Document the producer-private adaptive path, the dummy support workload diagnostics, the negative result of the old serial binning and the 2026-09-13 full-day comparison (splat 282.944 s vs atomic 481.417 s). Add the corresponding raw logs, hotspot fixtures and runner evidence, and lay out the staged plan toward a sub-240 s full-day render without changing the default atomic path.
9 lines
1.3 KiB
Plaintext
9 lines
1.3 KiB
Plaintext
COMMAND OMP_NUM_THREADS=16 OMP_DYNAMIC=FALSE env HIP_PSF_ACCUMULATION=adaptive build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/boundary.events 32771 production-prepared mixed
|
|
TIMEOUT 45s
|
|
GIT 2d01c2c101ccea8193a64bb46ceafca3009f0ef5
|
|
BINARY_SHA256 d056d76de917e764c4f1d516a51657c8d9e9cf3adf97615ccb50b6c81a565002
|
|
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.714 s
|
|
device=AMD Radeon RX 9070 arch=gfx1201 events=32771 rounds=1 frame=128x96 mode=production-prepared distribution=fixture-mixed-direct contributions_per_round=142133685 CPU_reference=0.275578976 create=0.038097858
|
|
complete_replay=0.060217857 replay_wall=0.022119999 select=0.000179393 bin=0.002129981 upload=0.000288204 prepare=0.000000000 accumulation=0.016224077 merge=0.000000000 download=0.000132740 cleanup=0.000000000 events_s=1481510.017 contributions_s=6425573773.203 center_tiles=0 tile_chunks=2 atomic_chunks=1 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=319908 max_abs=5.9685589803848416e-11 max_rel=5.9595772318269279e-13 flux_R=2.8323267191886195e-14 flux_G=-5.5281251977629701e-15 flux_B=9.6507636840237455e-15 flux_Y=1.1503592402127278e-14 validation=scaled-cpu-double-reference
|
|
PROCESS_WALL 1.165812081 EXIT 0
|