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.
4 lines
431 B
Plaintext
4 lines
431 B
Plaintext
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.661 s
|
|
device=AMD Radeon RX 9070 arch=gfx1201 events=4096 spread=16 frame=3840x2160 event_bytes=56 CPU_reference=0.051952 s
|
|
HIP create=0.027773 replay_wall=0.027614 upload=0.000021 kernel=0.022490 download=0.004796 batches=1 timed=1 max_abs=4.7073456244106637e-14 max_rel=1.1345618109894268e-14 flux_rel=1.138425198954238e-16
|