Test: Add adaptive HIP tile replay selection

Add a bounded per-chunk center-tile selector to the real-event replay prototype and retain the paired timing, mixed-boundary, CPU, HIP, and sandbox-failure evidence.
This commit is contained in:
wyj committed 2026-09-11 23:27:24 -04:00
1 parent 11e703e33d
commit 776f9b7247
31 files changed
+347 -11

No files matched your search

+48
View File
@@ -13,6 +13,54 @@ RX 9070 上,65,536 个真实银心视场事件的累积回放中位数从 104.
一个通用生产默认算法;后续集成应先考虑分布选择及生产流式 producer 的端到端对照。
没有运行完整全天渲染,也没有推断新的全天加速比。
## 2026-09-11 自适应选择后续实验
在提交 `11e703e33dffb1ff168ba11dd922e68b448116b9` 之上增加了仅用于回放的
`adaptive` 模式,production sink 仍未改变。选择器逐个 16,384-event chunk 扫描
32×32 中心 tile 占用;chunk 至少有 8,192 events、且平均每个占用中心 tile 至少
32 events 时选择 tile16,否则选择现有 atomic。该阈值是基于本页固定输入提出的实验
假设,不是跨场景或跨设备参数。
选择扫描不构建 support 引用,四个样本的中位成本为 0.037--0.455 ms。tile 路径使用
独立的有界 event device buffer,不复用 production 双 staging slot,因此同一 stream 内
可以按 chunk 混合 atomic/tile;mixed fixture 实际覆盖 2 个 tile chunk、1 个 atomic chunk
和中途 direct fallback。所有额外 scratch 仍在 replay sink 创建时一次分配,未进入 renderer。
同一新 binary(SHA256
`121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151`)串行运行,
每项三次;表中为包含选择、分桶、上传、kernel、合并、下载和清理的 `replay_wall`
中位数:
| 65,536-event 输入 | paired atomic | paired tile16 | adaptive | adaptive 选择 |
| --- | ---: | ---: | ---: | ---: |
| 银心密集 | 95.018 ms | 67.354 ms | 67.834 ms | 0.177 ms |
| 同贡献分散 | 78.203 ms | 99.693 ms | 80.092 ms | 0.455 ms |
自适应路径在密集输入相对 paired atomic 快约 1.40×,距固定 tile16 中位数 0.7%;在分散
输入保留 atomic,距其 paired 中位数 2.4%。另外两个真实输入的自适应中位数为强放大
21.617 ms、普通区域 18.347 ms,分别选择 1/1 tile chunk。银心选择 4/4 tile chunks,
分散对照选择 4/4 atomic chunks。此结果支持继续研究 production 流式集成,但尚未包含
OpenMP producer 与 sink 锁竞争,也没有授权用本回放结果宣称完整全天加速。
全部 adaptive/mixed 检查通过原有 finite、double HDR 和 RGB/Y 通量阈值;最坏
`max_abs=5.96856e-11`、`max_rel=5.95958e-13`、RGB 通量相对差
`<=2.83233e-14`、Y `<=1.15036e-14`。`make -j1 test` 与 production HIP primitive
也通过。第一次在受限沙箱内运行明确失败为 `no ROCm-capable device is detected`,随后只在
获准的主机 GPU 环境执行;失败记录保留,没有删除或覆盖。
原始证据:
- 构建:[adaptive_build_host.log](hip_psf_replay_2026-09-07/adaptive_build_host.log);
- adaptive 三次:`adaptive_{center_65536,dispersed_65536,lensed_16384,ordinary_12765}_host_{0,1,2}.log`;
- paired 基线:`paired_{center,dispersed}_{atomic,16}_{0,1,2}.log`;
- mixed、CPU 与 HIP 回归:`adaptive_boundary_mixed_host_0.log`、
`adaptive_cpu_regression.log`、`adaptive_hip_primitive_host.log`;
- 受限环境失败:`adaptive_center_65536_0.log`。
每份日志均保留完整命令、45/90 s timeout、Git hash、binary hash(适用时)、程序原始输出、
process wall 和 exit status。所有性能进程均由现有独占 runner 串行执行,未与其他 renderer
或 profiler 并发。
实现入口:
- [capture_psf.c](../tests/capture_psf.c):调用真实 producer 的测试专用 consumer,捕获或诊断,不生成 HDR。
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/boundary.events 32771 adaptive mixed
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.691 s
device=AMD Radeon RX 9070 arch=gfx1201 events=32771 frame=128x96 mode=adaptive distribution=fixture-mixed-direct contributions=142133685 CPU_reference=0.271268845 create=0.036700010
complete_replay=0.060321093 replay_wall=0.023621082 select=0.000166893 bin=0.002514124 upload=0.000438220 prepare=0.000985861 accumulation=0.016374943 merge=0.000088215 download=0.000132840 cleanup=0.000163078 events_s=1387362.339 contributions_s=6017238463.474 center_tiles=26 tile_chunks=2 atomic_chunks=1 refs=829409 tasks=3275 scratch_used_peak=25249440 scratch_device_reserved=184549376 RSS_KiB=319696 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
PROCESS_WALL 1.117062220 EXIT 0
@@ -0,0 +1,7 @@
COMMAND OMP_NUM_THREADS=16 make -B -j1 PSF_BACKEND=hip 'HIP_CXXFLAGS=--offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic' hip-psf-replay
TIMEOUT 60s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
cc -DENABLE_PNG -DFRAME_PSF_EVENT_SINK=1 -DPSF_BACKEND_HIP -DSPACETIME_MINKOWSKI -std=c11 -march=native -pipe -Wall -Wextra -Wpedantic -O2 -DNDEBUG -fopenmp -Isrc -MMD -MP -c src/optics.c -o build/Release/obj/minkowski/standard_sink1_hip/src/optics.o
mkdir -p build/Release
hipcc --offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic -fopenmp -Isrc -x hip tests/replay_psf.hip -x none build/Release/obj/minkowski/standard_sink1_hip/src/optics.o -lm -lpng -o build/Release/replay_psf
PROCESS_WALL 1.266911305 EXIT 0
@@ -0,0 +1,7 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
no ROCm-capable device is detected
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.667 s
PROCESS_WALL 1.667466220 EXIT 1
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.679 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=captured contributions=432818979 CPU_reference=0.824280024 create=0.050632000
complete_replay=0.121458054 replay_wall=0.070826054 select=0.000172138 bin=0.007817984 upload=0.001097918 prepare=0.001653194 accumulation=0.051779747 merge=0.000582457 download=0.004020136 cleanup=0.000195980 events_s=925309.214 contributions_s=6111013629.616 center_tiles=35 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=713084 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 1.968497664 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.662 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=captured contributions=432818979 CPU_reference=0.812095881 create=0.036637783
complete_replay=0.104471922 replay_wall=0.067834139 select=0.000179052 bin=0.007610083 upload=0.001078129 prepare=0.001619816 accumulation=0.051049709 merge=0.000552416 download=0.004829631 cleanup=0.000203133 events_s=966121.205 contributions_s=6380547998.522 center_tiles=35 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=713056 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 1.918472017 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.664 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=captured contributions=432818979 CPU_reference=0.806693077 create=0.036690950
complete_replay=0.103733778 replay_wall=0.067042828 select=0.000176907 bin=0.007581234 upload=0.001075745 prepare=0.001624107 accumulation=0.051224947 merge=0.000552177 download=0.004083938 cleanup=0.000195026 events_s=977524.403 contributions_s=6455858060.497 center_tiles=35 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=713112 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 1.918304047 EXIT 0
@@ -0,0 +1,38 @@
COMMAND OMP_NUM_THREADS=16 make -j1 test
TIMEOUT 90s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
make SPACETIME=minkowski ENABLE_HDR=1 backend
make[1]: Entering directory '/home/wyj/Code/C/GR_4d_raytracing'
cc -O2 -DNDEBUG -fopenmp build/Release/obj/minkowski/hdr_sink1_cpu/src/catalog.o build/Release/obj/minkowski/hdr_sink1_cpu/src/frame.o build/Release/obj/minkowski/hdr_sink1_cpu/src/geodesic.o build/Release/obj/minkowski/hdr_sink1_cpu/src/lens_map.o build/Release/obj/minkowski/hdr_sink1_cpu/src/movie.o build/Release/obj/minkowski/hdr_sink1_cpu/src/observer.o build/Release/obj/minkowski/hdr_sink1_cpu/src/observer_track.o build/Release/obj/minkowski/hdr_sink1_cpu/src/optics.o build/Release/obj/minkowski/hdr_sink1_cpu/src/ray.o build/Release/obj/minkowski/hdr_sink1_cpu/src/spacetime_common.o build/Release/obj/minkowski/hdr_sink1_cpu/src/spacetime_minkowski.o build/Release/obj/minkowski/hdr_sink1_cpu/src/main.o -lm -lpng -lcfitsio -o build/Release/minkowski_sky
make[1]: Leaving directory '/home/wyj/Code/C/GR_4d_raytracing'
mkdir -p /tmp/gr_psf_event_sink_reference
OMP_NUM_THREADS=16 build/Release/minkowski_sky --catalog assets/sky_grid_5deg.csv --output /tmp/gr_psf_event_sink_reference/minkowski_ra1_dec1_640x360.png --hdr-output --width 640 --height 360 --fov-deg 30 --look-ra-deg 1 --look-dec-deg 1 --exposure 0.1 --observer-radius 30 --observer-velocity 0 0 0 --psf-fwhm-pixels 2.7 --psf-moffat-beta 4.5 --max-magnification 1e300 --max-cache-psf-flux 1 --psf-relative-tail 1e-8 --psf-min-y 0 --coarse-cell-pixels 16 --refine-max-level 0 --refine-angle-abs-deg 0.001 --refine-angle-rel 0.1 --refine-jacobian-min 1e-3 --refine-min-edge-pixels 0.5 --refine-min-area-pixels2 0.25 --catalog-load-workers 4
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.667 s
Rendered 35 images from 5654 catalog stars to /tmp/gr_psf_event_sink_reference/minkowski_ra1_dec1_640x360.png (ok)
PSF splats: cached 35, cached wing-clipped 0, direct fallbacks 0, discarded below min-Y 0
python3 scripts/fits_floatdiff.py tests/data/psf_event_sink_reference/minkowski_ra1_dec1_640x360_HDR.fits /tmp/gr_psf_event_sink_reference/minkowski_ra1_dec1_640x360_HDR.fits
floatdiff: shape=(640, 360, 3) samples=691200 mismatches=0 max_abs=0 max_rel=0 worst_sample=0
make SPACETIME=schwarzschild ENABLE_HDR=1 backend
make[1]: Entering directory '/home/wyj/Code/C/GR_4d_raytracing'
cc -O2 -DNDEBUG -fopenmp build/Release/obj/schwarzschild/hdr_sink1_cpu/src/catalog.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/frame.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/geodesic.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/lens_map.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/movie.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/observer.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/observer_track.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/optics.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/ray.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/spacetime_common.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/spacetime_schwarzschild.o build/Release/obj/schwarzschild/hdr_sink1_cpu/src/main.o -lm -lpng -lcfitsio -o build/Release/schwarzschild_sky
make[1]: Leaving directory '/home/wyj/Code/C/GR_4d_raytracing'
OMP_NUM_THREADS=16 build/Release/schwarzschild_sky --catalog assets/sky_grid_5deg.csv --output /tmp/gr_psf_event_sink_reference/schwarzschild_ra1_dec1_fov60_640x360.png --hdr-output --width 640 --height 360 --fov-deg 60 --look-ra-deg 1 --look-dec-deg 1 --exposure 0.1 --observer-radius 30 --observer-velocity 0 0 0 --psf-fwhm-pixels 2.7 --psf-moffat-beta 4.5 --max-magnification 1e300 --max-cache-psf-flux 1 --psf-relative-tail 1e-8 --psf-min-y 0 --coarse-cell-pixels 16 --refine-max-level 0 --refine-angle-abs-deg 0.001 --refine-angle-rel 0.1 --refine-jacobian-min 1e-3 --refine-min-edge-pixels 0.5 --refine-min-area-pixels2 0.25 --catalog-load-workers 4
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.665 s
Rendered 5206 images from 5654 catalog stars to /tmp/gr_psf_event_sink_reference/schwarzschild_ra1_dec1_fov60_640x360.png (ok)
PSF splats: cached 5206, cached wing-clipped 0, direct fallbacks 0, discarded below min-Y 0
python3 scripts/fits_floatdiff.py tests/data/psf_event_sink_reference/schwarzschild_ra1_dec1_fov60_640x360_HDR.fits /tmp/gr_psf_event_sink_reference/schwarzschild_ra1_dec1_fov60_640x360_HDR.fits
floatdiff: shape=(640, 360, 3) samples=691200 mismatches=0 max_abs=0 max_rel=0 worst_sample=0
./build/Release/test_observer_minkowski
coordinate-camera regression passed
./build/Release/test_observer_schwarzschild
coordinate-camera regression passed
./build/Release/test_geodesic
./build/Release/test_frame
./build/Release/test_schwarzschild
./build/Release/test_observer_track
./build/Release/test_catalog_prefetch
python3 tests/test_camera_cli.py build/Release
minkowski: CLI checks passed; single/movie PNG identical, map max error 0
schwarzschild: movie lens map identical with 1, 4 and 16 threads
schwarzschild: CLI checks passed; single/movie PNG identical, map max error 4.44e-16
PROCESS_WALL 26.018675067 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.682 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.491110802 create=0.037611008
complete_replay=0.117703199 replay_wall=0.080092192 select=0.000455141 bin=0.000000000 upload=0.000191523 prepare=0.000000000 accumulation=0.075263899 merge=0.000000000 download=0.004099738 cleanup=0.000207186 events_s=818257.044 contributions_s=5404009677.272 center_tiles=26986 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=184549376 RSS_KiB=705516 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.2382136141425945e-18 flux_G=1.811942792627668e-18 flux_B=1.5829277137138293e-18 flux_Y=1.5978644712371554e-18
PROCESS_WALL 2.620178348 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.733 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.488748074 create=0.038790941
complete_replay=0.121706009 replay_wall=0.082915068 select=0.000465870 bin=0.000000000 upload=0.000181281 prepare=0.000000000 accumulation=0.077964972 merge=0.000000000 download=0.004236780 cleanup=0.000192881 events_s=790399.162 contributions_s=5220028049.767 center_tiles=26986 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=184549376 RSS_KiB=705940 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.377382799700594e-18 flux_G=1.939309838343059e-18 flux_B=2.0425953472603454e-18 flux_Y=1.7396938046841301e-18
PROCESS_WALL 2.720085292 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 adaptive disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.671 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=adaptive distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.462161779 create=0.037038088
complete_replay=0.115585089 replay_wall=0.078547001 select=0.000451088 bin=0.000000000 upload=0.000188241 prepare=0.000000000 accumulation=0.073739567 merge=0.000000000 download=0.004098460 cleanup=0.000214100 events_s=834353.944 contributions_s=5510318333.269 center_tiles=26986 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=184549376 RSS_KiB=705560 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.4160413575526434e-18 flux_G=1.6738012163520145e-18 flux_B=2.0518958448496421e-18 flux_Y=1.5923904683351809e-18
PROCESS_WALL 2.568827678 EXIT 0
@@ -0,0 +1,6 @@
COMMAND OMP_NUM_THREADS=16 build/Release/test_hip_psf
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 39cd23b6d9aef423ba97ba0085b9a411a47a49e4b66cf59197f471de419ef9b8
HIP PSF cache comparison: max_abs=2.8421709430404007e-14 max_rel=7.5319184269262976e-16
PROCESS_WALL 0.816928134 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/lensed_16384.events 16384 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
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=16384 frame=3840x2160 mode=adaptive distribution=captured contributions=107949448 CPU_reference=0.213827133 create=0.041162014
complete_replay=0.062693119 replay_wall=0.021531105 select=0.000054836 bin=0.003102064 upload=0.000283003 prepare=0.000669003 accumulation=0.012633085 merge=0.000146866 download=0.004084578 cleanup=0.000169992 events_s=760945.617 contributions_s=5013651077.913 center_tiles=359 tile_chunks=1 atomic_chunks=0 refs=740784 tasks=5251 scratch_used_peak=31785268 scratch_device_reserved=184549376 RSS_KiB=710652 max_abs=5.3290705182007514e-15 max_rel=3.8619817275125971e-15 flux_R=-5.5779263000586243e-18 flux_G=-2.9489947183383731e-19 flux_B=4.3765760168230462e-18 flux_Y=-2.1608907287060103e-18
PROCESS_WALL 1.268419138 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/lensed_16384.events 16384 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.667 s
device=AMD Radeon RX 9070 arch=gfx1201 events=16384 frame=3840x2160 mode=adaptive distribution=captured contributions=107949448 CPU_reference=0.214478970 create=0.036618948
complete_replay=0.058495998 replay_wall=0.021877050 select=0.000056028 bin=0.003196001 upload=0.000288010 prepare=0.000689983 accumulation=0.012602091 merge=0.000144958 download=0.004350181 cleanup=0.000192165 events_s=748912.660 contributions_s=4934369397.489 center_tiles=359 tile_chunks=1 atomic_chunks=0 refs=740784 tasks=5251 scratch_used_peak=31785268 scratch_device_reserved=184549376 RSS_KiB=710384 max_abs=5.3290705182007514e-15 max_rel=3.8619817275125971e-15 flux_R=-5.5779263000586243e-18 flux_G=-2.9489947183383731e-19 flux_B=4.3765760168230462e-18 flux_Y=-2.1608907287060103e-18
PROCESS_WALL 1.216200115 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/lensed_16384.events 16384 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.664 s
device=AMD Radeon RX 9070 arch=gfx1201 events=16384 frame=3840x2160 mode=adaptive distribution=captured contributions=107949448 CPU_reference=0.214956999 create=0.038650990
complete_replay=0.060267925 replay_wall=0.021616936 select=0.000054121 bin=0.003103971 upload=0.000282049 prepare=0.000669956 accumulation=0.012650013 merge=0.000149012 download=0.004124364 cleanup=0.000187874 events_s=757924.259 contributions_s=4993744226.675 center_tiles=359 tile_chunks=1 atomic_chunks=0 refs=740784 tasks=5251 scratch_used_peak=31785268 scratch_device_reserved=184549376 RSS_KiB=710600 max_abs=5.3290705182007514e-15 max_rel=3.8619817275125971e-15 flux_R=-5.5779263000586243e-18 flux_G=-2.9489947183383731e-19 flux_B=4.3765760168230462e-18 flux_Y=-2.1608907287060103e-18
PROCESS_WALL 1.216335608 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/ordinary_16384.events 12765 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.683 s
device=AMD Radeon RX 9070 arch=gfx1201 events=12765 frame=3840x2160 mode=adaptive distribution=captured contributions=84287857 CPU_reference=0.161495924 create=0.036530018
complete_replay=0.054877043 replay_wall=0.018347025 select=0.000042915 bin=0.001914978 upload=0.000241995 prepare=0.000617027 accumulation=0.009811878 merge=0.000136137 download=0.005169831 cleanup=0.000195026 events_s=695753.129 contributions_s=4594088544.521 center_tiles=8 tile_chunks=1 atomic_chunks=0 refs=575476 tasks=2331 scratch_used_peak=27265820 scratch_device_reserved=184549376 RSS_KiB=708332 max_abs=2.1371793224034263e-15 max_rel=1.6186841366251043e-14 flux_R=1.3070869891010463e-16 flux_G=2.5758793226204442e-16 flux_B=1.7069617471680846e-16 flux_Y=2.1355251009923229e-16
PROCESS_WALL 1.166123833 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/ordinary_16384.events 12765 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.679 s
device=AMD Radeon RX 9070 arch=gfx1201 events=12765 frame=3840x2160 mode=adaptive distribution=captured contributions=84287857 CPU_reference=0.164183140 create=0.036640882
complete_replay=0.054260731 replay_wall=0.017619848 select=0.000036955 bin=0.001922131 upload=0.000246048 prepare=0.000601053 accumulation=0.010066986 merge=0.000137806 download=0.004148300 cleanup=0.000171900 events_s=724467.079 contributions_s=4783688020.331 center_tiles=8 tile_chunks=1 atomic_chunks=0 refs=575476 tasks=2331 scratch_used_peak=27265820 scratch_device_reserved=184549376 RSS_KiB=707824 max_abs=2.1371793224034263e-15 max_rel=1.6186841366251043e-14 flux_R=1.3070869891010463e-16 flux_G=2.5758793226204442e-16 flux_B=1.7069617471680846e-16 flux_Y=2.1355251009923229e-16
PROCESS_WALL 1.167055415 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/ordinary_16384.events 12765 adaptive
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.674 s
device=AMD Radeon RX 9070 arch=gfx1201 events=12765 frame=3840x2160 mode=adaptive distribution=captured contributions=84287857 CPU_reference=0.159490824 create=0.036442041
complete_replay=0.056708097 replay_wall=0.020266056 select=0.000033855 bin=0.001877069 upload=0.000234127 prepare=0.000597954 accumulation=0.010081053 merge=0.000137806 download=0.004184938 cleanup=0.000163078 events_s=629870.951 contributions_s=4159065619.239 center_tiles=8 tile_chunks=1 atomic_chunks=0 refs=575476 tasks=2331 scratch_used_peak=27265820 scratch_device_reserved=184549376 RSS_KiB=707952 max_abs=2.1371793224034263e-15 max_rel=1.6186841366251043e-14 flux_R=1.3070869891010463e-16 flux_G=2.5758793226204442e-16 flux_B=1.7069617471680846e-16 flux_Y=2.1355251009923229e-16
PROCESS_WALL 1.167496176 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.783 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=captured contributions=432818979 CPU_reference=0.805742979 create=0.036848068
complete_replay=0.103791952 replay_wall=0.066943884 select=0.000000000 bin=0.007535458 upload=0.001190662 prepare=0.001640081 accumulation=0.051215172 merge=0.000553846 download=0.004045417 cleanup=0.000201941 events_s=978969.193 contributions_s=6465399881.387 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=713288 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 2.019127664 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.668 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=captured contributions=432818979 CPU_reference=0.815722942 create=0.036595821
complete_replay=0.106936932 replay_wall=0.070341110 select=0.000000000 bin=0.007705212 upload=0.001186848 prepare=0.001616001 accumulation=0.051277876 merge=0.000541925 download=0.004584385 cleanup=0.000200987 events_s=931688.451 contributions_s=6153143980.638 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=712508 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 1.917609542 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.670 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=captured contributions=432818979 CPU_reference=0.802520990 create=0.037091017
complete_replay=0.104444981 replay_wall=0.067353964 select=0.000000000 bin=0.007662058 upload=0.001219988 prepare=0.001631737 accumulation=0.051412106 merge=0.000540018 download=0.004093417 cleanup=0.000197887 events_s=973008.807 contributions_s=6426035740.844 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2973775 tasks=11935 scratch_used_peak=35382764 scratch_device_reserved=184549376 RSS_KiB=712736 max_abs=2.7105054312137611e-19 max_rel=1.9611487209714066e-14 flux_R=-2.8081518355845397e-17 flux_G=4.7080671715585728e-17 flux_B=5.9271432925574641e-17 flux_Y=2.0330567515243999e-17
PROCESS_WALL 1.917963698 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.687 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=captured contributions=432818979 CPU_reference=0.809880018 create=0.039862156
complete_replay=0.135050297 replay_wall=0.095188141 select=0.000000000 bin=0.000000000 upload=0.000205602 prepare=0.000000000 accumulation=0.090687719 merge=0.000000000 download=0.004133141 cleanup=0.000000000 events_s=688489.127 contributions_s=4546984267.662 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=705156 max_abs=1.2874900798265365e-19 max_rel=7.4131884297116165e-15 flux_R=3.5244625165286513e-17 flux_G=-1.6770129667889592e-17 flux_B=-1.4396324706080044e-17 flux_Y=2.0737623150838269e-18
PROCESS_WALL 1.967518921 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.671 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=captured contributions=432818979 CPU_reference=0.802126169 create=0.039602995
complete_replay=0.134557009 replay_wall=0.094954014 select=0.000000000 bin=0.000000000 upload=0.000198362 prepare=0.000000000 accumulation=0.090435339 merge=0.000000000 download=0.004166579 cleanup=0.000000000 events_s=690186.727 contributions_s=4558195715.666 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=705688 max_abs=1.0842021724855044e-19 max_rel=7.9583748032166079e-15 flux_R=7.6396533553465937e-18 flux_G=1.6562512796306053e-17 flux_B=1.5235277925542237e-18 flux_Y=1.2880679208252085e-17
PROCESS_WALL 1.918794264 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.676 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=captured contributions=432818979 CPU_reference=0.799952984 create=0.039901972
complete_replay=0.134919882 replay_wall=0.095017910 select=0.000000000 bin=0.000000000 upload=0.000204603 prepare=0.000000000 accumulation=0.090419817 merge=0.000000000 download=0.004226341 cleanup=0.000000000 events_s=689722.601 contributions_s=4555130490.487 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=705636 max_abs=1.2874900798265365e-19 max_rel=7.9482312095117156e-15 flux_R=-5.3427317744228327e-18 flux_G=6.0837775507051433e-17 flux_B=-9.8579921222560893e-19 flux_Y=3.5056388280753197e-17
PROCESS_WALL 1.968038807 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16 disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.662 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.480471134 create=0.038483858
complete_replay=0.138176918 replay_wall=0.099693060 select=0.000000000 bin=0.035099983 upload=0.001532316 prepare=0.001661777 accumulation=0.049884081 merge=0.000493050 download=0.004275622 cleanup=0.000198841 events_s=657377.756 contributions_s=4341515641.528 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2987132 tasks=129439 scratch_used_peak=17137368 scratch_device_reserved=184549376 RSS_KiB=716772 max_abs=6.7762635780344027e-21 max_rel=2.2452117590762424e-15 flux_R=1.0178317181173255e-18 flux_G=1.4444219523404554e-18 flux_B=2.8354584230664648e-18 flux_Y=1.3331859086679348e-18
PROCESS_WALL 2.620675482 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16 disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.672 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.477596998 create=0.037245035
complete_replay=0.137820959 replay_wall=0.100575924 select=0.000000000 bin=0.035495043 upload=0.001560211 prepare=0.001640797 accumulation=0.050065994 merge=0.000494242 download=0.004161540 cleanup=0.000195980 events_s=651607.238 contributions_s=4303405448.660 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2987132 tasks=129439 scratch_used_peak=17137368 scratch_device_reserved=184549376 RSS_KiB=716808 max_abs=6.7762635780344027e-21 max_rel=2.2452117590762424e-15 flux_R=1.0178317181173255e-18 flux_G=1.4444219523404554e-18 flux_B=2.8354584230664648e-18 flux_Y=1.3331859086679348e-18
PROCESS_WALL 2.667392709 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 16 disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.675 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=16 distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.470952988 create=0.038564920
complete_replay=0.130317926 replay_wall=0.091753006 select=0.000000000 bin=0.034946680 upload=0.001475096 prepare=0.001478195 accumulation=0.042901754 merge=0.000442028 download=0.004153220 cleanup=0.000182867 events_s=714265.427 contributions_s=4717218519.113 center_tiles=0 tile_chunks=4 atomic_chunks=0 refs=2987132 tasks=129439 scratch_used_peak=17137368 scratch_device_reserved=184549376 RSS_KiB=714840 max_abs=6.7762635780344027e-21 max_rel=2.2452117590762424e-15 flux_R=1.0178317181173255e-18 flux_G=1.4444219523404554e-18 flux_B=2.8354584230664648e-18 flux_Y=1.3331859086679348e-18
PROCESS_WALL 2.623926037 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.685 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.483494043 create=0.036720991
complete_replay=0.115373135 replay_wall=0.078652143 select=0.000000000 bin=0.000000000 upload=0.000209722 prepare=0.000000000 accumulation=0.074174986 merge=0.000000000 download=0.004105619 cleanup=0.000000000 events_s=833238.576 contributions_s=5502952111.139 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=705688 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.4264853877147901e-18 flux_G=1.7304063360850003e-18 flux_B=2.1361348632691914e-18 flux_Y=1.6331855317630113e-18
PROCESS_WALL 2.620796063 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.669 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.474539995 create=0.037378073
complete_replay=0.115452051 replay_wall=0.078073978 select=0.000000000 bin=0.000000000 upload=0.000202122 prepare=0.000000000 accumulation=0.073547550 merge=0.000000000 download=0.004160663 cleanup=0.000000000 events_s=839408.998 contributions_s=5543703391.789 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=704932 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.4285334484627677e-18 flux_G=1.6416822084297311e-18 flux_B=2.2250851163298864e-18 flux_Y=1.5826745498492225e-18
PROCESS_WALL 2.620563869 EXIT 0
@@ -0,0 +1,8 @@
COMMAND OMP_NUM_THREADS=16 build/Release/replay_psf benchmarks/hip_psf_replay_2026-09-07/center_65536.events 65536 atomic disperse
TIMEOUT 45s
GIT 11e703e33dffb1ff168ba11dd922e68b448116b9
BINARY_SHA256 121b85ade12680929cf0f560e04485e2ad3d8a56ff9dcbba950a323f840c5151
PSF cache ready: 64x64 phases, radius 47 px, relative tail 1e-08, tail abs 1e-06, boundary 1e-07, build 0.666 s
device=AMD Radeon RX 9070 arch=gfx1201 events=65536 frame=3840x2160 mode=atomic distribution=synthetic-phase-preserving-dispersal contributions=432818979 CPU_reference=1.498821974 create=0.037057161
complete_replay=0.115260124 replay_wall=0.078202963 select=0.000000000 bin=0.000000000 upload=0.000203722 prepare=0.000000000 accumulation=0.073602102 merge=0.000000000 download=0.004232413 cleanup=0.000000000 events_s=838024.515 contributions_s=5534559856.636 center_tiles=0 tile_chunks=0 atomic_chunks=4 refs=0 tasks=0 scratch_used_peak=0 scratch_device_reserved=0 RSS_KiB=705384 max_abs=3.3881317890172014e-21 max_rel=8.4356460581299069e-16 flux_R=1.4138169203080735e-18 flux_G=1.5950365444592374e-18 flux_B=2.1462694853060243e-18 flux_Y=1.5465636583759892e-18
PROCESS_WALL 2.619888980 EXIT 0