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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -S -disable-O0-optnone -Werror -Wall -emit-llvm -o - -x c++ %s | opt -S -passes=mem2reg,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
#include <arm_sve.h>
#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif
// NOTE: For these tests clang converts the struct parameter into
// several parameters, one for each member of the original struct.
// CHECK-LABEL: @test_svget4_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.extract.nxv16i8.nxv64i8(<vscale x 64 x i8> [[TUPLE:%.*]], i64 0)
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z14test_svget4_s810svint8x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.extract.nxv16i8.nxv64i8(<vscale x 64 x i8> [[TUPLE:%.*]], i64 0)
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svget4_s8(svint8x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_s8,,)(tuple, 0);
}
// CHECK-LABEL: @test_svget4_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv32i16(<vscale x 32 x i16> [[TUPLE:%.*]], i64 16)
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_s1611svint16x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv32i16(<vscale x 32 x i16> [[TUPLE:%.*]], i64 16)
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svint16_t test_svget4_s16(svint16x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_s16,,)(tuple, 2);
}
// CHECK-LABEL: @test_svget4_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> [[TUPLE:%.*]], i64 8)
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_s3211svint32x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> [[TUPLE:%.*]], i64 8)
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svint32_t test_svget4_s32(svint32x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_s32,,)(tuple, 2);
}
// CHECK-LABEL: @test_svget4_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.extract.nxv2i64.nxv8i64(<vscale x 8 x i64> [[TUPLE:%.*]], i64 6)
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_s6411svint64x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.extract.nxv2i64.nxv8i64(<vscale x 8 x i64> [[TUPLE:%.*]], i64 6)
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svint64_t test_svget4_s64(svint64x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_s64,,)(tuple, 3);
}
// CHECK-LABEL: @test_svget4_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.extract.nxv16i8.nxv64i8(<vscale x 64 x i8> [[TUPLE:%.*]], i64 32)
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z14test_svget4_u811svuint8x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.extract.nxv16i8.nxv64i8(<vscale x 64 x i8> [[TUPLE:%.*]], i64 32)
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svget4_u8(svuint8x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_u8,,)(tuple, 2);
}
// CHECK-LABEL: @test_svget4_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv32i16(<vscale x 32 x i16> [[TUPLE:%.*]], i64 24)
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_u1612svuint16x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.extract.nxv8i16.nxv32i16(<vscale x 32 x i16> [[TUPLE:%.*]], i64 24)
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP0]]
//
svuint16_t test_svget4_u16(svuint16x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_u16,,)(tuple, 3);
}
// CHECK-LABEL: @test_svget4_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> [[TUPLE:%.*]], i64 0)
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_u3212svuint32x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> [[TUPLE:%.*]], i64 0)
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP0]]
//
svuint32_t test_svget4_u32(svuint32x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_u32,,)(tuple, 0);
}
// CHECK-LABEL: @test_svget4_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.extract.nxv2i64.nxv8i64(<vscale x 8 x i64> [[TUPLE:%.*]], i64 6)
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_u6412svuint64x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.extract.nxv2i64.nxv8i64(<vscale x 8 x i64> [[TUPLE:%.*]], i64 6)
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP0]]
//
svuint64_t test_svget4_u64(svuint64x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_u64,,)(tuple, 3);
}
// CHECK-LABEL: @test_svget4_f16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.vector.extract.nxv8f16.nxv32f16(<vscale x 32 x half> [[TUPLE:%.*]], i64 16)
// CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_f1613svfloat16x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.vector.extract.nxv8f16.nxv32f16(<vscale x 32 x half> [[TUPLE:%.*]], i64 16)
// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
//
svfloat16_t test_svget4_f16(svfloat16x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_f16,,)(tuple, 2);
}
// CHECK-LABEL: @test_svget4_f32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv16f32(<vscale x 16 x float> [[TUPLE:%.*]], i64 0)
// CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_f3213svfloat32x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv16f32(<vscale x 16 x float> [[TUPLE:%.*]], i64 0)
// CPP-CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
//
svfloat32_t test_svget4_f32(svfloat32x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_f32,,)(tuple, 0);
}
// CHECK-LABEL: @test_svget4_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.vector.extract.nxv2f64.nxv8f64(<vscale x 8 x double> [[TUPLE:%.*]], i64 4)
// CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svget4_f6413svfloat64x4_t(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.vector.extract.nxv2f64.nxv8f64(<vscale x 8 x double> [[TUPLE:%.*]], i64 4)
// CPP-CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
//
svfloat64_t test_svget4_f64(svfloat64x4_t tuple)
{
return SVE_ACLE_FUNC(svget4,_f64,,)(tuple, 2);
}
|
