diff options
author | Pablo Marquez Tello <pablo.tello@arm.com> | 2023-11-13 15:57:54 +0000 |
---|---|---|
committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2023-11-16 10:07:38 +0000 |
commit | ba93371f2316218a09a24403076ab3fdf967b168 (patch) | |
tree | 6e1ff3b974c3893cb50ccb6226e580e4553ab5a7 /src/cpu/kernels/norm_layer/generic/neon/fp32.cpp | |
parent | d4650e9e98c8f854776ae78fb6d3e46e7fe4ba20 (diff) | |
download | ComputeLibrary-ba93371f2316218a09a24403076ab3fdf967b168.tar.gz |
NormalizationLayer changes to enable fp16 in armv8a multi_isa builds
* Moved the template arm_compute::normalize_float to impl.h because
we need to instantiate it from both NENormalizationLayerKernel.cpp
and src/cpu/kernels/norm_layer/generic/neon/fp16.cpp
* Changes in filelist.json: added a new fp16.cpp file for the float16_t kernels
* Replaced the guard __ARM_FEATURE_FP16_VECTOR_ARITHMETIC in
NENormalizationLayerKernel by ARM_COMPUTE_ENABLE_FP16 so that
the fp16 kernels can be compiled in for multi_isa builds
* Moved fp32 kernels to the corresponding file
src/cpu/kernels/norm_layer/generic/neon/fp32.cpp
* Partially resolves MLCE-1102
Change-Id: I3f2eb2ed0b6c7f68092b17872b85082fbb5f39e2
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10739
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/cpu/kernels/norm_layer/generic/neon/fp32.cpp')
-rw-r--r-- | src/cpu/kernels/norm_layer/generic/neon/fp32.cpp | 63 |
1 files changed, 63 insertions, 0 deletions
diff --git a/src/cpu/kernels/norm_layer/generic/neon/fp32.cpp b/src/cpu/kernels/norm_layer/generic/neon/fp32.cpp new file mode 100644 index 0000000000..0b64f46956 --- /dev/null +++ b/src/cpu/kernels/norm_layer/generic/neon/fp32.cpp @@ -0,0 +1,63 @@ +/* + * Copyright (c) 2023 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. + */ + +#include "src/core/NEON/wrapper/wrapper.h" +#include "src/cpu/CpuTypes.h" +#include "src/cpu/kernels/norm_layer/generic/neon/impl.h" + +namespace arm_compute +{ +namespace cpu +{ +void neon_normalize_float32_4_0_2D( + const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) +{ + arm_compute::normalize_float<float, 4, 0, true>(window, in, in_squared, out, ninfo); +} + +void neon_normalize_float32_4_0( + const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) +{ + arm_compute::normalize_float<float, 4, 0, false>(window, in, in_squared, out, ninfo); +} + +void neon_normalize_float32_4_1_2D( + const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) +{ + arm_compute::normalize_float<float, 4, 1, true>(window, in, in_squared, out, ninfo); +} + +void neon_normalize_float32_4_1( + const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) +{ + arm_compute::normalize_float<float, 4, 1, false>(window, in, in_squared, out, ninfo); +} + +void neon_normalize_float32_4_2( + const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo) +{ + arm_compute::normalize_float<float, 4, 2, false>(window, in, in_squared, out, ninfo); +} +} // namespace cpu +} // namespace arm_compute |