diff options
| author | Manuel Bottini <manuel.bottini@arm.com> | 2021-06-18 15:47:28 +0100 |
|---|---|---|
| committer | Manuel Bottini <manuel.bottini@arm.com> | 2021-07-08 14:47:38 +0000 |
| commit | cfac51c779f9bf05e8b2d386fbfb4022767d1d30 (patch) | |
| tree | 6ded148068c32bb1b2926946f59d0262d928b9ab /src/runtime/gpu/cl/utils/ClAuxTensorHandler.h | |
| parent | 06ac6e438fc95aa7f8228be8217e0776d692b8e7 (diff) | |
| download | ComputeLibrary-cfac51c779f9bf05e8b2d386fbfb4022767d1d30.tar.gz | |
Port NEGEMMLowp Part 2
Details:
Extend NEConvertQuantizedSignednessKernel
Port NEGEMMInterleave4x4Kernel to CpuGemmInterleave4x4Kernel
Port NEGEMMTranspose1xWKernel to CpuGemmTranspose1xWKernel
Port NEGEMMLowpMatrixAReductionKernel to CpuGemmLowpMatrixAReductionKernel
Port NEGEMMLowpMatrixBReductionKernel to CpuGemmLowpMatrixBReductionKernel
Port NEGEMMLowpOffsetContributionOutputStageKernel to CpuGemmLowpOffsetContributionOutputStageKernel
Port NEGEMMLowpOffsetContributionKernel to CpuGemmLowpOffsetContributionKernel
Resolves: COMPMID-4403
Change-Id: I3227f052f25e7b41d073bbea1da8a881fcd78b8e
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5875
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Diffstat (limited to 'src/runtime/gpu/cl/utils/ClAuxTensorHandler.h')
| -rw-r--r-- | src/runtime/gpu/cl/utils/ClAuxTensorHandler.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/src/runtime/gpu/cl/utils/ClAuxTensorHandler.h b/src/runtime/gpu/cl/utils/ClAuxTensorHandler.h index 152e3c6c04..1cf717cf6f 100644 --- a/src/runtime/gpu/cl/utils/ClAuxTensorHandler.h +++ b/src/runtime/gpu/cl/utils/ClAuxTensorHandler.h @@ -41,6 +41,10 @@ public: CLAuxTensorHandler(int slot_id, TensorInfo &info, ITensorPack &pack, bool pack_inject = false) : _tensor() { + if(info.total_size() == 0) + { + return; + } _tensor.allocator()->soft_init(info); ICLTensor *packed_tensor = utils::cast::polymorphic_downcast<ICLTensor *>(pack.get_tensor(slot_id)); |