diff options
| author | josh minor <josh.minor@arm.com> | 2019-11-15 14:53:22 -0600 |
|---|---|---|
| committer | Matteo Martincigh <matteo.martincigh@arm.com> | 2019-11-19 11:38:35 +0000 |
| commit | 036f02d859c307f514c77e91665fbff05048ba11 (patch) | |
| tree | 88b82ad93b797bdcdd3b9dec150a44a1d17ee01d /src/backends/neon/NeonLayerSupport.cpp | |
| parent | 49d0f1209e2494fcbc4c807af49322a66fee4d20 (diff) | |
| download | armnn-036f02d859c307f514c77e91665fbff05048ba11.tar.gz | |
IVGCVSW-3729 Added neon slice workload and supporting neon layer tests
* Support added for ACL neon slice workload
* Utility function created to translate ArmNN slice layer params to ACL neon slice layer equivalent
* Neon slice layer tests added as per SliceTestImpl.hpp
Signed-off-by: josh minor <josh.minor@arm.com>
Change-Id: Id583465311879af139e8e977f16ed2280c937ac7
Diffstat (limited to 'src/backends/neon/NeonLayerSupport.cpp')
| -rw-r--r-- | src/backends/neon/NeonLayerSupport.cpp | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/src/backends/neon/NeonLayerSupport.cpp b/src/backends/neon/NeonLayerSupport.cpp index 0eeb948d3f..5410ef42df 100644 --- a/src/backends/neon/NeonLayerSupport.cpp +++ b/src/backends/neon/NeonLayerSupport.cpp @@ -46,6 +46,7 @@ #include "workloads/NeonQuantizedLstmWorkload.hpp" #include "workloads/NeonResizeWorkload.hpp" #include "workloads/NeonRsqrtWorkload.hpp" +#include "workloads/NeonSliceWorkload.hpp" #include "workloads/NeonSoftmaxBaseWorkload.hpp" #include "workloads/NeonSpaceToDepthWorkload.hpp" #include "workloads/NeonSplitterWorkload.hpp" @@ -619,6 +620,18 @@ bool NeonLayerSupport::IsRsqrtSupported(const TensorInfo& input, FORWARD_WORKLOAD_VALIDATE_FUNC(NeonRsqrtWorkloadValidate, reasonIfUnsupported, input, output); } +bool NeonLayerSupport::IsSliceSupported(const TensorInfo& input, + const TensorInfo& output, + const SliceDescriptor& descriptor, + Optional<std::string&> reasonIfUnsupported) const +{ + FORWARD_WORKLOAD_VALIDATE_FUNC(NeonSliceWorkloadValidate, + reasonIfUnsupported, + input, + output, + descriptor); +} + bool NeonLayerSupport::IsSoftmaxSupported(const TensorInfo& input, const TensorInfo& output, const SoftmaxDescriptor& descriptor, |