Filip LeonarskiandClaude Opus 5.5
229a432a66
Build Packages / Create release (push) Successful in 8s
Build Packages / build:portable:macos-arm64:nocuda (push) Successful in 5m54s
Build Packages / build:rugnux:linux-aarch64:cuda (push) Successful in 8m49s
Build Packages / build:portable:linux-x86_64:nocuda (push) Successful in 13m58s
Build Packages / build:portable:linux-x86_64:cuda (push) Successful in 18m10s
Build Packages / build:jfjoch:ubuntu2204:nocuda (push) Successful in 20m35s
Build Packages / build:portable:windows-x86_64:nocuda (push) Successful in 21m13s
Build Packages / build:jfjoch:rocky8:nocuda (push) Successful in 24m25s
Build Packages / build:jfjoch:rocky9:nocuda (push) Successful in 25m6s
Build Packages / build:portable:windows-x86_64:cuda (push) Successful in 25m48s
Build Packages / HDF5 consumer tests (DIALS, XDS) (push) Successful in 26m15s
Build Packages / build:jfjoch:ubuntu2404:nocuda (push) Successful in 19m34s
Build Packages / Generate python client (push) Successful in 26s
Build Packages / Build documentation (push) Successful in 1m1s
Build Packages / build:jfjoch:rocky8:cuda-sls9 (push) Successful in 21m5s
Build Packages / build:jfjoch:rocky9:cuda-sls9 (push) Successful in 23m36s
Build Packages / build:jfjoch:rocky8:cuda (push) Successful in 24m54s
Build Packages / build:jfjoch:ubuntu2204:cuda (push) Successful in 22m7s
Build Packages / build:jfjoch:ubuntu2404:cuda (push) Successful in 25m53s
Build Packages / build:jfjoch:rocky9:cuda (push) Successful in 28m8s
Build Packages / Unit tests (push) Failing after 3h11m38s
Build Packages / Validation Battery (push) Successful in 33m42s
Pass B of BraggIntegrationEngineCPU is split where a device can take over: per reflection, what the
fit needs is worked out in double (BraggFitSetup), the profile, its readable mass and the reweighted
fit run in single precision (FitProfile -> BraggFitOut), and the error, the summation guard and the
result are finished in double. BraggIntegrationEngineMetal runs the middle as a Metal kernel, one
thread per reflection, summing in the CPU's order (FitOnDevice); the CUDA engine is untouched.
The Gaussian's exp is now BraggExp (BraggExp.h), on the CPU and on the GPU: no GPU exp reproduces the
host's expf, and BraggExp uses only +, -, * and exact power-of-two scaling, so both compile it to the
same bits. Checked on the Apple M6 over every float in [-110, 89] (2.2e9 arguments), with subnormal
products and sums matching too. It is closer to correctly rounded than macOS expf (max 0.53 ulp;
0.2% of arguments below -1 not correctly rounded vs 0.62%). This is the one result change: per
observation |dI|/sigma p99.9 <= 1.7e-6, max 1e-4, 10-30x below what ba3f75475 moved. Merged
statistics (resolution, completeness, CC1/2, R_meas, I/sigma, ISa, space group) are identical on
lysozyme, cytochrome C, myoglobin, a small-molecule set and 4nwv; only tNCS fields that flip on any
last-digit change move (cytochrome C's pseudo-translation flag, whose modulation ratio sits at the
2.5 threshold, turns off).
The Metal engine stays bit-identical to the CPU engine: BraggIntegrationEngineMetalTest passes
unchanged, and catches planted kernel bugs (another exp, 3 iterations, a dropped lost-peak test, <=
for the disk, inverted exclude logic).
Measured wall time, Apple M6 (CPU pass B -> GPU pass B): lysozyme 24.7 -> 18.6 s, myoglobin 39.8 ->
35.7 s, cytochrome C 59.3 -> 49.0 s, 4nwv 150.2 -> 131.3 s; the small-molecule set, sparse frames,
92.5 -> 95.6 s (noise of +-3 s). Metal's fast::exp in the kernel instead measured the same on every
set (18.6, 35.8, 49.1, 131.2 s), so it would buy nothing for the bitwise check it would cost. On the
CPU alone BraggExp costs nothing measurable (cytochrome C --no-gpu 72.8 -> 73.1 s).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
