blob: 47f1b90abdf093762254a02b7261019e92eb60d0 [file] [log] [blame]
/*
* Copyright (c) 2024 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef ACL_SRC_CPU_KERNELS_QUANTIZE_GENERIC_NEON_IMPL_FP16_H
#define ACL_SRC_CPU_KERNELS_QUANTIZE_GENERIC_NEON_IMPL_FP16_H
#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
#include "src/core/helpers/WindowHelpers.h"
#include "src/core/NEON/NEAsymm.h"
namespace arm_compute
{
namespace cpu
{
inline float32x4x4_t load_value(const float16_t *input_ptr)
{
return {vcvt_f32_f16(wrapper::vload(input_ptr)), vcvt_f32_f16(wrapper::vload(input_ptr + 4)),
vcvt_f32_f16(wrapper::vload(input_ptr + 8)), vcvt_f32_f16(wrapper::vload(input_ptr + 12))};
}
} // namespace cpu
} // namespace arm_compute
#include "impl.h"
#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
#endif // ACL_SRC_CPU_KERNELS_QUANTIZE_GENERIC_NEON_IMPL_FP16_H