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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 -mattr=+sve < %s | FileCheck %s
; This tests that various ands, sexts, and zexts (and other operations)
; operating on vscale or the SVE count instructions can be eliminated
; (via demanded bits) due to their known limited range.
; On AArch64 vscale can be at most 16 (for a 2048-bit vector).
; The counting instructions (sans multiplier) have a value of at most 256
; (for a 2048-bit vector of i8s).
define i32 @vscale_and_elimination() vscale_range(1,16) {
; CHECK-LABEL: vscale_and_elimination:
; CHECK: // %bb.0:
; CHECK-NEXT: rdvl x8, #1
; CHECK-NEXT: lsr x8, x8, #4
; CHECK-NEXT: and w9, w8, #0x1c
; CHECK-NEXT: add w0, w8, w9
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%and_redundant = and i32 %vscale, 31
%and_required = and i32 %vscale, 17179869180
%result = add i32 %and_redundant, %and_required
ret i32 %result
}
define i64 @cntb_and_elimination() {
; CHECK-LABEL: cntb_and_elimination:
; CHECK: // %bb.0:
; CHECK-NEXT: cntb x8
; CHECK-NEXT: and x9, x8, #0x1fc
; CHECK-NEXT: add x0, x8, x9
; CHECK-NEXT: ret
%cntb = call i64 @llvm.aarch64.sve.cntb(i32 31)
%and_redundant = and i64 %cntb, 511
%and_required = and i64 %cntb, 17179869180
%result = add i64 %and_redundant, %and_required
ret i64 %result
}
define i64 @cnth_and_elimination() {
; CHECK-LABEL: cnth_and_elimination:
; CHECK: // %bb.0:
; CHECK-NEXT: cnth x8
; CHECK-NEXT: and x9, x8, #0xfc
; CHECK-NEXT: add x0, x8, x9
; CHECK-NEXT: ret
%cnth = call i64 @llvm.aarch64.sve.cnth(i32 31)
%and_redundant = and i64 %cnth, 1023
%and_required = and i64 %cnth, 17179869180
%result = add i64 %and_redundant, %and_required
ret i64 %result
}
define i64 @cntw_and_elimination() {
; CHECK-LABEL: cntw_and_elimination:
; CHECK: // %bb.0:
; CHECK-NEXT: cntw x8
; CHECK-NEXT: and x9, x8, #0x7c
; CHECK-NEXT: add x0, x8, x9
; CHECK-NEXT: ret
%cntw = call i64 @llvm.aarch64.sve.cntw(i32 31)
%and_redundant = and i64 %cntw, 127
%and_required = and i64 %cntw, 17179869180
%result = add i64 %and_redundant, %and_required
ret i64 %result
}
define i64 @cntd_and_elimination() {
; CHECK-LABEL: cntd_and_elimination:
; CHECK: // %bb.0:
; CHECK-NEXT: cntd x8
; CHECK-NEXT: and x9, x8, #0x3c
; CHECK-NEXT: add x0, x8, x9
; CHECK-NEXT: ret
%cntd = call i64 @llvm.aarch64.sve.cntd(i32 31)
%and_redundant = and i64 %cntd, 63
%and_required = and i64 %cntd, 17179869180
%result = add i64 %and_redundant, %and_required
ret i64 %result
}
define i64 @vscale_trunc_zext() vscale_range(1,16) {
; CHECK-LABEL: vscale_trunc_zext:
; CHECK: // %bb.0:
; CHECK-NEXT: rdvl x8, #1
; CHECK-NEXT: lsr x0, x8, #4
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%zext = zext i32 %vscale to i64
ret i64 %zext
}
define i64 @vscale_trunc_sext() vscale_range(1,16) {
; CHECK-LABEL: vscale_trunc_sext:
; CHECK: // %bb.0:
; CHECK-NEXT: rdvl x8, #1
; CHECK-NEXT: lsr x0, x8, #4
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%sext = sext i32 %vscale to i64
ret i64 %sext
}
define i64 @count_bytes_trunc_zext() {
; CHECK-LABEL: count_bytes_trunc_zext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntb x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntb(i32 31)
%trunc = trunc i64 %cnt to i32
%zext = zext i32 %trunc to i64
ret i64 %zext
}
define i64 @count_halfs_trunc_zext() {
; CHECK-LABEL: count_halfs_trunc_zext:
; CHECK: // %bb.0:
; CHECK-NEXT: cnth x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cnth(i32 31)
%trunc = trunc i64 %cnt to i32
%zext = zext i32 %trunc to i64
ret i64 %zext
}
define i64 @count_words_trunc_zext() {
; CHECK-LABEL: count_words_trunc_zext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntw x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntw(i32 31)
%trunc = trunc i64 %cnt to i32
%zext = zext i32 %trunc to i64
ret i64 %zext
}
define i64 @count_doubles_trunc_zext() {
; CHECK-LABEL: count_doubles_trunc_zext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntd x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntd(i32 31)
%trunc = trunc i64 %cnt to i32
%zext = zext i32 %trunc to i64
ret i64 %zext
}
define i64 @count_bytes_trunc_sext() {
; CHECK-LABEL: count_bytes_trunc_sext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntb x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntb(i32 31)
%trunc = trunc i64 %cnt to i32
%sext = sext i32 %trunc to i64
ret i64 %sext
}
define i64 @count_halfs_trunc_sext() {
; CHECK-LABEL: count_halfs_trunc_sext:
; CHECK: // %bb.0:
; CHECK-NEXT: cnth x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cnth(i32 31)
%trunc = trunc i64 %cnt to i32
%sext = sext i32 %trunc to i64
ret i64 %sext
}
define i64 @count_words_trunc_sext() {
; CHECK-LABEL: count_words_trunc_sext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntw x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntw(i32 31)
%trunc = trunc i64 %cnt to i32
%sext = sext i32 %trunc to i64
ret i64 %sext
}
define i64 @count_doubles_trunc_sext() {
; CHECK-LABEL: count_doubles_trunc_sext:
; CHECK: // %bb.0:
; CHECK-NEXT: cntd x0
; CHECK-NEXT: ret
%cnt = call i64 @llvm.aarch64.sve.cntd(i32 31)
%trunc = trunc i64 %cnt to i32
%sext = sext i32 %trunc to i64
ret i64 %sext
}
define i32 @vscale_with_multiplier() vscale_range(1,16) {
; CHECK-LABEL: vscale_with_multiplier:
; CHECK: // %bb.0:
; CHECK-NEXT: rdvl x8, #1
; CHECK-NEXT: mov w9, #5
; CHECK-NEXT: lsr x8, x8, #4
; CHECK-NEXT: mul x8, x8, x9
; CHECK-NEXT: and w9, w8, #0x3f
; CHECK-NEXT: add w0, w8, w9
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%mul = mul i32 %vscale, 5
%and_redundant = and i32 %mul, 127
%and_required = and i32 %mul, 63
%result = add i32 %and_redundant, %and_required
ret i32 %result
}
define i32 @vscale_with_negative_multiplier() vscale_range(1,16) {
; CHECK-LABEL: vscale_with_negative_multiplier:
; CHECK: // %bb.0:
; CHECK-NEXT: rdvl x8, #1
; CHECK-NEXT: mov x9, #-5
; CHECK-NEXT: lsr x8, x8, #4
; CHECK-NEXT: mul x8, x8, x9
; CHECK-NEXT: and w9, w8, #0xffffffc0
; CHECK-NEXT: add w0, w8, w9
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%mul = mul i32 %vscale, -5
%or_redundant = or i32 %mul, 4294967168
%or_required = and i32 %mul, 4294967232
%result = add i32 %or_redundant, %or_required
ret i32 %result
}
define i32 @pow2_vscale_with_negative_multiplier() vscale_range(1,16) {
; CHECK-LABEL: pow2_vscale_with_negative_multiplier:
; CHECK: // %bb.0:
; CHECK-NEXT: cntd x8
; CHECK-NEXT: neg x8, x8
; CHECK-NEXT: orr w9, w8, #0xfffffff0
; CHECK-NEXT: add w0, w8, w9
; CHECK-NEXT: ret
%vscale = call i32 @llvm.vscale.i32()
%mul = mul i32 %vscale, -2
%or_redundant = or i32 %mul, 4294967264
%or_required = or i32 %mul, 4294967280
%result = add i32 %or_redundant, %or_required
ret i32 %result
}
declare i32 @llvm.vscale.i32()
declare i64 @llvm.aarch64.sve.cntb(i32 %pattern)
declare i64 @llvm.aarch64.sve.cnth(i32 %pattern)
declare i64 @llvm.aarch64.sve.cntw(i32 %pattern)
declare i64 @llvm.aarch64.sve.cntd(i32 %pattern)
|
