wyj
7ddc58515a
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
1.2 KiB
Plaintext
9 lines
1.2 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/center_65536.events 65536 production-busy 128
|
|
TIMEOUT 45s
|
|
GIT 2d01c2c101ccea8193a64bb46ceafca3009f0ef5
|
|
BINARY_SHA256 876b6c3d92312e42b8521887d3ad15a95d28185ec6d7fe480bb765bd597ce85e
|
|
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.706 s
|
|
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 rounds=128 frame=3840x2160 mode=production-busy distribution=captured contributions_per_round=432818979 CPU_reference=0.819939137 create=0.042913914
|
|
complete_replay=3.962181807 replay_wall=3.919267893 select=0.054163949 bin=1.240586689 upload=0.092119292 prepare=0.000000000 accumulation=3.668894874 merge=0.000000000 download=0.005043460 cleanup=0.000000000 events_s=2140350.757 contributions_s=14135504595.959 center_tiles=0 tile_chunks=512 atomic_chunks=0 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=716016 max_abs=4.2500725161431774e-17 max_rel=2.146162751251728e-14 flux_R=-1.871866178468806e-16 flux_G=1.3413216273651358e-16 flux_B=8.2669907468878767e-17 flux_Y=1.6595004964231178e-17 validation=scaled-cpu-double-reference
|
|
PROCESS_WALL 5.826439530 EXIT 0
|