diff options
author | Mike Kelly <mike.kelly@arm.com> | 2020-11-12 10:58:48 +0000 |
---|---|---|
committer | Jim Flynn <jim.flynn@arm.com> | 2020-11-13 14:25:30 +0000 |
commit | 07810fc2fcdd34db74222d90cc73ef12a88e7b78 (patch) | |
tree | 8becef8453674822d079815b06ae37310b97d2cf /src/backends/cl/workloads/ClDivisionFloatWorkload.cpp | |
parent | 8502adeafbbb1db0acefa62560d93453e38dcadb (diff) | |
download | armnn-07810fc2fcdd34db74222d90cc73ef12a88e7b78.tar.gz |
IVGCVSW-5328-5329 Fuse Activation
* Added Fused Activation Optimization to both CL and Neon backends.
* Added Fused Activation support to all the CL and Neon workloads
that support it.
* Changed ProfilingTest network to be a Convolution layer
followed by an Abs layer rather than an Activation layer.
* Added IBackendInternal::OptimizeSubgraphView function that can accept a
ModelOptions.
* Network will now call OptimizeSubgraphView passing in the ModelOptions.
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib536ac3cbafc7d9b35c139ad9a65b7735262cd9d
Diffstat (limited to 'src/backends/cl/workloads/ClDivisionFloatWorkload.cpp')
-rw-r--r-- | src/backends/cl/workloads/ClDivisionFloatWorkload.cpp | 19 |
1 files changed, 14 insertions, 5 deletions
diff --git a/src/backends/cl/workloads/ClDivisionFloatWorkload.cpp b/src/backends/cl/workloads/ClDivisionFloatWorkload.cpp index 2a27f8a9bc..c79e55ebdd 100644 --- a/src/backends/cl/workloads/ClDivisionFloatWorkload.cpp +++ b/src/backends/cl/workloads/ClDivisionFloatWorkload.cpp @@ -4,9 +4,12 @@ // #include "ClDivisionFloatWorkload.hpp" -#include <cl/ClTensorHandle.hpp> + +#include <aclCommon/ArmComputeUtils.hpp> #include <backendsCommon/CpuTensorHandle.hpp> +#include <cl/ClTensorHandle.hpp> + #include "ClWorkloadUtils.hpp" namespace armnn @@ -14,13 +17,17 @@ namespace armnn arm_compute::Status ClDivisionWorkloadValidate(const TensorInfo& input0, const TensorInfo& input1, - const TensorInfo& output) + const TensorInfo& output, + const ActivationDescriptor* activationDescriptor) { const arm_compute::TensorInfo aclInput1 = armcomputetensorutils::BuildArmComputeTensorInfo(input0); const arm_compute::TensorInfo aclInput2 = armcomputetensorutils::BuildArmComputeTensorInfo(input1); const arm_compute::TensorInfo aclOutput = armcomputetensorutils::BuildArmComputeTensorInfo(output); - return arm_compute::CLArithmeticDivision::validate(&aclInput1, &aclInput2, &aclOutput); + const arm_compute::ActivationLayerInfo activationInfo = ConvertActivationDescriptorToAclActivationLayerInfo( + activationDescriptor); + + return arm_compute::CLArithmeticDivision::validate(&aclInput1, &aclInput2, &aclOutput, activationInfo); } @@ -33,8 +40,10 @@ ClDivisionFloatWorkload::ClDivisionFloatWorkload(const DivisionQueueDescriptor& arm_compute::ICLTensor& input0 = static_cast<IClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor(); arm_compute::ICLTensor& input1 = static_cast<IClTensorHandle*>(m_Data.m_Inputs[1])->GetTensor(); arm_compute::ICLTensor& output = static_cast<IClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor(); - // Construct - m_ArithmeticDivision.configure(&input0, &input1, &output); + + const arm_compute::ActivationLayerInfo activationInfo = ConvertAdditionalInfoToAclActivationLayerInfo(descriptor); + + m_ArithmeticDivision.configure(&input0, &input1, &output, activationInfo); } void ClDivisionFloatWorkload::Execute() const |