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
|
// 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
// CHECK-LABEL: @test_svld1rq_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1rq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svld1rq_s8u10__SVBool_tPKa(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1rq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svint8_t test_svld1rq_s8(svbool_t pg, const int8_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_s8,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1rq.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_s16u10__SVBool_tPKs(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1rq.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
//
svint16_t test_svld1rq_s16(svbool_t pg, const int16_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_s16,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1rq.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_s32u10__SVBool_tPKi(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1rq.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
//
svint32_t test_svld1rq_s32(svbool_t pg, const int32_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_s32,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_s64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1rq.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_s64u10__SVBool_tPKl(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1rq.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
//
svint64_t test_svld1rq_s64(svbool_t pg, const int64_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_s64,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1rq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z15test_svld1rq_u8u10__SVBool_tPKh(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1rq.nxv16i8(<vscale x 16 x i1> [[PG:%.*]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 16 x i8> [[TMP0]]
//
svuint8_t test_svld1rq_u8(svbool_t pg, const uint8_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_u8,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1rq.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_u16u10__SVBool_tPKt(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1rq.nxv8i16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
//
svuint16_t test_svld1rq_u16(svbool_t pg, const uint16_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_u16,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1rq.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_u32u10__SVBool_tPKj(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1rq.nxv4i32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]]
//
svuint32_t test_svld1rq_u32(svbool_t pg, const uint32_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_u32,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_u64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1rq.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_u64u10__SVBool_tPKm(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1rq.nxv2i64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x i64> [[TMP1]]
//
svuint64_t test_svld1rq_u64(svbool_t pg, const uint64_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_u64,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_f16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1rq.nxv8f16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_f16u10__SVBool_tPKDh(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1rq.nxv8f16(<vscale x 8 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svld1rq_f16(svbool_t pg, const float16_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_f16,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_f32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1rq.nxv4f32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_f32u10__SVBool_tPKf(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1rq.nxv4f32(<vscale x 4 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svld1rq_f32(svbool_t pg, const float32_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_f32,,)(pg, base);
}
// CHECK-LABEL: @test_svld1rq_f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1rq.nxv2f64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z16test_svld1rq_f64u10__SVBool_tPKd(
// CPP-CHECK-NEXT: entry:
// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1rq.nxv2f64(<vscale x 2 x i1> [[TMP0]], ptr [[BASE:%.*]])
// CPP-CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svld1rq_f64(svbool_t pg, const float64_t *base)
{
return SVE_ACLE_FUNC(svld1rq,_f64,,)(pg, base);
}
|
