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_INVSQRT_H 25 #define ARM_COMPUTE_WRAPPER_INVSQRT_H 26 27 #include "src/core/NEON/NEMath.h" 28 #include <arm_neon.h> 29 30 namespace arm_compute 31 { 32 namespace wrapper 33 { 34 #define VINVSQRT_IMPL(stype, vtype, prefix, postfix) \ 35 inline vtype vinvsqrt(const vtype &a) \ 36 { \ 37 return prefix##_##postfix(a); \ 38 } 39 40 #define VINVSQRT_IMPL_INT(stype, vtype, prefix, postfix) \ 41 inline vtype vinvsqrt(const vtype &a) \ 42 { \ 43 ARM_COMPUTE_UNUSED(a); \ 44 ARM_COMPUTE_ERROR("Not supported"); \ 45 } 46 47 VINVSQRT_IMPL(float, float32x2_t, vinvsqrt, f32) 48 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 49 VINVSQRT_IMPL(float16_t, float16x4_t, vinvsqrt, f16) 50 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 51 VINVSQRT_IMPL_INT(int, int32x4_t, vinvsqrt, s32) 52 53 VINVSQRT_IMPL(float, float32x4_t, vinvsqrtq, f32) 54 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 55 VINVSQRT_IMPL(float16_t, float16x8_t, vinvsqrtq, f16) 56 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 57 58 #undef VINVSQRT_IMPL 59 } // namespace wrapper 60 } // namespace arm_compute 61 #endif /* ARM_COMPUTE_WRAPPER_INVSQRT_H */ 62