Method configure

src/cpu/kernels/CpuAddKernel.cpp:167–199

} // namespace

void CpuAddKernel::configure(const ITensorInfo *src0, const ITensorInfo *src1, ITensorInfo *dst, ConvertPolicy policy)
{
    ARM_COMPUTE_TRACE_EVENT(ARM_COMPUTE_PROF_CAT_CPU, ARM_COMPUTE_PROF_LVL_CPU, "CpuAddKernel::configure");
    ARM_COMPUTE_ERROR_ON_NULLPTR(src0, src1, dst);
    ARM_COMPUTE_ERROR_THROW_ON(validate_arguments(*src0, *src1, *dst, policy));

    const auto can_use_fixedpoint = add_q8_neon_fixedpoint_possible(src0, src1, dst);
#ifdef ARM_COMPUTE_ENABLE_SME2
    const auto can_use_sme2_impl = add_q8_sme2_fixedpoint_possible(src0, src1, dst);
#else  /* ARM_COMPUTE_ENABLE_SME2 */
    const auto can_use_sme2_impl = false;
#endif /* ARM_COMPUTE_ENABLE_SME2 */
    const auto uk =
        CpuAddKernel::get_implementation<CpuAddKernelDataTypeISASelectorData>(CpuAddKernelDataTypeISASelectorData{
            src0->data_type(), CPUInfo::get().get_isa(), can_use_fixedpoint, can_use_sme2_impl});

    ARM_COMPUTE_ERROR_ON_NULLPTR(uk);

    _policy     = policy;
    _run_method = uk->ukernel;
    _name       = std::string("CpuAddKernel").append("/").append(uk->name);

    // Auto initialize dst if not initialized
    const TensorShape &out_shape = TensorShape::broadcast_shape(src0->tensor_shape(), src1->tensor_shape());
    set_shape_if_empty(*dst, out_shape);
    set_data_type_if_unknown(*dst, src0->data_type());

    // Configure kernel window
    Window win;
    std::tie(win, _split_dimension) = calculate_squashed_or_max_window(*src0, *src1);

    ICpuKernel::configure(win);
}

Status
CpuAddKernel::validate(const ITensorInfo *src0, const ITensorInfo *src1, const ITensorInfo *dst, ConvertPolicy policy)