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
|
// RUN: %clang_cc1 -O1 -triple x86_64 %s -emit-llvm -disable-llvm-passes -o - | FileCheck --check-prefixes=CHECK %s
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -O1 -triple aarch64 -target-feature +neon %s -emit-llvm -disable-llvm-passes -o - | FileCheck --check-prefixes=CHECK,NEON %s
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -O1 -triple aarch64 -target-feature +sve %s -emit-llvm -disable-llvm-passes -o - | FileCheck --check-prefixes=CHECK,SVE %s
// REQUIRES: riscv-registered-target
// RUN: %clang_cc1 -O1 -triple riscv64 -target-feature +v %s -emit-llvm -disable-llvm-passes -o - | FileCheck --check-prefixes=CHECK,RISCV %s
/// Note that this does not make sense to check for x86 SIMD types, because
/// __m128i, __m256i, and __m512i do not specify the element type. There are no
/// "logical" number of elements in them.
typedef int int1 __attribute__((vector_size(4)));
typedef int int4 __attribute__((vector_size(16)));
typedef int int8 __attribute__((vector_size(32)));
typedef int int16 __attribute__((vector_size(64)));
typedef float float2 __attribute__((vector_size(8)));
typedef long extLong4 __attribute__((ext_vector_type(4)));
int test_builtin_vectorelements_int1() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_int1(
// CHECK: ret i32 1
return __builtin_vectorelements(int1);
}
int test_builtin_vectorelements_int4() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_int4(
// CHECK: ret i32 4
return __builtin_vectorelements(int4);
}
int test_builtin_vectorelements_int8() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_int8(
// CHECK: ret i32 8
return __builtin_vectorelements(int8);
}
int test_builtin_vectorelements_int16() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_int16(
// CHECK: ret i32 16
return __builtin_vectorelements(int16);
}
int test_builtin_vectorelements_float2() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_float2(
// CHECK: ret i32 2
return __builtin_vectorelements(float2);
}
int test_builtin_vectorelements_extLong4() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_extLong4(
// CHECK: ret i32 4
return __builtin_vectorelements(extLong4);
}
int test_builtin_vectorelements_multiply_constant() {
// CHECK-LABEL: i32 @test_builtin_vectorelements_multiply_constant(
// CHECK: ret i32 32
return __builtin_vectorelements(int16) * 2;
}
#if defined(__ARM_NEON)
#include <arm_neon.h>
int test_builtin_vectorelements_neon32x4() {
// NEON: i32 @test_builtin_vectorelements_neon32x4(
// NEON: ret i32 4
return __builtin_vectorelements(uint32x4_t);
}
int test_builtin_vectorelements_neon64x1() {
// NEON: i32 @test_builtin_vectorelements_neon64x1(
// NEON: ret i32 1
return __builtin_vectorelements(uint64x1_t);
}
#endif
#if defined(__ARM_FEATURE_SVE)
#include <arm_sve.h>
long test_builtin_vectorelements_sve32() {
// SVE: i64 @test_builtin_vectorelements_sve32(
// SVE: [[VSCALE:%.+]] = call i64 @llvm.vscale.i64()
// SVE: [[RES:%.+]] = mul i64 [[VSCALE]], 4
// SVE: ret i64 [[RES]]
return __builtin_vectorelements(svuint32_t);
}
long test_builtin_vectorelements_sve8() {
// SVE: i64 @test_builtin_vectorelements_sve8(
// SVE: [[VSCALE:%.+]] = call i64 @llvm.vscale.i64()
// SVE: [[RES:%.+]] = mul i64 [[VSCALE]], 16
// SVE: ret i64 [[RES]]
return __builtin_vectorelements(svuint8_t);
}
#endif
#if defined(__riscv)
#include <riscv_vector.h>
long test_builtin_vectorelements_riscv8() {
// RISCV: i64 @test_builtin_vectorelements_riscv8(
// RISCV: [[VSCALE:%.+]] = call i64 @llvm.vscale.i64()
// RISCV: [[RES:%.+]] = mul i64 [[VSCALE]], 8
// RISCV: ret i64 [[RES]]
return __builtin_vectorelements(vuint8m1_t);
}
long test_builtin_vectorelements_riscv64() {
// RISCV: i64 @test_builtin_vectorelements_riscv64(
// RISCV: [[VSCALE:%.+]] = call i64 @llvm.vscale.i64()
// RISCV: ret i64 [[VSCALE]]
return __builtin_vectorelements(vuint64m1_t);
}
long test_builtin_vectorelements_riscv32m2() {
// RISCV: i64 @test_builtin_vectorelements_riscv32m2(
// RISCV: [[VSCALE:%.+]] = call i64 @llvm.vscale.i64()
// RISCV: [[RES:%.+]] = mul i64 [[VSCALE]], 4
// RISCV: ret i64 [[RES]]
return __builtin_vectorelements(vuint32m2_t);
}
#endif
|
