Files
Jungfraujoch/image_analysis/geom_refinement/GeometryRefiner.cpp
T
leonarski_fandClaude Opus 5 641f890a40 Build the frame's constants once, and page-lock what the integration engine copies
The per-image geometry refinement is the largest stage of the image loop, and a
third of it was arithmetic on numbers that never change.

The residual derives the detector angles' sines and cosines, the goniometer's
back-rotation - a three-argument hypot, a sine, a cosine and a division - and the
reciprocal basis of the cell on every evaluation. On the rotation path the detector
angles and the axis are held fixed and stored as plain doubles, so all of it is
constant, not merely constant per block: there is one frame per image and one cell.
Three solves an image, fifty iterations a solve and a thousand spots make it tens of
thousands of repetitions of the same result. The frame's constants are now built
once and handed in. The body they feed is the same body, split out rather than
copied, so no expression is reassociated - in particular the reciprocal vector is
still formed as the basis times the inverse volume, with the volume not folded into
the basis.

The spot confidence weights depend only on each spot's resolution and intensity,
which no solver touches, and were recomputed identically for each of the three
passes. They are computed once. The sort behind them ordered indices through a
projection that chased a random eighty-byte-strided element per comparison; it now
sorts a packed resolution and index, which makes the same comparisons in the same
sequence and therefore the same permutation. The spot list itself was copied per
image through an initializer list whose elements are const; it is passed as a view.

The integration engine was the last one in the loop copying through pageable host
memory - three transfers in and eight out per image, twenty-six bytes a reflection,
while every other engine already page-locks its staging. A driver copy from pageable
memory stages through its own pinned buffer on the calling thread, which is why an
asynchronous copy was averaging a hundred and thirteen microseconds. Page-locked, the
same seventeen thousand calls cost four hundred and thirty-two milliseconds instead
of one and a half seconds, and the wait moves to the synchronisation point where it
belongs.

Two smaller ones: the reflections were copied into the per-image message for a
process file that a merging run does not write, so the copy is made where a writer
exists; and the intensity statistics and the Wilson estimate walked the same
eighty-byte array twice to read twelve bytes, which is now one pass with each
accumulation in its own order.

Every reflection file is byte-identical on four crystals; the process file's
reflections match dataset for dataset, and its azimuthal arrays differ no more
between this build and the last than the last differs from itself.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EGpGdgmJ8MyY9pCGWjktyi
2026-08-25 01:08:22 +02:00

320 lines
16 KiB
C++

// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "GeometryRefiner.h"
#include <algorithm>
#include <array>
#include <cmath>
#include <vector>
#include "../../common/JFJochMath.h" // PI
#include "LatticeReduction.h"
#include "XtalResidual.h"
#include "ceres/ceres.h"
namespace {
// Trigonal is described with the hexagonal cell + B, same as the per-image XtalOptimizer.
gemmi::CrystalSystem MapSystem(gemmi::CrystalSystem s) {
return (s == gemmi::CrystalSystem::Trigonal) ? gemmi::CrystalSystem::Hexagonal : s;
}
// The cell angles (radians) that XtalResidual bakes into its B matrix for a given system. Only
// monoclinic (beta) and triclinic (all three) read p2; the rest use fixed symmetry angles. We keep the
// angles constant in v1, so these are set once from the input cell.
void InitCellAngles(gemmi::CrystalSystem system, const UnitCell &cell, double ang[3]) {
const double d2r = PI / 180.0;
switch (system) {
case gemmi::CrystalSystem::Hexagonal:
ang[0] = PI / 2.0; ang[1] = PI / 2.0; ang[2] = 2.0 * PI / 3.0;
break;
case gemmi::CrystalSystem::Monoclinic:
// XtalResidual reads p2[0] as beta.
ang[0] = cell.beta * d2r; ang[1] = PI / 2.0; ang[2] = PI / 2.0;
break;
case gemmi::CrystalSystem::Triclinic:
ang[0] = cell.alpha * d2r; ang[1] = cell.beta * d2r; ang[2] = cell.gamma * d2r;
break;
default: // orthorhombic / tetragonal / cubic
ang[0] = PI / 2.0; ang[1] = PI / 2.0; ang[2] = PI / 2.0;
break;
}
}
// Effective (lengths, alpha,beta,gamma) that reproduce the lattice XtalResidual builds from (len, ang),
// so a frame's lattice can be reconstructed with AngleAxisAndCellToLattice for HKL re-assignment.
void EffectiveCell(gemmi::CrystalSystem system, const double len[3], const double ang[3],
double lengths[3], double &alpha, double &beta, double &gamma) {
switch (system) {
case gemmi::CrystalSystem::Hexagonal:
lengths[0] = len[0]; lengths[1] = len[0]; lengths[2] = len[2];
alpha = PI / 2.0; beta = PI / 2.0; gamma = 2.0 * PI / 3.0;
break;
case gemmi::CrystalSystem::Tetragonal:
lengths[0] = len[0]; lengths[1] = len[0]; lengths[2] = len[2];
alpha = PI / 2.0; beta = PI / 2.0; gamma = PI / 2.0;
break;
case gemmi::CrystalSystem::Cubic:
lengths[0] = len[0]; lengths[1] = len[0]; lengths[2] = len[0];
alpha = PI / 2.0; beta = PI / 2.0; gamma = PI / 2.0;
break;
case gemmi::CrystalSystem::Monoclinic:
lengths[0] = len[0]; lengths[1] = len[1]; lengths[2] = len[2];
alpha = PI / 2.0; beta = ang[0]; gamma = PI / 2.0;
break;
case gemmi::CrystalSystem::Triclinic:
lengths[0] = len[0]; lengths[1] = len[1]; lengths[2] = len[2];
alpha = ang[0]; beta = ang[1]; gamma = ang[2];
break;
default: // orthorhombic
lengths[0] = len[0]; lengths[1] = len[1]; lengths[2] = len[2];
alpha = PI / 2.0; beta = PI / 2.0; gamma = PI / 2.0;
break;
}
}
// Orientation seed (angle-axis) for a frame's lattice, using the per-system decomposition the per-image
// optimizer uses so it matches XtalResidual's B convention.
void OrientationSeed(gemmi::CrystalSystem system, const CrystalLattice &latt, double rod[3]) {
double scratch[3];
if (system == gemmi::CrystalSystem::Hexagonal) {
LatticeToRodriguesAndLengths_Hex(latt, rod, scratch);
} else if (system == gemmi::CrystalSystem::Monoclinic) {
double beta;
LatticeToRodriguesLengthsBeta_Mono(latt, rod, scratch, beta);
} else {
LatticeToRodriguesAndLengths_GS(latt, rod, scratch);
}
}
UnitCell BuildUnitCell(gemmi::CrystalSystem system, const double len[3], const double ang[3]) {
const double r2d = 180.0 / PI;
UnitCell uc{};
switch (system) {
case gemmi::CrystalSystem::Hexagonal:
uc = {(float)len[0], (float)len[0], (float)len[2], 90.0f, 90.0f, 120.0f};
break;
case gemmi::CrystalSystem::Tetragonal:
uc = {(float)len[0], (float)len[0], (float)len[2], 90.0f, 90.0f, 90.0f};
break;
case gemmi::CrystalSystem::Cubic:
uc = {(float)len[0], (float)len[0], (float)len[0], 90.0f, 90.0f, 90.0f};
break;
case gemmi::CrystalSystem::Monoclinic:
uc = {(float)len[0], (float)len[1], (float)len[2], 90.0f, (float)(ang[0] * r2d), 90.0f};
break;
case gemmi::CrystalSystem::Triclinic:
uc = {(float)len[0], (float)len[1], (float)len[2],
(float)(ang[0] * r2d), (float)(ang[1] * r2d), (float)(ang[2] * r2d)};
break;
default: // orthorhombic
uc = {(float)len[0], (float)len[1], (float)len[2], 90.0f, 90.0f, 90.0f};
break;
}
return uc;
}
// Anchors the cell lengths to the input cell. Penalises each length's deviation from its input value
// with a large weight, breaking the low-resolution distance<->cell-scale degeneracy (position ~
// distance / cell_scale) so distance is determined by the data with the cell pinned.
struct CellLengthRegularizer {
double w0, w1, w2;
double l0, l1, l2;
template <typename T>
bool operator()(const T *const len, T *r) const {
r[0] = T(w0) * (len[0] - T(l0));
r[1] = T(w1) * (len[1] - T(l1));
r[2] = T(w2) * (len[2] - T(l2));
return true;
}
};
} // namespace
GeometryRefinerResult RefineGlobalGeometry(const DiffractionGeometry &nominal_geom,
const UnitCell &input_cell,
const std::vector<GeomRefineFrame> &frames,
const GeometryRefinerSettings &settings) {
GeometryRefinerResult result;
try {
const gemmi::CrystalSystem system = MapSystem(settings.crystal_system);
// Shared geometry parameter blocks (refined). Detector tilt and the rotation axis are constant.
double beam[2] = {nominal_geom.GetBeamX_pxl(), nominal_geom.GetBeamY_pxl()};
double distance_mm = nominal_geom.GetDetectorDistance_mm();
double detector_rot[2] = {nominal_geom.GetPoniRot1_rad(), nominal_geom.GetPoniRot2_rad()};
double rot_vec[3] = {1.0, 0.0, 0.0};
const double rot3 = nominal_geom.GetPoniRot3_rad();
// Same for every spot of every frame, so taken once here rather than per residual.
const double cos_rot3 = std::cos(rot3), sin_rot3 = std::sin(rot3);
const double lambda = nominal_geom.GetWavelength_A();
const double pixel = nominal_geom.GetPixelSize_mm();
// Shared cell blocks. Lengths refined (regularized); angles constant.
double cell_len[3] = {input_cell.a, input_cell.b, input_cell.c};
const double cell_len0[3] = {input_cell.a, input_cell.b, input_cell.c};
double cell_ang[3];
InitCellAngles(system, input_cell, cell_ang);
double eff_len[3], eff_alpha, eff_beta, eff_gamma; // recomputed each round from cell_len/ang
// Per-frame orientation seeds.
std::vector<std::array<double, 3>> orient(frames.size());
for (size_t i = 0; i < frames.size(); ++i)
OrientationSeed(system, frames[i].lattice, orient[i].data());
// Reciprocal length of one detector pixel at the nominal geometry, used to scale the robust
// loss (~3 px) into the reciprocal-space residual units.
const double recip_per_px = pixel / (distance_mm * lambda);
const double loss_scale = 3.0 * recip_per_px;
// Tolerance schedule (fractional-hkl norm), tightening each round like the per-image optimizer.
auto round_tol = [&](int r) {
if (settings.rounds <= 1) return 0.2;
const double t = static_cast<double>(r) / (settings.rounds - 1);
return 0.3 - (0.3 - 0.1) * t;
};
// Whether the last solve that ran produced a usable solution; folded into result.ok below,
// which otherwise reports success on spot and frame counts alone.
bool solve_usable = false;
for (int round = 0; round < settings.rounds; ++round) {
EffectiveCell(system, cell_len, cell_ang, eff_len, eff_alpha, eff_beta, eff_gamma);
DiffractionGeometry cur = nominal_geom;
cur.BeamX_pxl(beam[0]).BeamY_pxl(beam[1]).DetectorDistance_mm(distance_mm);
const double tol = round_tol(round);
const double tol_sq = tol * tol;
ceres::Problem problem;
auto ordering = std::make_shared<ceres::ParameterBlockOrdering>();
int spots_used = 0, frames_used = 0;
for (size_t i = 0; i < frames.size(); ++i) {
const CrystalLattice latt = AngleAxisAndCellToLattice(
orient[i].data(), eff_len, eff_alpha, eff_beta, eff_gamma);
const Coord v0 = latt.Vec0(), v1 = latt.Vec1(), v2 = latt.Vec2();
int used_in_frame = 0;
for (const auto &s : frames[i].spots) {
const Coord recip = cur.DetectorToRecip(s.x, s.y);
const double hf = recip * v0, kf = recip * v1, lf = recip * v2;
const double h = std::round(hf), k = std::round(kf), l = std::round(lf);
const double dn = (hf - h) * (hf - h) + (kf - k) * (kf - k) + (lf - l) * (lf - l);
if (dn > tol_sq)
continue;
problem.AddResidualBlock(
new ceres::AutoDiffCostFunction<XtalResidual, 3, 2, 1, 2, 3, 3, 3, 3>(
new XtalResidual(s.x, s.y, lambda, pixel, cos_rot3, sin_rot3, 0.0,
h, k, l, system)),
new ceres::CauchyLoss(loss_scale),
beam, &distance_mm, detector_rot, rot_vec, orient[i].data(), cell_len, cell_ang);
++used_in_frame;
++spots_used;
}
if (used_in_frame > 0) {
ordering->AddElementToGroup(orient[i].data(), 0); // eliminate orientations first
++frames_used;
}
}
if (spots_used < settings.min_spots_total) {
if (round == 0)
return result; // ok stays false
break; // keep the previous round's solution
}
// Cell-length regularizer (weight ~ coeff * sqrt(N_obs) / L0^2 -> effectively pins the cell).
const double sqrtN = std::sqrt(static_cast<double>(spots_used));
CellLengthRegularizer *reg = new CellLengthRegularizer{
settings.cell_reg_coeff * sqrtN / (cell_len0[0] * cell_len0[0]),
settings.cell_reg_coeff * sqrtN / (cell_len0[1] * cell_len0[1]),
settings.cell_reg_coeff * sqrtN / (cell_len0[2] * cell_len0[2]),
cell_len0[0], cell_len0[1], cell_len0[2]};
problem.AddResidualBlock(
new ceres::AutoDiffCostFunction<CellLengthRegularizer, 3, 3>(reg), nullptr, cell_len);
// Shared blocks go in the second elimination group; constant ones are stripped by Ceres.
for (double *b : {beam, &distance_mm, detector_rot, rot_vec, cell_len, cell_ang})
ordering->AddElementToGroup(b, 1);
// Beam + distance bounds around the nominal value; cell lengths loosely bounded (the
// regularizer does the anchoring).
problem.SetParameterLowerBound(beam, 0, nominal_geom.GetBeamX_pxl() - settings.beam_range_px);
problem.SetParameterUpperBound(beam, 0, nominal_geom.GetBeamX_pxl() + settings.beam_range_px);
problem.SetParameterLowerBound(beam, 1, nominal_geom.GetBeamY_pxl() - settings.beam_range_px);
problem.SetParameterUpperBound(beam, 1, nominal_geom.GetBeamY_pxl() + settings.beam_range_px);
problem.SetParameterLowerBound(&distance_mm, 0,
std::max(1.0, nominal_geom.GetDetectorDistance_mm() - settings.distance_range_mm));
problem.SetParameterUpperBound(&distance_mm, 0,
nominal_geom.GetDetectorDistance_mm() + settings.distance_range_mm);
for (int j = 0; j < 3; ++j) {
problem.SetParameterLowerBound(cell_len, j, 0.7 * cell_len0[j]);
problem.SetParameterUpperBound(cell_len, j, 1.3 * cell_len0[j]);
}
problem.SetParameterBlockConstant(detector_rot); // tilt not refined
problem.SetParameterBlockConstant(rot_vec);
problem.SetParameterBlockConstant(cell_ang); // angles not refined in v1
ceres::Solver::Options options;
options.linear_solver_type = ceres::DENSE_SCHUR;
options.linear_solver_ordering = ordering;
options.num_threads = std::max(1, settings.num_threads);
options.max_num_iterations = 100;
options.max_solver_time_in_seconds = 60.0;
options.logging_type = ceres::LoggingType::SILENT;
options.minimizer_progress_to_stdout = false;
ceres::Solver::Summary summary;
ceres::Solve(options, &problem, &summary);
solve_usable = summary.IsSolutionUsable();
result.frames_used = frames_used;
result.spots_used = spots_used;
}
// Final fit quality: median detector residual of the retained spots at the refined geometry.
EffectiveCell(system, cell_len, cell_ang, eff_len, eff_alpha, eff_beta, eff_gamma);
DiffractionGeometry cur = nominal_geom;
cur.BeamX_pxl(beam[0]).BeamY_pxl(beam[1]).DetectorDistance_mm(distance_mm);
std::vector<double> residuals;
for (size_t i = 0; i < frames.size(); ++i) {
const CrystalLattice latt = AngleAxisAndCellToLattice(
orient[i].data(), eff_len, eff_alpha, eff_beta, eff_gamma);
const Coord a = latt.Astar(), b = latt.Bstar(), c = latt.Cstar();
const Coord v0 = latt.Vec0(), v1 = latt.Vec1(), v2 = latt.Vec2();
for (const auto &s : frames[i].spots) {
const Coord recip = cur.DetectorToRecip(s.x, s.y);
const double hf = recip * v0, kf = recip * v1, lf = recip * v2;
const double h = std::round(hf), k = std::round(kf), l = std::round(lf);
const double dn = (hf - h) * (hf - h) + (kf - k) * (kf - k) + (lf - l) * (lf - l);
if (dn > 0.1 * 0.1)
continue;
const Coord recip_pred = a * (float)h + b * (float)k + c * (float)l;
const auto [px, py] = cur.RecipToDetector(recip_pred);
if (std::isfinite(px) && std::isfinite(py))
residuals.push_back(std::hypot(px - s.x, py - s.y));
}
}
if (!residuals.empty()) {
std::nth_element(residuals.begin(), residuals.begin() + residuals.size() / 2, residuals.end());
result.median_residual_px = residuals[residuals.size() / 2];
}
result.ok = solve_usable && result.spots_used >= settings.min_spots_total && result.frames_used > 0;
result.beam_x_px = beam[0];
result.beam_y_px = beam[1];
result.distance_mm = distance_mm;
result.cell = BuildUnitCell(system, cell_len, cell_ang);
return result;
} catch (...) {
result.ok = false;
return result;
}
}