Beanstalk Longshot test farm
Menu

Report rp_01c20b8226d7940d 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 Hidden tester,

This report disagrees with its peers.

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

Machine

Commit
3569b8da6a4f90bc036bbb40cb52993b865b0a39
Baseline
09cbdd979eacfbd0c83e27fad7e50380985af02d
App
nightly-172-736563c0, attempt 2
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 9 5900X 12-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)

1,320.6 s warm

from 09cbdd979eac

lift
111.9 s
read
511.7 s
finish
162.3 s
compile
526.1 s

PR

162.7 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_code00±0%
log_forbidden_hits00±0%
log_expected_missing00±0%
kokiri-standing.fps_mean74.780.71+8%
market-standing.fps_mean59.1762.55+5.7%
kokiri-standing.draws_mean667701.4+5.2%
market-standing.draws_mean2,469.852,485+0.6%
kokiri-standing.hitch_count00±0%
market-standing.hitch_count00±0%
kokiri-after-motion.fps_mean74.8183.94+12.2%
market-after-motion.fps_mean72.8276.53+5.1%
kokiri-standing.stutter_count1.51.5±0%
market-standing.stutter_count1.52+33.3%
kokiri-after-motion.draws_mean676.15652.2−3.5%
market-after-motion.draws_mean1,398.51,337.1−4.4%
kokiri-after-motion.hitch_count00±0%
market-after-motion.hitch_count00±0%
kokiri-standing.frametime_max_ms29.3229.15−0.6%
kokiri-standing.frametime_p50_ms13.4512.45−7.5%
kokiri-standing.frametime_p99_ms15.6114.99−4%
market-standing.frametime_max_ms35.6433.94−4.8%
market-standing.frametime_p50_ms16.6515.82−5%
market-standing.frametime_p99_ms20.4319.22−5.9%
kokiri-after-motion.stutter_count22.5+25%
market-after-motion.stutter_count22±0%
kokiri-after-motion.frametime_max_ms30.8128.75−6.7%
kokiri-after-motion.frametime_p50_ms13.6912.08−11.7%
kokiri-after-motion.frametime_p99_ms15.4214.92−3.3%
market-after-motion.frametime_max_ms31.0930.15−3%
market-after-motion.frametime_p50_ms13.4712.7−5.7%
market-after-motion.frametime_p99_ms17.8416.59−7%
kokiri-standing.frametime_1pct_low_ms18.2117.78−2.4%
market-standing.frametime_1pct_low_ms24.6623.2−5.9%
kokiri-after-motion.frametime_1pct_low_ms20.0420.27+1.1%
market-after-motion.frametime_1pct_low_ms21.5220.41−5.2%
screenshot_diff—0.86—

Pictures against main: kokiri-standing 5 s diff 0.7099 (main against itself 0.0303), kokiri-standing 9 s diff 0.7187 (main against itself 0.1606), kokiri-after-motion 5 s diff 0.7888 (main against itself 0.5428), kokiri-after-motion 9 s diff 0.9755 (main against itself 0.5358), market-standing 5 s diff 0.129 (main against itself 0.0347), market-standing 9 s diff 0.1294 (main against itself 0.1035), market-after-motion 5 s diff 0.7511 (main against itself 0.7805), market-after-motion 9 s diff 0.7526 (main against itself 0.7898), kokiri-standing diff 0.7062 (main against itself 0.1596), kokiri-after-motion diff 0.9736 (main against itself 0.5325), market-standing diff 0.1361 (main against itself 0.0449), market-after-motion diff 0.7534 (main against itself 0.7919)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code00—0
log_forbidden_hits0000
log_expected_missing0000
kokiri-standing.fps_mean74.3578.4982.9375.05
market-standing.fps_mean59.1662.55—59.19
kokiri-standing.draws_mean666.6666.3736.5667.4
market-standing.draws_mean2,454.22,485—2,485.5
kokiri-standing.hitch_count0000
market-standing.hitch_count00—0
kokiri-after-motion.fps_mean75.4678.988.9774.15
market-after-motion.fps_mean74.0976.53—71.55
kokiri-standing.stutter_count2121
market-standing.stutter_count12—2
kokiri-after-motion.draws_mean676.7697.9606.5675.6
market-after-motion.draws_mean1,401.91,337.1—1,395.1
kokiri-after-motion.hitch_count0000
market-after-motion.hitch_count00—0
kokiri-standing.frametime_max_ms29.5130.3227.9929.14
kokiri-standing.frametime_p50_ms13.412.8712.0213.5
kokiri-standing.frametime_p99_ms16.1214.5615.4115.1
market-standing.frametime_max_ms34.1533.94—37.12
market-standing.frametime_p50_ms16.6615.82—16.63
market-standing.frametime_p99_ms20.2219.22—20.65
kokiri-after-motion.stutter_count2232
market-after-motion.stutter_count22—2
kokiri-after-motion.frametime_max_ms31.229.2928.2230.43
kokiri-after-motion.frametime_p50_ms13.6112.7611.413.77
kokiri-after-motion.frametime_p99_ms15.5914.8115.0315.26
market-after-motion.frametime_max_ms32.4530.15—29.73
market-after-motion.frametime_p50_ms1312.7—13.94
market-after-motion.frametime_p99_ms17.2316.59—18.45
kokiri-standing.frametime_1pct_low_ms18.921718.5717.5
market-standing.frametime_1pct_low_ms24.4123.2—24.91
kokiri-after-motion.frametime_1pct_low_ms20.8520.2320.319.22
market-after-motion.frametime_1pct_low_ms21.6620.41—21.38
screenshot_diff—0.750.98—

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%
log_forbidden_hits00±0%
log_expected_missing00±0%
kokiri-standing.fps_mean76.6682.81+8%
market-standing.fps_mean59.4863.31+6.4%
kokiri-standing.draws_mean673.2705.3+4.8%
market-standing.draws_mean2,454.42,528.9+3%
kokiri-standing.hitch_count00±0%
market-standing.hitch_count00±0%
kokiri-after-motion.fps_mean77.185.19+10.5%
market-after-motion.fps_mean75.7477.93+2.9%
kokiri-standing.stutter_count11±0%
market-standing.stutter_count0.52+300%
kokiri-after-motion.draws_mean676.25680+0.6%
market-after-motion.draws_mean1,249.851,387.4+11%
kokiri-after-motion.hitch_count00±0%
market-after-motion.hitch_count00±0%
kokiri-standing.frametime_max_ms28.7926.88−6.6%
kokiri-standing.frametime_p50_ms13.1812.12−8.1%
kokiri-standing.frametime_p99_ms14.6513.63−7%
market-standing.frametime_max_ms32.9231.4−4.6%
market-standing.frametime_p50_ms16.5115.59−5.6%
market-standing.frametime_p99_ms20.1418.23−9.5%
kokiri-after-motion.stutter_count1.53+100%
market-after-motion.stutter_count22±0%
kokiri-after-motion.frametime_max_ms29.9229.77−0.5%
kokiri-after-motion.frametime_p50_ms13.3511.77−11.8%
kokiri-after-motion.frametime_p99_ms14.9914.41−3.9%
market-after-motion.frametime_max_ms31.2330.24−3.2%
market-after-motion.frametime_p50_ms12.9312.63−2.3%
market-after-motion.frametime_p99_ms17.3916.34−6%
kokiri-standing.frametime_1pct_low_ms16.9815.7−7.5%
market-standing.frametime_1pct_low_ms23.6821.64−8.7%
kokiri-after-motion.frametime_1pct_low_ms19.0119.01+0%
market-after-motion.frametime_1pct_low_ms21.8420.55−5.9%
screenshot_diff—0.85—

Pictures against main: kokiri-standing 5 s diff 0.7097 (main against itself 0.0123), kokiri-standing 9 s diff 0.7292 (main against itself 0.1807), kokiri-after-motion 5 s diff 0.8786 (main against itself 0.1872), kokiri-after-motion 9 s diff 0.9661 (main against itself 0.1597), market-standing 5 s diff 0.0765 (main against itself 0.0974), market-standing 9 s diff 0.0758 (main against itself 0.0891), market-after-motion 5 s diff 0.7353 (main against itself 0.9114), market-after-motion 9 s diff 0.7307 (main against itself 0.9134), kokiri-standing diff 0.725 (main against itself 0.0427), kokiri-after-motion diff 0.9657 (main against itself 0.1612), market-standing diff 0.0345 (main against itself 0.0297), market-after-motion diff 0.7284 (main against itself 0.912)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code00—0
log_forbidden_hits0000
log_expected_missing0000
kokiri-standing.fps_mean76.779.9385.6976.61
market-standing.fps_mean59.6263.31—59.35
kokiri-standing.draws_mean671.2666.7743.9675.2
market-standing.draws_mean2,452.92,528.9—2,455.9
kokiri-standing.hitch_count0000
market-standing.hitch_count00—0
kokiri-after-motion.fps_mean77.980.3390.0676.3
market-after-motion.fps_mean75.3777.93—76.11
kokiri-standing.stutter_count1111
market-standing.stutter_count02—1
kokiri-after-motion.draws_mean676.4756.8603.2676.1
market-after-motion.draws_mean1,348.71,387.4—1,151
kokiri-after-motion.hitch_count0000
market-after-motion.hitch_count00—0
kokiri-standing.frametime_max_ms30.2726.8726.8927.32
kokiri-standing.frametime_p50_ms13.1512.511.7413.22
kokiri-standing.frametime_p99_ms14.614.0713.1914.7
market-standing.frametime_max_ms32.6131.4—33.23
market-standing.frametime_p50_ms16.4315.59—16.6
market-standing.frametime_p99_ms20.3518.23—19.93
kokiri-after-motion.stutter_count1242
market-after-motion.stutter_count22—2
kokiri-after-motion.frametime_max_ms29.6729.629.9530.16
kokiri-after-motion.frametime_p50_ms13.2712.3511.213.43
kokiri-after-motion.frametime_p99_ms14.7914.3314.4915.18
market-after-motion.frametime_max_ms32.1430.24—30.33
market-after-motion.frametime_p50_ms12.812.63—13.06
market-after-motion.frametime_p99_ms17.7216.34—17.05
kokiri-standing.frametime_1pct_low_ms16.8416.315.1117.11
market-standing.frametime_1pct_low_ms24.0121.64—23.36
kokiri-after-motion.frametime_1pct_low_ms18.8217.7320.319.19
market-after-motion.frametime_1pct_low_ms22.0420.55—21.64
screenshot_diff—0.740.97—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
default-presentercrashFalse00—pass
default-presenterkokiri-standing.fps_mean.min_delta_pct1574.780.71+8%pass
default-presenterkokiri-after-motion.fps_mean.min_delta_pct1574.8183.94+12.2%pass
default-presentermarket-standing.fps_mean.min_delta_pct1559.1762.55+5.7%pass
default-presentermarket-after-motion.fps_mean.min_delta_pct1572.8276.53+5.1%pass
default-presenterscreenshot.max_diff0.40.790.98—fail
default-presenterkokiri-standing.frametime_p99_ms.max_delta_pct2015.6114.99−4%pass
default-presenterkokiri-after-motion.frametime_p99_ms.max_delta_pct2015.4214.92−3.3%pass
default-presentermarket-standing.frametime_p99_ms.max_delta_pct2020.4319.22−5.9%pass
default-presentermarket-after-motion.frametime_p99_ms.max_delta_pct2017.8416.59−7%pass
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_pct1576.6682.81+8%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.fps_mean.min_delta_pct1577.185.19+10.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.fps_mean.min_delta_pct1559.4863.31+6.4%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.fps_mean.min_delta_pct1575.7477.93+2.9%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)screenshot.max_diff0.40.910.97—fail
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-standing.frametime_p99_ms.max_delta_pct2014.6513.63−7%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)kokiri-after-motion.frametime_p99_ms.max_delta_pct2014.9914.41−3.9%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-standing.frametime_p99_ms.max_delta_pct2020.1418.23−9.5%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)market-after-motion.frametime_p99_ms.max_delta_pct2017.3916.34−6%pass
forced-presenterRX_VK_PRESENT_THREAD=1 (PR only)log_forbidden_hits.max000—pass

Pictures of the failure

This report had 2 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:   54 MB: 0x10001eb6200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2843 presents ago
[hos host] vk:   54 MB: 0x10001d49a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 34 (9494 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: 4 (123 KB); 242x40x1 NVN 0x25: 3 (113 KB); 260x260x1 NVN 0xd: 2 (351 KB); 262x104x1 NVN 0x1: 4 (106 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 host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos Presentation Thread] vk: presents after the CPU's signal (600): 89 waited for it, 1.17 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 29.7 ms; VRAM 6.9 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: 3 program records loaded (2.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, 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): 4573 queued, 4573 loaded (median 0.51 ms, 99th percentile 5.51 ms, worst 17.76 ms, 3917 ms and 990.0 MB read in all); 6326 programs (1367 of them compute variants without their code, 0 graphics programs no note names), 8221 graphics pipelines (0 not in a cache), 365 compute pipelines (231 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 870 pipelines made at create taken by draws; 2473 create calls with nothing kept for their stages, 0 before the index; units 7046 (4573 ready, 0 loading), 12265 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 658 known, 0 learned in this run; 365 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: 44 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.65, present 0.31, draw 2.50, descriptors 1.08, texture lookups 0.06, uploads 0.00, pipelines 0.10, programs 0.47, commands 0.65, dispatch 0.57, memory sync 0.36, queue submit 0.32, slot wait 0.14
[hos host] vk: a frame: mirrors 83 (795 MB): 4.07 MB synced in 846.0 copies, 23.06 MB written back
[hos host] vk: 13200 presents, 87.3 fps; a frame: 665 draws (0 skipped), 94 dispatches, 143 passes, 142 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1635 textures (4231 MB)
[hos host] vk: host time in GPU resource waits: 2.99 ms a frame (fences 0.02, timelines 2.98, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 345.9 full barriers recorded, 181.4 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: 38.2; 0x12: 73.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 4.2 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, 11.12 ms a frame): its jobs 5.19 ms a frame (submits 4.19, presents 0.26, others 0.74), idle 5.93; the game waited for room at 2 presents, 8.35 ms each (0.03 a frame; 3.69 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); 91 captures at a CPU signal; the submits' waits read in 0.026 ms a frame; readbacks: 2991 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 4.43 ms after its hand-over (19.94 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 3.49 + 0.26 (the window's copy is in the idle), after it 0.48 + 0.19; 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): 3.58 parts a frame recorded in the signal's job, 42.0% of them took nothing that came with the signal; of the others, 2.08 a frame took pages of the signal's capture into a mirror (59.1 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 4 of 91 frames, its first three in 4
[hos host] vk: frame ahead, what came with the signal: 91 signals with a capture, each of 77.9 pages in 9.4 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: 0.41+0.13, 0.03+0.03, 0.02+0.02, 0.01+0.01, 0.00+0.00, 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
[hos host] vk: slow present: 16.1 ms:
[hos host] vk: present 13202 written to <data>\jobs\jb_e9152b3953bb4fdf\runs\forced-presenter-g0-02-pr\shots/forced-presenter-c0-pr-02-kokiri-after-motion.png (the control bridge)
[hos host] control: teleport to destination 3 asked for
[hos BaseProcExecutor5] cheats: teleport waits until the current event ends
[hos ModuleSystemWorker1] vcores: 200339 takes, 24601 waits (mean 28 us, longest 4.6 ms, 0 over HOS_VCORE_LOG_MS), 12095 kicks, 11927 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1380000 (632378 pages from the captures)
[hos host] vk: texture #2253 0x100019ace00 1440x900 x1 NVN 0x25 the GPU drew, finalized by the game, sampled again at frame 13216 (drawn at 12848)
[hos host] vk: upload over a drawn image: #286 0x10001ef0e00 1440x900x1 x1 NVN 0x25 at present 13216 (texture frame 13217), finalized, 636 KB dirty in 1 ranges
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 176 pages written, 176 copied (0.7 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 0.002, bytes copied 0.000; 24 kept (114 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1400000 (645594 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 960 so far (2049 MB), 861 of them (1840 MB) between the passes
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1590 dirty pages from their submits' captures, 59527 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): 1349 dispatches, 50324 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6464 runs, 1374.9 MB compared; 183 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19612 in captures, 2 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1420000 (658807 pages from the captures)
[hos host] vk: mirror of pool 0x7fd3400000 (32 MB) given back: idle, 6017 submissions since its sync
[hos host] vk: texture #2854 0x100066fa000 1920x1920 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 13276 (drawn at 13215)
[hos host] vk: readback pages refreshed from guest memory: 771705 pages so far (0 held: may be written ahead in their submission)
[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: 1440000 (672051 pages from the captures)
[hos ModuleSystemWorker3] nvn: 600000 recordings made, 41257 live copies (10.8 MB), 796 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: late pages found at the replay (600 takes): 58 pages in 2 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 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 1143 ranges, 1913 MB), 165 pages written, 165 copied (0.6 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 0.002, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #70000: event 0x100c5e8008 mode 0 value 69998 (lr 0x80660f34)
[hos host] vk: sparse mirrors: 56, 771 MB with memory of 948 MB (177 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 153 binds (6.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 21 taken from the spares, 62 made new; 27 kept as spares, 0 destroyed; 6 spares now, 140 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1826 dirty pages from their submits' captures, 58243 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): 1320 dispatches, 49972 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6245 runs, 1370.9 MB compared; 164 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19406 in captures, 3 only in the collection, 60 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: a frame: 31 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.41, present 0.31, draw 2.33, descriptors 1.03, texture lookups 0.06, uploads 0.00, pipelines 0.09, programs 0.44, commands 0.59, dispatch 0.55, memory sync 0.35, queue submit 0.30, slot wait 0.13
[hos host] vk: a frame: mirrors 83 (771 MB): 3.94 MB synced in 835.2 copies, 22.87 MB written back
[hos host] vk: 13320 presents, 91.7 fps; a frame: 612 draws (0 skipped), 85 dispatches, 140 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1644 textures (4262 MB)
[hos host] vk: host time in GPU resource waits: 2.64 ms a frame (fences 0.02, timelines 2.62, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 334.5 full barriers recorded, 180.3 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: 37.9; 0x12: 72.8; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 4.6 ms); 0.2 textures made a frame
[hos host] vk: a frame: 0.04 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] nvn: QueueSubmitCommands #80000: queue 000010100C560020 (its #13333), 1 handles (lr 0x805282f4)
[hos host] vk: replay reads of guest memory as submitted: 1460000 (685223 pages from the captures)
[hos host] vk: 2 textures retired (1642 left, 4256 MB): budget 0, drawn over 2, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #120000: event 0x100c5e8030 mode 0 value 70502 (now 70483) (lr 0x806614d8)
[hos host] vk: mirror of pool 0x7fd6800000 (16 MB) given back: idle, 6038 submissions since its sync
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1297 of 3000 waited for their write-back, 0.26 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: 2467 kept their virtual core (nothing there to wait for), 2909 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: program picks: 1646632 kept (649749 by the last picks' textures, a uniform buffer bound since), 55975 new, 897392 with other textures (of 2600000)
[hos sead::MainThread] nvn: GPU waits in 5 s: 135 sync waits (126 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 1480000 (698494 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1901 dirty pages from their submits' captures, 57253 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): 1298 dispatches, 49191 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6148 runs, 1348.0 MB compared; 156 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19281 in captures, 1 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker4] barrier: 170911 looks: 23455 found the masks moved already, 119213 waited until they moved, 28243 for the whole 1 ms (a wait 371 us on average); 150089 wakes
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 140000 so far (x1 0x11778c4000 x2 0x1 x3 0x11778c4000 x4 0x4040)
[hos host] vk: replay reads of guest memory as submitted: 1500000 (711719 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos Presentation Thread] vi: 13401 frames presented (89.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 445, 15.5-17.8 0, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 163 pages written, 163 copied (0.6 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 0.002, bytes copied 0.000; 25 kept (104 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1520000 (724975 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: sparse mirrors: 55, 757 MB with memory of 932 MB (174 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 154 binds (6.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 21 taken from the spares, 62 made new; 28 kept as spares, 0 destroyed; 7 spares now, 156 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1813 dirty pages from their submits' captures, 58363 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): 1322 dispatches, 50002 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6255 runs, 1370.9 MB compared; 173 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19395 in captures, 1 only in the collection, 60 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: queues ordered by their events: 60000 submissions stopped at a wait, 59985 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 122425, not met 0; captures at a CPU event's wait 6590, 0 of them at a wait met on arrival
[hos host] vk: a frame: 29 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.36, present 0.17, draw 2.30, descriptors 1.03, texture lookups 0.05, uploads 0.00, pipelines 0.08, programs 0.45, commands 0.57, dispatch 0.54, memory sync 0.35, queue submit 0.29, slot wait 0.15
[hos host] vk: a frame: mirrors 83 (757 MB): 3.92 MB synced in 833.3 copies, 22.85 MB written back
[hos host] vk: 13440 presents, 93.8 fps; a frame: 597 draws (0 skipped), 84 dispatches, 139 passes, 140 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1642 textures (4256 MB)
[hos host] vk: host time in GPU resource waits: 2.48 ms a frame (fences 0.02, timelines 2.46, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 332.4 full barriers recorded, 180.0 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: 37.7; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 4.6 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: 1540000 (738457 pages from the captures)
[hos host] control: teleport to destination 3 asked for
[hos BaseProcExecutor3] cheats: teleport waits until the current event ends
[hos host] vk: replay reads of guest memory as submitted: 1560000 (751528 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 285 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1810 dirty pages from their submits' captures, 57341 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): 1298 dispatches, 49170 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6148 runs, 1348.1 MB compared; 150 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19285 in captures, 2 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 164 pages written, 164 copied (0.6 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 0.002, bytes copied 0.000; 25 kept (102 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos sead::MainThread] vk: readbacks of GPU results: 1328 of 3000 waited for their write-back, 0.25 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: 2723 kept their virtual core (nothing there to wait for), 2909 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: 1580000 (764588 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #125000: event 0x100c5e8030 mode 0 value 74302 (now 74283) (lr 0x806614d8)
[hos host] vk: sparse mirrors: 55, 757 MB with memory of 932 MB (174 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 154 binds (6.4 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 21 taken from the spares, 62 made new; 28 kept as spares, 0 destroyed; 7 spares now, 156 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: replay reads of guest memory as submitted: 1600000 (777715 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1906 dirty pages from their submits' captures, 58242 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): 1318 dispatches, 50015 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6152 runs, 1348.1 MB compared; 165 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19531 in captures, 3 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[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: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 29 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.42, present 0.18, draw 2.32, descriptors 1.04, texture lookups 0.05, uploads 0.00, pipelines 0.08, programs 0.44, commands 0.58, dispatch 0.54, memory sync 0.36, queue submit 0.28, slot wait 0.17
[hos host] vk: a frame: mirrors 83 (757 MB): 3.92 MB synced in 833.4 copies, 22.85 MB written back
[hos host] vk: 13560 presents, 93.4 fps; a frame: 598 draws (0 skipped), 84 dispatches, 139 passes, 140 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1642 textures (4256 MB)
[hos host] vk: host time in GPU resource waits: 2.49 ms a frame (fences 0.02, timelines 2.47, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 332.6 full barriers recorded, 180.0 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: 37.7; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.3 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #75000: event 0x100c5e801c mode 0 value 75000 (lr 0x802915c8)
[hos host] vk: readback pages refreshed from guest memory: 845875 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 1620000 (790840 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 165 pages written, 165 copied (0.6 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 0.002, bytes copied 0.000; 24 kept (106 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1633 dirty pages from their submits' captures, 57540 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): 1330 dispatches, 49173 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6250 runs, 1370.9 MB compared; 152 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19202 in captures, 2 only in the collection, 60 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1640000 (804035 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 1660000 (817194 pages from the captures)
[hos sead::MainThread] vk: readbacks of GPU results: 1328 of 3000 waited for their write-back, 0.24 ms each; 0 looked at the stopped queues first, 2 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: 2645 kept their virtual core (nothing there to wait for), 2987 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: sparse mirrors: 57, 769 MB with memory of 952 MB (182 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 156 binds (6.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 62 made new; 28 kept as spares, 0 destroyed; 5 spares now, 136 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1882 dirty pages from their submits' captures, 57496 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): 1357 dispatches, 49237 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6149 runs, 1348.2 MB compared; 149 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19212 in captures, 6 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos BaseProcExecutor1] vcores: 209611 takes, 25720 waits (mean 27 us, longest 5.1 ms, 0 over HOS_VCORE_LOG_MS), 12712 kicks, 12687 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 1680000 (830368 pages from the captures)
[hos host] vk: a frame: 29 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.47, present 0.18, draw 2.29, descriptors 1.02, texture lookups 0.06, uploads 0.00, pipelines 0.08, programs 0.44, commands 0.57, dispatch 0.54, memory sync 0.38, queue submit 0.30, slot wait 0.18
[hos host] vk: a frame: mirrors 85 (769 MB): 4.03 MB synced in 834.1 copies, 22.85 MB written back
[hos host] vk: 13680 presents, 93.0 fps; a frame: 599 draws (0 skipped), 84 dispatches, 140 passes, 140 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1632 textures (4256 MB)
[hos host] vk: host time in GPU resource waits: 2.35 ms a frame (fences 0.02, timelines 2.34, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 333.6 full barriers recorded, 180.2 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; 0x10: 0.0; 0x11: 37.7; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.2 ms a frame (the longest submission 4.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 164 pages written, 164 copied (0.6 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 0.002, bytes copied 0.000; 24 kept (86 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[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: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 1778670 kept (708801 by the last picks' textures, a uniform buffer bound since), 55975 new, 965354 with other textures (of 2800000)
[hos host] vk: recorder: 4175353 packets run in 10.0 s (busy 0.93 s, spun idle 3.52 s, slept 4634 times, 1332 of them under 200 us), 0 calls made directly (no room); the replay waited for it 29484 times, 79.30 ms in all, the longest 0.10 ms; vkResetDescriptorPool 8995/42.92 ms (max 0.10), vkEndCommandBuffer 9040/18.51 ms (max 0.09), replay_mu unlock 11197/16.61 ms (max 0.07), vmaInvalidateAllocation 245/1.23 ms (max 0.09), vkQueueBindSparse 7/0.02 ms (max 0.01)
[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: 1700000 (843530 pages from the captures)
[hos host] vk: 1 textures retired (1631 left, 4255 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1608 dirty pages from their submits' captures, 58762 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): 1381 dispatches, 50056 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6254 runs, 1370.4 MB compared; 157 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19462 in captures, 3 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 1720000 (856857 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #130000: event 0x100c5e8030 mode 0 value 78102 (now 78083) (lr 0x806614d8)
[hos host] control: teleport to destination 3 asked for
[hos BaseProcExecutor2] cheats: teleport waits until the current event ends
[hos host] vk: replay reads of guest memory as submitted: 1740000 (870089 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1143 ranges, 1913 MB), 165 pages written, 165 copied (0.6 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 0.002, bytes copied 0.000; 25 kept (94 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 285 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 57, 769 MB with memory of 952 MB (182 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 156 binds (6.5 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 62 made new; 28 kept as spares, 0 destroyed; 5 spares now, 136 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1353 dirty pages from their submits' captures, 57914 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): 1357 dispatches, 49256 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6163 runs, 1348.8 MB compared; 162 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19109 in captures, 4 only in the collection, 60 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: memory: working set 13631 MB (peak 13806), private 21715 MB, staging 32 MB in 2 arenas, 26 made so far (68 ms)
[hos host] vk: memory heaps: heap 0 (system): 16 blocks 784 MB, 39 allocations 746 MB; used 1928 of 15565 MB; heap 1 (device): 185 blocks 6014 MB, 14214 allocations 5560 MB; used 7058 of 15419 MB;
[hos host] vk: image blocks: 2 blocks 64 MB, 7 images 35 MB; 2 free ranges, the largest 22 MB
[hos host] vk: image blocks (render targets): 14 blocks 448 MB, 103 images 223 MB; 50 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 78 blocks 2496 MB, 1512 images 2474 MB; 193 free ranges, the largest 7 MB
[hos host] vk: render target images: 555 reused from the pool, 809 made new, 702 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 7058 MB used of 15419 MB allowed (453 MB of it free in the blocks); textures 4255 MB (budget 11000 MB), 1631 textures
[hos host] vk: budget: VRAM 6014 of 15419 MB (7058 MB by the driver, 1044 MB unaccounted): textures 4255, mirrors 769, blocks free 453, shadows 296, other buffers 155, other images 50, staging 32; RAM 1912 MB (the process's private memory 21715 MB): imports 1128, capture spares 640, captures 118, capture table 26, others 0
[hos host] vk: textures: decoded ASTC 2474 MB, rendered 889 MB (55 drawn in one frame, kept: 25158 KB), other 427 MB; used in the last 8 presents 1973 MB
[hos host] vk: decoded ASTC used again: 0 textures (0 MB) copied from ones the game finalized, not decoded; 0 of those retired, 7 listed; 512 MB of blocks hashed in 47 ms
[hos host] vk:   288 MB: 0x1146afa000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a4a42c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a11ca600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 4192 presents ago
[hos host] vk:   64 MB: 0x113647c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113ba8d000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001771a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1774 presents ago
[hos host] vk:   54 MB: 0x10001d49a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 25 (14177 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: 1 (30 KB); 260x260x1 NVN 0xd: 2 (351 KB); 262x104x1 NVN 0x1: 1 (26 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 720x450x1 NVN 0x29: 1 (2531 KB); 720x450x1 NVN 0x34: 2 (2531 KB); 1466x282x1 NVN 0x25: 5 (8074 KB);
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos Presentation Thread] vk: presents after the CPU's signal (600): 286 waited for it, 0.72 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 21.8 ms; VRAM 6.9 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: 3 program records loaded (2.0 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, 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): 4573 queued, 4573 loaded (median 0.51 ms, 99th percentile 5.51 ms, worst 17.76 ms, 3917 ms and 990.0 MB read in all); 6326 programs (1367 of them compute variants without their code, 0 graphics programs no note names), 8221 graphics pipelines (0 not in a cache), 365 compute pipelines (231 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 870 pipelines made at create taken by draws; 2473 create calls with nothing kept for their stages, 0 before the index; units 7046 (4573 ready, 0 loading), 12265 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: module identifiers (play): 658 known, 0 learned in this run; 365 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: 29 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.46, present 0.18, draw 2.34, descriptors 1.06, texture lookups 0.05, uploads 0.00, pipelines 0.08, programs 0.44, commands 0.57, dispatch 0.55, memory sync 0.37, queue submit 0.29, slot wait 0.18
[hos host] vk: a frame: mirrors 85 (769 MB): 3.93 MB synced in 834.5 copies, 22.85 MB written back
[hos host] vk: 13800 presents, 93.3 fps; a frame: 599 draws (0 skipped), 84 dispatches, 140 passes, 140 barriers, 6 submits, 0.0 uploads (0.0 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41163 pipelines (21507 ms), 0 programs (11 failed), 1631 textures (4255 MB)
[hos host] vk: host time in GPU resource waits: 2.31 ms a frame (fences 0.02, timelines 2.29, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 333.6 full barriers recorded, 180.2 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: 37.7; 0x12: 72.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.2 ms a frame (the longest submission 4.5 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, 10.75 ms a frame): its jobs 5.05 ms a frame (submits 2.86, presents 0.21, others 1.99), idle 5.69; the game waited for room at 1 presents, 8.62 ms each (0.01 a frame; 3.14 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); 290 captures at a CPU signal; the submits' waits read in 0.023 ms a frame; readbacks: 2995 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 4.25 ms after its hand-over (20.09 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 2.67 + 0.27 (the window's copy is in the idle), after it 0.41 + 0.16; after a frame's last recording that reads or writes the game's memory come 1.04 recordings (0.02 ms of GPU time), after its last that reads it 1.04 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 3.62 parts a frame recorded in the signal's job, 46.2% of them took nothing that came with the signal; of the others, 1.94 a frame took pages of the signal's capture into a mirror (54.1 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 5 of 290 frames, its first three in 5
[hos host] vk: frame ahead, what came with the signal: 290 signals with a capture, each of 74.3 pages in 9.1 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: 0.35+0.11, 0.01+0.02, 0.03+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, 0.00+0.00
[hos host] vk: replay reads of guest memory as submitted: 1760000 (883305 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: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1330 of 3000 waited for their write-back, 0.23 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 ModuleSystemWorker3] vk: invalidates since the last readbacks line: 2516 kept their virtual core (nothing there to wait for), 2860 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: mirror of pool 0x7f92400000 (8 MB) given back: idle, 6047 submissions since its sync
[hos host] vk: mirror of pool 0x7fb4800000 (8 MB) given back: idle, 6047 submissions since its sync
[hos host] vk: replay reads of guest memory as submitted: 1780000 (896582 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 231 sync waits (154 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #80000: event 0x100c5e801c mode 0 value 79997 (lr 0x802911b8)
[hos host] vk: render targets drawn over from another start, let go: 975 so far (2050 MB), 876 of them (1841 MB) between the passes
[hos host] vk: write-backs left out (600 submits): 1320, 5137.7 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1677 dirty pages from their submits' captures, 58646 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): 1375 dispatches, 50046 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6146 runs, 1348.2 MB compared; 165 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19152 in captures, 4 only in the collection, 59 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x11779c8000 x2 0 x3 0x11779c8000 x4 0xf0040)
[hos ModuleSystemWorker4] nvn: 650000 recordings made, 41286 live copies (11.1 MB), 800 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 1800000 (909891 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.05 over 1138 ranges, 1881 MB), 164 pages written, 164 copied (0.6 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 0.002, bytes copied 0.000; 25 kept (114 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos Presentation Thread] vi: 13868 frames presented (93.3 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 466, 15.5-17.8 1, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: readback pages refreshed from guest memory: 920035 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 1820000 (923102 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: sparse mirrors: 55, 759 MB with memory of 936 MB (176 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 157 binds (6.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 62 made new; 30 kept as spares, 0 destroyed; 7 spares now, 152 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1298, 5052.1 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1777 dirty pages from their submits' captures, 57361 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): 1306 dispatches, 49203 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6252 runs, 1370.9 MB compared; 171 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 19376 in captures, 2 only in the collection, 60 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: upload over a drawn image: #286 0x10001ef0e00 1440x900x1 x1 NVN 0x25 at present 13916 (texture frame 13917), finalized, 636 KB dirty in 1 ranges
[hos host] vk: a frame: 29 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.49, present 0.18, draw 2.39, descriptors 1.11, texture lookups 0.11, uploads 0.04, pipelines 0.08, programs 0.44, commands 0.58, dispatch 0.55, memory sync 0.36, queue submit 0.29, slot wait 0.18
[hos host] vk: a frame: mirrors 88 (797 MB): 4.32 MB synced in 834.4 copies, 22.85 MB written back
[hos host] vk: 13920 presents, 92.9 fps; a frame: 606 draws (0 skipped), 84 dispatches, 140 passes, 140 barriers, 6 submits, 0.1 uploads (0.3 MB), 94 ub updates (64 overlays), GPU-bound wait 0.0 ms (recording slots only); 41164 pipelines (21507 ms), 0 programs (11 failed), 1637 textures (4289 MB)
[hos host] vk: host time in GPU resource waits: 2.33 ms a frame (fences 0.02, timelines 2.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 333.4 full barriers recorded, 180.0 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: 37.8; 0x12: 72.6; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.2 ms a frame (the longest submission 4.5 ms); 0.3 textures made a frame
[hos host] vk: a frame: 0.32 MB unswizzled on the CPU in 0.04 ms
[hos host] vk: replay reads of guest memory as submitted: 1840000 (935936 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: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #135000: event 0x100c5e8014 mode 0 value 81895 (now 81876) (lr 0x8066179c)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.06 over 1139 ranges, 2083 MB), 175 pages written, 175 copied (0.7 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 0.002, bytes copied 0.000; 25 kept (122 MB), 10 spare buffers, 0 texture pages copied (0 MB)
[hos sead::MainThread] vk: readbacks of GPU results: 1235 of 3000 waited for their write-back, 0.28 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: 2623 kept their virtual core (nothing there to wait for), 3265 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: 1860000 (944506 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1408, 5480.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 584 dirty pages from their submits' captures, 66585 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): 1489 dispatches, 53639 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6785 runs, 1470.7 MB compared; 198 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 21398 in captures, 4 only in the collection, 64 only by the replay itself
[hos host] vk:   read live, by pool:
[hos rmbl::VibrationThread] hid: 12288 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: program picks: 1907551 kept (763923 by the last picks' textures, a uniform buffer bound since), 55976 new, 1036472 with other textures (of 3000000)
[hos host] vk: replay reads of guest memory as submitted: 1880000 (952315 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: shadow staging (600 takes): 0 shadow copies from staging, 0 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 58, 797 MB with memory of 988 MB (190 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 160 binds (7.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 26 taken from the spares, 62 made new; 30 kept as spares, 0 destroyed; 4 spares now, 100 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1430, 5565.9 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 375 dirty pages from their submits' captures, 65513 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): 1502 dispatches, 54227 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6903 runs, 1494.2 MB compared; 223 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 21354 in captures, 4 only in the collection, 64 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: 4 textures retired (1630 left, 4280 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: a frame: 15 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.47, present 0.18, draw 2.30, descriptors 1.03, texture lookups 0.06, uploads 0.01, pipelines 0.08, programs 0.47, commands 0.56, dispatch 0.56, memory sync 0.38, queue submit 0.33, slot wait 0.18
[hos host] vk: a frame: mirrors 88 (797 MB): 3.96 MB synced in 834.8 copies, 23.00 MB written back
[hos host] vk: 14040 presents, 89.0 fps; a frame: 563 draws (0 skipped), 87 dispatches, 137 passes, 139 barriers, 6 submits, 0.1 uploads (0.0 MB), 78 ub updates (54 overlays), GPU-bound wait 0.0 ms (recording slots only); 41164 pipelines (21507 ms), 0 programs (11 failed), 1630 textures (4280 MB)
[hos host] vk: host time in GPU resource waits: 2.82 ms a frame (fences 0.02, timelines 2.80, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 324.1 full barriers recorded, 179.7 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; 0x10: 0.0; 0x11: 40.1; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.3 ms a frame (the longest submission 3.5 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.01 ms
[hos host] control: teleport to destination 3 asked for
[hos BaseProcExecutor2] cheats: teleport waits until the current event ends
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 1139 ranges, 2083 MB), 178 pages written, 178 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (126 MB), 10 spare buffers, 14 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 1900000 (960746 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.05
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 285 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1408, 5480.2 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 375 dirty pages from their submits' captures, 64855 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): 1540 dispatches, 53491 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6816 runs, 1472.5 MB compared; 204 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 21237 in captures, 3 only in the collection, 65 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #85000: event 0x100c5e8030 mode 0 value 84999 (lr 0x806612a8)
[hos host] vk: replay reads of guest memory as submitted: 1920000 (968856 pages from the captures)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1105 of 3000 waited for their write-back, 0.40 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: 2690 kept their virtual core (nothing there to wait for), 2942 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos rmbl::VibrationThread] vcores: 207285 takes, 25982 waits (mean 28 us, longest 5.0 ms, 0 over HOS_VCORE_LOG_MS), 12780 kicks, 12665 yields, 0 starved grants, 0 escapes in 5 s
[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: shadow staging (600 takes): 0 shadow copies from staging, 14 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #140000: event 0x100c5e801c mode 0 value 85697 (now 85678) (lr 0x8066179c)
[hos host] vk: 1 textures retired (1629 left, 4280 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a frame: 17 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 84 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.52, present 0.18, draw 2.32, descriptors 1.05, texture lookups 0.05, uploads 0.00, pipelines 0.08, programs 0.46, commands 0.56, dispatch 0.58, memory sync 0.36, queue submit 0.33, slot wait 0.19
[hos host] vk: a frame: mirrors 88 (797 MB): 3.98 MB synced in 836.0 copies, 23.00 MB written back
[hos host] vk: 14160 presents, 89.2 fps; a frame: 568 draws (0 skipped), 87 dispatches, 138 passes, 139 barriers, 6 submits, 0.0 uploads (0.0 MB), 78 ub updates (54 overlays), GPU-bound wait 0.0 ms (recording slots only); 41164 pipelines (21507 ms), 0 programs (11 failed), 1629 textures (4280 MB)
[hos host] vk: host time in GPU resource waits: 2.94 ms a frame (fences 0.02, timelines 2.93, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 324.8 full barriers recorded, 179.6 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: 40.1; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.3 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 1138 ranges, 2079 MB), 179 pages written, 179 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.005; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (130 MB), 11 spare buffers, 14 texture pages copied (0 MB)
[hos host] vk: sparse mirrors: 58, 797 MB with memory of 988 MB (190 MB spared); blocks given memory later 165, given back 1650; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 160 binds (7.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 26 taken from the spares, 62 made new; 30 kept as spares, 0 destroyed; 4 spares now, 100 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1430, 5565.9 MB; 26 bindings followed, 33 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 376 dirty pages from their submits' captures, 65833 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): 1562 dispatches, 54362 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 6913 runs, 1494.9 MB compared; 213 pages read into the shadows; 296 MB of shadows; pages the shadows knew that the CPU wrote: 21497 in captures, 3 only in the collection, 65 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 67 live (1128 MB), 0 retired still imported (0 MB), 7 retired given back (92 MB)
[hos host] vk: replay reads of guest memory as submitted: 1940000 (977035 pages from the captures)