blob: db6d7b957aa428ee5a4c02426421d7ef246d2fd0 [file] [log] [blame]
Michalis Spyroua6825a42018-09-13 12:24:03 +01001/*
2 * Copyright (c) 2018 ARM Limited.
3 *
4 * SPDX-License-Identifier: MIT
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to
8 * deal in the Software without restriction, including without limitation the
9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10 * sell copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in all
14 * copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24#ifndef __ARM_COMPUTE_WRAPPER_MLA_H__
25#define __ARM_COMPUTE_WRAPPER_MLA_H__
26
27#include <arm_neon.h>
28
29namespace arm_compute
30{
31namespace wrapper
32{
33#define VMLA_IMPL(stype, vtype, prefix, postfix) \
34 inline vtype vmla(const vtype &a, const vtype &b, const vtype &c) \
35 { \
36 return prefix##_##postfix(a, b, c); \
37 }
Michalis Spyrou0c71d0b2018-11-22 11:22:18 +000038#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
39#define VMLA_IMPL2(stype, vtype, prefix1, prefix2, postfix) \
40 inline vtype vmla(const vtype &a, const vtype &b, const vtype &c) \
41 { \
42 return prefix1##_##postfix(a, prefix2##_##postfix(b, c)); \
43 }
44#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
Michalis Spyroua6825a42018-09-13 12:24:03 +010045
46VMLA_IMPL(uint8x8_t, uint8x8_t, vmla, u8)
47VMLA_IMPL(int8x8_t, int8x8_t, vmla, s8)
48VMLA_IMPL(uint16x4_t, uint16x4_t, vmla, u16)
49VMLA_IMPL(int16x4_t, int16x4_t, vmla, s16)
50VMLA_IMPL(uint32x2_t, uint32x2_t, vmla, u32)
51VMLA_IMPL(int32x2_t, int32x2_t, vmla, s32)
52VMLA_IMPL(float32x2_t, float32x2_t, vmla, f32)
Michalis Spyrou0c71d0b2018-11-22 11:22:18 +000053#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
54VMLA_IMPL2(float16x4_t, float16x4_t, vadd, vmul, f16)
55#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
Michalis Spyroua6825a42018-09-13 12:24:03 +010056
57VMLA_IMPL(uint8x16_t, uint8x16_t, vmlaq, u8)
58VMLA_IMPL(int8x16_t, int8x16_t, vmlaq, s8)
59VMLA_IMPL(uint16x8_t, uint16x8_t, vmlaq, u16)
60VMLA_IMPL(int16x8_t, int16x8_t, vmlaq, s16)
61VMLA_IMPL(uint32x4_t, uint32x4_t, vmlaq, u32)
62VMLA_IMPL(int32x4_t, int32x4_t, vmlaq, s32)
63VMLA_IMPL(float32x4_t, float32x4_t, vmlaq, f32)
Michalis Spyrou0c71d0b2018-11-22 11:22:18 +000064#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
65VMLA_IMPL2(float16x8_t, float16x8_t, vaddq, vmulq, f16)
66#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
Michalis Spyroua6825a42018-09-13 12:24:03 +010067
68#undef VMLA_IMPL
69} // namespace wrapper
70} // namespace arm_compute
71#endif /* __ARM_COMPUTE_WRAPPER_MLA_H__ */