Replace the free functions BraggIntegrate2D/ProfileIntegrate2D with the BraggIntegrationEngine (CPU/GPU) as the live integrator. - IndexAndRefine no longer holds the integrator: ProcessImage takes a per-worker BraggIntegrateFn callback (ProcessImage is called concurrently by the shared IndexAndRefine, so the stateful engine must not be a member). - WithoutFPGA/jfjoch_process: owns a GPU engine when a GPU is present, else CPU, and passes the GPU-resident preprocessed buffer so integration runs on-device. - AfterFPGA: forces CPU and integrates straight off the assembled CompressedImage via a templated per-pixel sampler - only the reflection-disk pixels are read, no whole-image copy (the FPGA host runs up to 36 GB/s). Sampler maps type min/max to INT32_MIN/INT32_MAX on read; special/saturation only, no +/-1 band. - Remove BraggIntegrate2D/ProfileIntegrate2D and their test; keep IntegratorMode. Prediction: buffer up to 20000 candidates but return the 10000 closest to the Ewald sphere (deterministic partial_sort on |dist_ewald|, hkl tiebreak) instead of the GPU atomic-fill order. Serialized output stays <=10000, so the frame transport headroom and its CBOR guard are unchanged. integration_model exposed via OpenAPI (bragg_integration_settings schema, /config/bragg_integration PUT/GET, added to jfjoch_settings and jfjoch_statistics) and the frontend (BraggIntegrationSettings dropdown). Regenerated C++/TS clients and redoc. Validated old-vs-new on all 18 /data/rotation_test crystals: indexing rate and space group bit-identical; ISa/CC identical on 16/18 (one improved, EcwtAL500 ISa 0.0->6.7); new CompressedImage-vs-buffer and GPU-vs-CPU parity tests pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
163 lines
7.6 KiB
C++
163 lines
7.6 KiB
C++
// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#include "MXAnalysisWithoutFPGA.h"
|
|
|
|
#include "spot_finding/StrongPixelSet.h"
|
|
#include "../compression/JFJochDecompress.h"
|
|
|
|
#include "spot_finding/SpotUtils.h"
|
|
#include "bragg_prediction/BraggPredictionFactory.h"
|
|
#include "image_preprocessing/ImagePreprocessorCPU.h"
|
|
|
|
#include "azint/AzIntEngineCPU.h"
|
|
#include "roi/ROIIntegrationCPU.h"
|
|
#include "spot_finding/ImageSpotFinderCPU.h"
|
|
#include "bragg_integration/BraggIntegrationEngineCPU.h"
|
|
#ifdef JFJOCH_USE_CUDA
|
|
#include "azint/AzIntEngineGPU.h"
|
|
#include "roi/ROIIntegrationGPU.h"
|
|
#include "spot_finding/ImageSpotFinderGPU.h"
|
|
#include "image_preprocessing/ImagePreprocessorGPU.h"
|
|
#include "image_preprocessing/ImagePreprocessorBufferGPU.h"
|
|
#include "bragg_integration/BraggIntegrationEngineGPU.h"
|
|
#include "../common/CUDAWrapper.h"
|
|
#endif
|
|
|
|
|
|
MXAnalysisWithoutFPGA::MXAnalysisWithoutFPGA(const DiffractionExperiment &in_experiment,
|
|
const AzimuthalIntegrationMapping &in_integration,
|
|
const PixelMask &in_mask,
|
|
IndexAndRefine &in_indexer)
|
|
: experiment(in_experiment),
|
|
integration(in_integration),
|
|
npixels(experiment.GetPixelsNum()),
|
|
xpixels(experiment.GetXPixelsNum()),
|
|
indexer(in_indexer),
|
|
prediction(CreateBraggPrediction(experiment.IsRotationIndexing())),
|
|
mask(in_mask),
|
|
mask_resolution(experiment.GetPixelsNum(), false),
|
|
mask_high_res(-1),
|
|
mask_low_res(-1) {
|
|
#ifdef JFJOCH_USE_CUDA
|
|
if (get_gpu_count() == 0) {
|
|
#endif
|
|
preprocessor_buffer = std::make_unique<ImagePreprocessorBuffer>(experiment.GetPixelsNum());
|
|
spotFinder = std::make_unique<ImageSpotFinderCPU>(experiment.GetXPixelsNum(), experiment.GetYPixelsNum());
|
|
azint = std::make_unique<AzIntEngineCPU>(integration);
|
|
preprocessor = std::make_unique<ImagePreprocessorCPU>(in_experiment, in_mask);
|
|
bragg_engine = std::make_unique<BraggIntegrationEngineCPU>(in_experiment);
|
|
if (experiment.ROI().size() >= 1)
|
|
roi = std::make_unique<ROIIntegrationCPU>(experiment);
|
|
#ifdef JFJOCH_USE_CUDA
|
|
} else {
|
|
stream = std::make_shared<CudaStream>();
|
|
preprocessor_buffer = std::make_unique<ImagePreprocessorBufferGPU>(experiment.GetPixelsNum());
|
|
preprocessor = std::make_unique<ImagePreprocessorGPU>(in_experiment, in_mask, stream);
|
|
spotFinder = std::make_unique<ImageSpotFinderGPU>(experiment.GetXPixelsNum(), experiment.GetYPixelsNum(), stream);
|
|
azint = std::make_unique<AzIntEngineGPU>(integration, stream);
|
|
bragg_engine = std::make_unique<BraggIntegrationEngineGPU>(in_experiment, stream);
|
|
if (experiment.ROI().size() >= 1)
|
|
roi = std::make_unique<ROIIntegrationGPU>(experiment, stream);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
void MXAnalysisWithoutFPGA::Analyze(DataMessage &output,
|
|
AzimuthalIntegrationProfile &profile,
|
|
const SpotFindingSettings &spot_finding_settings) {
|
|
if ((output.image.GetWidth() != xpixels)
|
|
|| (output.image.GetWidth() * output.image.GetHeight() != npixels))
|
|
throw JFJochException(JFJochExceptionCategory::InputParameterInvalid,
|
|
"Mismatch in pixel size");
|
|
|
|
const auto compression_start_time = std::chrono::steady_clock::now();
|
|
const uint8_t *image_ptr = output.image.GetUncompressedPtr(decompression_buffer);
|
|
const auto compression_end_time = std::chrono::steady_clock::now();
|
|
if (output.image.GetCompressionAlgorithm() != CompressionAlgorithm::NO_COMPRESSION)
|
|
output.compression_time_s = std::chrono::duration<float>(compression_end_time - compression_start_time).count();
|
|
|
|
const auto preprocessing_start_time = std::chrono::steady_clock::now();
|
|
auto ret = preprocessor->Analyze(*preprocessor_buffer, image_ptr, output.image.GetMode());
|
|
const auto preprocessing_end_time = std::chrono::steady_clock::now();
|
|
output.preprocessing_time_s = std::chrono::duration<float>(preprocessing_end_time - preprocessing_start_time).count();
|
|
|
|
const auto azint_start_time = std::chrono::steady_clock::now();
|
|
azint->Run(*preprocessor_buffer, profile);
|
|
const auto azint_end_time = std::chrono::steady_clock::now();
|
|
output.azint_time_s = std::chrono::duration<float>(azint_end_time - azint_start_time).count();
|
|
|
|
if (roi)
|
|
roi->Run(*preprocessor_buffer, output.roi);
|
|
|
|
if (spot_finding_settings.enable) {
|
|
// Update resolution mask
|
|
if (mask_high_res != spot_finding_settings.high_resolution_limit
|
|
|| mask_low_res != spot_finding_settings.low_resolution_limit)
|
|
UpdateMaskResolution(spot_finding_settings);
|
|
|
|
const auto spot_finding_start_time = std::chrono::steady_clock::now();
|
|
const std::vector<DiffractionSpot> spots = spotFinder->Run(*preprocessor_buffer, spot_finding_settings, mask_resolution);
|
|
SpotAnalyze(experiment, spot_finding_settings, spots, output);
|
|
const auto spot_finding_end_time = std::chrono::steady_clock::now();
|
|
output.spot_finding_time_s = std::chrono::duration<float>(spot_finding_end_time - spot_finding_start_time).count();
|
|
|
|
if (spot_finding_settings.indexing)
|
|
indexer.ProcessImage(output, spot_finding_settings, *prediction,
|
|
[this](const std::vector<Reflection> &predicted, size_t npredicted, int64_t image_number) {
|
|
return bragg_engine->Run(*preprocessor_buffer, predicted, npredicted, image_number);
|
|
});
|
|
}
|
|
|
|
output.max_viable_pixel_value = ret.max_value;
|
|
output.min_viable_pixel_value = ret.min_value;
|
|
output.error_pixel_count = ret.error_pixel_count;
|
|
output.saturated_pixel_count = ret.saturated_pixel_count;
|
|
output.az_int_profile = profile.GetResult();
|
|
output.az_int_profile_count = profile.GetPixelCount();
|
|
output.az_int_profile_std = profile.GetStd();
|
|
|
|
output.bkg_estimate = profile.GetBkgEstimate(integration.Settings());
|
|
output.ice_ring_score = profile.GetIceRingScore(integration.Settings(),
|
|
spot_finding_settings.ice_ring_width_Q_recipA);
|
|
}
|
|
|
|
void MXAnalysisWithoutFPGA::RebuildROI() {
|
|
if (experiment.ROI().empty()) {
|
|
roi.reset();
|
|
return;
|
|
}
|
|
#ifdef JFJOCH_USE_CUDA
|
|
if (stream) {
|
|
roi = std::make_unique<ROIIntegrationGPU>(experiment, stream);
|
|
return;
|
|
}
|
|
#endif
|
|
roi = std::make_unique<ROIIntegrationCPU>(experiment);
|
|
}
|
|
|
|
void MXAnalysisWithoutFPGA::AnalyzeROIOnly(DataMessage &output) {
|
|
if ((output.image.GetWidth() != xpixels)
|
|
|| (output.image.GetWidth() * output.image.GetHeight() != npixels))
|
|
throw JFJochException(JFJochExceptionCategory::InputParameterInvalid,
|
|
"Mismatch in pixel size");
|
|
|
|
const uint8_t *image_ptr = output.image.GetUncompressedPtr(decompression_buffer);
|
|
preprocessor->Analyze(*preprocessor_buffer, image_ptr, output.image.GetMode());
|
|
RunROIOnly(output);
|
|
}
|
|
|
|
void MXAnalysisWithoutFPGA::RunROIOnly(DataMessage &output) {
|
|
output.roi.clear();
|
|
if (roi)
|
|
roi->Run(*preprocessor_buffer, output.roi);
|
|
}
|
|
|
|
void MXAnalysisWithoutFPGA::UpdateMaskResolution(const SpotFindingSettings &settings) {
|
|
mask_low_res = settings.low_resolution_limit;
|
|
mask_high_res = settings.high_resolution_limit;
|
|
auto const &resolution_map = integration.Resolution();
|
|
for (int i = 0; i < mask_resolution.size(); i++)
|
|
mask_resolution[i] = (resolution_map[i] > mask_low_res) || (resolution_map[i] < mask_high_res);
|
|
}
|