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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s | FileCheck %s
define <vscale x 1 x i8> @masked_load_nxv1i8(<vscale x 1 x i8>* %a, <vscale x 1 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv1i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, mf8, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 1 x i8> @llvm.masked.load.nxv1i8(<vscale x 1 x i8>* %a, i32 1, <vscale x 1 x i1> %mask, <vscale x 1 x i8> undef)
ret <vscale x 1 x i8> %load
}
declare <vscale x 1 x i8> @llvm.masked.load.nxv1i8(<vscale x 1 x i8>*, i32, <vscale x 1 x i1>, <vscale x 1 x i8>)
define <vscale x 1 x i16> @masked_load_nxv1i16(<vscale x 1 x i16>* %a, <vscale x 1 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv1i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, mf4, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 1 x i16> @llvm.masked.load.nxv1i16(<vscale x 1 x i16>* %a, i32 2, <vscale x 1 x i1> %mask, <vscale x 1 x i16> undef)
ret <vscale x 1 x i16> %load
}
declare <vscale x 1 x i16> @llvm.masked.load.nxv1i16(<vscale x 1 x i16>*, i32, <vscale x 1 x i1>, <vscale x 1 x i16>)
define <vscale x 1 x i32> @masked_load_nxv1i32(<vscale x 1 x i32>* %a, <vscale x 1 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv1i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, mf2, ta, mu
; CHECK-NEXT: vle32.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 1 x i32> @llvm.masked.load.nxv1i32(<vscale x 1 x i32>* %a, i32 4, <vscale x 1 x i1> %mask, <vscale x 1 x i32> undef)
ret <vscale x 1 x i32> %load
}
declare <vscale x 1 x i32> @llvm.masked.load.nxv1i32(<vscale x 1 x i32>*, i32, <vscale x 1 x i1>, <vscale x 1 x i32>)
define <vscale x 1 x i64> @masked_load_nxv1i64(<vscale x 1 x i64>* %a, <vscale x 1 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv1i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e64, m1, ta, mu
; CHECK-NEXT: vle64.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 1 x i64> @llvm.masked.load.nxv1i64(<vscale x 1 x i64>* %a, i32 8, <vscale x 1 x i1> %mask, <vscale x 1 x i64> undef)
ret <vscale x 1 x i64> %load
}
declare <vscale x 1 x i64> @llvm.masked.load.nxv1i64(<vscale x 1 x i64>*, i32, <vscale x 1 x i1>, <vscale x 1 x i64>)
define <vscale x 2 x i8> @masked_load_nxv2i8(<vscale x 2 x i8>* %a, <vscale x 2 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv2i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(<vscale x 2 x i8>* %a, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> undef)
ret <vscale x 2 x i8> %load
}
declare <vscale x 2 x i8> @llvm.masked.load.nxv2i8(<vscale x 2 x i8>*, i32, <vscale x 2 x i1>, <vscale x 2 x i8>)
define <vscale x 2 x i16> @masked_load_nxv2i16(<vscale x 2 x i16>* %a, <vscale x 2 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv2i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.masked.load.nxv2i16(<vscale x 2 x i16>* %a, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> undef)
ret <vscale x 2 x i16> %load
}
declare <vscale x 2 x i16> @llvm.masked.load.nxv2i16(<vscale x 2 x i16>*, i32, <vscale x 2 x i1>, <vscale x 2 x i16>)
define <vscale x 2 x i32> @masked_load_nxv2i32(<vscale x 2 x i32>* %a, <vscale x 2 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv2i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, mu
; CHECK-NEXT: vle32.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32(<vscale x 2 x i32>* %a, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> undef)
ret <vscale x 2 x i32> %load
}
declare <vscale x 2 x i32> @llvm.masked.load.nxv2i32(<vscale x 2 x i32>*, i32, <vscale x 2 x i1>, <vscale x 2 x i32>)
define <vscale x 2 x i64> @masked_load_nxv2i64(<vscale x 2 x i64>* %a, <vscale x 2 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e64, m2, ta, mu
; CHECK-NEXT: vle64.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64(<vscale x 2 x i64>* %a, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x i64> undef)
ret <vscale x 2 x i64> %load
}
declare <vscale x 2 x i64> @llvm.masked.load.nxv2i64(<vscale x 2 x i64>*, i32, <vscale x 2 x i1>, <vscale x 2 x i64>)
define <vscale x 4 x i8> @masked_load_nxv4i8(<vscale x 4 x i8>* %a, <vscale x 4 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv4i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, mf2, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8(<vscale x 4 x i8>* %a, i32 1, <vscale x 4 x i1> %mask, <vscale x 4 x i8> undef)
ret <vscale x 4 x i8> %load
}
declare <vscale x 4 x i8> @llvm.masked.load.nxv4i8(<vscale x 4 x i8>*, i32, <vscale x 4 x i1>, <vscale x 4 x i8>)
define <vscale x 4 x i16> @masked_load_nxv4i16(<vscale x 4 x i16>* %a, <vscale x 4 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv4i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.masked.load.nxv4i16(<vscale x 4 x i16>* %a, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x i16> undef)
ret <vscale x 4 x i16> %load
}
declare <vscale x 4 x i16> @llvm.masked.load.nxv4i16(<vscale x 4 x i16>*, i32, <vscale x 4 x i1>, <vscale x 4 x i16>)
define <vscale x 4 x i32> @masked_load_nxv4i32(<vscale x 4 x i32>* %a, <vscale x 4 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, mu
; CHECK-NEXT: vle32.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32(<vscale x 4 x i32>* %a, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x i32> undef)
ret <vscale x 4 x i32> %load
}
declare <vscale x 4 x i32> @llvm.masked.load.nxv4i32(<vscale x 4 x i32>*, i32, <vscale x 4 x i1>, <vscale x 4 x i32>)
define <vscale x 4 x i64> @masked_load_nxv4i64(<vscale x 4 x i64>* %a, <vscale x 4 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e64, m4, ta, mu
; CHECK-NEXT: vle64.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 4 x i64> @llvm.masked.load.nxv4i64(<vscale x 4 x i64>* %a, i32 8, <vscale x 4 x i1> %mask, <vscale x 4 x i64> undef)
ret <vscale x 4 x i64> %load
}
declare <vscale x 4 x i64> @llvm.masked.load.nxv4i64(<vscale x 4 x i64>*, i32, <vscale x 4 x i1>, <vscale x 4 x i64>)
define <vscale x 8 x i8> @masked_load_nxv8i8(<vscale x 8 x i8>* %a, <vscale x 8 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv8i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, m1, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8(<vscale x 8 x i8>* %a, i32 1, <vscale x 8 x i1> %mask, <vscale x 8 x i8> undef)
ret <vscale x 8 x i8> %load
}
declare <vscale x 8 x i8> @llvm.masked.load.nxv8i8(<vscale x 8 x i8>*, i32, <vscale x 8 x i1>, <vscale x 8 x i8>)
define <vscale x 8 x i16> @masked_load_nxv8i16(<vscale x 8 x i16>* %a, <vscale x 8 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 8 x i16> @llvm.masked.load.nxv8i16(<vscale x 8 x i16>* %a, i32 2, <vscale x 8 x i1> %mask, <vscale x 8 x i16> undef)
ret <vscale x 8 x i16> %load
}
declare <vscale x 8 x i16> @llvm.masked.load.nxv8i16(<vscale x 8 x i16>*, i32, <vscale x 8 x i1>, <vscale x 8 x i16>)
define <vscale x 8 x i32> @masked_load_nxv8i32(<vscale x 8 x i32>* %a, <vscale x 8 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m4, ta, mu
; CHECK-NEXT: vle32.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 8 x i32> @llvm.masked.load.nxv8i32(<vscale x 8 x i32>* %a, i32 4, <vscale x 8 x i1> %mask, <vscale x 8 x i32> undef)
ret <vscale x 8 x i32> %load
}
declare <vscale x 8 x i32> @llvm.masked.load.nxv8i32(<vscale x 8 x i32>*, i32, <vscale x 8 x i1>, <vscale x 8 x i32>)
define <vscale x 8 x i64> @masked_load_nxv8i64(<vscale x 8 x i64>* %a, <vscale x 8 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv8i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e64, m8, ta, mu
; CHECK-NEXT: vle64.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 8 x i64> @llvm.masked.load.nxv8i64(<vscale x 8 x i64>* %a, i32 8, <vscale x 8 x i1> %mask, <vscale x 8 x i64> undef)
ret <vscale x 8 x i64> %load
}
declare <vscale x 8 x i64> @llvm.masked.load.nxv8i64(<vscale x 8 x i64>*, i32, <vscale x 8 x i1>, <vscale x 8 x i64>)
define <vscale x 16 x i8> @masked_load_nxv16i8(<vscale x 16 x i8>* %a, <vscale x 16 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv16i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, m2, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8(<vscale x 16 x i8>* %a, i32 1, <vscale x 16 x i1> %mask, <vscale x 16 x i8> undef)
ret <vscale x 16 x i8> %load
}
declare <vscale x 16 x i8> @llvm.masked.load.nxv16i8(<vscale x 16 x i8>*, i32, <vscale x 16 x i1>, <vscale x 16 x i8>)
define <vscale x 16 x i16> @masked_load_nxv16i16(<vscale x 16 x i16>* %a, <vscale x 16 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv16i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m4, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 16 x i16> @llvm.masked.load.nxv16i16(<vscale x 16 x i16>* %a, i32 2, <vscale x 16 x i1> %mask, <vscale x 16 x i16> undef)
ret <vscale x 16 x i16> %load
}
declare <vscale x 16 x i16> @llvm.masked.load.nxv16i16(<vscale x 16 x i16>*, i32, <vscale x 16 x i1>, <vscale x 16 x i16>)
define <vscale x 16 x i32> @masked_load_nxv16i32(<vscale x 16 x i32>* %a, <vscale x 16 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv16i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, mu
; CHECK-NEXT: vle32.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 16 x i32> @llvm.masked.load.nxv16i32(<vscale x 16 x i32>* %a, i32 4, <vscale x 16 x i1> %mask, <vscale x 16 x i32> undef)
ret <vscale x 16 x i32> %load
}
declare <vscale x 16 x i32> @llvm.masked.load.nxv16i32(<vscale x 16 x i32>*, i32, <vscale x 16 x i1>, <vscale x 16 x i32>)
define <vscale x 32 x i8> @masked_load_nxv32i8(<vscale x 32 x i8>* %a, <vscale x 32 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv32i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, m4, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 32 x i8> @llvm.masked.load.nxv32i8(<vscale x 32 x i8>* %a, i32 1, <vscale x 32 x i1> %mask, <vscale x 32 x i8> undef)
ret <vscale x 32 x i8> %load
}
declare <vscale x 32 x i8> @llvm.masked.load.nxv32i8(<vscale x 32 x i8>*, i32, <vscale x 32 x i1>, <vscale x 32 x i8>)
define <vscale x 32 x i16> @masked_load_nxv32i16(<vscale x 32 x i16>* %a, <vscale x 32 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv32i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m8, ta, mu
; CHECK-NEXT: vle16.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 32 x i16> @llvm.masked.load.nxv32i16(<vscale x 32 x i16>* %a, i32 2, <vscale x 32 x i1> %mask, <vscale x 32 x i16> undef)
ret <vscale x 32 x i16> %load
}
declare <vscale x 32 x i16> @llvm.masked.load.nxv32i16(<vscale x 32 x i16>*, i32, <vscale x 32 x i1>, <vscale x 32 x i16>)
define <vscale x 64 x i8> @masked_load_nxv64i8(<vscale x 64 x i8>* %a, <vscale x 64 x i1> %mask) nounwind {
; CHECK-LABEL: masked_load_nxv64i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, m8, ta, mu
; CHECK-NEXT: vle8.v v8, (a0), v0.t
; CHECK-NEXT: ret
%load = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8(<vscale x 64 x i8>* %a, i32 1, <vscale x 64 x i1> %mask, <vscale x 64 x i8> undef)
ret <vscale x 64 x i8> %load
}
declare <vscale x 64 x i8> @llvm.masked.load.nxv64i8(<vscale x 64 x i8>*, i32, <vscale x 64 x i1>, <vscale x 64 x i8>)
define <vscale x 2 x i8> @masked_load_zero_mask(<vscale x 2 x i8>* %a) nounwind {
; CHECK-LABEL: masked_load_zero_mask:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(<vscale x 2 x i8>* %a, i32 1, <vscale x 2 x i1> zeroinitializer, <vscale x 2 x i8> undef)
ret <vscale x 2 x i8> %load
}
define <vscale x 2 x i8> @masked_load_allones_mask(<vscale x 2 x i8>* %a, <vscale x 2 x i8> %maskedoff) nounwind {
; CHECK-LABEL: masked_load_allones_mask:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e8, mf4, ta, mu
; CHECK-NEXT: vle8.v v8, (a0)
; CHECK-NEXT: ret
%insert = insertelement <vscale x 2 x i1> poison, i1 1, i32 0
%mask = shufflevector <vscale x 2 x i1> %insert, <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer
%load = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8(<vscale x 2 x i8>* %a, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> %maskedoff)
ret <vscale x 2 x i8> %load
}
|
