vmulq.c
6.97 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
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
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
#include <arm_mve.h>
// CHECK-LABEL: @test_vmulq_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = mul <16 x i8> [[A:%.*]], [[B:%.*]]
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t test_vmulq_u8(uint8x16_t a, uint8x16_t b)
{
#ifdef POLYMORPHIC
return vmulq(a, b);
#else /* POLYMORPHIC */
return vmulq_u8(a, b);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = mul <8 x i16> [[A:%.*]], [[B:%.*]]
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t test_vmulq_s16(int16x8_t a, int16x8_t b)
{
#ifdef POLYMORPHIC
return vmulq(a, b);
#else /* POLYMORPHIC */
return vmulq_s16(a, b);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = mul <4 x i32> [[A:%.*]], [[B:%.*]]
// CHECK-NEXT: ret <4 x i32> [[TMP0]]
//
uint32x4_t test_vmulq_u32(uint32x4_t a, uint32x4_t b)
{
#ifdef POLYMORPHIC
return vmulq(a, b);
#else /* POLYMORPHIC */
return vmulq_u32(a, b);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_f32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = fmul <4 x float> [[A:%.*]], [[B:%.*]]
// CHECK-NEXT: ret <4 x float> [[TMP0]]
//
float32x4_t test_vmulq_f32(float32x4_t a, float32x4_t b)
{
#ifdef POLYMORPHIC
return vmulq(a, b);
#else /* POLYMORPHIC */
return vmulq_f32(a, b);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_m_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.mul.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t test_vmulq_m_s8(int8x16_t inactive, int8x16_t a, int8x16_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_m(inactive, a, b, p);
#else /* POLYMORPHIC */
return vmulq_m_s8(inactive, a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_m_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mul.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t test_vmulq_m_u16(uint16x8_t inactive, uint16x8_t a, uint16x8_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_m(inactive, a, b, p);
#else /* POLYMORPHIC */
return vmulq_m_u16(inactive, a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_m_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.mul.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
int32x4_t test_vmulq_m_s32(int32x4_t inactive, int32x4_t a, int32x4_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_m(inactive, a, b, p);
#else /* POLYMORPHIC */
return vmulq_m_s32(inactive, a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_m_f16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x half> @llvm.arm.mve.mul.predicated.v8f16.v8i1(<8 x half> [[A:%.*]], <8 x half> [[B:%.*]], <8 x i1> [[TMP1]], <8 x half> [[INACTIVE:%.*]])
// CHECK-NEXT: ret <8 x half> [[TMP2]]
//
float16x8_t test_vmulq_m_f16(float16x8_t inactive, float16x8_t a, float16x8_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_m(inactive, a, b, p);
#else /* POLYMORPHIC */
return vmulq_m_f16(inactive, a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_x_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.mul.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> undef)
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t test_vmulq_x_u8(uint8x16_t a, uint8x16_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_x(a, b, p);
#else /* POLYMORPHIC */
return vmulq_x_u8(a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_x_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.mul.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> undef)
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t test_vmulq_x_s16(int16x8_t a, int16x8_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_x(a, b, p);
#else /* POLYMORPHIC */
return vmulq_x_s16(a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_x_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.mul.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> undef)
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
uint32x4_t test_vmulq_x_u32(uint32x4_t a, uint32x4_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_x(a, b, p);
#else /* POLYMORPHIC */
return vmulq_x_u32(a, b, p);
#endif /* POLYMORPHIC */
}
// CHECK-LABEL: @test_vmulq_m_f32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x float> @llvm.arm.mve.mul.predicated.v4f32.v4i1(<4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x i1> [[TMP1]], <4 x float> undef)
// CHECK-NEXT: ret <4 x float> [[TMP2]]
//
float32x4_t test_vmulq_m_f32(float32x4_t a, float32x4_t b, mve_pred16_t p)
{
#ifdef POLYMORPHIC
return vmulq_x(a, b, p);
#else /* POLYMORPHIC */
return vmulq_x_f32(a, b, p);
#endif /* POLYMORPHIC */
}