acle_sve_zip2-fp64.c
4.28 KB
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
// RUN: %clang_cc1 -target-feature +f64mm -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -target-feature +f64mm -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %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
svint8_t test_svzip2_s8(svint8_t op1, svint8_t op2) {
// CHECK-LABEL: test_svzip2_s8
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.zip2q.nxv16i8(<vscale x 16 x i8> %op1, <vscale x 16 x i8> %op2)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _s8, , )(op1, op2);
}
svint16_t test_svzip2_s16(svint16_t op1, svint16_t op2) {
// CHECK-LABEL: test_svzip2_s16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.zip2q.nxv8i16(<vscale x 8 x i16> %op1, <vscale x 8 x i16> %op2)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _s16, , )(op1, op2);
}
svint32_t test_svzip2_s32(svint32_t op1, svint32_t op2) {
// CHECK-LABEL: test_svzip2_s32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.zip2q.nxv4i32(<vscale x 4 x i32> %op1, <vscale x 4 x i32> %op2)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _s32, , )(op1, op2);
}
svint64_t test_svzip2_s64(svint64_t op1, svint64_t op2) {
// CHECK-LABEL: test_svzip2_s64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.zip2q.nxv2i64(<vscale x 2 x i64> %op1, <vscale x 2 x i64> %op2)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _s64, , )(op1, op2);
}
svuint8_t test_svzip2_u8(svuint8_t op1, svuint8_t op2) {
// CHECK-LABEL: test_svzip2_u8
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.zip2q.nxv16i8(<vscale x 16 x i8> %op1, <vscale x 16 x i8> %op2)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _u8, , )(op1, op2);
}
svuint16_t test_svzip2_u16(svuint16_t op1, svuint16_t op2) {
// CHECK-LABEL: test_svzip2_u16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.zip2q.nxv8i16(<vscale x 8 x i16> %op1, <vscale x 8 x i16> %op2)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _u16, , )(op1, op2);
}
svuint32_t test_svzip2_u32(svuint32_t op1, svuint32_t op2) {
// CHECK-LABEL: test_svzip2_u32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.zip2q.nxv4i32(<vscale x 4 x i32> %op1, <vscale x 4 x i32> %op2)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _u32, , )(op1, op2);
}
svuint64_t test_svzip2_u64(svuint64_t op1, svuint64_t op2) {
// CHECK-LABEL: test_svzip2_u64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.zip2q.nxv2i64(<vscale x 2 x i64> %op1, <vscale x 2 x i64> %op2)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _u64, , )(op1, op2);
}
svfloat16_t test_svzip2_f16(svfloat16_t op1, svfloat16_t op2) {
// CHECK-LABEL: test_svzip2_f16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.zip2q.nxv8f16(<vscale x 8 x half> %op1, <vscale x 8 x half> %op2)
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _f16, , )(op1, op2);
}
svfloat32_t test_svzip2_f32(svfloat32_t op1, svfloat32_t op2) {
// CHECK-LABEL: test_svzip2_f32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.zip2q.nxv4f32(<vscale x 4 x float> %op1, <vscale x 4 x float> %op2)
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _f32, , )(op1, op2);
}
svfloat64_t test_svzip2_f64(svfloat64_t op1, svfloat64_t op2) {
// CHECK-LABEL: test_svzip2_f64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.zip2q.nxv2f64(<vscale x 2 x double> %op1, <vscale x 2 x double> %op2)
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svzip2q, _f64, , )(op1, op2);
}