funnel-shift.ll
8.42 KB
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
292
293
294
295
296
297
298
299
300
301
; 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>)
; General case - all operands can be variables.
define i32 @fshl_i32(i32 %x, i32 %y, i32 %z) {
; CHECK-LABEL: fshl_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ands w9, w2, #0x1f
; CHECK-NEXT: neg w9, w9
; CHECK-NEXT: lsl w8, w0, w2
; CHECK-NEXT: lsr w9, w1, w9
; CHECK-NEXT: orr w8, w8, w9
; CHECK-NEXT: csel w0, w0, w8, eq
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 %z)
ret i32 %f
}
; Verify that weird types are minimally supported.
declare i37 @llvm.fshl.i37(i37, i37, i37)
define i37 @fshl_i37(i37 %x, i37 %y, i37 %z) {
; CHECK-LABEL: fshl_i37:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x10, #31883
; CHECK-NEXT: movk x10, #3542, lsl #16
; CHECK-NEXT: movk x10, #51366, lsl #32
; CHECK-NEXT: and x9, x2, #0x1fffffffff
; CHECK-NEXT: movk x10, #56679, lsl #48
; CHECK-NEXT: umulh x10, x9, x10
; CHECK-NEXT: mov w11, #37
; CHECK-NEXT: lsr x10, x10, #5
; CHECK-NEXT: msub x9, x10, x11, x9
; CHECK-NEXT: and x8, x1, #0x1fffffffff
; CHECK-NEXT: sub x11, x11, x9
; CHECK-NEXT: lsl x10, x0, x9
; CHECK-NEXT: lsr x8, x8, x11
; CHECK-NEXT: orr x8, x10, x8
; CHECK-NEXT: cmp x9, #0 // =0
; CHECK-NEXT: csel x0, x0, x8, eq
; CHECK-NEXT: ret
%f = call i37 @llvm.fshl.i37(i37 %x, i37 %y, i37 %z)
ret i37 %f
}
; extract(concat(0b1110000, 0b1111111) << 2) = 0b1000011
declare i7 @llvm.fshl.i7(i7, i7, i7)
define i7 @fshl_i7_const_fold() {
; CHECK-LABEL: fshl_i7_const_fold:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #67
; CHECK-NEXT: ret
%f = call i7 @llvm.fshl.i7(i7 112, i7 127, i7 2)
ret i7 %f
}
define i8 @fshl_i8_const_fold_overshift_1() {
; CHECK-LABEL: fshl_i8_const_fold_overshift_1:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #128
; CHECK-NEXT: ret
%f = call i8 @llvm.fshl.i8(i8 255, i8 0, i8 15)
ret i8 %f
}
define i8 @fshl_i8_const_fold_overshift_2() {
; CHECK-LABEL: fshl_i8_const_fold_overshift_2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #120
; CHECK-NEXT: ret
%f = call i8 @llvm.fshl.i8(i8 15, i8 15, i8 11)
ret i8 %f
}
define i8 @fshl_i8_const_fold_overshift_3() {
; CHECK-LABEL: fshl_i8_const_fold_overshift_3:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
%f = call i8 @llvm.fshl.i8(i8 0, i8 225, i8 8)
ret i8 %f
}
; With constant shift amount, this is 'extr'.
define i32 @fshl_i32_const_shift(i32 %x, i32 %y) {
; CHECK-LABEL: fshl_i32_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr w0, w0, w1, #23
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 9)
ret i32 %f
}
; Check modulo math on shift amount.
define i32 @fshl_i32_const_overshift(i32 %x, i32 %y) {
; CHECK-LABEL: fshl_i32_const_overshift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr w0, w0, w1, #23
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 41)
ret i32 %f
}
; 64-bit should also work.
define i64 @fshl_i64_const_overshift(i64 %x, i64 %y) {
; CHECK-LABEL: fshl_i64_const_overshift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr x0, x0, x1, #23
; CHECK-NEXT: ret
%f = call i64 @llvm.fshl.i64(i64 %x, i64 %y, i64 105)
ret i64 %f
}
; This should work without any node-specific logic.
define i8 @fshl_i8_const_fold() {
; CHECK-LABEL: fshl_i8_const_fold:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #128
; CHECK-NEXT: ret
%f = call i8 @llvm.fshl.i8(i8 255, i8 0, i8 7)
ret i8 %f
}
; Repeat everything for funnel shift right.
; General case - all operands can be variables.
define i32 @fshr_i32(i32 %x, i32 %y, i32 %z) {
; CHECK-LABEL: fshr_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ands w9, w2, #0x1f
; CHECK-NEXT: neg w9, w9
; CHECK-NEXT: lsr w8, w1, w2
; CHECK-NEXT: lsl w9, w0, w9
; CHECK-NEXT: orr w8, w9, w8
; CHECK-NEXT: csel w0, w1, w8, eq
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 %z)
ret i32 %f
}
; Verify that weird types are minimally supported.
declare i37 @llvm.fshr.i37(i37, i37, i37)
define i37 @fshr_i37(i37 %x, i37 %y, i37 %z) {
; CHECK-LABEL: fshr_i37:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x10, #31883
; CHECK-NEXT: movk x10, #3542, lsl #16
; CHECK-NEXT: movk x10, #51366, lsl #32
; CHECK-NEXT: and x9, x2, #0x1fffffffff
; CHECK-NEXT: movk x10, #56679, lsl #48
; CHECK-NEXT: umulh x10, x9, x10
; CHECK-NEXT: mov w11, #37
; CHECK-NEXT: lsr x10, x10, #5
; CHECK-NEXT: msub x9, x10, x11, x9
; CHECK-NEXT: and x8, x1, #0x1fffffffff
; CHECK-NEXT: sub x10, x11, x9
; CHECK-NEXT: lsr x8, x8, x9
; CHECK-NEXT: lsl x10, x0, x10
; CHECK-NEXT: orr x8, x10, x8
; CHECK-NEXT: cmp x9, #0 // =0
; CHECK-NEXT: csel x0, x1, x8, eq
; CHECK-NEXT: ret
%f = call i37 @llvm.fshr.i37(i37 %x, i37 %y, i37 %z)
ret i37 %f
}
; extract(concat(0b1110000, 0b1111111) >> 2) = 0b0011111
declare i7 @llvm.fshr.i7(i7, i7, i7)
define i7 @fshr_i7_const_fold() {
; CHECK-LABEL: fshr_i7_const_fold:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #31
; CHECK-NEXT: ret
%f = call i7 @llvm.fshr.i7(i7 112, i7 127, i7 2)
ret i7 %f
}
define i8 @fshr_i8_const_fold_overshift_1() {
; CHECK-LABEL: fshr_i8_const_fold_overshift_1:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #254
; CHECK-NEXT: ret
%f = call i8 @llvm.fshr.i8(i8 255, i8 0, i8 15)
ret i8 %f
}
define i8 @fshr_i8_const_fold_overshift_2() {
; CHECK-LABEL: fshr_i8_const_fold_overshift_2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #225
; CHECK-NEXT: ret
%f = call i8 @llvm.fshr.i8(i8 15, i8 15, i8 11)
ret i8 %f
}
define i8 @fshr_i8_const_fold_overshift_3() {
; CHECK-LABEL: fshr_i8_const_fold_overshift_3:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #255
; CHECK-NEXT: ret
%f = call i8 @llvm.fshr.i8(i8 0, i8 255, i8 8)
ret i8 %f
}
; With constant shift amount, this is 'extr'.
define i32 @fshr_i32_const_shift(i32 %x, i32 %y) {
; CHECK-LABEL: fshr_i32_const_shift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr w0, w0, w1, #9
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 9)
ret i32 %f
}
; Check modulo math on shift amount. 41-32=9.
define i32 @fshr_i32_const_overshift(i32 %x, i32 %y) {
; CHECK-LABEL: fshr_i32_const_overshift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr w0, w0, w1, #9
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 41)
ret i32 %f
}
; 64-bit should also work. 105-64 = 41.
define i64 @fshr_i64_const_overshift(i64 %x, i64 %y) {
; CHECK-LABEL: fshr_i64_const_overshift:
; CHECK: // %bb.0:
; CHECK-NEXT: extr x0, x0, x1, #41
; CHECK-NEXT: ret
%f = call i64 @llvm.fshr.i64(i64 %x, i64 %y, i64 105)
ret i64 %f
}
; This should work without any node-specific logic.
define i8 @fshr_i8_const_fold() {
; CHECK-LABEL: fshr_i8_const_fold:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, #254
; CHECK-NEXT: ret
%f = call i8 @llvm.fshr.i8(i8 255, i8 0, i8 7)
ret i8 %f
}
define i32 @fshl_i32_shift_by_bitwidth(i32 %x, i32 %y) {
; CHECK-LABEL: fshl_i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%f = call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 32)
ret i32 %f
}
define i32 @fshr_i32_shift_by_bitwidth(i32 %x, i32 %y) {
; CHECK-LABEL: fshr_i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w0, w1
; CHECK-NEXT: ret
%f = call i32 @llvm.fshr.i32(i32 %x, i32 %y, i32 32)
ret i32 %f
}
define <4 x i32> @fshl_v4i32_shift_by_bitwidth(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: fshl_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> %y, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
ret <4 x i32> %f
}
define <4 x i32> @fshr_v4i32_shift_by_bitwidth(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: fshr_v4i32_shift_by_bitwidth:
; CHECK: // %bb.0:
; CHECK-NEXT: mov v0.16b, v1.16b
; CHECK-NEXT: ret
%f = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x, <4 x i32> %y, <4 x i32> <i32 32, i32 32, i32 32, i32 32>)
ret <4 x i32> %f
}