Method do_tune_kernel_dynamic

src/runtime/CL/CLTuner.cpp:105–144

}

void CLTuner::do_tune_kernel_dynamic(ICLKernel &kernel, IKernelData *data)
{
    // Get the configuration ID from the kernel and append GPU target name and number of available compute units
    const std::string config_id = kernel.config_id() + "_" + string_from_target(kernel.get_target()) + "_MP" +
                                  support::cpp11::to_string(CLKernelLibrary::get().get_num_compute_units());

    // Check if we need to find the Optimal LWS. If the kernel's config_id is equal to default_config_id, the kernel does not require to be tuned
    if (kernel.config_id() != arm_compute::default_config_id)
    {
        auto p = _tuning_params_table.find(config_id);

        if (p == _tuning_params_table.end())
        {
            if (_tune_new_kernels)
            {
                // Find the optimal LWS for the kernel
                CLTuningParams opt_tuning_params = find_optimal_tuning_params(kernel, data);

                // Insert the optimal LWS in the table
                add_tuning_params(config_id, opt_tuning_params);

                // Set Local-Workgroup-Size
                kernel.set_lws_hint(opt_tuning_params.get_lws());
                if (_tuning_info.tune_wbsm)
                {
                    kernel.set_wbsm_hint(opt_tuning_params.get_wbsm());
                }
            }
        }
        else
        {
            // Set Local-Workgroup-Size
            kernel.set_lws_hint(p->second.get_lws());
            if (_tuning_info.tune_wbsm)
            {
                kernel.set_wbsm_hint(p->second.get_wbsm());
            }
        }
    }
}
void CLTuner::tune_kernel_dynamic(ICLKernel &kernel, ITensorPack &tensors)
{
    DefaultKernelData data{tensors};