Jungfraujoch/image_analysis/MXAnalysisWithoutFPGA.h

// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <mutex>

#include "../common/JFJochMessages.h"
#include "../common/DiffractionExperiment.h"
#include "../common/AzimuthalIntegrationMapping.h"
#include "../common/PixelMask.h"
#include "../common/AzimuthalIntegrationProfile.h"
#include "bragg_prediction/BraggPrediction.h"
#include "bragg_integration/BraggIntegrationEngine.h"
#include "bragg_integration/BraggIntegrationEngineCPU.h"
#include "spot_finding/ImageSpotFinder.h"
#include "spot_finding/AdaptiveSpotFinderCPU.h"
#include "indexing/IndexerThreadPool.h"
#include "azint/AzIntEngine.h"
#include "roi/ROIIntegration.h"
#include "IndexAndRefine.h"
#include "image_preprocessing/ImagePreprocessor.h"
#include "image_preprocessing/ImagePreprocessorBuffer.h"
#include "image_preprocessing/ImagePreprocessorCPU.h"

class CudaStream;
class AdaptiveSpotFinderGPU;

// MXAnalysisWithoutFPGA is not thread safe - it has to owned by a single thread
class MXAnalysisWithoutFPGA {
    const DiffractionExperiment &experiment;
    const AzimuthalIntegrationMapping &integration;

    std::vector<uint8_t> decompression_buffer;

    std::unique_ptr<ImagePreprocessor> preprocessor;
    // The preprocessor, where it is the CPU one.
    ImagePreprocessorCPU *preprocessor_cpu = nullptr;

    size_t npixels;
    size_t xpixels;

    // Built on first use: the fused adaptive finder produces the azimuthal profile as a by-product,
    // so on the rugnux path this engine is constructed and then never run.
    std::unique_ptr<AzIntEngine> azint;
    AzIntEngine &AzInt();
    std::unique_ptr<ROIIntegration> roi;
    // Built on first use. Which finder an image takes arrives with its SpotFindingSettings, and
    // with adaptive detection on - the default everywhere but the broker - this one is never asked
    // for; on the GPU it is ~14 MB and 15 device allocations per worker.
    std::unique_ptr<ImageSpotFinder> spotFinder;
    ImageSpotFinder &FixedThresholdFinder();
    // Self-calibrating finder, used when spot settings request adaptive detection. Kept alongside the
    // default finder because the choice arrives with the per-image settings, not at construction. It is
    // an AdaptiveSpotFinderCPU by default; on the GPU path, when the fused engine is enabled (rugnux
    // offline only), it is instead an AdaptiveSpotFinderGPU that also computes the azimuthal profile,
    // aliased through fused_adaptive so Analyze() can take that profile and skip the separate azint pass.
    std::unique_ptr<ImageSpotFinder> adaptiveSpotFinder;
    AdaptiveSpotFinderGPU *fused_adaptive = nullptr;
    // The CPU finder, where it gives the profile too (the azimuthal integration being on the CPU).
    AdaptiveSpotFinderCPU *fused_adaptive_cpu = nullptr;
    const bool enable_fused_adaptive_gpu;
    IndexAndRefine &indexer;
    std::unique_ptr<BraggPrediction> prediction;
    std::unique_ptr<BraggIntegrationEngine> bragg_engine;
    // What the supercell probe's integrations added to bragg_engine's counts (see BraggCounts).
    BraggIntegrationCounts probe_counts;
    // Counts the neighbour crowding of the integrated reflections at another stencil (CountCrowdingAt),
    // on the images for which count_crowding is on.
    std::unique_ptr<BraggIntegrationEngineCPU> crowding_engine;
    bool count_crowding = false;
    std::unique_ptr<ImagePreprocessorBuffer> preprocessor_buffer;
    const PixelMask &mask;

    // Decompress the image into decompression_buffer (or read it straight from the message, when it is
    // not compressed) and return where it landed.
    const uint8_t *Decompress(const CompressedImage &image);

    // The CPU preprocessing. A bitshuffled image is decoded a block (~32 KB) at a time and each block
    // is preprocessed while it is in cache, then - with ring_pass - put through the adaptive finder's
    // plain ring pass as well, so the image is never written out whole before it is preprocessed and
    // the preprocessed pixels are read back from cache, not from memory. The blocks come in pixel
    // order, so every sum is taken in the same order as by separate passes.
    ImageStatistics PreprocessCPU(const CompressedImage &image, bool ring_pass);

    // Pixels outside the resolution limits, bit-packed. Built by the integration mapping, which is
    // shared by every worker's engine and hands out the same mask to all of them.
    std::shared_ptr<const std::vector<uint32_t>> mask_resolution;
    // The limits mask_resolution was built for. Kept as the OPTIONAL the caller passed, so an unset
    // high-resolution limit compares equal to itself and the mask is not rebuilt on every image.
    std::optional<float> mask_high_res;
    std::optional<float> mask_low_res;
    void UpdateMaskResolution(const SpotFindingSettings& settings);
#ifdef JFJOCH_USE_CUDA
    std::shared_ptr<CudaStream> stream;   // kept so RebuildROI() can recreate the GPU ROI engine
#endif
public:
    // enable_fused_adaptive_gpu turns on the fused GPU azint+adaptive spot finder (only takes effect on
    // the GPU path with adaptive detection). The rugnux offline path and the interactive viewer enable
    // it by default, as does the online receiver. It only changes performance - the fused engine
    // reproduces the CPU finder's spots. Note it also decides whether the preprocessed image is copied
    // back to the host each frame: that copy exists only for a CPU engine to read, and with the flag on
    // no CPU engine is built, so the copy is skipped.
    MXAnalysisWithoutFPGA(const DiffractionExperiment &experiment, const AzimuthalIntegrationMapping &integration,
                     const PixelMask &mask, IndexAndRefine &indexer, bool enable_fused_adaptive_gpu = false);
    void Analyze(DataMessage &output, AzimuthalIntegrationProfile &profile, const SpotFindingSettings &spot_finding_settings);

    // Surgical ROI-only paths used when a full re-analysis is not wanted: rebuild the
    // ROI engine after the ROI set changes, recompute ROIs after preprocessing a new
    // image (reanalyze off), or just rerun ROIs on the current preprocessed image (an
    // interactive ROI move). A full Analyze() already computes ROIs, so needs nothing.
    void RebuildROI();
    void AnalyzeROIOnly(DataMessage &output);
    void RunROIOnly(DataMessage &output);

    // What this worker's Bragg integrator counted (BraggIntegrationCounts). Each worker builds its own
    // analysis, so a caller that wants the run's totals sums this over the workers it started.
    [[nodiscard]] BraggIntegrationCounts BraggCounts() const;

    // Also count, on the images Analyze is given while CountCrowding(true), how crowded the background
    // rings of the integrated reflections would be at `settings` rather than the experiment's own
    // (BraggIntegrationEngineCPU::CountNeighbourCrowding), read back with CrowdingCounts.
    void CountCrowdingAt(const BraggIntegrationSettings &settings);
    void CountCrowding(bool on) { count_crowding = on; }
    [[nodiscard]] BraggIntegrationCounts CrowdingCounts() const;
};