Files
Jungfraujoch/tests/ShrinkMaskMetalTest.cpp
leonarski_f 4809c1622c
Build Packages / build:portable:linux-x86_64:nocuda (push) Successful in 16m43s
Build Packages / build:jfjoch:ubuntu2404:nocuda (push) Successful in 28m46s
Build Packages / build:jfjoch:rocky8:cuda-sls9 (push) Successful in 32m5s
Build Packages / build:jfjoch:rocky9:cuda (push) Successful in 39m44s
Build Packages / build:portable:macos-arm64:nocuda (push) Successful in 5m7s
Build Packages / Create release (push) Successful in 8s
Build Packages / Build documentation (push) Successful in 49s
Build Packages / build:portable:linux-x86_64:cuda (push) Successful in 22m30s
Build Packages / build:jfjoch:rocky8:nocuda (push) Successful in 31m54s
Build Packages / build:rugnux:linux-aarch64:cuda (push) Successful in 11m29s
Build Packages / build:portable:windows-x86_64:nocuda (push) Successful in 23m51s
Build Packages / build:jfjoch:ubuntu2204:nocuda (push) Successful in 26m7s
Build Packages / build:jfjoch:ubuntu2204:cuda (push) Successful in 29m38s
Build Packages / build:portable:windows-x86_64:cuda (push) Successful in 28m6s
Build Packages / HDF5 consumer tests (DIALS, XDS) (push) Successful in 29m44s
Build Packages / build:jfjoch:rocky9:nocuda (push) Successful in 33m22s
Build Packages / Generate python client (push) Successful in 47s
Build Packages / build:jfjoch:rocky9:cuda-sls9 (push) Successful in 34m6s
Build Packages / Unit tests (push) Successful in 1h2m47s
Build Packages / build:jfjoch:rocky8:cuda (push) Successful in 35m59s
Build Packages / build:jfjoch:ubuntu2404:cuda (push) Successful in 34m8s
Build Packages / Validation Battery (push) Successful in 38m31s
v1.0.0-rc.187 (#98)
* Rugnux: Refinement several times faster, one protocol on the CPU and the GPU, parts of it on the Apple GPU; its random draws are the same on every platform.
* Rugnux: Refinement follows common practice: the free set decides only the restraint weights and the displacement model (isotropic, TLS or anisotropic, by Hamilton's test), everything else is decided on the working set; lower R-free for placed and predicted models.
* Rugnux: Restraint dictionaries via `--restraints` (or among the inputs) and more built-in ligands; a model whose space group is a subgroup of the data's is refined in its own group; reflections plus a model select `--mode refine` on their own.
* Rugnux: `-C` fixes the crystal system on the axes as typed; `-S` alone fixes the space group only, the cell is still found and reduced; a space group or cell stored in the input file is ignored, with a line in the log.
* Rugnux: More reliable multi-sweep merging; `--mode scale` merges several stills runs as one; `_plot.txt` and the report name each input; a second crystal form is reported for stills given a cell.
* jfjoch_broker (experimental): Live Rugnux on FPGA detectors (JUNGFRAU) takes the same path as a DECTRIS stream, rotation and serial alike, model step included, with analysis threads per GPU; frames waiting for the analysis can be viewed; no host stage drops a frame - a source faster than the analysis is held at the card.
* jfjoch_broker: Summation of more than 256 frames per image is split between the card and the host (`summation_mode` is then `hybrid`), and live Rugnux runs on such collections; pedestal runs take a receiver of their own.
* jfjoch_broker (experimental): `stills_downsample` analyses 1 of every N serial images (chosen by a hash; the first 2000 all; the others written without analysis; reset to 1 by `/initialize`); `max_spot_count` left out means 250 for per-image indexing and up to 1000 for live stills; the live status gives the merge before the model work, the fitted resolution and the anomalous peak height of each unexplained blob.
* jfjoch_broker: Without a `pcie` entry the broker runs on a mock of the card instead of the HLS simulation; its spot, ROI and azimuthal results are zero then.
* Web frontend: Redesigned Rugnux live page; Vite 8, TypeScript 6, Mol* 5.13 and dependency security updates.
* Tools: `jfjoch_fpga_stills_test` measures live stills on the cards with a stored dataset; `jfjoch_fpga_test` loses the HLS-simulation option.
* Other: FFTW no longer fetched or linked (the CPU FFT indexer keeps the name `FFTW`); PCIe driver now GPL-2.0-or-later and third-party notices complete; several crash fixes.

Reviewed-on: #98
Co-authored-by: Filip Leonarski <filip.leonarski@psi.ch>
2026-11-19 20:49:28 +01:00

81 lines
3.3 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>
#ifdef __APPLE__
#include <cstring>
#include <random>
#include <vector>
#include <gemmi/model.hpp>
#include "../image_analysis/structure_refinement/ModelGrid.h"
#include "../image_analysis/structure_refinement/RefinementXray.h"
#include "../image_analysis/structure_refinement/ShrinkMaskMetal.h"
// The bulk-solvent mask shrunk on the Apple GPU (ShrinkMaskMetal.h) is the CPU's, bit for bit. A Mac without a
// Metal device fails rather than skips, as in ModelDensityMetalTest.cpp.
namespace {
// Atoms in clusters over the cell - so that the mask has an edge to shrink everywhere and boxes wrap at every face.
gemmi::Model clustered_atoms(const gemmi::UnitCell &cell) {
std::mt19937 rng(29);
std::uniform_real_distribution<double> frac(0.0, 1.0);
std::normal_distribution<double> spread(0.0, 2.5);
const gemmi::El elements[] = {gemmi::El::C, gemmi::El::N, gemmi::El::O, gemmi::El::S};
gemmi::Model model(1);
gemmi::Chain chain("A");
gemmi::Residue res;
res.name = "UNK";
res.seqid = gemmi::SeqId(1, ' ');
for (int c = 0; c < 40; c++) {
const gemmi::Position centre = cell.orthogonalize(gemmi::Fractional(frac(rng), frac(rng), frac(rng)));
for (int i = 0; i < 50; i++) {
gemmi::Atom a;
a.name = "X";
a.element = elements[i % 4];
a.pos = centre + gemmi::Position(spread(rng), spread(rng), spread(rng));
a.b_iso = 20.0f;
a.occ = 1.0f;
res.atoms.push_back(a);
}
}
chain.residues.push_back(res);
model.chains.push_back(chain);
return model;
}
void check_same_mask(const gemmi::UnitCell &cell, const char *group, double d_min) {
const gemmi::SpaceGroup &sg = *gemmi::find_spacegroup_by_name(group);
gemmi::Grid<float> cpu = BulkSolventMask::MaskGrid(cell, sg, d_min);
cpu.data.resize(cpu.point_count());
gemmi::Grid<float> gpu = cpu;
const std::vector<size_t> leaders = OrbitLeaders(cpu, 4);
const gemmi::Model model = clustered_atoms(cell);
PutMaskOnGrid(cpu, model, leaders, 4, false);
const size_t before = ShrinkMaskMetalCalls();
PutMaskOnGrid(gpu, model, leaders, 4, true);
REQUIRE(ShrinkMaskMetalCalls() == before + 1); // the GPU shrank it
REQUIRE(gpu.data.size() == cpu.data.size());
size_t different = 0, solvent = 0;
for (size_t i = 0; i < cpu.data.size(); i++) {
different += std::memcmp(&cpu.data[i], &gpu.data[i], sizeof(float)) != 0;
solvent += cpu.data[i] >= 1.0f;
}
CAPTURE(group, solvent, cpu.data.size());
CHECK(solvent > cpu.data.size() / 10);
CHECK(solvent < cpu.data.size() * 9 / 10);
CHECK(different == 0);
}
}
TEST_CASE("ShrinkMaskMetal_BitIdenticalToCPU", "[portable][Metal]") {
// Triclinic, so that the offsets are not symmetric in the axes; then a group with symmetry.
check_same_mask(gemmi::UnitCell(41, 46, 52, 81, 96, 107), "P 1", 2.0);
check_same_mask(gemmi::UnitCell(50, 56, 63, 90, 90, 90), "P 21 21 21", 1.6);
}
#endif