1 /* 2 * Copyright (c) 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_CGTZ_H 25 #define ARM_COMPUTE_WRAPPER_CGTZ_H 26 27 #ifdef __aarch64__ 28 #include <arm_neon.h> 29 30 namespace arm_compute 31 { 32 namespace wrapper 33 { 34 #define VCGTZ_IMPL(vtype, rtype, prefix, postfix) \ 35 inline rtype vcgtz(const vtype &a) \ 36 { \ 37 return prefix##_##postfix(a); \ 38 } 39 40 VCGTZ_IMPL(int8x8_t, uint8x8_t, vcgtz, s8) 41 VCGTZ_IMPL(int16x4_t, uint16x4_t, vcgtz, s16) 42 VCGTZ_IMPL(int32x2_t, uint32x2_t, vcgtz, s32) 43 VCGTZ_IMPL(float32x2_t, uint32x2_t, vcgtz, f32) 44 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 45 VCGTZ_IMPL(float16x4_t, uint16x4_t, vcgtz, f16) 46 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 47 48 VCGTZ_IMPL(int8x16_t, uint8x16_t, vcgtzq, s8) 49 VCGTZ_IMPL(int16x8_t, uint16x8_t, vcgtzq, s16) 50 VCGTZ_IMPL(int32x4_t, uint32x4_t, vcgtzq, s32) 51 VCGTZ_IMPL(float32x4_t, uint32x4_t, vcgtzq, f32) 52 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 53 VCGTZ_IMPL(float16x8_t, uint16x8_t, vcgtzq, f16) 54 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC 55 56 #undef VCGTZ_IMPL 57 58 } // namespace wrapper 59 } // namespace arm_compute 60 61 #endif // __aarch64__ 62 #endif /* ARM_COMPUTE_WRAPPER_CGTZ_H */ 63