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
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
; RUN: llc -O0 -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
;
; LD1B
;
define <vscale x 16 x i8> @ld1b_i8(<vscale x 16 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1b_i8:
; CHECK: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.ld1.nxv16i8(<vscale x 16 x i1> %pred, i8* %addr)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @ld1b_h(<vscale x 8 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1b_h:
; CHECK: ld1b { z0.h }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 8 x i8> @llvm.aarch64.sve.ld1.nxv8i8(<vscale x 8 x i1> %pred, i8* %addr)
%res = zext <vscale x 8 x i8> %load to <vscale x 8 x i16>
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x i16> @ld1sb_h(<vscale x 8 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1sb_h:
; CHECK: ld1sb { z0.h }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 8 x i8> @llvm.aarch64.sve.ld1.nxv8i8(<vscale x 8 x i1> %pred, i8* %addr)
%res = sext <vscale x 8 x i8> %load to <vscale x 8 x i16>
ret <vscale x 8 x i16> %res
}
define <vscale x 4 x i32> @ld1b_s(<vscale x 4 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1b_s:
; CHECK: ld1b { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ld1.nxv4i8(<vscale x 4 x i1> %pred, i8* %addr)
%res = zext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x i32> @ld1sb_s(<vscale x 4 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1sb_s:
; CHECK: ld1sb { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i8> @llvm.aarch64.sve.ld1.nxv4i8(<vscale x 4 x i1> %pred, i8* %addr)
%res = sext <vscale x 4 x i8> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @ld1b_d(<vscale x 2 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1b_d:
; CHECK: ld1b { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ld1.nxv2i8(<vscale x 2 x i1> %pred, i8* %addr)
%res = zext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @ld1sb_d(<vscale x 2 x i1> %pred, i8* %addr) {
; CHECK-LABEL: ld1sb_d:
; CHECK: ld1sb { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ld1.nxv2i8(<vscale x 2 x i1> %pred, i8* %addr)
%res = sext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
;
; LD1H
;
define <vscale x 8 x i16> @ld1h_i16(<vscale x 8 x i1> %pred, i16* %addr) {
; CHECK-LABEL: ld1h_i16:
; CHECK: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.ld1.nxv8i16(<vscale x 8 x i1> %pred, i16* %addr)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x half> @ld1h_f16(<vscale x 8 x i1> %pred, half* %addr) {
; CHECK-LABEL: ld1h_f16:
; CHECK: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.aarch64.sve.ld1.nxv8f16(<vscale x 8 x i1> %pred, half* %addr)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x bfloat> @ld1h_bf16(<vscale x 8 x i1> %pred, bfloat* %addr) #0 {
; CHECK-LABEL: ld1h_bf16:
; CHECK: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1.nxv8bf16(<vscale x 8 x i1> %pred, bfloat* %addr)
ret <vscale x 8 x bfloat> %res
}
define <vscale x 4 x i32> @ld1h_s(<vscale x 4 x i1> %pred, i16* %addr) {
; CHECK-LABEL: ld1h_s:
; CHECK: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ld1.nxv4i16(<vscale x 4 x i1> %pred, i16* %addr)
%res = zext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x i32> @ld1sh_s(<vscale x 4 x i1> %pred, i16* %addr) {
; CHECK-LABEL: ld1sh_s:
; CHECK: ld1sh { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 4 x i16> @llvm.aarch64.sve.ld1.nxv4i16(<vscale x 4 x i1> %pred, i16* %addr)
%res = sext <vscale x 4 x i16> %load to <vscale x 4 x i32>
ret <vscale x 4 x i32> %res
}
define <vscale x 2 x i64> @ld1h_d(<vscale x 2 x i1> %pred, i16* %addr) {
; CHECK-LABEL: ld1h_d:
; CHECK: ld1h { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ld1.nxv2i16(<vscale x 2 x i1> %pred, i16* %addr)
%res = zext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @ld1sh_d(<vscale x 2 x i1> %pred, i16* %addr) {
; CHECK-LABEL: ld1sh_d:
; CHECK: ld1sh { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ld1.nxv2i16(<vscale x 2 x i1> %pred, i16* %addr)
%res = sext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
;
; LD1W
;
define <vscale x 4 x i32> @ld1w_i32(<vscale x 4 x i1> %pred, i32* %addr) {
; CHECK-LABEL: ld1w_i32:
; CHECK: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.ld1.nxv4i32(<vscale x 4 x i1> %pred, i32* %addr)
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x float> @ld1w_f32(<vscale x 4 x i1> %pred, float* %addr) {
; CHECK-LABEL: ld1w_f32:
; CHECK: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.aarch64.sve.ld1.nxv4f32(<vscale x 4 x i1> %pred, float* %addr)
ret <vscale x 4 x float> %res
}
define <vscale x 2 x i64> @ld1w_d(<vscale x 2 x i1> %pred, i32* %addr) {
; CHECK-LABEL: ld1w_d:
; CHECK: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ld1.nxv2i32(<vscale x 2 x i1> %pred, i32* %addr)
%res = zext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @ld1sw_d(<vscale x 2 x i1> %pred, i32* %addr) {
; CHECK-LABEL: ld1sw_d:
; CHECK: ld1sw { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ld1.nxv2i32(<vscale x 2 x i1> %pred, i32* %addr)
%res = sext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
;
; LD1D
;
define <vscale x 2 x i64> @ld1d_i64(<vscale x 2 x i1> %pred, i64* %addr) {
; CHECK-LABEL: ld1d_i64:
; CHECK: ld1d { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.ld1.nxv2i64(<vscale x 2 x i1> %pred,
i64* %addr)
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x double> @ld1d_f64(<vscale x 2 x i1> %pred, double* %addr) {
; CHECK-LABEL: ld1d_f64:
; CHECK: ld1d { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.aarch64.sve.ld1.nxv2f64(<vscale x 2 x i1> %pred,
double* %addr)
ret <vscale x 2 x double> %res
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.ld1.nxv16i8(<vscale x 16 x i1>, i8*)
declare <vscale x 8 x i8> @llvm.aarch64.sve.ld1.nxv8i8(<vscale x 8 x i1>, i8*)
declare <vscale x 8 x i16> @llvm.aarch64.sve.ld1.nxv8i16(<vscale x 8 x i1>, i16*)
declare <vscale x 8 x half> @llvm.aarch64.sve.ld1.nxv8f16(<vscale x 8 x i1>, half*)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1.nxv8bf16(<vscale x 8 x i1>, bfloat*)
declare <vscale x 4 x i8> @llvm.aarch64.sve.ld1.nxv4i8(<vscale x 4 x i1>, i8*)
declare <vscale x 4 x i16> @llvm.aarch64.sve.ld1.nxv4i16(<vscale x 4 x i1>, i16*)
declare <vscale x 4 x i32> @llvm.aarch64.sve.ld1.nxv4i32(<vscale x 4 x i1>, i32*)
declare <vscale x 4 x float> @llvm.aarch64.sve.ld1.nxv4f32(<vscale x 4 x i1>, float*)
declare <vscale x 2 x i8> @llvm.aarch64.sve.ld1.nxv2i8(<vscale x 2 x i1>, i8*)
declare <vscale x 2 x i16> @llvm.aarch64.sve.ld1.nxv2i16(<vscale x 2 x i1>, i16*)
declare <vscale x 2 x i32> @llvm.aarch64.sve.ld1.nxv2i32(<vscale x 2 x i1>, i32*)
declare <vscale x 2 x i64> @llvm.aarch64.sve.ld1.nxv2i64(<vscale x 2 x i1>, i64*)
declare <vscale x 2 x double> @llvm.aarch64.sve.ld1.nxv2f64(<vscale x 2 x i1>, double*)
; +bf16 is required for the bfloat version.
attributes #0 = { "target-features"="+sve,+bf16" }
|
