leonarski_fandClaude Opus 5.5
d14e32b19a
The compiler's register choice held the fused decode/un-transpose/preprocess kernel to four resident blocks per SM on the RTX 5080, where its shared buffer allows five. Asking for five (48 registers, a small spill) takes it from ~391 to ~313 us per 18 Mpx frame (myob, -N 1, nsys, repeated). sm_75 cannot hold five 256-thread blocks, so its code is unchanged (55 registers). Output identical: ci tier base vs new, compare 0 changed, p.hkl identical on 26 sets, MTZ reflection arrays identical on 49 files; [ImagePreprocessorGPU] passes. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EizBKhTqrAYago9KJG3dA3
Jungfraujoch
Application to receive and analyse data from the PSI JUNGFRAU and EIGER detectors, together with
rugnux, its program for processing stored diffraction data - rotation and serial, macromolecular
and small-molecule - from images to merged reflections.
All documentation is now placed in docs/ subdirectory and for the current version hosted on Jungfraujoch Read The Docs page.