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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-- | FileCheck %s
declare i8 @llvm.fshl.i8(i8, i8, i8)
declare i16 @llvm.fshl.i16(i16, i16, i16)
declare i32 @llvm.fshl.i32(i32, i32, i32)
declare i64 @llvm.fshl.i64(i64, i64, i64)
declare <4 x i32> @llvm.fshl.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
declare i8 @llvm.fshr.i8(i8, i8, i8)
declare i16 @llvm.fshr.i16(i16, i16, i16)
declare i32 @llvm.fshr.i32(i32, i32, i32)
declare i64 @llvm.fshr.i64(i64, i64, i64)
declare <4 x i32> @llvm.fshr.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
; When first 2 operands match, it's a rotate.
define i8 @rotl_i8_const_shift(i8 %x) {
; CHECK-LABEL: rotl_i8_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ubfx w8, w0, #5, #3
; CHECK-NEXT: bfi w8, w0, #3, #29
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%f = call i8 @llvm.fshl.i8(i8 %x, i8 %x, i8 3)
ret i8 %f
}
define i64 @rotl_i64_const_shift(i64 %x) {
; CHECK-LABEL: rotl_i64_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ror x0, x0, #61
; CHECK-NEXT: ret
%f = call i64 @llvm.fshl.i64(i64 %x, i64 %x, i64 3)
ret i64 %f
}
; When first 2 operands match, it's a rotate (by variable amount).
define i16 @rotl_i16(i16 %x, i16 %z) {
; CHECK-LABEL: rotl_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: orr w10, wzr, #0x10
; CHECK-NEXT: sub w10, w10, w1
; CHECK-NEXT: and w8, w0, #0xffff
; CHECK-NEXT: and w9, w1, #0xf
; CHECK-NEXT: and w10, w10, #0xf
; CHECK-NEXT: lsl w9, w0, w9
; CHECK-NEXT: lsr w8, w8, w10
; CHECK-NEXT: orr w0, w9, w8
; CHECK-NEXT: ret
%f = call i16 @llvm.fshl.i16(i16 %x, i16 %x, i16 %z)
ret i16 %f
}
define i32 @rotl_i32(i32 %x, i32 %z) {
; CHECK-LABEL: rotl_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: orr w8, wzr, #0x20
; CHECK-NEXT: sub w8, w8, w1
; CHECK-NEXT: ror w0, w0, w8
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %x, i32 %z)
ret i32 %f
}
define i64 @rotl_i64(i64 %x, i64 %z) {
; CHECK-LABEL: rotl_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: orr w9, wzr, #0x40
; CHECK-NEXT: sub w9, w9, w1
; CHECK-NEXT: lsl x8, x0, x1
; CHECK-NEXT: lsr x9, x0, x9
; CHECK-NEXT: orr x0, x8, x9
; CHECK-NEXT: ret
%f = call i64 @llvm.fshl.i64(i64 %x, i64 %x, i64 %z)
ret i64 %f
}
; Vector rotate.
define <4 x i32> @rotl_v4i32(<4 x i32> %x, <4 x i32> %z) {
; CHECK-LABEL: rotl_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v2.4s, #31
; CHECK-NEXT: movi v3.4s, #32
; CHECK-NEXT: and v4.16b, v1.16b, v2.16b
; CHECK-NEXT: sub v1.4s, v3.4s, v1.4s
; CHECK-NEXT: and v1.16b, v1.16b, v2.16b
; CHECK-NEXT: neg v1.4s, v1.4s
; CHECK-NEXT: ushl v3.4s, v0.4s, v4.4s
; CHECK-NEXT: ushl v0.4s, v0.4s, v1.4s
; CHECK-NEXT: orr v0.16b, v3.16b, v0.16b
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> %z)
ret <4 x i32> %f
}
; Vector rotate by constant splat amount.
define <4 x i32> @rotl_v4i32_rotl_const_shift(<4 x i32> %x) {
; CHECK-LABEL: rotl_v4i32_rotl_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ushr v1.4s, v0.4s, #29
; CHECK-NEXT: shl v0.4s, v0.4s, #3
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> <i32 3, i32 3, i32 3, i32 3>)
ret <4 x i32> %f
}
; Repeat everything for funnel shift right.
; When first 2 operands match, it's a rotate.
define i8 @rotr_i8_const_shift(i8 %x) {
; CHECK-LABEL: rotr_i8_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ubfx w8, w0, #3, #5
; CHECK-NEXT: bfi w8, w0, #5, #27
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%f = call i8 @llvm.fshr.i8(i8 %x, i8 %x, i8 3)
ret i8 %f
}
define i32 @rotr_i32_const_shift(i32 %x) {
; CHECK-LABEL: rotr_i32_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ror w0, w0, #3
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %x, i32 3)
ret i32 %f
}
; When first 2 operands match, it's a rotate (by variable amount).
define i16 @rotr_i16(i16 %x, i16 %z) {
; CHECK-LABEL: rotr_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: and w8, w0, #0xffff
; CHECK-NEXT: and w9, w1, #0xf
; CHECK-NEXT: orr w10, wzr, #0x10
; CHECK-NEXT: lsr w8, w8, w9
; CHECK-NEXT: sub w9, w10, w1
; CHECK-NEXT: and w9, w9, #0xf
; CHECK-NEXT: lsl w9, w0, w9
; CHECK-NEXT: orr w0, w9, w8
; CHECK-NEXT: ret
%f = call i16 @llvm.fshr.i16(i16 %x, i16 %x, i16 %z)
ret i16 %f
}
define i32 @rotr_i32(i32 %x, i32 %z) {
; CHECK-LABEL: rotr_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ror w0, w0, w1
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %x, i32 %z)
ret i32 %f
}
define i64 @rotr_i64(i64 %x, i64 %z) {
; CHECK-LABEL: rotr_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ror x0, x0, x1
; CHECK-NEXT: ret
%f = call i64 @llvm.fshr.i64(i64 %x, i64 %x, i64 %z)
ret i64 %f
}
; Vector rotate.
define <4 x i32> @rotr_v4i32(<4 x i32> %x, <4 x i32> %z) {
; CHECK-LABEL: rotr_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v2.4s, #31
; CHECK-NEXT: movi v3.4s, #32
; CHECK-NEXT: and v4.16b, v1.16b, v2.16b
; CHECK-NEXT: sub v1.4s, v3.4s, v1.4s
; CHECK-NEXT: neg v3.4s, v4.4s
; CHECK-NEXT: and v1.16b, v1.16b, v2.16b
; CHECK-NEXT: ushl v2.4s, v0.4s, v3.4s
; CHECK-NEXT: ushl v0.4s, v0.4s, v1.4s
; CHECK-NEXT: orr v0.16b, v0.16b, v2.16b
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> %z)
ret <4 x i32> %f
}
; Vector rotate by constant splat amount.
define <4 x i32> @rotr_v4i32_const_shift(<4 x i32> %x) {
; CHECK-LABEL: rotr_v4i32_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: ushr v1.4s, v0.4s, #3
; CHECK-NEXT: shl v0.4s, v0.4s, #29
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> <i32 3, i32 3, i32 3, i32 3>)
ret <4 x i32> %f
}
define i32 @rotl_i32_shift_by_bitwidth(i32 %x) {
; CHECK-LABEL: rotl_i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %x, i32 32)
ret i32 %f
}
define i32 @rotr_i32_shift_by_bitwidth(i32 %x) {
; CHECK-LABEL: rotr_i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %x, i32 32)
ret i32 %f
}
define <4 x i32> @rotl_v4i32_shift_by_bitwidth(<4 x i32> %x) {
; CHECK-LABEL: rotl_v4i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
ret <4 x i32> %f
}
define <4 x i32> @rotr_v4i32_shift_by_bitwidth(<4 x i32> %x) {
; CHECK-LABEL: rotr_v4i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x, <4 x i32> %x, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
ret <4 x i32> %f
}
|
