHECK-NEXT: ret
%lshr = lshr i64 %a, 23
%and = and i64 %lshr, 2199006478336
%or = xor i64 %and, %b
ret i64 %or
}
; logic shift reg pattern: mvn
; already optimized by another pattern
define i64 @mvn_shiftedreg_from_and(i64 %a) {
; CHECK-LABEL: mvn_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #9007199254740991 // =0x1fffffffffffff
; CHECK-NEXT: orn x0, x8, x0, lsl #36
; CHECK-NEXT: ret
%shl = shl i64 %a, 36
%and = and i64 %shl, -9007199254740992
%xor = xor i64 %and, -1
ret i64 %xor
}
; logic shift reg pattern: orn
; already optimized by another pattern
define i64 @orn_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: orn_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: orn x8, x1, x0, lsr #23
; CHECK-NEXT: orr x0, x8, #0xfffffe0000ffffff
; CHECK-NEXT: ret
%lshr = lshr i64 %a, 23
%and = and i64 %lshr, 2199006478336
%not = xor i64 %and, -1
%or = or i64 %not, %b
ret i64 %or
}
; logic shift reg pattern: orr
; srl constant bitwidth == (lowbits + masklen + shiftamt)
define i64 @orr_shiftedreg_from_and(i64 %a, i64 %b) {
; CHECK-LABEL: orr_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #47
; CHECK-NEXT: orr x0, x1, x8, lsl #24
; CHECK-NEXT: ret
%lshr = lshr i64 %a, 23
%and = and i64 %lshr, 2199006478336 ; 0x1ffff000000
%or = or i64 %and, %b
ret i64 %or
}
; logic shift reg pattern: orr
; srl constant bitwidth < (lowbits + masklen + shiftamt)
define i64 @orr_shiftedreg_from_and_mask2(i64 %a, i64 %b) {
; CHECK-LABEL: orr_shiftedreg_from_and_mask2:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #47
; CHECK-NEXT: orr x0, x1, x8, lsl #24
; CHECK-NEXT: ret
%lshr = lshr i64 %a, 23
%and = and i64 %lshr, 4398029733888 ; 0x3ffff000000
%or = or i64 %and, %b
ret i64 %or
}
; arithmetic shift reg pattern: add
define i32 @add_shiftedreg_from_and(i32 %a, i32 %b) {
; CHECK-LABEL: add_shiftedreg_from_and:
; CHECK: // %bb.0:
; CHECK-NEXT: asr w8, w0, #27
; CHECK-NEXT: add w0, w1, w8, lsl #24
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 3
%and = and i32 %ashr, -16777216
%add = add i32 %and, %b
ret i32 %add
}
; arithmetic shift reg pattern: sub
define i64 @sub_shiftedreg_from_and_shl(i64 %a, i64 %b) {
; CHECK-LABEL: sub_shiftedreg_from_and_shl:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #17
; CHECK-NEXT: sub x0, x1, x8, lsl #53
; CHECK-NEXT: ret
%shl = shl i64 %a, 36
%and = and i64 %shl, -9007199254740992
%sub = sub i64 %b, %and
ret i64 %sub
}
; negative test: type is not i32 or i64
define <2 x i32> @shiftedreg_from_and_negative_type(<2 x i32> %a, <2 x i32> %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_type:
; CHECK: // %bb.0:
; CHECK-NEXT: shl v0.2s, v0.2s, #2
; CHECK-NEXT: bic v0.2s, #28
; CHECK-NEXT: sub v0.2s, v1.2s, v0.2s
; CHECK-NEXT: ret
%shl = shl <2 x i32> %a, <i32 2, i32 2>
%and = and <2 x i32> %shl, <i32 -32, i32 -32>
%sub = sub <2 x i32> %b, %and
ret <2 x i32> %sub
}
; negative test: shift one-use
define i32 @shiftedreg_from_and_negative_oneuse1(i32 %a, i32 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_oneuse1:
; CHECK: // %bb.0:
; CHECK-NEXT: asr w8, w0, #23
; CHECK-NEXT: and w9, w8, #0xff000000
; CHECK-NEXT: add w9, w9, w1
; CHECK-NEXT: mul w0, w8, w9
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 23
%and = and i32 %ashr, -16777216
%add = add i32 %and, %b
%r = mul i32 %ashr, %add
ret i32 %r
}
; negative test: and one-use
define i32 @shiftedreg_from_and_negative_oneuse2(i32 %a, i32 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_oneuse2:
; CHECK: // %bb.0:
; CHECK-NEXT: asr w8, w0, #23
; CHECK-NEXT: and w8, w8, #0xff000000
; CHECK-NEXT: add w9, w8, w1
; CHECK-NEXT: mul w0, w8, w9
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 23
%and = and i32 %ashr, -16777216
%add = add i32 %and, %b
%r = mul i32 %and, %add
ret i32 %r
}
; negative test: and c is not mask
define i32 @shiftedreg_from_and_negative_andc1(i32 %a, i32 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc1:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #26215 // =0x6667
; CHECK-NEXT: movk w8, #65510, lsl #16
; CHECK-NEXT: and w8, w8, w0, asr #23
; CHECK-NEXT: add w0, w8, w1
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 23
%and = and i32 %ashr, -1677721
%add = add i32 %and, %b
ret i32 %add
}
; negative test: sra with and c is not legal mask
define i32 @shiftedreg_from_and_negative_andc2(i32 %a, i32 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-285212672 // =0xef000000
; CHECK-NEXT: and w8, w8, w0, asr #23
; CHECK-NEXT: add w0, w8, w1
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 23
%and = and i32 %ashr, 4009754624 ; 0xef000000
%add = add i32 %and, %b
ret i32 %add
}
; negative test: shl with and c is not legal mask
define i64 @shiftedreg_from_and_negative_andc3(i64 %a, i64 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc3:
; CHECK: // %bb.0:
; CHECK-NEXT: eor x0, x1, x0, lsl #36
; CHECK-NEXT: ret
%shl = shl i64 %a, 36
%and = and i64 %shl, -4294967296
%xor = xor i64 %and, %b
ret i64 %xor
}
; negative test: shl with and c is not legal mask
define i64 @shiftedreg_from_and_negative_andc4(i64 %a, i64 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc4:
; CHECK: // %bb.0:
; CHECK-NEXT: lsl x8, x0, #36
; CHECK-NEXT: and x8, x8, #0x7fe0000000000000
; CHECK-NEXT: eor x0, x8, x1
; CHECK-NEXT: ret
%shl = shl i64 %a, 36
%and = and i64 %shl, 9214364837600034816
%xor = xor i64 %and, %b
ret i64 %xor
}
; negative test: sra with and c is not legal mask
define i32 @shiftedreg_from_and_negative_andc5(i32 %a, i32 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc5:
; CHECK: // %bb.0:
; CHECK-NEXT: asr w8, w0, #23
; CHECK-NEXT: and w8, w8, #0xff000000
; CHECK-NEXT: add w0, w8, w1
; CHECK-NEXT: ret
%ashr = ashr i32 %a, 23
%and = and i32 %ashr, -16777216
%add = add i32 %and, %b
ret i32 %add
}
; negative test: srl with and c is not legal mask
; srl constant bitwidth > (lowbits + masklen + shiftamt)
define i64 @shiftedreg_from_and_negative_andc6(i64 %a, i64 %b) {
; CHECK-LABEL: shiftedreg_from_and_negative_andc6:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr x8, x0, #2
; CHECK-NEXT: and x8, x8, #0x6
; CHECK-NEXT: add x0, x8, x1
; CHECK-NEXT: ret
%lshr = lshr i64 %a, 2
%and = and i64 %lshr, 6
%add = add i64 %and, %b
ret i64 %add
}
|
