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
| // RUN: %clang_cc1 -triple thumbv7-apple-darwin \
// RUN: -target-abi apcs-gnu \
// RUN: -target-cpu cortex-a8 \
// RUN: -mfloat-abi soft \
// RUN: -target-feature +soft-float-abi \
// RUN: -ffreestanding \
// RUN: -disable-O0-optnone -emit-llvm -w -o - %s | opt -S -mem2reg | FileCheck %s
#include <arm_neon.h>
// Check that the vget_low/vget_high intrinsics generate a single shuffle
// without any bitcasting.
int8x8_t low_s8(int8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return vget_low_s8(a);
}
uint8x8_t low_u8 (uint8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return vget_low_u8(a);
}
int16x4_t low_s16( int16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
return vget_low_s16(a);
}
uint16x4_t low_u16(uint16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
return vget_low_u16(a);
}
int32x2_t low_s32( int32x4_t a) {
// CHECK: shufflevector <4 x i32> %a, <4 x i32> %a, <2 x i32> <i32 0, i32 1>
return vget_low_s32(a);
}
uint32x2_t low_u32(uint32x4_t a) {
// CHECK: shufflevector <4 x i32> %a, <4 x i32> %a, <2 x i32> <i32 0, i32 1>
return vget_low_u32(a);
}
int64x1_t low_s64( int64x2_t a) {
// CHECK: shufflevector <2 x i64> %a, <2 x i64> %a, <1 x i32> zeroinitializer
return vget_low_s64(a);
}
uint64x1_t low_u64(uint64x2_t a) {
// CHECK: shufflevector <2 x i64> %a, <2 x i64> %a, <1 x i32> zeroinitializer
return vget_low_u64(a);
}
poly8x8_t low_p8 (poly8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return vget_low_p8(a);
}
poly16x4_t low_p16(poly16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
return vget_low_p16(a);
}
float32x2_t low_f32(float32x4_t a) {
// CHECK: shufflevector <4 x float> %a, <4 x float> %a, <2 x i32> <i32 0, i32 1>
return vget_low_f32(a);
}
int8x8_t high_s8(int8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
return vget_high_s8(a);
}
uint8x8_t high_u8 (uint8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
return vget_high_u8(a);
}
int16x4_t high_s16( int16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
return vget_high_s16(a);
}
uint16x4_t high_u16(uint16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
return vget_high_u16(a);
}
int32x2_t high_s32( int32x4_t a) {
// CHECK: shufflevector <4 x i32> %a, <4 x i32> %a, <2 x i32> <i32 2, i32 3>
return vget_high_s32(a);
}
uint32x2_t high_u32(uint32x4_t a) {
// CHECK: shufflevector <4 x i32> %a, <4 x i32> %a, <2 x i32> <i32 2, i32 3>
return vget_high_u32(a);
}
int64x1_t high_s64( int64x2_t a) {
// CHECK: shufflevector <2 x i64> %a, <2 x i64> %a, <1 x i32> <i32 1>
return vget_high_s64(a);
}
uint64x1_t high_u64(uint64x2_t a) {
// CHECK: shufflevector <2 x i64> %a, <2 x i64> %a, <1 x i32> <i32 1>
return vget_high_u64(a);
}
poly8x8_t high_p8 (poly8x16_t a) {
// CHECK: shufflevector <16 x i8> %a, <16 x i8> %a, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
return vget_high_p8(a);
}
poly16x4_t high_p16(poly16x8_t a) {
// CHECK: shufflevector <8 x i16> %a, <8 x i16> %a, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
return vget_high_p16(a);
}
float32x2_t high_f32(float32x4_t a) {
// CHECK: shufflevector <4 x float> %a, <4 x float> %a, <2 x i32> <i32 2, i32 3>
return vget_high_f32(a);
}
|