leonarski_fandClaude Opus 4.8
fb399480e5
Serial stills currently treat every reflection as a full (partiality hardcoded to 1). Add an opt-in Gaussian excitation-error partiality set at prediction time (CPU + CUDA): p = exp(-dist_ewald^2 / (2*sigma^2)), sigma^2 = profile_radius^2 + (bandwidth_sigma*|recip_z|)^2, with sigma = the per-image profile radius (ewald_dist_cutoff/2), so an edge-of-acceptance reflection keeps p ~ exp(-2). Off by default; the merge weight (~p^2) then down-weights far-from-Ewald partials instead of trusting them as fulls. Validated: helps medium/strong stills (LOV R-free 0.336->0.329, lyso8 0.433->0.410, lowers the systematic error-model b in both) but HURTS weak OCP (dividing by a small, uncertain p amplifies orientation error -> high-res noise, resolution collapse), so it is left opt-in. A static forward p explains only ~6-10% of the partiality scatter; the full win needs per-image post-refinement (future work), for which this is the prediction-side groundwork. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
52 lines
1.4 KiB
C++
52 lines
1.4 KiB
C++
// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#pragma once
|
|
|
|
#include <vector>
|
|
|
|
#include "BraggPrediction.h"
|
|
|
|
#include "../indexing/CUDAMemHelpers.h"
|
|
|
|
struct KernelConsts {
|
|
float det_width_pxl;
|
|
float det_height_pxl;
|
|
float beam_x;
|
|
float beam_y;
|
|
float coeff_const;
|
|
float one_over_wavelength;
|
|
float one_over_dmax_sq;
|
|
float ewald_cutoff;
|
|
float bandwidth_sigma; // relative Δλ/λ (sigma); 0 = monochromatic
|
|
bool still_partiality; // experimental stills excitation-error partiality (off => p = 1, fulls)
|
|
float profile_radius_recipA; // Gaussian sigma [1/A] for the stills partiality
|
|
Coord Astar, Bstar, Cstar, S0;
|
|
float rot[9];
|
|
char centering;
|
|
};
|
|
|
|
class BraggPredictionGPU : public BraggPrediction {
|
|
CudaRegisteredVector<Reflection> reg_out; // requires stable storage
|
|
CudaDevicePtr<Reflection> d_out;
|
|
|
|
// Dedicated stream
|
|
CudaStream stream;
|
|
|
|
// Device allocations via helpers
|
|
CudaDevicePtr<KernelConsts> dK;
|
|
CudaDevicePtr<int> d_count;
|
|
|
|
// Host pinned buffer for async download (optional but faster)
|
|
CudaHostPtr<int> h_count;
|
|
|
|
public:
|
|
explicit BraggPredictionGPU(int max_reflections = kPredictionCapacity);
|
|
|
|
int Calc(const DiffractionExperiment &experiment,
|
|
const CrystalLattice &lattice,
|
|
const BraggPredictionSettings &settings) override;
|
|
};
|
|
|
|
|