1 /* Copyright 2019 The TensorFlow Authors. All Rights Reserved. 2 3 Licensed under the Apache License, Version 2.0 (the "License"); 4 you may not use this file except in compliance with the License. 5 You may obtain a copy of the License at 6 7 http://www.apache.org/licenses/LICENSE-2.0 8 9 Unless required by applicable law or agreed to in writing, software 10 distributed under the License is distributed on an "AS IS" BASIS, 11 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 See the License for the specific language governing permissions and 13 limitations under the License. 14 ==============================================================================*/ 15 #ifndef TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_NEON_CHECK_H_ 16 #define TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_NEON_CHECK_H_ 17 18 #if defined(__ARM_NEON__) || defined(__ARM_NEON) 19 #define USE_NEON 20 #include <arm_neon.h> 21 #endif 22 23 #if defined __GNUC__ && defined __SSE4_1__ && !defined TF_LITE_DISABLE_X86_NEON 24 #define USE_NEON 25 #include "NEON_2_SSE.h" 26 #if defined vld1q_lane_u64 27 #undef vld1q_lane_u64 28 // TODO(b/240305641): workaround a bug in the arm_neon_sse.h header, this can be 29 // removed after https://github.com/intel/ARM_NEON_2_x86_SSE/pull/60 is merged 30 // upstream. 31 #define vld1q_lane_u64(ptr, vec, lane) _MM_INSERT_EPI64(vec, *(ptr), lane) 32 #endif 33 #endif 34 35 // NEON_OR_PORTABLE(SomeFunc, args) calls NeonSomeFunc(args) if USE_NEON is 36 // defined, PortableSomeFunc(args) otherwise. 37 #ifdef USE_NEON 38 // Always use Neon code 39 #define NEON_OR_PORTABLE(funcname, ...) Neon##funcname(__VA_ARGS__) 40 41 #else 42 // No NEON available: Use Portable code 43 #define NEON_OR_PORTABLE(funcname, ...) Portable##funcname(__VA_ARGS__) 44 45 #endif // defined(USE_NEON) 46 47 #endif // TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_NEON_CHECK_H_ 48