Build Packages / Create release (push) Successful in 24s
Build Packages / build:viewer:macos-arm64:nocuda (push) Successful in 3m29s
Build Packages / build:rugnux:macos-arm64:nocuda (push) Successful in 2m43s
Build Packages / build:rugnux:linux-aarch64:cuda (push) Successful in 8m27s
Build Packages / build:rugnux:linux-x86_64:cuda (push) Successful in 9m53s
Build Packages / build:viewer:linux-x86_64:nocuda (push) Successful in 9m58s
Build Packages / build:viewer:linux-x86_64:cuda (push) Successful in 11m22s
Build Packages / build:jfjoch:rocky8:nocuda (push) Successful in 13m39s
Build Packages / build:viewer:windows-x86_64:nocuda (push) Successful in 18m37s
Build Packages / build:jfjoch:rocky9:nocuda (push) Successful in 16m32s
Build Packages / build:viewer:windows-x86_64:cuda (push) Successful in 24m11s
Build Packages / HDF5 consumer tests (DIALS, XDS) (push) Successful in 25m30s
Build Packages / build:jfjoch:ubuntu2404:nocuda (push) Successful in 19m3s
Build Packages / build:jfjoch:ubuntu2204:nocuda (push) Successful in 20m23s
Build Packages / build:jfjoch:rocky8:cuda-sls9 (push) Successful in 19m41s
Build Packages / Generate python client (push) Successful in 50s
Build Packages / Build documentation (push) Successful in 1m16s
Build Packages / build:jfjoch:rocky9:cuda-sls9 (push) Successful in 21m0s
Build Packages / build:jfjoch:rocky8:cuda (push) Successful in 18m38s
Build Packages / build:rugnux:windows-x86_64:cuda (push) Successful in 14m33s
Build Packages / build:jfjoch:rocky9:cuda (push) Successful in 17m55s
Build Packages / build:jfjoch:ubuntu2204:cuda (push) Successful in 20m50s
Build Packages / build:jfjoch:ubuntu2404:cuda (push) Successful in 18m38s
Build Packages / Unit tests (push) Successful in 1h46m14s
* jfjoch_broker: Optional per-dataset authentication - statistics, images and plots can require a bearer token, which jfjoch_viewer supports. * jfjoch_viewer: Dark mode and a theme-matched colour scheme, a magnifier panel, and simpler contrast and background controls. * Rugnux: Multiple performance improvements on GPU and CPU (CPU-only processing up to 40% faster, faster image decoding on ARM), with unchanged results. * Rugnux: `--model` rigid-body refinement runs on the GPU, and the model-validation check is faster and more reliable. * Rugnux: Improved scaling and merging - error model, outlier rejection, absorption correction and French-Wilson amplitudes now agree more closely with XDS and ctruncate. * Rugnux: Improved integration - radial background on powder and ice rings, crowded rotation data keep their reflections, and CPU-only builds integrate large unit cells as GPU builds do. * Rugnux: More robust detector geometry - measured beam centre, X-ray bandwidth and goniometer rate, and geometry refinement accepted only on significant evidence. * Rugnux: Merged files are written in the standard setting, or in the setting of a reference MTZ, structure-factor mmCIF or model, with its free-R flags. * Rugnux: Richer report - ice and powder rings, further lattices, superstructure candidates and mosaicity, with warnings worded as prompts to check. * Rugnux: Clear error messages when a data set needs more GPU or host memory than is available. Reviewed-on: #83 Co-authored-by: Filip Leonarski <filip.leonarski@psi.ch>
235 lines
11 KiB
C++
235 lines
11 KiB
C++
// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
||
// SPDX-License-Identifier: GPL-3.0-only
|
||
|
||
#include <algorithm>
|
||
|
||
#include "../../common/JFJochMath.h"
|
||
#include "../../common/Logger.h"
|
||
#include "BraggPrediction.h"
|
||
#include "../SensorAbsorption.h"
|
||
#include "../bragg_integration/SystematicAbsence.h"
|
||
|
||
void BraggPrediction::GrowCapacity(int count) {
|
||
reflections.resize(count);
|
||
max_reflections = count;
|
||
}
|
||
|
||
void BraggPrediction::OrderOutput(int count) {
|
||
order_keys.resize(count);
|
||
for (int i = 0; i < count; i++) {
|
||
const Reflection &r = reflections[i];
|
||
order_keys[i] = {r.h, r.k, r.l, r.delta_phi_deg, i};
|
||
}
|
||
std::sort(order_keys.begin(), order_keys.end(),
|
||
[](const OrderKey &a, const OrderKey &b) {
|
||
if (a.h != b.h) return a.h < b.h;
|
||
if (a.k != b.k) return a.k < b.k;
|
||
if (a.l != b.l) return a.l < b.l;
|
||
return a.delta_phi_deg < b.delta_phi_deg;
|
||
});
|
||
order_scratch.resize(count);
|
||
for (int i = 0; i < count; i++) order_scratch[i] = reflections[order_keys[i].index];
|
||
std::copy(order_scratch.begin(), order_scratch.end(), reflections.begin());
|
||
}
|
||
|
||
int BraggPrediction::TruncateToOutput(int count) {
|
||
if (count <= output_limit)
|
||
return count;
|
||
|
||
// Partiality first, then excitation error: exactly one of the two says anything on each path. On the
|
||
// rotation path dist_ewald is identically zero - BraggPredictionRot picks the rocking coordinate so
|
||
// that 2*S0.p + p.p = 0, i.e. |S| = 1/lambda exactly - so ranking by it there left an hkl-lexicographic
|
||
// prefix rather than the best-recorded reflections. On the still path every partiality is 1, so the
|
||
// ranking falls through to dist_ewald, which is what it has always been.
|
||
std::partial_sort(reflections.begin(), reflections.begin() + output_limit,
|
||
reflections.begin() + count,
|
||
[](const Reflection &a, const Reflection &b) {
|
||
if (a.partiality != b.partiality) return a.partiality > b.partiality;
|
||
if (a.dist_ewald != b.dist_ewald) return a.dist_ewald < b.dist_ewald;
|
||
if (a.h != b.h) return a.h < b.h;
|
||
if (a.k != b.k) return a.k < b.k;
|
||
return a.l < b.l;
|
||
});
|
||
return output_limit;
|
||
}
|
||
|
||
namespace {
|
||
// Number of bandwidth sigmas included in the (radially thickened) Ewald-shell
|
||
// acceptance window. 3σ captures essentially the whole pink-beam smear; matches
|
||
// the conservative end of the mosaicity cutoff used by callers.
|
||
constexpr float kBandwidthCutoffSigmas = 3.0f;
|
||
}
|
||
|
||
BraggPrediction::BraggPrediction(int max_reflections)
|
||
: max_reflections(max_reflections), reflections(max_reflections) {}
|
||
|
||
const std::vector<Reflection> &BraggPrediction::GetReflections() const {
|
||
return reflections;
|
||
}
|
||
|
||
int BraggPrediction::Calc(const DiffractionExperiment &experiment, const CrystalLattice &lattice,
|
||
const BraggPredictionSettings &settings) {
|
||
|
||
const auto geom = experiment.GetDiffractionGeometry();
|
||
const auto det_width_pxl = static_cast<float>(experiment.GetXPixelsNum());
|
||
const auto det_height_pxl = static_cast<float>(experiment.GetYPixelsNum());
|
||
|
||
const float one_over_dmax = 1.0f / settings.high_res_A;
|
||
const float one_over_dmax_sq = one_over_dmax * one_over_dmax;
|
||
|
||
float one_over_wavelength = 1.0f / geom.GetWavelength_A();
|
||
|
||
const Coord Astar = lattice.Astar();
|
||
const Coord Bstar = lattice.Bstar();
|
||
const Coord Cstar = lattice.Cstar();
|
||
const Coord S0 = geom.GetScatteringVector();
|
||
|
||
std::vector<float> rot = geom.GetDetectorMatrix().transpose().arr();
|
||
|
||
// Precompute detector geometry constants
|
||
float beam_x = geom.GetBeamX_pxl();
|
||
float beam_y = geom.GetBeamY_pxl();
|
||
float det_distance = geom.GetDetectorDistance_mm();
|
||
float pixel_size = geom.GetPixelSize_mm();
|
||
float F = det_distance / pixel_size;
|
||
|
||
// Angle-dependent sensor efficiency; per-dataset constants collapsed to two numbers. Inert
|
||
// wherever the sensor is opaque, which is every long wavelength.
|
||
const auto &det_setup = experiment.GetDetectorSetup();
|
||
const auto sensor_qe = sensor_absorption::SensorQE::Build(
|
||
det_setup.GetSensorMaterial(), det_setup.GetSensorThickness_um(), geom.GetWavelength_A());
|
||
// The air in the sample-to-pixel flight path carries the same cos(alpha) dependence, with the
|
||
// opposite sign. See sensor_absorption::FlightPathAttenuation; off leaves d_over_L at 0, which is
|
||
// bit-identical to not applying it.
|
||
const auto air = sensor_absorption::FlightPathAttenuation::Build(
|
||
experiment.GetBraggIntegrationSettings().GetFlightPath(), det_distance,
|
||
geom.GetWavelength_A());
|
||
|
||
const float epsilon = 1e-5f;
|
||
const float s0_sq = S0 * S0;
|
||
const float rad_to_deg = 180.0f / static_cast<float>(PI);
|
||
|
||
int i = 0;
|
||
|
||
for (int h = -settings.max_h; h <= settings.max_h; h++) {
|
||
// Precompute A* h contribution
|
||
const float Ah_x = Astar.x * h;
|
||
const float Ah_y = Astar.y * h;
|
||
const float Ah_z = Astar.z * h;
|
||
|
||
for (int k = -settings.max_k; k <= settings.max_k; k++) {
|
||
// Accumulate B* k contribution
|
||
const float AhBk_x = Ah_x + Bstar.x * k;
|
||
const float AhBk_y = Ah_y + Bstar.y * k;
|
||
const float AhBk_z = Ah_z + Bstar.z * k;
|
||
|
||
for (int l = -settings.max_l; l <= settings.max_l; l++) {
|
||
if (systematic_absence(h, k, l, settings.centering))
|
||
continue;
|
||
|
||
float recip_x = AhBk_x + Cstar.x * l;
|
||
float recip_y = AhBk_y + Cstar.y * l;
|
||
float recip_z = AhBk_z + Cstar.z * l;
|
||
|
||
float recip_sq = recip_x * recip_x + recip_y * recip_y + recip_z * recip_z;
|
||
if (recip_sq > one_over_dmax_sq)
|
||
continue;
|
||
|
||
float S_x = recip_x + S0.x;
|
||
float S_y = recip_y + S0.y;
|
||
float S_z = recip_z + S0.z;
|
||
float S_len = sqrtf(S_x * S_x + S_y * S_y + S_z * S_z);
|
||
float dist_ewald_sphere = std::fabs(S_len - one_over_wavelength);
|
||
|
||
// Energy bandwidth thickens the Ewald shell radially: at the
|
||
// diffraction condition |S|-1/λ shifts by recip_z·(Δλ/λ), i.e.
|
||
// σ_bw = |recip_z|·bandwidth_sigma (= bλ/2d²). Broaden the acceptance
|
||
// window in quadrature so high-resolution shells (smeared most, ∝1/d²)
|
||
// are not clipped.
|
||
float radial_cutoff = settings.ewald_dist_cutoff;
|
||
if (settings.bandwidth_sigma > 0.0f) {
|
||
const float bw_tol = kBandwidthCutoffSigmas * settings.bandwidth_sigma * std::fabs(recip_z);
|
||
radial_cutoff = std::sqrt(radial_cutoff * radial_cutoff + bw_tol * bw_tol);
|
||
}
|
||
|
||
if (dist_ewald_sphere <= radial_cutoff ) {
|
||
const float s0_p0 = S0.x * recip_x + S0.y * recip_y + S0.z * recip_z;
|
||
const float val = s0_sq * recip_sq - s0_p0 * s0_p0;
|
||
|
||
float delta_phi_deg = NAN;
|
||
if (std::fabs(val) >= epsilon && s0_sq > epsilon) {
|
||
const float a_num = (s0_sq - 0.25f * recip_sq) * recip_sq;
|
||
if (a_num >= 0.0f) {
|
||
const float A = std::sqrt(a_num / val);
|
||
const float B = (A * s0_p0 + 0.5f * recip_sq) / s0_sq;
|
||
|
||
const float p_star_x = A * recip_x - B * S0.x;
|
||
const float p_star_y = A * recip_y - B * S0.y;
|
||
const float p_star_z = A * recip_z - B * S0.z;
|
||
|
||
const float p_star_sq = p_star_x * p_star_x + p_star_y * p_star_y + p_star_z * p_star_z;
|
||
const float denom = std::sqrt(p_star_sq * recip_sq);
|
||
|
||
if (denom >= epsilon) {
|
||
float c = (p_star_x * recip_x + p_star_y * recip_y + p_star_z * recip_z) / denom;
|
||
c = std::fmax(-1.0f, std::fmin(1.0f, c));
|
||
delta_phi_deg = std::acos(c) * rad_to_deg;
|
||
}
|
||
}
|
||
}
|
||
|
||
// Inlined RecipToDetector: the full transposed detector matrix, tilt and discrete orientation
|
||
// Apply rotation matrix transpose
|
||
float S_rot_x = rot[0] * S_x + rot[1] * S_y + rot[2] * S_z;
|
||
float S_rot_y = rot[3] * S_x + rot[4] * S_y + rot[5] * S_z;
|
||
float S_rot_z = rot[6] * S_x + rot[7] * S_y + rot[8] * S_z;
|
||
|
||
if (S_rot_z <= 0)
|
||
continue;
|
||
|
||
// Project to detector coordinates
|
||
// Assume detector is along x,y,z coordinates after rotation
|
||
float x = beam_x + F * S_rot_x / S_rot_z;
|
||
float y = beam_y + F * S_rot_y / S_rot_z;
|
||
|
||
if ((x < 0) || (x >= det_width_pxl) || (y < 0) || (y >= det_height_pxl))
|
||
continue;
|
||
|
||
// Sensor quantum efficiency at this reflection's angle of incidence on the
|
||
// detector - the diffracted direction against the detector normal, so the
|
||
// detector tilt is carried for free. See sensor_absorption::SensorQE.
|
||
const float cos_alpha =
|
||
S_rot_z / std::sqrt(S_x * S_x + S_y * S_y + S_z * S_z);
|
||
const float qe_corr = sensor_qe.Factor(cos_alpha);
|
||
const float flight_corr = air.Factor(cos_alpha);
|
||
|
||
if (i == max_reflections)
|
||
GrowCapacity(2 * max_reflections);
|
||
|
||
float d = 1.0f / sqrtf(recip_sq);
|
||
reflections[i] = Reflection{
|
||
.h = h,
|
||
.k = k,
|
||
.l = l,
|
||
.delta_phi_deg = delta_phi_deg,
|
||
.predicted_x = x,
|
||
.predicted_y = y,
|
||
.observed_x = NAN,
|
||
.observed_y = NAN,
|
||
.d = d,
|
||
.dist_ewald = dist_ewald_sphere,
|
||
.prescaling_corr = 1.0f,
|
||
.qe_corr = qe_corr,
|
||
.flight_corr = flight_corr,
|
||
.partiality = 1.0f,
|
||
.zeta = 1.0,
|
||
.image_scale_corr = qe_corr * flight_corr
|
||
};
|
||
++i;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
return TruncateToOutput(i);
|
||
}
|