Method run

src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.cpp:180–205

}

void CLQLSTMLayerNormalizationKernel::run(const Window &window, cl::CommandQueue &queue)
{
    ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(this);
    ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(ICLKernel::window(), window);

    Window slice = window.first_slice_window_2D();
    // Set slice step equal to width to force gws[0] to 1, as each thread normalizes across all rows
    slice.set_dimension_step(Window::DimX, _input->info()->dimension(0));

    Window weight_window;
    Window weight_slice;

    weight_window.use_tensor_dimensions(_weight->info()->tensor_shape());
    weight_slice = weight_window.first_slice_window_1D();

    do
    {
        unsigned int idx = 0;
        add_2D_tensor_argument(idx, _input, slice);
        add_1D_tensor_argument(idx, _weight, weight_slice);
        add_1D_tensor_argument(idx, _bias, weight_slice);
        add_2D_tensor_argument(idx, _output, slice);

        enqueue(queue, *this, slice, lws_hint());
    } while (window.slide_window_slice_2D(slice));
}
} // namespace arm_compute