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
|
// 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 -target-feature +bf16 -msve-vector-bits=128 -fallow-half-arguments-and-returns -S -O1 -emit-llvm -o - %s -fhalf-no-semantic-interposition | FileCheck %s --check-prefix=CHECK-128
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -msve-vector-bits=512 -fallow-half-arguments-and-returns -S -O1 -emit-llvm -o - %s -fhalf-no-semantic-interposition | FileCheck %s --check-prefix=CHECK-512
#include <arm_sve.h>
#define N __ARM_FEATURE_SVE_BITS
typedef svint64_t fixed_int64_t __attribute__((arm_sve_vector_bits(N)));
typedef svbfloat16_t fixed_bfloat16_t __attribute__((arm_sve_vector_bits(N)));
typedef svbool_t fixed_bool_t __attribute__((arm_sve_vector_bits(N)));
fixed_int64_t global_i64;
fixed_bfloat16_t global_bf16;
fixed_bool_t global_bool;
//===----------------------------------------------------------------------===//
// WRITES
//===----------------------------------------------------------------------===//
// CHECK-128-LABEL: @write_global_i64(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[CASTFIXEDSVE:%.*]] = call <2 x i64> @llvm.experimental.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[V:%.*]], i64 0)
// CHECK-128-NEXT: store <2 x i64> [[CASTFIXEDSVE]], <2 x i64>* @global_i64, align 16, !tbaa [[TBAA6:![0-9]+]]
// CHECK-128-NEXT: ret void
//
// CHECK-512-LABEL: @write_global_i64(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[CASTFIXEDSVE:%.*]] = call <8 x i64> @llvm.experimental.vector.extract.v8i64.nxv2i64(<vscale x 2 x i64> [[V:%.*]], i64 0)
// CHECK-512-NEXT: store <8 x i64> [[CASTFIXEDSVE]], <8 x i64>* @global_i64, align 16, !tbaa [[TBAA6:![0-9]+]]
// CHECK-512-NEXT: ret void
//
void write_global_i64(svint64_t v) { global_i64 = v; }
// CHECK-128-LABEL: @write_global_bf16(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[CASTFIXEDSVE:%.*]] = call <8 x bfloat> @llvm.experimental.vector.extract.v8bf16.nxv8bf16(<vscale x 8 x bfloat> [[V:%.*]], i64 0)
// CHECK-128-NEXT: store <8 x bfloat> [[CASTFIXEDSVE]], <8 x bfloat>* @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: ret void
//
// CHECK-512-LABEL: @write_global_bf16(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[CASTFIXEDSVE:%.*]] = call <32 x bfloat> @llvm.experimental.vector.extract.v32bf16.nxv8bf16(<vscale x 8 x bfloat> [[V:%.*]], i64 0)
// CHECK-512-NEXT: store <32 x bfloat> [[CASTFIXEDSVE]], <32 x bfloat>* @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: ret void
//
void write_global_bf16(svbfloat16_t v) { global_bf16 = v; }
// CHECK-128-LABEL: @write_global_bool(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[SAVED_VALUE:%.*]] = alloca <vscale x 16 x i1>, align 16
// CHECK-128-NEXT: store <vscale x 16 x i1> [[V:%.*]], <vscale x 16 x i1>* [[SAVED_VALUE]], align 16, !tbaa [[TBAA9:![0-9]+]]
// CHECK-128-NEXT: [[CASTFIXEDSVE:%.*]] = bitcast <vscale x 16 x i1>* [[SAVED_VALUE]] to <2 x i8>*
// CHECK-128-NEXT: [[TMP0:%.*]] = load <2 x i8>, <2 x i8>* [[CASTFIXEDSVE]], align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: store <2 x i8> [[TMP0]], <2 x i8>* @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-128-NEXT: ret void
//
// CHECK-512-LABEL: @write_global_bool(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[SAVED_VALUE:%.*]] = alloca <vscale x 16 x i1>, align 16
// CHECK-512-NEXT: store <vscale x 16 x i1> [[V:%.*]], <vscale x 16 x i1>* [[SAVED_VALUE]], align 16, !tbaa [[TBAA9:![0-9]+]]
// CHECK-512-NEXT: [[CASTFIXEDSVE:%.*]] = bitcast <vscale x 16 x i1>* [[SAVED_VALUE]] to <8 x i8>*
// CHECK-512-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* [[CASTFIXEDSVE]], align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: store <8 x i8> [[TMP0]], <8 x i8>* @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-512-NEXT: ret void
//
void write_global_bool(svbool_t v) { global_bool = v; }
//===----------------------------------------------------------------------===//
// READS
//===----------------------------------------------------------------------===//
// CHECK-128-LABEL: @read_global_i64(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* @global_i64, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[TMP0]], i64 0)
// CHECK-128-NEXT: ret <vscale x 2 x i64> [[CASTSCALABLESVE]]
//
// CHECK-512-LABEL: @read_global_i64(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[TMP0:%.*]] = load <8 x i64>, <8 x i64>* @global_i64, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: [[CASTSCALABLESVE:%.*]] = call <vscale x 2 x i64> @llvm.experimental.vector.insert.nxv2i64.v8i64(<vscale x 2 x i64> undef, <8 x i64> [[TMP0]], i64 0)
// CHECK-512-NEXT: ret <vscale x 2 x i64> [[CASTSCALABLESVE]]
//
svint64_t read_global_i64() { return global_i64; }
// CHECK-128-LABEL: @read_global_bf16(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[TMP0:%.*]] = load <8 x bfloat>, <8 x bfloat>* @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[TMP0]], i64 0)
// CHECK-128-NEXT: ret <vscale x 8 x bfloat> [[CASTSCALABLESVE]]
//
// CHECK-512-LABEL: @read_global_bf16(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[TMP0:%.*]] = load <32 x bfloat>, <32 x bfloat>* @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: [[CASTSCALABLESVE:%.*]] = call <vscale x 8 x bfloat> @llvm.experimental.vector.insert.nxv8bf16.v32bf16(<vscale x 8 x bfloat> undef, <32 x bfloat> [[TMP0]], i64 0)
// CHECK-512-NEXT: ret <vscale x 8 x bfloat> [[CASTSCALABLESVE]]
//
svbfloat16_t read_global_bf16() { return global_bf16; }
// CHECK-128-LABEL: @read_global_bool(
// CHECK-128-NEXT: entry:
// CHECK-128-NEXT: [[SAVED_VALUE:%.*]] = alloca <2 x i8>, align 16
// CHECK-128-NEXT: [[TMP0:%.*]] = load <2 x i8>, <2 x i8>* @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-128-NEXT: store <2 x i8> [[TMP0]], <2 x i8>* [[SAVED_VALUE]], align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: [[CASTFIXEDSVE:%.*]] = bitcast <2 x i8>* [[SAVED_VALUE]] to <vscale x 16 x i1>*
// CHECK-128-NEXT: [[TMP1:%.*]] = load <vscale x 16 x i1>, <vscale x 16 x i1>* [[CASTFIXEDSVE]], align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT: ret <vscale x 16 x i1> [[TMP1]]
//
// CHECK-512-LABEL: @read_global_bool(
// CHECK-512-NEXT: entry:
// CHECK-512-NEXT: [[SAVED_VALUE:%.*]] = alloca <8 x i8>, align 16
// CHECK-512-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-512-NEXT: store <8 x i8> [[TMP0]], <8 x i8>* [[SAVED_VALUE]], align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: [[CASTFIXEDSVE:%.*]] = bitcast <8 x i8>* [[SAVED_VALUE]] to <vscale x 16 x i1>*
// CHECK-512-NEXT: [[TMP1:%.*]] = load <vscale x 16 x i1>, <vscale x 16 x i1>* [[CASTFIXEDSVE]], align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT: ret <vscale x 16 x i1> [[TMP1]]
//
svbool_t read_global_bool() { return global_bool; }
|
