Files
Jungfraujoch/tests/WriteReflectionsTest.cpp
T
leonarski_fandClaude Opus 5.5 aa6ec193e9 Unmerged MTZ: build the file on several workers, byte-identical
The unmerged export (_unmerged.mtz) was serial apart from its final row
sort: gathering the partials, sorting them by (h,k,l,image), summing the
rocking events and filling the rows all ran on one thread. On a 17 M
partial rotation set that was 2.8 s (sort 1.6 s, event sums 0.6 s,
gather 0.25 s, rows 0.19 s); on a synthetic 122 M partial sweep 23 s.

- The partials are gathered into preallocated slots per outcome, left
  uninitialised so the workers first-touch the pages, and sorted with
  ParallelSort. The sort key now ends with the part's input position
  (outcome, index), so the order is total and the same on any number
  of workers. It differs from the previous std::sort order only among
  parts with equal (h,k,l,image_number); measured on four in-house
  sweeps (464-6138 such positions each), every summed full is bitwise
  the same.
- Events are summed in chunks whose bounds move forward to the next
  event start, so no event is split; the chunks are returned as pieces
  in order rather than concatenated.
- Rows are filled by index into a preallocated table; absences and the
  batch range are still decided in one serial pass. The final row
  gather after the sort is parallel too.

Measured: the 17 M set 2.82 s -> 0.86 s, the 8 M set 1.37 -> 0.49 s,
all while the P1 cross-check merge shares the pool; a synthetic 122 M
partial sweep 22.7 s -> 7.7 s at 32 workers. What remains is mostly
ParallelSort's pairwise merge levels. The file write (0.1 s for 112 MB)
is I/O and left as it is.

p.hkl, p.mtz, p_P1.mtz and p_unmerged.mtz are md5-identical to the base
on four in-house sets, on the GPU and the CPU build, and at -N 1.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01D1G8gJVAy6gp1K5Dz3NE5C
2026-09-28 16:52:13 +02:00

188 lines
8.9 KiB
C++

// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include <catch2/catch_all.hpp>
#include <filesystem>
#include <string>
#include <cstring>
#include <gemmi/mtz.hpp>
#include "../common/DiffractionExperiment.h"
#include "../image_analysis/WriteReflections.h"
#include "../image_analysis/IntegrationOutcome.h"
#include <cmath>
#include "SyntheticMergedReflections.h"
namespace {
// The wavelength CCP4's mtzlib substitutes when the data columns belong to dataset 0, which it
// takes for the reserved HKL_base: Cu K-alpha, and the wrong edge for anything reading f'/f''
// out of the file.
constexpr double CU_KALPHA_A = 1.54187;
constexpr UnitCell TETRAGONAL_CELL{47.0f, 47.0f, 63.0f, 90.0f, 90.0f, 90.0f};
DiffractionExperiment TestExperiment() {
DiffractionExperiment x;
x.IncidentEnergy_keV(12.7f); // ~0.976 A, nowhere near the Cu K-alpha default
x.SpaceGroupNumber(96); // P 43 21 2
x.SetUnitCell(TETRAGONAL_CELL);
return x;
}
}
TEST_CASE("Merged MTZ: the data dataset is id 1 and carries the wavelength", "[write_reflections][portable]") {
jfjoch_test::SyntheticMergeParams params;
params.true_space_group = "P 43 21 2";
params.twin_supergroup = "P 43 21 2";
params.d_min_A = 5.0;
const auto reflections = jfjoch_test::GenerateSyntheticMerged(params);
REQUIRE(!reflections.empty());
const auto experiment = TestExperiment();
const auto path = (std::filesystem::temp_directory_path() / "rugnux_merged_wavelength.mtz").string();
WriteMtzReflections(reflections, TETRAGONAL_CELL, experiment, path);
const gemmi::Mtz mtz = gemmi::read_mtz_file(path);
std::filesystem::remove(path);
// HKL_base at id 0, the data at id 1. A data dataset written at id 0 occupies the id MTZ
// reserves for the base, and mtzlib then reports CU_KALPHA_A instead of the real wavelength.
REQUIRE(mtz.datasets.size() == 2);
CHECK(mtz.datasets[0].id == 0);
CHECK(mtz.datasets[0].dataset_name == "HKL_base");
CHECK(mtz.datasets[1].id == 1);
CHECK(mtz.datasets[1].wavelength == Catch::Approx(experiment.GetWavelength_A()).epsilon(1e-5));
CHECK(mtz.datasets[1].wavelength != Catch::Approx(CU_KALPHA_A).epsilon(1e-3));
// The wavelength is read off the dataset the data columns belong to, so they have to be on the
// data dataset and not on the base.
for (const char *label : {"IMEAN", "SIGIMEAN", "F", "SIGF", "FreeR_flag"}) {
const gemmi::Mtz::Column *col = mtz.column_with_label(label);
REQUIRE(col != nullptr);
CHECK(col->dataset_id == 1);
}
// Cell and space group travel in the same header.
CHECK(mtz.spacegroup != nullptr);
CHECK(mtz.spacegroup->number == 96);
CHECK(mtz.cell.a == Catch::Approx(TETRAGONAL_CELL.a).epsilon(1e-5));
CHECK(mtz.cell.c == Catch::Approx(TETRAGONAL_CELL.c).epsilon(1e-5));
CHECK(mtz.cell.gamma == Catch::Approx(90.0).epsilon(1e-5));
CHECK(mtz.datasets[1].cell.a == Catch::Approx(TETRAGONAL_CELL.a).epsilon(1e-5));
CHECK(mtz.nreflections == static_cast<int>(reflections.size()));
}
TEST_CASE("Unmerged MTZ: LP is Lorentz-polarization, QE the sensor efficiency, FLIGHT the flight path",
"[write_reflections][portable]") {
// The whole point of the split: LP must mean what XDS and DIALS mean by it, and the raw count
// sum must still be recoverable from the file alone, as I / LP * QE * FLIGHT.
auto experiment = TestExperiment();
experiment.Goniometer(GoniometerAxis("omega", 0.0f, 0.1f, Coord(-1, 0, 0), {}));
IntegrationOutcome outcome;
const float raw[3] = {1000.0f, 250.0f, 40.0f};
const float lp[3] = {1.75f, 2.50f, 0.90f}; // Lorentz x polarization, and nothing else
const float qe[3] = {0.9375f, 0.8125f, 1.0f}; // 1.0 = the sensor said nothing to correct
const float fl[3] = {1.0125f, 1.0400f, 1.0f}; // >= 1: an oblique reflection crossed more air
for (int i = 0; i < 3; ++i) {
Reflection r{};
r.h = 4 + i; r.k = 2; r.l = 6;
r.image_number = static_cast<float>(i);
r.d = 5.0f + i;
r.I = raw[i]; // the writer is what applies the factor
r.sigma = std::sqrt(raw[i]);
r.prescaling_corr = lp[i];
r.qe_corr = qe[i];
r.flight_corr = fl[i];
r.partiality = 1.0f;
r.predicted_x = 100.0f + i; r.predicted_y = 200.0f + i;
r.observed_x = NAN; r.observed_y = NAN;
outcome.reflections.push_back(r);
}
const auto path = (std::filesystem::temp_directory_path() / "rugnux_unmerged_qe.mtz").string();
WriteUnmergedMtzReflections({outcome}, TETRAGONAL_CELL, experiment, false, path);
const gemmi::Mtz mtz = gemmi::read_mtz_file(path);
std::filesystem::remove(path);
const gemmi::Mtz::Column *c_I = mtz.column_with_label("I");
const gemmi::Mtz::Column *c_lp = mtz.column_with_label("LP");
const gemmi::Mtz::Column *c_qe = mtz.column_with_label("QE");
const gemmi::Mtz::Column *c_fl = mtz.column_with_label("FLIGHT");
REQUIRE(c_I != nullptr);
REQUIRE(c_lp != nullptr);
REQUIRE(c_qe != nullptr); // DIALS writes this column even when there is nothing in it
REQUIRE(c_fl != nullptr);
REQUIRE(mtz.nreflections == 3);
for (int i = 0; i < 3; ++i) {
const float I = mtz.data[i * mtz.columns.size() + c_I->idx];
const float LP = mtz.data[i * mtz.columns.size() + c_lp->idx];
const float QE = mtz.data[i * mtz.columns.size() + c_qe->idx];
const float FL = mtz.data[i * mtz.columns.size() + c_fl->idx];
INFO("row " << i);
// LP holds Lorentz x polarization alone: the sensor term was never inside it.
CHECK(LP == Catch::Approx(lp[i]).epsilon(1e-5));
// QE is a divisor normalised to 1 at normal incidence, so it never drops below 1.
CHECK(QE == Catch::Approx(1.0f / qe[i]).epsilon(1e-5));
CHECK(QE >= 1.0f);
// FLIGHT is a divisor in the same convention, and runs the other way: the sensor favours an
// oblique reflection, the medium attenuates it, so this one never rises above 1.
CHECK(FL == Catch::Approx(1.0f / fl[i]).epsilon(1e-5));
CHECK(FL <= 1.0f);
// ... and the three together put the raw counts back.
CHECK(I / LP * QE * FL == Catch::Approx(raw[i]).epsilon(1e-4));
// The intensity itself is the fully corrected value - all three applied.
CHECK(I == Catch::Approx(raw[i] * lp[i] * qe[i] * fl[i]).epsilon(1e-5));
}
}
TEST_CASE("Unmerged MTZ: built on several workers, the same rows as on one", "[write_reflections][portable]") {
// A sweep large enough that the sort, the event sums and the row fill are all split into
// pieces, with events of several parts, events cut short by the sweep's ends, and parts that
// share (h,k,l) and image_number - the tie the sort has to break the same way every time.
auto experiment = TestExperiment();
experiment.Goniometer(GoniometerAxis("omega", 0.0f, 0.1f, Coord(-1, 0, 0), {}));
uint32_t seed = 12345;
const auto next = [&seed] { seed = seed * 1664525u + 1013904223u; return (seed >> 8) / 16777216.0f; };
std::vector<IntegrationOutcome> outcomes(200);
for (int f = 0; f < 200; ++f) {
for (int q = 0; q < 8000; ++q) {
if ((f + q) % 7 >= 3)
continue; // each reflection is seen on three consecutive images out of seven
Reflection r{};
r.h = q % 20 - 10; r.k = (q / 20) % 20 - 10; r.l = q / 400 + 1;
r.image_number = static_cast<float>(f);
r.I = 1000.0f * next();
r.sigma = 1.0f + 10.0f * next();
r.bkg = next();
r.var_bkg = next();
r.prescaling_corr = 1.0f + next();
r.partiality = 0.2f + 0.2f * next();
r.predicted_x = 1000.0f * next(); r.predicted_y = 1000.0f * next();
r.observed_x = NAN; r.observed_y = NAN;
outcomes[f].reflections.push_back(r);
if (q % 97 == 0) {
r.I = 1000.0f * next();
outcomes[f].reflections.push_back(r);
}
}
}
for (bool sum_partials : {true, false}) {
INFO("sum_partials " << sum_partials);
const gemmi::Mtz serial = UnmergedMtz(outcomes, TETRAGONAL_CELL, experiment, sum_partials, 1);
const gemmi::Mtz parallel = UnmergedMtz(outcomes, TETRAGONAL_CELL, experiment, sum_partials, 8);
REQUIRE(serial.nreflections > 100000);
REQUIRE(parallel.nreflections == serial.nreflections);
CHECK(std::memcmp(parallel.data.data(), serial.data.data(), serial.data.size() * sizeof(float)) == 0);
REQUIRE(parallel.batches.size() == serial.batches.size());
CHECK(parallel.batches.front().number == serial.batches.front().number);
CHECK(parallel.batches.back().number == serial.batches.back().number);
}
}