wyj
e1ec480669
Cooperate across 32 lanes per PSF and use two completion-protected staging slots with complete batch timing. Restore coarse OpenMP event production while serializing shared GPU submissions and direct fallback boundaries. Add bounded benchmarks, streaming and renderer regressions, and preserve validation evidence and ownership documentation.
10 lines
750 B
Plaintext
10 lines
750 B
Plaintext
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.694 s
|
|
Frame 0: finding and prefetching catalog tiles...
|
|
Frame 0: catalog prefetch finished (0 candidate tiles).
|
|
Frame 0: splatting 130882 lens triangles...
|
|
Frame 0: catalog splatting finished in 4.4 s; writing image...
|
|
Rendered 12765 images from 8192 catalog stars to /tmp/gr-hip-baseline-8192.png (ok; imported lens map)
|
|
PSF splats: cached 12765, cached wing-clipped 0, direct fallbacks 0, discarded below min-Y 0
|
|
HIP PSF: 12765 events in 1 batches (1 timed); upload 0.000041 s, kernel 0.171573 s, download 0.025041 s
|
|
OMP_NUM_THREADS=16 timeout --kill-after=5s 60s --catalog --psf-relative-tai 14.92s user 0.17s system 274% cpu 5.489 total
|