diff options
author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-11-13 17:20:45 +0000 |
---|---|---|
committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-12-07 09:42:47 +0000 |
commit | 47370943471c98b5ed4c954b350b925d368a810e (patch) | |
tree | f5fd7d4c4a51b538874632607887b93d8ece3c07 /src/runtime/NEON/functions | |
parent | 17e116e90e6b962a09c133c646b6ad7884e94693 (diff) | |
download | ComputeLibrary-47370943471c98b5ed4c954b350b925d368a810e.tar.gz |
Optimize CPU depth-to-space
Resolves: COMPMID-6622
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: Ibac276618bdda125dcbb9c851c547f12739b15b4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10749
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/NEON/functions')
-rw-r--r-- | src/runtime/NEON/functions/NEDepthToSpaceLayer.cpp | 17 |
1 files changed, 14 insertions, 3 deletions
diff --git a/src/runtime/NEON/functions/NEDepthToSpaceLayer.cpp b/src/runtime/NEON/functions/NEDepthToSpaceLayer.cpp index 47564059ec..5eea4dca65 100644 --- a/src/runtime/NEON/functions/NEDepthToSpaceLayer.cpp +++ b/src/runtime/NEON/functions/NEDepthToSpaceLayer.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019-2021 Arm Limited. + * Copyright (c) 2019-2021, 2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -25,15 +25,20 @@ #include "arm_compute/runtime/NEON/functions/NEDepthToSpaceLayer.h" #include "arm_compute/core/Error.h" -#include "arm_compute/core/TensorInfo.h" #include "arm_compute/core/Types.h" -#include "arm_compute/core/Validate.h" +#include "arm_compute/runtime/NEON/NEScheduler.h" #include "src/common/utils/Log.h" #include "src/core/NEON/kernels/NEDepthToSpaceLayerKernel.h" namespace arm_compute { +NEDepthToSpaceLayer::NEDepthToSpaceLayer() : _kernel{} +{ +} + +NEDepthToSpaceLayer::~NEDepthToSpaceLayer() = default; + void NEDepthToSpaceLayer::configure(const ITensor *input, ITensor *output, int32_t block_shape) { ARM_COMPUTE_LOG_PARAMS(input, output, block_shape); @@ -47,4 +52,10 @@ Status NEDepthToSpaceLayer::validate(const ITensorInfo *input, const ITensorInfo { return NEDepthToSpaceLayerKernel::validate(input, output, block_shape); } + +void NEDepthToSpaceLayer::run() +{ + NEScheduler::get().schedule(_kernel.get(), _kernel->get_split_dimension()); +} + } // namespace arm_compute |