Method prepare

src/cpu/operators/CpuWinogradConv2d.cpp:426–475

}

void CpuWinogradConv2d::prepare(ITensorPack &tensors)
{
    if (!_is_prepared)
    {
        const ITensor *weights = tensors.get_const_tensor(ACL_SRC_1);
        ITensor       *weights_aux =
            utils::cast::polymorphic_cast<ITensor *>(tensors.get_tensor(offset_int_vec(PermutedWeights)));

        CpuAuxTensorHandler permuted_weights(_weights_hwio, *weights_aux);
        ITensorPack         permute_tensors{{ACL_SRC, weights}, {ACL_DST, permuted_weights.get()}};
        _permute_weights->run(permute_tensors);
        const int element_size_in_bytes = permuted_weights.get()->info()->element_size();
        // Weights were in OHWI format, before being permuted "permuted_weights" to be in HWIO format.
        const unsigned int height_idx  = 3; // H in HWIO
        const unsigned int width_idx   = 2; // W in HWIO
        const unsigned int channel_idx = 1; // I in HWIO

        const int permuted_weight_row_stride =
            permuted_weights.get()->info()->strides_in_bytes()[height_idx] / element_size_in_bytes;
        const int permuted_weight_col_stride =
            permuted_weights.get()->info()->strides_in_bytes()[width_idx] / element_size_in_bytes;
        const int permuted_weight_channel_stride =
            permuted_weights.get()->info()->strides_in_bytes()[channel_idx] / element_size_in_bytes;

        // Wrap the winograd-domain transformed weight TensorInfo in Auxiliary tensor and allocate the required memory.
        ITensor *weights_transf =
            utils::cast::polymorphic_cast<ITensor *>(tensors.get_tensor(offset_int_vec(TransformedWeights)));
        ARM_COMPUTE_ERROR_ON_NULLPTR(weights_transf);
        CpuAuxTensorHandler winograd_transformed_weights(_winograd_transformed_weights, *weights_transf);

        const void *permuted_weights_ptr;
        void       *win_wght_transf_ptr;

        permuted_weights_ptr = reinterpret_cast<const void *>(
            permuted_weights.get()->buffer() + permuted_weights.get()->info()->offset_first_element_in_bytes());
        win_wght_transf_ptr =
            reinterpret_cast<void *>(winograd_transformed_weights.get()->buffer() +
                                     winograd_transformed_weights.get()->info()->offset_first_element_in_bytes());

        // Prepare Weights
        _winograd_impl.weight_transform->execute(
            *_conv_args, permuted_weights_ptr, permuted_weight_row_stride, permuted_weight_col_stride,
            permuted_weight_channel_stride, win_wght_transf_ptr, _winograd_impl.winograd_spec, 0, 1 // Thread 1 of 1
        );
        ITensorPack gemm_pack = tensors;
        gemm_pack.add_const_tensor(ACL_SRC_1, winograd_transformed_weights.get());
        _gemm_function->prepare(gemm_pack);
        _is_prepared = 1;
    }
}
experimental::MemoryRequirements CpuWinogradConv2d::workspace() const
{
    return _aux_mem;