20.11
|
#include <NeonConvertBf16ToFp32Workload.hpp>
Public Member Functions | |
NeonConvertBf16ToFp32Workload (const ConvertBf16ToFp32QueueDescriptor &descriptor, const WorkloadInfo &info) | |
virtual void | Execute () const override |
![]() | |
MultiTypedWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info) | |
![]() | |
BaseWorkload (const QueueDescriptor &descriptor, const WorkloadInfo &info) | |
void | PostAllocationConfigure () override |
const QueueDescriptor & | GetData () const |
profiling::ProfilingGuid | GetGuid () const final |
![]() | |
virtual | ~IWorkload () |
virtual void | RegisterDebugCallback (const DebugCallbackFunction &) |
Additional Inherited Members | |
![]() | |
const QueueDescriptor | m_Data |
const profiling::ProfilingGuid | m_Guid |
Definition at line 15 of file NeonConvertBf16ToFp32Workload.hpp.
NeonConvertBf16ToFp32Workload | ( | const ConvertBf16ToFp32QueueDescriptor & | descriptor, |
const WorkloadInfo & | info | ||
) |
Definition at line 17 of file NeonConvertBf16ToFp32Workload.cpp.
References armnn::GatherTensorHandlePairs(), BaseWorkload< QueueDescriptor >::m_Data, and QueueDescriptor::ValidateInputsOutputs().
|
overridevirtual |
Implements IWorkload.
Definition at line 25 of file NeonConvertBf16ToFp32Workload.cpp.
References ARMNN_SCOPED_PROFILING_EVENT_NEON, FloatingPointConverter::ConvertBFloat16ToFloat32(), and armnn::CopyTensorContentsGeneric().