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/neon/workloads/NeonMultiplicationWorkload.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/neon/workloads/NeonMultiplicationWorkload.cpp')
-rw-r--r-- | src/backends/neon/workloads/NeonMultiplicationWorkload.cpp | 16 |
1 files changed, 13 insertions, 3 deletions
diff --git a/src/backends/neon/workloads/NeonMultiplicationWorkload.cpp b/src/backends/neon/workloads/NeonMultiplicationWorkload.cpp index 6f78b8eacc..e4ed195922 100644 --- a/src/backends/neon/workloads/NeonMultiplicationWorkload.cpp +++ b/src/backends/neon/workloads/NeonMultiplicationWorkload.cpp @@ -7,6 +7,8 @@ #include "NeonWorkloadUtils.hpp" +#include <aclCommon/ArmComputeUtils.hpp> + #include <armnn/utility/PolymorphicDowncast.hpp> #include <arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h> @@ -16,7 +18,8 @@ namespace armnn arm_compute::Status NeonMultiplicationWorkloadValidate(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); @@ -26,6 +29,9 @@ arm_compute::Status NeonMultiplicationWorkloadValidate(const TensorInfo& input0, arm_compute::ConvertPolicy::SATURATE : arm_compute::ConvertPolicy::WRAP; + const arm_compute::ActivationLayerInfo activationInfo = ConvertActivationDescriptorToAclActivationLayerInfo( + activationDescriptor); + // At the time of writing, configure() will fail if a rounding policy other than TO_ZERO is supplied to it, // when providing a scale of 1.0 for F32 tensors, even though the provided rounding policy appears to be // ignored for F32 tensors. @@ -34,7 +40,8 @@ arm_compute::Status NeonMultiplicationWorkloadValidate(const TensorInfo& input0, &aclOutput, 1.0f, convertPolicy, - arm_compute::RoundingPolicy::TO_ZERO); + arm_compute::RoundingPolicy::TO_ZERO, + activationInfo); } NeonMultiplicationWorkload::NeonMultiplicationWorkload(const MultiplicationQueueDescriptor& descriptor, @@ -52,6 +59,8 @@ NeonMultiplicationWorkload::NeonMultiplicationWorkload(const MultiplicationQueue arm_compute::ConvertPolicy::SATURATE : arm_compute::ConvertPolicy::WRAP; + const arm_compute::ActivationLayerInfo activationInfo = ConvertAdditionalInfoToAclActivationLayerInfo(descriptor); + // At the time of writing, configure() will fail if a rounding policy other than TO_ZERO is supplied to it, // when providing a scale of 1.0 for F32 tensors, even though the provided rounding policy appears to be // ignored for F32 tensors. @@ -61,7 +70,8 @@ NeonMultiplicationWorkload::NeonMultiplicationWorkload(const MultiplicationQueue &output, 1.0f, convertPolicy, - arm_compute::RoundingPolicy::TO_ZERO); + arm_compute::RoundingPolicy::TO_ZERO, + activationInfo); m_PixelWiseMultiplication.reset(layer.release()); } |