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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve -aarch64-enable-mgather-combine=0 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve -aarch64-enable-mgather-combine=1 < %s | FileCheck %s
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; unscaled unpacked 32-bit offsets
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
define <vscale x 2 x i64> @masked_gather_nxv2i8(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1b { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%vals = call <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x i8*> %ptrs, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> undef)
%vals.zext = zext <vscale x 2 x i8> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.zext
}
define <vscale x 2 x i64> @masked_gather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i16*>
%vals = call <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x i16*> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> undef)
%vals.zext = zext <vscale x 2 x i16> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.zext
}
define <vscale x 2 x i64> @masked_gather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i32*>
%vals = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x i32*> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> undef)
%vals.zext = zext <vscale x 2 x i32> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.zext
}
define <vscale x 2 x i64> @masked_gather_nxv2i64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i64*>
%vals = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64(<vscale x 2 x i64*> %ptrs, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x i64> undef)
ret <vscale x 2 x i64> %vals
}
define <vscale x 2 x half> @masked_gather_nxv2f16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x half*>
%vals = call <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x half*> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x half> undef)
ret <vscale x 2 x half> %vals
}
define <vscale x 2 x bfloat> @masked_gather_nxv2bf16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) #0 {
; CHECK-LABEL: masked_gather_nxv2bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x bfloat*>
%vals = call <vscale x 2 x bfloat> @llvm.masked.gather.nxv2bf16(<vscale x 2 x bfloat*> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x bfloat> undef)
ret <vscale x 2 x bfloat> %vals
}
define <vscale x 2 x float> @masked_gather_nxv2f32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x float*>
%vals = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32(<vscale x 2 x float*> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x float> undef)
ret <vscale x 2 x float> %vals
}
define <vscale x 2 x double> @masked_gather_nxv2f64(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv2f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x double*>
%vals = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x double*> %ptrs, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x double> undef)
ret <vscale x 2 x double> %vals
}
define <vscale x 2 x i64> @masked_sgather_nxv2i8(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_sgather_nxv2i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1sb { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%vals = call <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x i8*> %ptrs, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> undef)
%vals.sext = sext <vscale x 2 x i8> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.sext
}
define <vscale x 2 x i64> @masked_sgather_nxv2i16(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_sgather_nxv2i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1sh { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i16*>
%vals = call <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x i16*> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> undef)
%vals.sext = sext <vscale x 2 x i16> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.sext
}
define <vscale x 2 x i64> @masked_sgather_nxv2i32(i8* %base, <vscale x 2 x i32> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_sgather_nxv2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1sw { z0.d }, p0/z, [x0, z0.d, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 2 x i32> %offsets to <vscale x 2 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 2 x i64> %offsets.zext
%ptrs = bitcast <vscale x 2 x i8*> %byte_ptrs to <vscale x 2 x i32*>
%vals = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x i32*> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> undef)
%vals.sext = sext <vscale x 2 x i32> %vals to <vscale x 2 x i64>
ret <vscale x 2 x i64> %vals.sext
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; unscaled packed 32-bit offsets
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
define <vscale x 4 x i32> @masked_gather_nxv4i8(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv4i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1b { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%vals = call <vscale x 4 x i8> @llvm.masked.gather.nxv4i8(<vscale x 4 x i8*> %ptrs, i32 1, <vscale x 4 x i1> %mask, <vscale x 4 x i8> undef)
%vals.zext = zext <vscale x 4 x i8> %vals to <vscale x 4 x i32>
ret <vscale x 4 x i32> %vals.zext
}
define <vscale x 4 x i32> @masked_gather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x i16*>
%vals = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16(<vscale x 4 x i16*> %ptrs, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x i16> undef)
%vals.zext = zext <vscale x 4 x i16> %vals to <vscale x 4 x i32>
ret <vscale x 4 x i32> %vals.zext
}
define <vscale x 4 x i32> @masked_gather_nxv4i32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x i32*>
%vals = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ptrs, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x i32> undef)
ret <vscale x 4 x i32> %vals
}
define <vscale x 4 x half> @masked_gather_nxv4f16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv4f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x half*>
%vals = call <vscale x 4 x half> @llvm.masked.gather.nxv4f16(<vscale x 4 x half*> %ptrs, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x half> undef)
ret <vscale x 4 x half> %vals
}
define <vscale x 4 x bfloat> @masked_gather_nxv4bf16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) #0 {
; CHECK-LABEL: masked_gather_nxv4bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x bfloat*>
%vals = call <vscale x 4 x bfloat> @llvm.masked.gather.nxv4bf16(<vscale x 4 x bfloat*> %ptrs, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x bfloat> undef)
ret <vscale x 4 x bfloat> %vals
}
define <vscale x 4 x float> @masked_gather_nxv4f32(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_gather_nxv4f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x float*>
%vals = call <vscale x 4 x float> @llvm.masked.gather.nxv4f32(<vscale x 4 x float*> %ptrs, i32 4, <vscale x 4 x i1> %mask, <vscale x 4 x float> undef)
ret <vscale x 4 x float> %vals
}
define <vscale x 4 x i32> @masked_sgather_nxv4i8(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_sgather_nxv4i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1sb { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%vals = call <vscale x 4 x i8> @llvm.masked.gather.nxv4i8(<vscale x 4 x i8*> %ptrs, i32 1, <vscale x 4 x i1> %mask, <vscale x 4 x i8> undef)
%vals.sext = sext <vscale x 4 x i8> %vals to <vscale x 4 x i32>
ret <vscale x 4 x i32> %vals.sext
}
define <vscale x 4 x i32> @masked_sgather_nxv4i16(i8* %base, <vscale x 4 x i32> %offsets, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: masked_sgather_nxv4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1sh { z0.s }, p0/z, [x0, z0.s, uxtw]
; CHECK-NEXT: ret
%offsets.zext = zext <vscale x 4 x i32> %offsets to <vscale x 4 x i64>
%byte_ptrs = getelementptr i8, i8* %base, <vscale x 4 x i64> %offsets.zext
%ptrs = bitcast <vscale x 4 x i8*> %byte_ptrs to <vscale x 4 x i16*>
%vals = call <vscale x 4 x i16> @llvm.masked.gather.nxv4i16(<vscale x 4 x i16*> %ptrs, i32 2, <vscale x 4 x i1> %mask, <vscale x 4 x i16> undef)
%vals.sext = sext <vscale x 4 x i16> %vals to <vscale x 4 x i32>
ret <vscale x 4 x i32> %vals.sext
}
declare <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x i8*>, i32, <vscale x 2 x i1>, <vscale x 2 x i8>)
declare <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x i16*>, i32, <vscale x 2 x i1>, <vscale x 2 x i16>)
declare <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x i32*>, i32, <vscale x 2 x i1>, <vscale x 2 x i32>)
declare <vscale x 2 x i64> @llvm.masked.gather.nxv2i64(<vscale x 2 x i64*>, i32, <vscale x 2 x i1>, <vscale x 2 x i64>)
declare <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x half*>, i32, <vscale x 2 x i1>, <vscale x 2 x half>)
declare <vscale x 2 x bfloat> @llvm.masked.gather.nxv2bf16(<vscale x 2 x bfloat*>, i32, <vscale x 2 x i1>, <vscale x 2 x bfloat>)
declare <vscale x 2 x float> @llvm.masked.gather.nxv2f32(<vscale x 2 x float*>, i32, <vscale x 2 x i1>, <vscale x 2 x float>)
declare <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x double*>, i32, <vscale x 2 x i1>, <vscale x 2 x double>)
declare <vscale x 4 x i8> @llvm.masked.gather.nxv4i8(<vscale x 4 x i8*>, i32, <vscale x 4 x i1>, <vscale x 4 x i8>)
declare <vscale x 4 x i16> @llvm.masked.gather.nxv4i16(<vscale x 4 x i16*>, i32, <vscale x 4 x i1>, <vscale x 4 x i16>)
declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*>, i32, <vscale x 4 x i1>, <vscale x 4 x i32>)
declare <vscale x 4 x half> @llvm.masked.gather.nxv4f16(<vscale x 4 x half*>, i32, <vscale x 4 x i1>, <vscale x 4 x half>)
declare <vscale x 4 x bfloat> @llvm.masked.gather.nxv4bf16(<vscale x 4 x bfloat*>, i32, <vscale x 4 x i1>, <vscale x 4 x bfloat>)
declare <vscale x 4 x float> @llvm.masked.gather.nxv4f32(<vscale x 4 x float*>, i32, <vscale x 4 x i1>, <vscale x 4 x float>)
attributes #0 = { "target-features"="+sve,+bf16" }
|
