24.02.1
|
Interface for the kernel to perform addition between two tensors. More...
#include <CpuAddMulAddKernel.h>
Data Structures | |
struct | AddMulAddKernel |
Public Member Functions | |
CpuAddMulAddKernel ()=default | |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE (CpuAddMulAddKernel) | |
void | configure (const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *bn_mul, const ITensorInfo *bn_add, ITensorInfo *add_output, ITensorInfo *final_output, ConvertPolicy policy, const ActivationLayerInfo &act_info) |
Initialize the kernel's inputs and outputs. More... | |
void | run_op (ITensorPack &tensors, const Window &window, const ThreadInfo &info) override |
Execute the kernel on the passed window. More... | |
const char * | name () const override |
Name of the kernel. More... | |
Public Member Functions inherited from ICPPKernel | |
virtual | ~ICPPKernel ()=default |
Default destructor. More... | |
virtual void | run (const Window &window, const ThreadInfo &info) |
Execute the kernel on the passed window. More... | |
virtual void | run_nd (const Window &window, const ThreadInfo &info, const Window &thread_locator) |
legacy compatibility layer for implemantions which do not support thread_locator In these cases we simply narrow the interface down the legacy version More... | |
virtual size_t | get_mws (const CPUInfo &platform, size_t thread_count) const |
Return minimum workload size of the relevant kernel. More... | |
Public Member Functions inherited from IKernel | |
IKernel () | |
Constructor. More... | |
virtual | ~IKernel ()=default |
Destructor. More... | |
virtual bool | is_parallelisable () const |
Indicates whether or not the kernel is parallelisable. More... | |
virtual BorderSize | border_size () const |
The size of the border for that kernel. More... | |
const Window & | window () const |
The maximum window the kernel can be executed on. More... | |
bool | is_window_configured () const |
Function to check if the embedded window of this kernel has been configured. More... | |
Static Public Member Functions | |
static Status | validate (const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *bn_mul, const ITensorInfo *bn_add, const ITensorInfo *add_output, const ITensorInfo *final_output, ConvertPolicy policy, const ActivationLayerInfo &act_info) |
Static function to check if given info will lead to a valid configuration. More... | |
static const std::vector< AddMulAddKernel > & | get_available_kernels () |
Static Public Member Functions inherited from ICpuKernel< CpuAddMulAddKernel > | |
static const auto * | get_implementation (const SelectorType &selector, KernelSelectionType selection_type=KernelSelectionType::Supported) |
Micro-kernel selector. More... | |
Additional Inherited Members | |
Static Public Attributes inherited from ICPPKernel | |
static constexpr size_t | default_mws = 1 |
Interface for the kernel to perform addition between two tensors.
Definition at line 40 of file CpuAddMulAddKernel.h.
|
default |
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE | ( | CpuAddMulAddKernel | ) |
void configure | ( | const ITensorInfo * | input1, |
const ITensorInfo * | input2, | ||
const ITensorInfo * | bn_mul, | ||
const ITensorInfo * | bn_add, | ||
ITensorInfo * | add_output, | ||
ITensorInfo * | final_output, | ||
ConvertPolicy | policy, | ||
const ActivationLayerInfo & | act_info | ||
) |
Initialize the kernel's inputs and outputs.
Similar to NEAddMulAdd::configure()
Definition at line 121 of file CpuAddMulAddKernel.cpp.
References arm_compute::test::validation::act_info, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ARM_COMPUTE_UNUSED, arm_compute::calculate_max_window(), ITensorInfo::data_type(), CPUInfo::get(), arm_compute::set_data_type_if_unknown(), arm_compute::set_shape_if_empty(), ITensorInfo::tensor_shape(), and arm_compute::cpu::kernels::validate_arguments().
|
static |
Definition at line 203 of file CpuAddMulAddKernel.cpp.
|
overridevirtual |
Name of the kernel.
Implements ICPPKernel.
Definition at line 198 of file CpuAddMulAddKernel.cpp.
|
overridevirtual |
Execute the kernel on the passed window.
[in] | tensors | A vector containing the tensors to operate on. |
[in] | window | Region on which to execute the kernel. (Must be a region of the window returned by window()) |
[in] | info | Info about executing thread and CPU. |
Reimplemented from ICPPKernel.
Definition at line 178 of file CpuAddMulAddKernel.cpp.
References arm_compute::ACL_DST_0, arm_compute::ACL_DST_1, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, arm_compute::ACL_SRC_3, ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW, ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL, ARM_COMPUTE_UNUSED, ITensorPack::empty(), ITensorPack::get_const_tensor(), ITensorPack::get_tensor(), arm_compute::test::validation::info, and IKernel::window().
|
static |
Static function to check if given info will lead to a valid configuration.
Similar to CpuAddMulAddKernel::configure()
Definition at line 161 of file CpuAddMulAddKernel.cpp.
References arm_compute::test::validation::act_info, ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, ARM_COMPUTE_RETURN_ON_ERROR, and arm_compute::cpu::kernels::validate_arguments().
Referenced by CpuAddMulAdd::validate().