diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2022-07-28 17:44:00 +0100 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2022-08-01 20:13:56 +0000 |
| commit | 9b921be1ff7283050eb39d9ce1b10b5c8bfc1300 (patch) | |
| tree | 0cb274a6c529717b8ef987aa3e270647927e9d89 /src/cpu/operators/CpuAdd.cpp | |
| parent | 385dad2bffecbf395aa9aad257809de81c727ac7 (diff) | |
| download | ComputeLibrary-9b921be1ff7283050eb39d9ce1b10b5c8bfc1300.tar.gz | |
Optimize add layer by considering the input tensors as 1D array
Resolves: COMPMID-5108
Change-Id: I544f8160fbe5b4ffbef348d1fbd3dd626a6e1bdb
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8002
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/cpu/operators/CpuAdd.cpp')
| -rw-r--r-- | src/cpu/operators/CpuAdd.cpp | 16 |
1 files changed, 15 insertions, 1 deletions
diff --git a/src/cpu/operators/CpuAdd.cpp b/src/cpu/operators/CpuAdd.cpp index 76ec7d7d8d..828361e7cf 100644 --- a/src/cpu/operators/CpuAdd.cpp +++ b/src/cpu/operators/CpuAdd.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -27,6 +27,8 @@ #include "src/common/utils/Log.h" +#include "arm_compute/runtime/NEON/NEScheduler.h" + namespace arm_compute { namespace cpu @@ -45,5 +47,17 @@ Status CpuAdd::validate(const ITensorInfo *src0, const ITensorInfo *src1, const ARM_COMPUTE_RETURN_ERROR_ON(act_info.enabled()); return kernels::CpuAddKernel::validate(src0, src1, dst, policy); } + +void CpuAdd::run(ITensorPack &tensors) +{ + if(static_cast<kernels::CpuAddKernel *>(_kernel.get())->get_can_interpret_inputs_as_1d_array()) + { + NEScheduler::get().schedule_op(_kernel.get(), Window::DimX, _kernel->window(), tensors); + } + else + { + ICpuOperator::run(tensors); + } +} } // namespace cpu } // namespace arm_compute |