// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

// Included only under JFJOCH_USE_CUDA. Free of CUDA headers, so the host fit can hold one.

#include <cstdint>
#include <memory>
#include <vector>

#include "BackgroundBand.h"

// The two passes over the pixels of the background beam-centre fit (FindBeamCenterFromBackground),
// on the device: binning every usable pixel into its cell about a trial centre, and summing the
// binned pixels again under a clip. They are all of the fit's cost; the fit itself stays on the host.
//
// Each cell is summed in the order the host sums it - pixel order within each of the host's row
// blocks, the blocks then added in block order - so a pixel that lands in the same cell on both
// sides adds the same rounding on both. Whatever differs comes from BackgroundBandCell (see there).
class BeamCenterBackgroundGPU {
    struct Impl;
    std::unique_ptr<Impl> impl;
public:
    // block_row: the first row of each of the host's row blocks, and one past the last row at the end.
    // panels: where the image's panels are on the plane; empty when the image is the plane.
    BeamCenterBackgroundGPU(int width, int height, const std::vector<int> &block_row,
                            const std::vector<BackgroundPanel> &panels, const char *usable, const float *mean);
    ~BeamCenterBackgroundGPU();

    // Bin the band about (beam_x, beam_y) and sum each cell: the values, their squares, the two
    // derivatives, and the count.
    void Bin(const BackgroundBand &band, float beam_x, float beam_y,
             std::vector<double> &sum, std::vector<double> &sum_sq,
             std::vector<double> &sum_jx, std::vector<double> &sum_jy, std::vector<int32_t> &count);

    // Sum the pixels the last Bin put in each cell again, leaving out those above the cell's
    // clip_limit and every pixel of a cell whose limit is negative.
    void Clip(const std::vector<float> &clip_limit,
              std::vector<double> &sum, std::vector<double> &sum_sq, std::vector<int32_t> &count);
};