1 /* 2 * Copyright (c) 2018-2020 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_MUL_H 25 #define ARM_COMPUTE_WRAPPER_MUL_H 26 27 #include <arm_neon.h> 28 29 namespace arm_compute 30 { 31 namespace wrapper 32 { 33 #define VMUL_IMPL(stype, vtype, prefix, postfix) \ 34 inline vtype vmul(const vtype &a, const vtype &b) \ 35 { \ 36 return prefix##_##postfix(a, b); \ 37 } 38 39 VMUL_IMPL(uint8x8_t, uint8x8_t, vmul, u8) 40 VMUL_IMPL(int8x8_t, int8x8_t, vmul, s8) 41 VMUL_IMPL(uint16x4_t, uint16x4_t, vmul, u16) 42 VMUL_IMPL(int16x4_t, int16x4_t, vmul, s16) 43 VMUL_IMPL(uint32x2_t, uint32x2_t, vmul, u32) 44 VMUL_IMPL(int32x2_t, int32x2_t, vmul, s32) 45 VMUL_IMPL(float32x2_t, float32x2_t, vmul, f32) 46 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 47 VMUL_IMPL(float16_t, float16x4_t, vmul, f16) 48 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 49 50 VMUL_IMPL(uint8_t, uint8x16_t, vmulq, u8) 51 VMUL_IMPL(int8_t, int8x16_t, vmulq, s8) 52 VMUL_IMPL(uint16_t, uint16x8_t, vmulq, u16) 53 VMUL_IMPL(int16_t, int16x8_t, vmulq, s16) 54 VMUL_IMPL(uint32_t, uint32x4_t, vmulq, u32) 55 VMUL_IMPL(int32_t, int32x4_t, vmulq, s32) 56 VMUL_IMPL(float32x4_t, float32x4_t, vmulq, f32) 57 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 58 VMUL_IMPL(float16_t, float16x8_t, vmulq, f16) 59 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 60 61 #undef VMUL_IMPL 62 } // namespace wrapper 63 } // namespace arm_compute 64 #endif /* ARM_COMPUTE_WRAPPER_MUL_H */ 65