// 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.

#include <cstdint>
#include <vector>

#include <cuda_runtime.h>

// What the mask is drawn about: the detector, the beam centre, and the geometry the rings and the
// polarization factor are read off (ShadowFinder keeps it as a DiffractionGeometry; the device takes
// it as numbers).
struct ShadowMaskSetup {
    int width = 0, height = 0;
    float beam_x = 0.0f, beam_y = 0.0f;
    float det_matrix[9] = {};   // row major
    float pixel_size_mm = 0.0f;
    float distance_mm = 0.0f;
    bool has_polarization = false;
    float polarization = 0.0f;
    float gain = 1.0f;   // detector units per photon (ShadowFinder::gain)
};

// ShadowFinder::GetMask on the device, from the projection ShadowAccumulatorGPU holds there. Step for
// step the host's algorithm - the same pooling, ring medians, components, morphology and arm search -
// and the same answer wherever the arithmetic is exact: every integer, comparison, sort and component
// is. What is not is the floating point the two compilers evaluate differently - the polarization
// factor's trigonometry, the Poisson test's logarithm and the azimuth of the arm search - so a pixel
// within a rounding of one of those thresholds can come out the other way.
std::vector<uint32_t> ShadowMaskOnDevice(const ShadowMaskSetup &setup, const std::vector<uint32_t> &pixel_mask,
                                         const int64_t *max_value, const int64_t *sum_value,
                                         const uint32_t *valid_count, uint32_t frames, cudaStream_t stream);

// The mean projection the host's GetMeanProjection makes, computed where the sums are: the same
// division, so the same bits, and a quarter of the bytes to bring back.
std::vector<float> MeanProjectionOnDevice(const std::vector<uint32_t> &pixel_mask, const int64_t *sum_value,
                                          const uint32_t *valid_count, size_t npixels, cudaStream_t stream);