Beanstalk Longshot test farm
Menu

Report rp_4af36d408d9304cf fail

#1702 perf(vk): the presenter thread on by default with NVIDIA on Linux and AMD on Windows, with NVIDIA Reflex; after #1121

windows+amd on Razytos/agent-d8f902,

This report disagrees with its peers.

default-presenter kokiri-after-motion.frametime_max_ms: +31.9% against peers' -6.7%
default-presenter kokiri-after-motion.stutter_count: +66.7% against peers' +25.0%
default-presenter kokiri-standing.frametime_max_ms: +56.6% against peers' -0.6%
forced-presenter kokiri-standing.stutter_count: +50.0% against peers' +0.0%
forced-presenter market-standing.stutter_count: +0.0% against peers' +300.0%

Machine

Commit
3569b8da6a4f90bc036bbb40cb52993b865b0a39
Baseline
09cbdd979eacfbd0c83e27fad7e50380985af02d
App
nightly-177-99542c21, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
AMD Radeon RX 9070 XT
tags
windowsamdamd-proprietarydgpu
driver
2.0.416
ram_gb
32
vram_mb
16,304
gpu_vendor
amd
os_version
Windows 10.0.26300

Builds

main (baseline)

1,253 s warm

from 09cbdd979eac

lift
109.4 s
read
541.6 s
finish
132 s
compile
463.1 s

PR

170.3 s warm

Program cache: warm

Scenarios

default-presenter

error

the game refused a step: refused: the game refused the teleport: an event is playing (a cutscene, a map change's)

Metric (median)mainPRΔ
exit_code0——
run_hitch_count85−37.5%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms378.85285.85−24.5%
kokiri-standing.fps_mean95.79109.18+14%
market-standing.fps_mean65.01——
kokiri-standing.draws_mean720.85761.35+5.6%
market-standing.draws_mean2,491——
kokiri-standing.hitch_count00.5—
market-standing.hitch_count0——
kokiri-after-motion.fps_mean101.22111.09+9.8%
market-after-motion.fps_mean89.01——
kokiri-standing.stutter_count22.5+25%
market-standing.stutter_count2——
kokiri-after-motion.draws_mean716.05609.7−14.9%
market-after-motion.draws_mean942——
kokiri-after-motion.hitch_count00.5—
market-after-motion.hitch_count0——
kokiri-standing.frametime_max_ms26.7841.95+56.6%
kokiri-standing.frametime_p50_ms10.39.24−10.3%
kokiri-standing.frametime_p99_ms14.8311.24−24.2%
market-standing.frametime_max_ms31.59——
market-standing.frametime_p50_ms15.14——
market-standing.frametime_p99_ms19.55——
kokiri-after-motion.stutter_count35+66.7%
market-after-motion.stutter_count2——
kokiri-after-motion.frametime_max_ms33.5744.29+31.9%
kokiri-after-motion.frametime_p50_ms9.758.97−8%
kokiri-after-motion.frametime_p99_ms13.1512.64−3.9%
market-after-motion.frametime_max_ms27.6——
market-after-motion.frametime_p50_ms11.01——
market-after-motion.frametime_p99_ms15.52——
kokiri-standing.frametime_1pct_low_ms17.3214.45−16.6%
market-standing.frametime_1pct_low_ms23.59——
kokiri-after-motion.frametime_1pct_low_ms17.1920.24+17.8%
market-after-motion.frametime_1pct_low_ms18.34——
screenshot_diff—0.74—

Pictures against main: kokiri-standing 5 s diff 0.714 (main against itself 0.7111), kokiri-standing 9 s diff 0.7134 (main against itself 0.7111), kokiri-after-motion 5 s diff 0.7449 (main against itself 0.7815), kokiri-after-motion 9 s diff 0.9485 (main against itself 0.938), kokiri-standing diff 0.7134 (main against itself 0.717), kokiri-after-motion diff 0.9458 (main against itself 0.9412)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0———
run_hitch_count11645
log_forbidden_hits0000
log_expected_missing0000
run_frametime_max_ms193.83510.6761.04563.87
kokiri-standing.fps_mean88.76106.33112.03102.82
market-standing.fps_mean65.01———
kokiri-standing.draws_mean674.8762.2760.5766.9
market-standing.draws_mean2,491———
kokiri-standing.hitch_count0100
market-standing.hitch_count0———
kokiri-after-motion.fps_mean92.63108.56113.62109.81
market-after-motion.fps_mean89.01———
kokiri-standing.stutter_count2322
market-standing.stutter_count2———
kokiri-after-motion.draws_mean803.1611.3608.1629
market-after-motion.draws_mean942———
kokiri-after-motion.hitch_count0100
market-after-motion.hitch_count0———
kokiri-standing.frametime_max_ms28.1859.5424.3525.37
kokiri-standing.frametime_p50_ms11.029.459.039.59
kokiri-standing.frametime_p99_ms16.5111.5810.8913.14
market-standing.frametime_max_ms31.59———
market-standing.frametime_p50_ms15.14———
market-standing.frametime_p99_ms19.55———
kokiri-after-motion.stutter_count2644
market-after-motion.stutter_count2———
kokiri-after-motion.frametime_max_ms26.2563.9924.5940.88
kokiri-after-motion.frametime_p50_ms10.569.168.778.95
kokiri-after-motion.frametime_p99_ms12.6413.2312.0513.67
market-after-motion.frametime_max_ms27.6———
market-after-motion.frametime_p50_ms11.01———
market-after-motion.frametime_p99_ms15.52———
kokiri-standing.frametime_1pct_low_ms19.4416.3612.5315.2
market-standing.frametime_1pct_low_ms23.59———
kokiri-after-motion.frametime_1pct_low_ms15.4523.8516.6418.94
market-after-motion.frametime_1pct_low_ms18.34———
screenshot_diff—0.950.52—

forced-presenter RX_VK_PRESENT_THREAD=1 (PR only)

error

the game refused a step: refused: the game refused the teleport: an event is playing (a cutscene, a map change's)

Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count12.57.5−40%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms261.13143.79−44.9%
kokiri-standing.fps_mean96.01106.25+10.7%
market-standing.fps_mean67.1171.32+6.3%
kokiri-standing.draws_mean668.8715.75+7%
market-standing.draws_mean2,466.452,474.3+0.3%
kokiri-standing.hitch_count00±0%
market-standing.hitch_count00±0%
kokiri-after-motion.fps_mean92.81105.34+13.5%
market-after-motion.fps_mean88.7690+1.4%
kokiri-standing.stutter_count11.5+50%
market-standing.stutter_count22±0%
kokiri-after-motion.draws_mean812.4708.25−12.8%
market-after-motion.draws_mean921.3917.4−0.4%
kokiri-after-motion.hitch_count00±0%
market-after-motion.hitch_count00±0%
kokiri-standing.frametime_max_ms25.7224.57−4.5%
kokiri-standing.frametime_p50_ms10.599.51−10.2%
kokiri-standing.frametime_p99_ms12.3411.4−7.6%
market-standing.frametime_max_ms32.7432.01−2.2%
market-standing.frametime_p50_ms14.7513.76−6.7%
market-standing.frametime_p99_ms18.8417.84−5.3%
kokiri-after-motion.stutter_count24+100%
market-after-motion.stutter_count22±0%
kokiri-after-motion.frametime_max_ms26.8927.45+2.1%
kokiri-after-motion.frametime_p50_ms10.529.47−10%
kokiri-after-motion.frametime_p99_ms12.9412.49−3.5%
market-after-motion.frametime_max_ms27.6225.92−6.1%
market-after-motion.frametime_p50_ms11.0611.01−0.5%
market-after-motion.frametime_p99_ms14.9514.59−2.4%
kokiri-standing.frametime_1pct_low_ms14.1613.03−8%
market-standing.frametime_1pct_low_ms22.3921.41−4.4%
kokiri-after-motion.frametime_1pct_low_ms16.0816.79+4.4%
market-after-motion.frametime_1pct_low_ms18.7117.2−8.1%
screenshot_diff—0.81—

Pictures against main: kokiri-standing 5 s diff 0.704 (main against itself 0.0182), kokiri-standing 9 s diff 0.7134 (main against itself 0.1467), kokiri-after-motion 5 s diff 0.8333 (main against itself 0.4115), kokiri-after-motion 9 s diff 0.944 (main against itself 0.4232), market-standing 5 s diff 0.0453 (main against itself 0.139), market-standing 9 s diff 0.0471 (main against itself 0.1604), market-after-motion 5 s diff 0.6638 (main against itself 0.5242), market-after-motion 9 s diff 0.6644 (main against itself 0.5055), kokiri-standing diff 0.7037 (main against itself 0.1504), kokiri-after-motion diff 0.961 (main against itself 0.4344), market-standing diff 0.0498 (main against itself 0.1603), market-after-motion diff 0.6596 (main against itself 0.5134)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0—00
run_hitch_count1251013
log_forbidden_hits0000
log_expected_missing0000
run_frametime_max_ms261.767.4220.18260.55
kokiri-standing.fps_mean96.01110.18102.3296.01
market-standing.fps_mean67.01—71.3267.21
kokiri-standing.draws_mean668.7760.2671.3668.9
market-standing.draws_mean2,466—2,474.32,466.9
kokiri-standing.hitch_count0000
market-standing.hitch_count0—00
kokiri-after-motion.fps_mean92.79114.7495.9592.84
market-after-motion.fps_mean88.81—9088.71
kokiri-standing.stutter_count1211
market-standing.stutter_count2—22
kokiri-after-motion.draws_mean819612.7803.8805.8
market-after-motion.draws_mean948.6—917.4894
kokiri-after-motion.hitch_count0000
market-after-motion.hitch_count0—00
kokiri-standing.frametime_max_ms26.4325.4123.7325.01
kokiri-standing.frametime_p50_ms10.599.059.9610.59
kokiri-standing.frametime_p99_ms12.3111.0811.7212.38
market-standing.frametime_max_ms31.7—32.0133.77
market-standing.frametime_p50_ms14.75—13.7614.75
market-standing.frametime_p99_ms18.69—17.8418.99
kokiri-after-motion.stutter_count2622
market-after-motion.stutter_count2—22
kokiri-after-motion.frametime_max_ms27.8728.9225.9925.91
kokiri-after-motion.frametime_p50_ms10.538.6910.2610.52
kokiri-after-motion.frametime_p99_ms13.021212.9712.85
market-after-motion.frametime_max_ms27.27—25.9227.97
market-after-motion.frametime_p50_ms10.9—11.0111.22
market-after-motion.frametime_p99_ms15.37—14.5914.53
kokiri-standing.frametime_1pct_low_ms14.2712.9213.1414.04
market-standing.frametime_1pct_low_ms22.23—21.4122.55
kokiri-after-motion.frametime_1pct_low_ms16.5217.7315.8615.65
market-after-motion.frametime_1pct_low_ms18.79—17.218.64
screenshot_diff—0.960.66—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
default-presentercrashFalse00—pass
default-presenterkokiri-standing.fps_mean.min_delta_pct1595.79109.18+14%pass
default-presenterkokiri-after-motion.fps_mean.min_delta_pct15101.22111.09+9.8%pass
default-presentermarket-standing.fps_mean.min_delta_pct1565.01——skippedthe metric was not measured
default-presentermarket-after-motion.fps_mean.min_delta_pct1589.01——skippedthe metric was not measured
default-presenterscreenshot.max_diff0.40.940.95—passover the limit, but main differs from itself by 0.9412 here: no more than 1.5x that is the scene, not the PR
default-presenterkokiri-standing.frametime_p99_ms.max_delta_pct2014.8311.24−24.2%pass
default-presenterkokiri-after-motion.frametime_p99_ms.max_delta_pct2013.1512.64−3.9%pass
default-presentermarket-standing.frametime_p99_ms.max_delta_pct2019.55——skippedthe metric was not measured
default-presentermarket-after-motion.frametime_p99_ms.max_delta_pct2015.52——skippedthe metric was not measured
default-presenterlog_forbidden_hits.max000—pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)crashFalse00—pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-standing.fps_mean.min_delta_pct1596.01106.25+10.7%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.fps_mean.min_delta_pct1592.81105.34+13.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.fps_mean.min_delta_pct1567.1171.32+6.3%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.fps_mean.min_delta_pct1588.7690+1.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)screenshot.max_diff0.40.520.96—fail
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-standing.frametime_p99_ms.max_delta_pct2012.3411.4−7.6%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.frametime_p99_ms.max_delta_pct2012.9412.49−3.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.frametime_p99_ms.max_delta_pct2018.8417.84−5.3%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.frametime_p99_ms.max_delta_pct2014.9514.59−2.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)log_forbidden_hits.max000—pass

Pictures of the failure

This report had 3 pictures of its failure (the last frame of a stuck step, or main's and the PR's picture where they differed too much). The farm keeps those for a day: they were deleted.

Log (PR side, end)

[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 37.4; 0x12: 79.2; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.3 ms a frame (the longest submission 2.6 ms); 2.6 textures made a frame
[hos host] vk: a frame: 0.18 MB unswizzled on the CPU in 0.05 ms
[hos host] vk: replay reads of guest memory as submitted: 4180000 (2516107 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1800599 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 452 dirty pages from their submits' captures, 59857 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1238 dispatches, 47570 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6758 runs, 954.3 MB compared; 111 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17445 in captures, 13 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: texture #5266 0x10006fe6c00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 16336 (drawn at 16275)
[hos host] vk: replay reads of guest memory as submitted: 4200000 (2531301 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: texture #5471 0x10006f56a00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 16359 (drawn at 16298)
[hos host] vk: replay reads of guest memory as submitted: 4220000 (2546668 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #180000: event 0x100c318038 mode 0 value 114555 (now 114536) (lr 0x80661fac)
[hos host] vk: replay reads of guest memory as submitted: 4240000 (2561883 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 293 KB; 0 made on demand (0 MB kept now); c1 stages: at most 176 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 112, 1070 MB with memory of 1656 MB (585 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (18.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 74 kept as spares, 0 destroyed; 5 spares now, 232 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 274 dirty pages from their submits' captures, 58661 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1201 dispatches, 46535 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6228 runs, 929.1 MB compared; 117 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16810 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #115000: event 0x100c31800c mode 0 value 115000 (lr 0x802915c8)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 4260000 (2577003 pages from the captures)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1172 of 3000 waited for their write-back, 0.07 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 8706 kept their virtual core (nothing there to wait for), 3070 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vi: 16409 frames presented (79.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 369, 15.5-17.8 22, 17.8-22 3, 22-30 2, 30-40 1, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 966 ranges, 3247 MB), 209 pages written, 209 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 24 kept (84 MB), 11 spare buffers, 3145 texture pages copied (12 MB)
[hos host] vk: replay reads of guest memory as submitted: 4280000 (2592120 pages from the captures)
[hos host] vk: 1 textures retired (1799 left, 3120 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4258 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 338 dirty pages from their submits' captures, 58753 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1199 dispatches, 46889 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6312 runs, 945.6 MB compared; 106 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17028 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4300000 (2607050 pages from the captures)
[hos host] vk: a frame: 151 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.35, present 0.13, draw 3.80, descriptors 1.55, texture lookups 0.06, uploads 0.01, pipelines 0.17, programs 0.59, commands 1.21, dispatch 0.67, memory sync 0.34, queue submit 0.42, slot wait 0.18
[hos host] vk: a frame: mirrors 186 (1070 MB): 4.23 MB synced in 856.7 copies, 17.31 MB written back
[hos host] vk: 16440 presents, 88.1 fps; a frame: 918 draws (0 skipped), 96 dispatches, 142 passes, 146 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1799 textures (3120 MB)
[hos host] vk: host time in GPU resource waits: 0.74 ms a frame (fences 0.02, timelines 0.72, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 346.0 full barriers recorded, 188.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 37.2; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.8 ms a frame (the longest submission 2.6 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: program picks: 5271093 kept (1879533 by the last picks' textures, a uniform buffer bound since), 61082 new, 2467824 with other textures (of 7800000)
[hos host] vk: replay reads of guest memory as submitted: 4320000 (2622145 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 4340000 (2637180 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 1460 so far (3288 MB), 1353 of them (3055 MB) between the passes
[hos host] vk: sparse mirrors: 112, 1070 MB with memory of 1656 MB (585 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 359 binds (18.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 74 kept as spares, 0 destroyed; 5 spares now, 232 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 267 dirty pages from their submits' captures, 59127 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1212 dispatches, 47041 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6197 runs, 943.5 MB compared; 133 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17026 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: replay reads of guest memory as submitted: 4360000 (2652208 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 965 ranges, 3237 MB), 210 pages written, 210 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.009; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 4172 texture pages copied (16 MB)
[hos host] vk: replay reads of guest memory as submitted: 4380000 (2667322 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 36 sync waits (52 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 16662 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 4400000 (2682588 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1218 of 3000 waited for their write-back, 0.11 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 8526 kept their virtual core (nothing there to wait for), 2994 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 374 dirty pages from their submits' captures, 58027 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1196 dispatches, 46191 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5900 runs, 921.1 MB compared; 109 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16709 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: mirror of pool 0x7f74000000 (4 MB) given back: idle, 6038 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4420000 (2697682 pages from the captures)
[hos host] vk: a frame: 150 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.47, present 0.14, draw 3.88, descriptors 1.61, texture lookups 0.13, uploads 0.05, pipelines 0.18, programs 0.59, commands 1.23, dispatch 0.66, memory sync 0.35, queue submit 0.42, slot wait 0.18
[hos host] vk: a frame: mirrors 186 (1070 MB): 4.22 MB synced in 855.7 copies, 17.20 MB written back
[hos host] vk: 16560 presents, 89.7 fps; a frame: 916 draws (0 skipped), 91 dispatches, 142 passes, 146 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1806 textures (3122 MB)
[hos host] vk: host time in GPU resource waits: 0.88 ms a frame (fences 0.02, timelines 0.86, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 341.6 full barriers recorded, 188.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 37.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.6 ms a frame (the longest submission 2.5 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #185000: event 0x100c318038 mode 0 value 118355 (now 118336) (lr 0x80661fac)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 4440000 (2713132 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4460000 (2728399 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: readback pages refreshed from guest memory: 1877699 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 111, 1070 MB with memory of 1652 MB (581 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 360 binds (18.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 75 kept as spares, 0 destroyed; 6 spares now, 236 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 367 dirty pages from their submits' captures, 59375 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1220 dispatches, 47235 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5839 runs, 934.1 MB compared; 116 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17033 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 963 ranges, 3219 MB), 218 pages written, 218 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 25 kept (86 MB), 11 spare buffers, 6147 texture pages copied (24 MB)
[hos BaseProcExecutor2] vcores: 201809 takes, 40288 waits (mean 57 us, longest 15.3 ms, 0 over HOS_VCORE_LOG_MS), 20344 kicks, 19972 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 4480000 (2743601 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4500000 (2758973 pages from the captures)
[hos ModuleSystemWorker5] nvn: 1150000 recordings made, 80868 live copies (19.9 MB), 1018 texture copies; 4 command buffers' segments (4.2 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6590 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror of pool 0x7fc2800000 (4 MB) given back: idle, 6011 submissions since its sync
[hos host] vk: recorder: 7341870 packets run in 10.0 s (busy 1.92 s, spun idle 5.10 s, slept 4040 times, 2003 of them under 200 us), 0 calls made directly (no room); the replay waited for it 31618 times, 127.10 ms in all, the longest 0.29 ms; vkResetDescriptorPool 10941/66.73 ms (max 0.11), replay_mu unlock 9591/30.57 ms (max 0.29), vkEndCommandBuffer 11016/29.34 ms (max 0.27), vmaInvalidateAllocation 53/0.31 ms (max 0.11), vkQueueBindSparse 17/0.14 ms (max 0.02)
[hos host] vk: replay reads of guest memory as submitted: 4520000 (2774151 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #120000: event 0x100c318018 mode 0 value 120000 (lr 0x80660c94)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 293 KB; 0 made on demand (0 MB kept now); c1 stages: at most 176 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 324 dirty pages from their submits' captures, 59014 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1206 dispatches, 46950 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5791 runs, 933.4 MB compared; 131 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17023 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 5391717 kept (1898179 by the last picks' textures, a uniform buffer bound since), 61082 new, 2547200 with other textures (of 8000000)
[hos Presentation Thread] nvn: QueueSubmitCommands #100000: queue 0000101004133020 (its #16674), 1 handles (lr 0x80590358)
[hos host] vk: mirror of pool 0x7f95c00000 (44 MB) given back: idle, 6038 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4540000 (2789506 pages from the captures)
[hos host] vk: a frame: 151 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.20, present 0.13, draw 3.53, descriptors 1.44, texture lookups 0.06, uploads 0.01, pipelines 0.16, programs 0.53, commands 1.14, dispatch 0.62, memory sync 0.33, queue submit 0.42, slot wait 0.16
[hos host] vk: a frame: mirrors 186 (1029 MB): 4.23 MB synced in 856.5 copies, 17.08 MB written back
[hos host] vk: 16680 presents, 91.5 fps; a frame: 919 draws (0 skipped), 86 dispatches, 142 passes, 145 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1812 textures (3123 MB)
[hos host] vk: host time in GPU resource waits: 0.73 ms a frame (fences 0.02, timelines 0.71, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 336.5 full barriers recorded, 187.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 36.9; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 2.5 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: mirror of pool 0x7fb7c00000 (4 MB) given back: idle, 6012 submissions since its sync
[hos host] vk: mirror of pool 0x7f86c00000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: mirror of pool 0x7fb1800000 (8 MB) given back: idle, 6056 submissions since its sync
[hos host] vk: mirror of pool 0x7fc2c00000 (4 MB) given back: idle, 6053 submissions since its sync
[hos host] vk: mirror of pool 0x7f72c00000 (4 MB) given back: idle, 6052 submissions since its sync
[hos host] vk: mirror of pool 0x7fbd800000 (4 MB) given back: idle, 6024 submissions since its sync
[hos host] vk: mirror of pool 0x7fb7000000 (4 MB) given back: idle, 6006 submissions since its sync
[hos host] vk: 84 mirrors given back (745 MB in all); 1012 MB of mirrors now, 44 MB of them idle and kept for what the GPU wrote there alone
[hos sead::MainThread] vk: readbacks of GPU results: 1225 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: invalidates since the last readbacks line: 8605 kept their virtual core (nothing there to wait for), 2915 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: replay reads of guest memory as submitted: 4560000 (2804800 pages from the captures)
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 240000 so far (x1 0x117b70c000 x2 0x2 x3 0x117b70c000 x4 0x230040)
[hos host] vk: mirror of pool 0x7f73c00000 (4 MB) given back: idle, 6053 submissions since its sync
[hos host] vk: mirror of pool 0x7f9ac00000 (12 MB) given back: idle, 6013 submissions since its sync
[hos host] vk: mirror of pool 0x7f9a000000 (8 MB) given back: idle, 6013 submissions since its sync
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: mirror of pool 0x7faf000000 (12 MB) given back: idle, 6049 submissions since its sync
[hos host] vk: mirror of pool 0x7fbd000000 (4 MB) given back: idle, 6048 submissions since its sync
[hos host] vk: mirror of pool 0x7f9d800000 (8 MB) given back: idle, 6046 submissions since its sync
[hos host] vk: mirror of pool 0x7fb5000000 (12 MB) given back: idle, 6044 submissions since its sync
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 963 ranges, 3223 MB), 215 pages written, 215 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 24 kept (92 MB), 10 spare buffers, 7171 texture pages copied (28 MB)
[hos host] vk: sparse mirrors: 95, 971 MB with memory of 1512 MB (540 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 366 binds (19.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 91 kept as spares, 0 destroyed; 22 spares now, 376 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 270 dirty pages from their submits' captures, 59178 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1207 dispatches, 47112 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5669 runs, 916.2 MB compared; 113 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17067 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: replay reads of guest memory as submitted: 4580000 (2820017 pages from the captures)
[hos host] vk: mirror of pool 0x7f6a400000 (4 MB) given back: idle, 6059 submissions since its sync
[hos host] vk: mirror of pool 0x7fbe400000 (8 MB) given back: idle, 6057 submissions since its sync
[hos host] vk: mirror of pool 0x7f9ec00000 (20 MB) given back: idle, 6008 submissions since its sync
[hos host] vk: mirror of pool 0x7fbd400000 (4 MB) given back: idle, 6025 submissions since its sync
[hos host] vk: mirror of pool 0x7fbf000000 (52 MB) given back: idle, 6011 submissions since its sync
[hos host] vk: mirror of pool 0x7fbe000000 (4 MB) given back: idle, 6011 submissions since its sync
[hos host] vk: mirror of pool 0x7f79c00000 (36 MB) given back: idle, 6002 submissions since its sync
[hos host] vk: 98 mirrors given back (860 MB in all); 897 MB of mirrors now, 44 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: mirror of pool 0x7fbb000000 (12 MB) given back: idle, 6063 submissions since its sync
[hos host] vk: mirror of pool 0x7fe1800000 (4 MB) given back: idle, 6063 submissions since its sync
[hos host] vk: mirror of pool 0x1051400000 (4 MB) given back: idle, 6052 submissions since its sync
[hos host] vk: mirror of pool 0x7fe1400000 (4 MB) given back: idle, 6005 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4600000 (2835211 pages from the captures)
[hos host] vk: mirror of pool 0x7fc2400000 (4 MB) given back: idle, 6034 submissions since its sync
[hos host] vk: mirror of pool 0x7f58000000 (4 MB) given back: idle, 6023 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4620000 (2850386 pages from the captures)
[hos host] vk: slow present: 15.3 ms:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2473 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: present 16754 written to <home>\AppData\Local\<user>\data\jobs\jb_cad9d677c60f0b82\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion_5s.png (the control bridge)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 390 dirty pages from their submits' captures, 59113 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1209 dispatches, 47095 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5765 runs, 933.2 MB compared; 124 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16877 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #190000: event 0x100c318038 mode 0 value 122155 (now 122136) (lr 0x80661fac)
[hos host] vk: replay reads of guest memory as submitted: 4640000 (2865583 pages from the captures)
[hos ModuleSystemWorker2] barrier: 198503 looks: 51047 found the masks moved already, 135760 waited until they moved, 11696 for the whole 1 ms (a wait 309 us on average); 183546 wakes
[hos host] vk: mirror of pool 0x7f73000000 (8 MB) given back: idle, 6038 submissions since its sync
[hos host] vk: mirror of pool 0x105b000000 (4 MB) given back: idle, 6024 submissions since its sync
[hos host] vk: mirror of pool 0x105a000000 (4 MB) given back: idle, 6051 submissions since its sync
[hos host] vk: mirror of pool 0x105b800000 (4 MB) given back: idle, 6006 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4660000 (2880860 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 48 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: mirror of pool 0x105ac00000 (4 MB) given back: idle, 6022 submissions since its sync
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: memory: working set 15634 MB (peak 15763), private 22331 MB, staging 48 MB in 3 arenas, 37 made so far (111 ms)
[hos host] vk: memory heaps: heap 0 (system): 14 blocks 800 MB, 39 allocations 714 MB; used 2716 of 15571 MB; heap 1 (device): 171 blocks 5028 MB, 16148 allocations 4526 MB; used 6232 of 15419 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 24 MB; 1 free ranges, the largest 7 MB
[hos host] vk: image blocks (render targets): 10 blocks 320 MB, 107 images 166 MB; 55 free ranges, the largest 29 MB
[hos host] vk: image blocks (textures, compacted): 76 blocks 2432 MB, 1698 images 2347 MB; 311 free ranges, the largest 21 MB
[hos host] vk: render target images: 842 reused from the pool, 889 made new, 778 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6232 MB used of 15419 MB allowed (501 MB of it free in the blocks); textures 3123 MB (budget 11000 MB), 1812 textures
[hos host] vk: budget: VRAM 5028 of 15419 MB (6232 MB by the driver, 1203 MB unaccounted): textures 3123, mirrors 879, blocks free 501, shadows 280, other buffers 156, staging 48, other images 40; RAM 2645 MB (the process's private memory 22331 MB): imports 1900, capture spares 620, captures 84, capture table 31, other buffers 10, others 0
[hos host] vk: textures: decoded ASTC 1655 MB, rendered 761 MB (60 drawn in one frame, kept: 23560 KB), other 383 MB; used in the last 8 presents 2079 MB
[hos host] vk: decoded ASTC used again: 163 textures (401 MB) copied from ones the game finalized, not decoded; 163 of those retired, 7 listed; 954 MB of blocks hashed in 106 ms
[hos host] vk:   288 MB: 0x114682a000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x11361ac000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113b7bd000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001a79a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 504 presents ago
[hos host] vk:   54 MB: 0x10001be6200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   32 MB: 0x115882b000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   31 MB: 0x11094e6a00 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk:   23 MB: 0x111959dc00 768x1536x1 x4 levels 11 NVN 0x7b ASTC, last used 2 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 47 (12220 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 260x260x1 NVN 0xd: 18 (3167 KB); 262x104x1 NVN 0x1: 3 (79 KB); 306x104x1 NVN 0x1: 3 (93 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 40 waited for it, 0.61 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 20.7 ms; VRAM 6.1 of 15.1 GB
[hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 14 program records loaded (13.2 ms), 1 new graphics pipelines, pipelines from the driver's cache 7, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5287 queued, 5287 loaded (median 0.69 ms, 99th percentile 7.04 ms, worst 25.19 ms, 6004 ms and 1182.3 MB read in all); 7253 programs (1428 of them compute variants without their code, 0 graphics programs no note names), 9542 graphics pipelines (0 not in a cache), 401 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1634 pipelines made at create taken by draws; 2961 create calls with nothing kept for their stages, 0 before the index; units 8248 (5287 ready, 0 loading), 14342 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 658 known, 62 learned in this run; 364 compute pipelines made by them at a create call, 231 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 150 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.14, present 0.27, draw 3.65, descriptors 1.47, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.56, commands 1.18, dispatch 0.62, memory sync 0.31, queue submit 0.40, slot wait 0.15
[hos host] vk: a frame: mirrors 186 (879 MB): 4.22 MB synced in 855.8 copies, 17.07 MB written back
[hos host] vk: 16800 presents, 90.5 fps; a frame: 919 draws (0 skipped), 86 dispatches, 143 passes, 145 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1812 textures (3123 MB)
[hos host] vk: host time in GPU resource waits: 0.79 ms a frame (fences 0.02, timelines 0.77, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 335.9 full barriers recorded, 187.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 36.9; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 2.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 11.23 ms a frame): its jobs 7.07 ms a frame (submits 6.33, presents 0.18, others 0.57), idle 4.15; the game waited for room at 1 presents, 8.75 ms each (0.01 a frame; 2.17 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 50 captures at a CPU signal; the submits' waits read in 0.032 ms a frame; readbacks: 1197 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 6.21 ms after its hand-over (21.64 at most)
[hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 3.84 + 0.18 (the window's copy is in the idle), after it 1.40 + 0.24; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 4.80 parts a frame recorded in the signal's job, 66.2% of them took nothing that came with the signal; of the others, 1.62 a frame took pages of the signal's capture into a mirror (18.7 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 7 of 50 frames, its first three in 6
[hos host] vk: frame ahead, what came with the signal: 50 signals with a capture, each of 66.4 pages in 10.2 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.60+0.10, 0.55+0.07, 0.19+0.04, 0.05+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: mirror of pool 0x1040c00000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: mirror of pool 0x1041000000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: mirror of pool 0x1053c00000 (4 MB) given back: idle, 6058 submissions since its sync
[hos host] vk: 112 mirrors given back (882 MB in all); 875 MB of mirrors now, 44 MB of them idle and kept for what the GPU wrote there alone
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 965 ranges, 3217 MB), 210 pages written, 210 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 7177 texture pages copied (28 MB)
[hos host] vk: replay reads of guest memory as submitted: 4680000 (2896227 pages from the captures)
[hos host] vk: mirror of pool 0x7f6a000000 (4 MB) given back: idle, 6009 submissions since its sync
[hos host] vk: mirror of pool 0x7fb5c00000 (16 MB) given back: idle, 6052 submissions since its sync
[hos host] vk: sparse mirrors: 72, 860 MB with memory of 1296 MB (435 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 377 binds (19.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 114 kept as spares, 0 destroyed; 45 spares now, 592 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 325 dirty pages from their submits' captures, 58529 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1211 dispatches, 46496 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5760 runs, 933.1 MB compared; 111 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17034 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: mirror of pool 0x7f6f400000 (24 MB) given back: idle, 6058 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4700000 (2911445 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1210 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 8603 kept their virtual core (nothing there to wait for), 3173 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: mirror of pool 0x103cc00000 (4 MB) given back: idle, 6033 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 4720000 (2926763 pages from the captures)
[hos host] vk: mirror of pool 0x7f84000000 (4 MB) given back: idle, 6061 submissions since its sync
[hos Presentation Thread] vi: 16863 frames presented (90.8 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 453, 15.5-17.8 0, 17.8-22 1, 22-30 0, 30-40 0, over 40 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4976 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 5512182 kept (1916931 by the last picks' textures, a uniform buffer bound since), 61082 new, 2626735 with other textures (of 8200000)
[hos host] vk: replay reads of guest memory as submitted: 4740000 (2941927 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1954862 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 323 dirty pages from their submits' captures, 59063 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1209 dispatches, 47040 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5782 runs, 933.2 MB compared; 111 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16718 in captures, 2 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4760000 (2957084 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 966 ranges, 3221 MB), 206 pages written, 206 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (86 MB), 11 spare buffers, 7177 texture pages copied (28 MB)
[hos host] vk: replay reads of guest memory as submitted: 4780000 (2972272 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #125000: event 0x100c318024 mode 0 value 125000 (lr 0x80667688)
[hos host] vk: a frame: 150 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.17, present 0.14, draw 3.68, descriptors 1.50, texture lookups 0.06, uploads 0.01, pipelines 0.17, programs 0.55, commands 1.19, dispatch 0.61, memory sync 0.31, queue submit 0.41, slot wait 0.15
[hos host] vk: a frame: mirrors 186 (839 MB): 4.22 MB synced in 855.6 copies, 17.07 MB written back
[hos host] vk: 16920 presents, 93.0 fps; a frame: 918 draws (0 skipped), 86 dispatches, 143 passes, 145 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1816 textures (3123 MB)
[hos host] vk: host time in GPU resource waits: 0.59 ms a frame (fences 0.02, timelines 0.57, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 336.3 full barriers recorded, 187.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 36.8; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 2.4 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4800000 (2987447 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 293 KB; 0 made on demand (0 MB kept now); c1 stages: at most 176 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 69, 839 MB with memory of 1264 MB (424 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 380 binds (19.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 117 kept as spares, 0 destroyed; 48 spares now, 624 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 471 dirty pages from their submits' captures, 58548 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1199 dispatches, 46760 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5765 runs, 933.1 MB compared; 120 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17041 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: replay reads of guest memory as submitted: 4820000 (3002609 pages from the captures)
[hos host] vk: queues ordered by their events: 84000 submissions stopped at a wait, 83983 went on once it was reached, 14 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.00 ms at most); waits met 194696, not met 0; captures at a CPU event's wait 8948, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 4840000 (3017825 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #195000: event 0x100c318038 mode 0 value 125955 (now 125936) (lr 0x80661fac)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2994 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1231 of 3000 waited for their write-back, 0.06 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 8274 kept their virtual core (nothing there to wait for), 2734 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 268 dirty pages from their submits' captures, 59257 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1211 dispatches, 47119 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5759 runs, 932.6 MB compared; 118 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17020 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 4860000 (3033068 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 966 ranges, 3219 MB), 207 pages written, 207 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (92 MB), 11 spare buffers, 7252 texture pages copied (28 MB)
[hos host] vk: replay reads of guest memory as submitted: 4880000 (3048244 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 4900000 (3063515 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 27 sync waits (14 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos sead::MainThread] nvn: 1200000 recordings made, 80860 live copies (19.7 MB), 1018 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: a frame: 150 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.13, present 0.13, draw 3.61, descriptors 1.45, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.55, commands 1.17, dispatch 0.62, memory sync 0.30, queue submit 0.42, slot wait 0.15
[hos host] vk: a frame: mirrors 186 (839 MB): 4.22 MB synced in 856.5 copies, 17.07 MB written back
[hos host] vk: 17040 presents, 91.7 fps; a frame: 917 draws (0 skipped), 86 dispatches, 143 passes, 145 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1816 textures (3123 MB)
[hos host] vk: host time in GPU resource waits: 0.63 ms a frame (fences 0.02, timelines 0.60, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 335.9 full barriers recorded, 187.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 36.8; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 2.4 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 69, 839 MB with memory of 1264 MB (424 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 380 binds (19.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 117 kept as spares, 0 destroyed; 48 spares now, 624 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 233 dirty pages from their submits' captures, 59185 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1207 dispatches, 47073 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5765 runs, 933.1 MB compared; 107 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17050 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: replay reads of guest memory as submitted: 4920000 (3078661 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 4940000 (3093959 pages from the captures)
[hos rmbl::VibrationThread] vcores: 211879 takes, 43339 waits (mean 57 us, longest 17.6 ms, 0 over HOS_VCORE_LOG_MS), 22184 kicks, 21779 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: program picks: 5632601 kept (1935618 by the last picks' textures, a uniform buffer bound since), 61082 new, 2706316 with other textures (of 8400000)
[hos host] vk: replay reads of guest memory as submitted: 4960000 (3108988 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7286 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: render targets drawn over from another start, let go: 1461 so far (3288 MB), 1354 of them (3055 MB) between the passes
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 310 dirty pages from their submits' captures, 58500 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1202 dispatches, 46517 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5683 runs, 916.7 MB compared; 109 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16838 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 965 ranges, 3213 MB), 208 pages written, 208 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (86 MB), 11 spare buffers, 7252 texture pages copied (28 MB)
[hos host] vk: replay reads of guest memory as submitted: 4980000 (3124274 pages from the captures)
[hos host] vk: slow present: 15.8 ms:
[hos host] vk: present 17120 written to <home>\AppData\Local\<user>\data\jobs\jb_cad9d677c60f0b82\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion_9s.png (the control bridge)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1209 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 8870 kept their virtual core (nothing there to wait for), 3162 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: replay reads of guest memory as submitted: 5000000 (3139310 pages from the captures)
[hos host] vk: late pages found at the replay (600 takes): 44 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: replay reads of guest memory as submitted: 5020000 (3154595 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 2032036 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 69, 839 MB with memory of 1264 MB (424 MB spared); blocks given memory later 2398, given back 6327; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 380 binds (19.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 69 taken from the spares, 117 made new; 117 kept as spares, 0 destroyed; 48 spares now, 624 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 301 dirty pages from their submits' captures, 58912 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1199 dispatches, 46924 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5752 runs, 933.1 MB compared; 126 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 16883 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 129 live (1900 MB), 0 retired still imported (0 MB), 7 retired given back (232 MB)
[hos host] vk: a frame: 150 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 64 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.10, present 0.26, draw 3.58, descriptors 1.44, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.55, commands 1.15, dispatch 0.62, memory sync 0.31, queue submit 0.42, slot wait 0.15
[hos host] vk: a frame: mirrors 186 (839 MB): 4.23 MB synced in 856.6 copies, 17.07 MB written back
[hos host] vk: 17160 presents, 91.0 fps; a frame: 917 draws (0 skipped), 86 dispatches, 142 passes, 145 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42504 pipelines (23087 ms), 0 programs (10 failed), 1816 textures (3123 MB)
[hos host] vk: host time in GPU resource waits: 0.80 ms a frame (fences 0.02, timelines 0.78, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 335.7 full barriers recorded, 187.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 36.9; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.5 ms a frame (the longest submission 2.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 5040000 (3169623 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #200000: event 0x100c318038 mode 0 value 129755 (now 129736) (lr 0x80661fac)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #130000: event 0x100c31802c mode 0 value 129999 (lr 0x80667688)
[hos host] vk: replay reads of guest memory as submitted: 5060000 (3184879 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4403 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 960 ranges, 3199 MB), 207 pages written, 207 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (86 MB), 11 spare buffers, 7252 texture pages copied (28 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 293 KB; 0 made on demand (0 MB kept now); c1 stages: at most 176 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 313 dirty pages from their submits' captures, 59135 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: mirror syncs' pass (600 submits): 1210 dispatches, 47096 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5771 runs, 933.1 MB compared; 114 pages read into the shadows; 280 MB of shadows; pages the shadows knew that the CPU wrote: 17085 in captures, 0 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 5080000 (3199799 pages from the captures)
[hos host] vk: slow present: 15.2 ms:
[hos host] vk: present 17213 written to <home>\AppData\Local\<user>\data\jobs\jb_cad9d677c60f0b82\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-market-after-motion.png (the control bridge)
[hos host] control: quit asked by a client
[hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 14 program records loaded (13.2 ms), 1 new graphics pipelines, pipelines from the driver's cache 7, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (close): 5287 queued, 5287 loaded (median 0.69 ms, 99th percentile 7.04 ms, worst 25.19 ms, 6004 ms and 1182.3 MB read in all); 7253 programs (1428 of them compute variants without their code, 0 graphics programs no note names), 9542 graphics pipelines (0 not in a cache), 401 compute pipelines (250 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1634 pipelines made at create taken by draws; 2961 create calls with nothing kept for their stages, 0 before the index; units 8248 (5287 ready, 0 loading), 14342 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (close): 658 known, 62 learned in this run; 364 compute pipelines made by them at a create call, 231 asked that way were in no cache (their code read, as before)
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4312 pools in the table now)
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)