diff options
Diffstat (limited to 'src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp')
-rw-r--r-- | src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp | 45 |
1 files changed, 45 insertions, 0 deletions
diff --git a/src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp b/src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp new file mode 100644 index 0000000000..ed84c10d72 --- /dev/null +++ b/src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp @@ -0,0 +1,45 @@ +/* + * Copyright (c) 2022 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. + */ +#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS) + +#include "src/cpu/kernels/l2normlayer/generic/neon/impl.h" + +#include "arm_compute/core/Helpers.h" +namespace arm_compute +{ +namespace cpu +{ +void neon_fp16_l2_normalize_x(const ITensor *in, const ITensor *sum, ITensor *out, float epsilon, const Window &window, size_t unused_axis) +{ + ARM_COMPUTE_UNUSED(unused_axis); + return l2_normalize_x<float16_t, 8>(in, sum, out, epsilon, window); +} + +void neon_fp16_l2_normalize_yz(const ITensor *in, const ITensor *sum, ITensor *out, float epsilon, const Window &window, size_t axis) +{ + return l2_normalize_yz<float16_t, 8>(in, sum, out, epsilon, window, axis); +} +} // namespace cpu +} // namespace arm_compute +#endif /* defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS) */ |