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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple riscv64-none-linux-gnu -target-feature +f -target-feature +d -target-feature +zve64d -mvscale-min=1 -mvscale-max=1 -O1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-64
// RUN: %clang_cc1 -triple riscv64-none-linux-gnu -target-feature +f -target-feature +d -target-feature +zve64d -mvscale-min=2 -mvscale-max=2 -O1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-128
// RUN: %clang_cc1 -triple riscv64-none-linux-gnu -target-feature +f -target-feature +d -target-feature +zve64d -mvscale-min=4 -mvscale-max=4 -O1 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-256
// REQUIRES: riscv-registered-target
#include <stdint.h>
typedef __rvv_int8m1_t vint8m1_t;
typedef __rvv_uint8m1_t vuint8m1_t;
typedef __rvv_int16m1_t vint16m1_t;
typedef __rvv_uint16m1_t vuint16m1_t;
typedef __rvv_int32m1_t vint32m1_t;
typedef __rvv_uint32m1_t vuint32m1_t;
typedef __rvv_int64m1_t vint64m1_t;
typedef __rvv_uint64m1_t vuint64m1_t;
typedef __rvv_float32m1_t vfloat32m1_t;
typedef __rvv_float64m1_t vfloat64m1_t;
typedef __rvv_bool1_t vbool1_t;
typedef __rvv_bool2_t vbool2_t;
typedef __rvv_bool4_t vbool4_t;
typedef __rvv_bool8_t vbool8_t;
typedef __rvv_bool16_t vbool16_t;
typedef __rvv_bool32_t vbool32_t;
typedef __rvv_bool64_t vbool64_t;
typedef vint64m1_t fixed_int64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vfloat64m1_t fixed_float64m1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vbool1_t fixed_bool1_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen)));
typedef vbool2_t fixed_bool2_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 2)));
typedef vbool4_t fixed_bool4_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 4)));
typedef vbool8_t fixed_bool8_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 8)));
#if __riscv_v_fixed_vlen >= 128
typedef vbool16_t fixed_bool16_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 16)));
#endif
#if __riscv_v_fixed_vlen >= 256
typedef vbool32_t fixed_bool32_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 32)));
#endif
#if __riscv_v_fixed_vlen >= 512
typedef vbool64_t fixed_bool64_t __attribute__((riscv_rvv_vector_bits(__riscv_v_fixed_vlen / 64)));
#endif
#define DEFINE_STRUCT(ty) \
struct struct_##ty { \
fixed_##ty##_t x, y[3]; \
} struct_##ty;
DEFINE_STRUCT(int64m1)
DEFINE_STRUCT(float64m1)
DEFINE_STRUCT(bool1)
DEFINE_STRUCT(bool2)
DEFINE_STRUCT(bool4)
DEFINE_STRUCT(bool8)
#if __riscv_v_fixed_vlen >= 128
DEFINE_STRUCT(bool16)
#endif
#if __riscv_v_fixed_vlen >= 256
DEFINE_STRUCT(bool32)
#endif
#if __riscv_v_fixed_vlen >= 512
DEFINE_STRUCT(bool64)
#endif
//===----------------------------------------------------------------------===//
// int64
//===----------------------------------------------------------------------===//
// CHECK-64-LABEL: @read_int64m1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: [[TMP0:%.*]] = load <1 x i64>, ptr [[Y]], align 8, !tbaa [[TBAA4:![0-9]+]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v1i64(<vscale x 1 x i64> undef, <1 x i64> [[TMP0]], i64 0)
// CHECK-64-NEXT: ret <vscale x 1 x i64> [[CAST_SCALABLE]]
//
// CHECK-128-LABEL: @read_int64m1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: [[TMP0:%.*]] = load <2 x i64>, ptr [[Y]], align 8, !tbaa [[TBAA4:![0-9]+]]
// CHECK-128-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v2i64(<vscale x 1 x i64> undef, <2 x i64> [[TMP0]], i64 0)
// CHECK-128-NEXT: ret <vscale x 1 x i64> [[CAST_SCALABLE]]
//
// CHECK-256-LABEL: @read_int64m1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: [[TMP0:%.*]] = load <4 x i64>, ptr [[Y]], align 8, !tbaa [[TBAA4:![0-9]+]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x i64> @llvm.vector.insert.nxv1i64.v4i64(<vscale x 1 x i64> undef, <4 x i64> [[TMP0]], i64 0)
// CHECK-256-NEXT: ret <vscale x 1 x i64> [[CAST_SCALABLE]]
//
vint64m1_t read_int64m1(struct struct_int64m1 *s) {
return s->y[0];
}
// CHECK-64-LABEL: @write_int64m1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <1 x i64> @llvm.vector.extract.v1i64.nxv1i64(<vscale x 1 x i64> [[X:%.*]], i64 0)
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: store <1 x i64> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: ret void
//
// CHECK-128-LABEL: @write_int64m1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[CAST_FIXED:%.*]] = tail call <2 x i64> @llvm.vector.extract.v2i64.nxv1i64(<vscale x 1 x i64> [[X:%.*]], i64 0)
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: store <2 x i64> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-128-NEXT: ret void
//
// CHECK-256-LABEL: @write_int64m1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <4 x i64> @llvm.vector.extract.v4i64.nxv1i64(<vscale x 1 x i64> [[X:%.*]], i64 0)
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: store <4 x i64> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_int64m1(struct struct_int64m1 *s, vint64m1_t x) {
s->y[0] = x;
}
//===----------------------------------------------------------------------===//
// float64
//===----------------------------------------------------------------------===//
// CHECK-64-LABEL: @read_float64m1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: [[TMP0:%.*]] = load <1 x double>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x double> @llvm.vector.insert.nxv1f64.v1f64(<vscale x 1 x double> undef, <1 x double> [[TMP0]], i64 0)
// CHECK-64-NEXT: ret <vscale x 1 x double> [[CAST_SCALABLE]]
//
// CHECK-128-LABEL: @read_float64m1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-128-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x double> @llvm.vector.insert.nxv1f64.v2f64(<vscale x 1 x double> undef, <2 x double> [[TMP0]], i64 0)
// CHECK-128-NEXT: ret <vscale x 1 x double> [[CAST_SCALABLE]]
//
// CHECK-256-LABEL: @read_float64m1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: [[TMP0:%.*]] = load <4 x double>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 1 x double> @llvm.vector.insert.nxv1f64.v4f64(<vscale x 1 x double> undef, <4 x double> [[TMP0]], i64 0)
// CHECK-256-NEXT: ret <vscale x 1 x double> [[CAST_SCALABLE]]
//
vfloat64m1_t read_float64m1(struct struct_float64m1 *s) {
return s->y[0];
}
// CHECK-64-LABEL: @write_float64m1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <1 x double> @llvm.vector.extract.v1f64.nxv1f64(<vscale x 1 x double> [[X:%.*]], i64 0)
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: store <1 x double> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: ret void
//
// CHECK-128-LABEL: @write_float64m1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[CAST_FIXED:%.*]] = tail call <2 x double> @llvm.vector.extract.v2f64.nxv1f64(<vscale x 1 x double> [[X:%.*]], i64 0)
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: store <2 x double> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-128-NEXT: ret void
//
// CHECK-256-LABEL: @write_float64m1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <4 x double> @llvm.vector.extract.v4f64.nxv1f64(<vscale x 1 x double> [[X:%.*]], i64 0)
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: store <4 x double> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_float64m1(struct struct_float64m1 *s, vfloat64m1_t x) {
s->y[0] = x;
}
//===----------------------------------------------------------------------===//
// bool
//===----------------------------------------------------------------------===//
// CHECK-64-LABEL: @read_bool1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: [[TMP0:%.*]] = load <8 x i8>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v8i8(<vscale x 8 x i8> undef, <8 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: [[TMP1:%.*]] = bitcast <vscale x 8 x i8> [[CAST_SCALABLE]] to <vscale x 64 x i1>
// CHECK-64-NEXT: ret <vscale x 64 x i1> [[TMP1]]
//
// CHECK-128-LABEL: @read_bool1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: [[TMP0:%.*]] = load <16 x i8>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-128-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v16i8(<vscale x 8 x i8> undef, <16 x i8> [[TMP0]], i64 0)
// CHECK-128-NEXT: [[TMP1:%.*]] = bitcast <vscale x 8 x i8> [[CAST_SCALABLE]] to <vscale x 64 x i1>
// CHECK-128-NEXT: ret <vscale x 64 x i1> [[TMP1]]
//
// CHECK-256-LABEL: @read_bool1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: [[TMP0:%.*]] = load <32 x i8>, ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: [[CAST_SCALABLE:%.*]] = tail call <vscale x 8 x i8> @llvm.vector.insert.nxv8i8.v32i8(<vscale x 8 x i8> undef, <32 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: [[TMP1:%.*]] = bitcast <vscale x 8 x i8> [[CAST_SCALABLE]] to <vscale x 64 x i1>
// CHECK-256-NEXT: ret <vscale x 64 x i1> [[TMP1]]
//
vbool1_t read_bool1(struct struct_bool1 *s) {
return s->y[0];
}
// CHECK-64-LABEL: @write_bool1(
// CHECK-64-NEXT: entry:
// CHECK-64-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i1> [[X:%.*]] to <vscale x 8 x i8>
// CHECK-64-NEXT: [[CAST_FIXED:%.*]] = tail call <8 x i8> @llvm.vector.extract.v8i8.nxv8i8(<vscale x 8 x i8> [[TMP0]], i64 0)
// CHECK-64-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 8
// CHECK-64-NEXT: store <8 x i8> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-64-NEXT: ret void
//
// CHECK-128-LABEL: @write_bool1(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i1> [[X:%.*]] to <vscale x 8 x i8>
// CHECK-128-NEXT: [[CAST_FIXED:%.*]] = tail call <16 x i8> @llvm.vector.extract.v16i8.nxv8i8(<vscale x 8 x i8> [[TMP0]], i64 0)
// CHECK-128-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 16
// CHECK-128-NEXT: store <16 x i8> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-128-NEXT: ret void
//
// CHECK-256-LABEL: @write_bool1(
// CHECK-256-NEXT: entry:
// CHECK-256-NEXT: [[TMP0:%.*]] = bitcast <vscale x 64 x i1> [[X:%.*]] to <vscale x 8 x i8>
// CHECK-256-NEXT: [[CAST_FIXED:%.*]] = tail call <32 x i8> @llvm.vector.extract.v32i8.nxv8i8(<vscale x 8 x i8> [[TMP0]], i64 0)
// CHECK-256-NEXT: [[Y:%.*]] = getelementptr inbounds i8, ptr [[S:%.*]], i64 32
// CHECK-256-NEXT: store <32 x i8> [[CAST_FIXED]], ptr [[Y]], align 8, !tbaa [[TBAA4]]
// CHECK-256-NEXT: ret void
//
void write_bool1(struct struct_bool1 *s, vbool1_t x) {
s->y[0] = x;
}
|
