Beanstalk Longshot test farm
Menu

Report rp_2f62a6866fd6272c pass

#1763 perf(vk): the renderer's threads rewritten: one render thread, the presenter on every PC, parts that end at the game's own pass ends

linux+nvidia on jabbaxipil/Blaine,

Machine

Commit
8ba0d0281b89c9b32abe3dce2ad1db1e2e365378
Baseline
08994a9ee1b391bf35b29ddd41eede8b3f4defb4
App
nightly-191-38dff5fc, attempt 1
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
NVIDIA GeForce RTX 4070
tags
linuxnvidianvidia-proprietarydgpu
driver
615.71.9
ram_gb
64
vram_mb
12,282
gpu_vendor
nvidia
os_version
Ubuntu 26.04.1 LTS (kernel 7.0.0)

Builds

main (baseline)

237.7 s warm

from 08994a9ee1b3

lift
97.6 s
read
4.6 s
finish
14.9 s
compile
100.7 s
shaders
11.6 s

PR

23.9 s warm

Program cache: warm

Scenarios

three-areas

ok
Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count35.530−15.5%
run_frametime_max_ms1,582.82,023.45+27.8%
field-standing.fps_mean114.14109.94−3.7%
forest-standing.fps_mean108.46110.52+1.9%
market-standing.fps_mean81.2579.89−1.7%
field-after-turn.fps_mean128.56131.85+2.6%
field-standing.draws_mean1,189.21,182.55−0.6%
field-standing.hitch_count1.50−100%
forest-after-turn.fps_mean114.05116.94+2.5%
forest-standing.draws_mean702.25682.75−2.8%
market-after-turn.fps_mean107.7103.97−3.5%
market-standing.draws_mean2,480.852,463.45−0.7%
field-after-turn.draws_mean887.6835.25−5.9%
forest-standing.hitch_count0.50−100%
market-standing.hitch_count10−100%
field-after-turn.hitch_count0.50−100%
field-standing.stutter_count2.50.5−80%
forest-after-turn.draws_mean904.45653.3−27.8%
market-after-turn.draws_mean633.11,434.1+126.5%
forest-after-turn.hitch_count10.5−50%
forest-standing.stutter_count51.5−70%
market-after-turn.hitch_count21−50%
market-standing.stutter_count53−40%
field-after-turn.stutter_count20−100%
field-standing.frametime_max_ms41.6623.66−43.2%
field-standing.frametime_p50_ms8.548.95+4.8%
field-standing.frametime_p99_ms11.9912.27+2.3%
forest-after-turn.stutter_count1.50.5−66.7%
market-after-turn.stutter_count42.5−37.5%
forest-standing.frametime_max_ms31.9235.92+12.5%
forest-standing.frametime_p50_ms8.978.76−2.4%
forest-standing.frametime_p99_ms13.4712.45−7.6%
market-standing.frametime_max_ms52.1933.71−35.4%
market-standing.frametime_p50_ms11.7512.12+3.1%
market-standing.frametime_p99_ms19.4518.61−4.3%
field-after-turn.frametime_max_ms57.3912.65−78%
field-after-turn.frametime_p50_ms7.617.45−2.1%
field-after-turn.frametime_p99_ms10.219.67−5.3%
forest-after-turn.frametime_max_ms52.9145.29−14.4%
forest-after-turn.frametime_p50_ms8.598.37−2.5%
forest-after-turn.frametime_p99_ms11.4910.87−5.4%
market-after-turn.frametime_max_ms68.0342.58−37.4%
market-after-turn.frametime_p50_ms8.889.57+7.8%
market-after-turn.frametime_p99_ms13.8214.33+3.7%
field-standing.frametime_1pct_low_ms16.9713.56−20.1%
forest-standing.frametime_1pct_low_ms15.8214.41−8.9%
market-standing.frametime_1pct_low_ms25.0321.36−14.7%
field-after-turn.frametime_1pct_low_ms13.710.44−23.8%
forest-after-turn.frametime_1pct_low_ms15.5513.42−13.7%
market-after-turn.frametime_1pct_low_ms22.0518.51−16.1%
screenshot_diff—0.12—

Pictures against main: forest diff 0.1388 (main against itself 0.6974), field diff 0.0174 (main against itself 0.0315), market diff 0.109 (main against itself 0.1781)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0000
run_hitch_count48312923
run_frametime_max_ms2,904.353,813.3233.61261.25
field-standing.fps_mean112.56107.61112.28115.71
forest-standing.fps_mean100.58109.14111.9116.34
market-standing.fps_mean75.6775.883.9786.82
field-after-turn.fps_mean132.45136.24127.47124.68
field-standing.draws_mean1,189.41,178.91,186.21,189
field-standing.hitch_count3000
forest-after-turn.fps_mean104.14112.79121.09123.95
forest-standing.draws_mean646.9630735.5757.6
market-after-turn.fps_mean103.3986.26121.69112.02
market-standing.draws_mean2,5202,462.92,4642,441.7
field-after-turn.draws_mean741.5751.59191,033.7
forest-standing.hitch_count1000
market-standing.hitch_count2000
field-after-turn.hitch_count1000
field-standing.stutter_count5010
forest-after-turn.draws_mean1,188.9713.6593620
market-after-turn.draws_mean751.62,385.1483.1514.6
forest-after-turn.hitch_count1011
forest-standing.stutter_count10210
market-after-turn.hitch_count1023
market-standing.stutter_count6604
field-after-turn.stutter_count3001
field-standing.frametime_max_ms69.8616.1531.1713.46
field-standing.frametime_p50_ms8.539.018.888.55
field-standing.frametime_p99_ms13.3513.6910.8610.64
forest-after-turn.stutter_count1012
market-after-turn.stutter_count2236
forest-standing.frametime_max_ms51.4926.6645.1812.35
forest-standing.frametime_p50_ms9.418.568.968.54
forest-standing.frametime_p99_ms16.2614.410.510.68
market-standing.frametime_max_ms79.0846.3921.0325.29
market-standing.frametime_p50_ms12.3812.611.6411.12
market-standing.frametime_p99_ms21.6322.2614.9617.26
field-after-turn.frametime_max_ms71.6611.8813.4243.12
field-after-turn.frametime_p50_ms7.327.227.677.89
field-after-turn.frametime_p99_ms10.479.429.929.95
forest-after-turn.frametime_max_ms53.1113.0777.552.7
forest-after-turn.frametime_p50_ms9.348.678.077.83
forest-after-turn.frametime_p99_ms12.0811.0410.710.91
market-after-turn.frametime_max_ms61.6832.752.4674.37
market-after-turn.frametime_p50_ms9.1511.128.028.61
market-after-turn.frametime_p99_ms14.4316.3812.2813.21
field-standing.frametime_1pct_low_ms22.5514.7712.3411.39
forest-standing.frametime_1pct_low_ms20.3516.0712.7411.29
market-standing.frametime_1pct_low_ms29.5225.9816.7420.54
field-after-turn.frametime_1pct_low_ms14.7910.1710.7112.6
forest-after-turn.frametime_1pct_low_ms15.3411.7415.1115.77
market-after-turn.frametime_1pct_low_ms19.1519.5317.4824.96
screenshot_diff—0.110.14—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
three-areascrashFalse00—pass
three-areasforest-standing.fps_mean.min_delta_pct5108.46110.52+1.9%pass
three-areasforest-after-turn.fps_mean.min_delta_pct5114.05116.94+2.5%pass
three-areasfield-standing.fps_mean.min_delta_pct5114.14109.94−3.7%pass
three-areasfield-after-turn.fps_mean.min_delta_pct5128.56131.85+2.6%pass
three-areasmarket-standing.fps_mean.min_delta_pct581.2579.89−1.7%pass
three-areasmarket-after-turn.fps_mean.min_delta_pct5107.7103.97−3.5%pass
three-areasscreenshot.max_diff0.050.70.14—passover the limit, but main differs from itself by 0.6974 here: no more than 1.5x that is the scene, not the PR
three-areasforest-standing.stutter_count.max_delta_pct5051.5−70%pass
three-areasforest-after-turn.stutter_count.max_delta_pct501.50.5−66.7%pass
three-areasfield-standing.stutter_count.max_delta_pct502.50.5−80%pass
three-areasfield-after-turn.stutter_count.max_delta_pct5020−100%pass
three-areasmarket-standing.stutter_count.max_delta_pct5053−40%pass
three-areasmarket-after-turn.stutter_count.max_delta_pct5042.5−37.5%pass
three-areasforest-standing.frametime_p99_ms.max_delta_pct1513.4712.45−7.6%pass
three-areasforest-after-turn.frametime_p99_ms.max_delta_pct1511.4910.87−5.4%pass
three-areasfield-standing.frametime_p99_ms.max_delta_pct1511.9912.27+2.3%pass
three-areasfield-after-turn.frametime_p99_ms.max_delta_pct1510.219.67−5.3%pass
three-areasmarket-standing.frametime_p99_ms.max_delta_pct1519.4518.61−4.3%pass
three-areasmarket-after-turn.frametime_p99_ms.max_delta_pct1513.8214.33+3.7%pass

Log (PR side, end)

[hos host] vk: frame ahead, what came with the signal: 51 signals with a capture, each of 54.5 pages in 5.9 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: 0.58+0.14, 0.24+0.04, 0.03+0.03, 0.01+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: malloc: 13585 MB in arenas (11927 MB in use, 1658 MB free, 0 MB of it at the tops), 8 MB mapped
[hos host] vk: malloc_trim: 1658 MB free in the arenas now, the process's private memory 12628 -> 12607 MB (14 ms)
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 680000 so far (x1 0x11791f0000 x2 0x2 x3 0x11791f0000 x4 0x654040)
[hos host] vk: 2 textures retired (2540 left, 4690 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: 3 textures retired (2539 left, 4685 MB): budget 0, drawn over 3, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 914 ranges, 3120 MB), 196 pages written, 196 copied (0.8 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 0.003, bytes copied 0.000; 25 kept (86 MB), 9 spare buffers, 3747 texture pages copied (14 MB)
[hos host] vk: 2 textures retired (2537 left, 4670 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 8080000 (4294493 pages from the captures)
[hos host] vk: 3 textures retired (2534 left, 4648 MB): budget 0, drawn over 3, dead targets 0
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 522 of 3000 waited for their write-back, 0.02 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8682 kept their virtual core (nothing there to wait for), 2838 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: 1 textures retired (2533 left, 4638 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 265 KB; 0 made on demand (0 MB kept now); c1 stages: at most 90 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 22932; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 169 dirty pages from their submits' captures, 56487 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): 1191 dispatches, 45700 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5599 runs, 943.0 MB compared; 210 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18753 in captures, 2 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos host] vk: 2 textures retired (2535 left, 4653 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: readback pages refreshed from guest memory: 4870053 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #420000: event 0x100d6c802c mode 0 value 298606 (now 298587) (lr 0x8028c554)
[hos host] vk: replay reads of guest memory as submitted: 8100000 (4307169 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: 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, 3664 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 5 textures retired (2533 left, 4641 MB): budget 0, drawn over 5, dead targets 0
[hos ModuleSystemWorker1] vcores: 186580 takes, 45846 waits (mean 88 us, longest 17.6 ms, 0 over HOS_VCORE_LOG_MS), 21758 kicks, 21317 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 235 dirty pages from their submits' captures, 56641 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): 1189 dispatches, 45811 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5588 runs, 941.9 MB compared; 203 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18660 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.68, present 0.17, draw 2.34, descriptors 0.72, texture lookups 0.08, uploads 0.00, pipelines 0.08, programs 0.29, commands 1.06, dispatch 0.68, memory sync 0.28, queue submit 0.14, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 847.0 copies, 17.44 MB written back
[hos host] vk: 25320 presents, 117.7 fps; a frame: 482 draws (0 skipped), 77 dispatches, 127 passes, 142 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2535 textures (4661 MB)
[hos host] vk: host time in GPU resource waits: 0.08 ms a frame (fences 0.01, timelines 0.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.7 full barriers recorded, 185.2 left out (nothing recorded since the one before), 13.4 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.7 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.7 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] vk: capture: a submit 0.11 ms (lock 0.00, scan 0.04 over 894 ranges, 3006 MB), 198 pages written, 198 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, 3235 texture pages copied (12 MB)
[hos host] vk: replay reads of guest memory as submitted: 8120000 (4319832 pages from the captures)
[hos host] vk: 3 textures retired (2534 left, 4654 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: slow present: 43.2 ms:
[hos host] vk: 1 textures retired (2533 left, 4644 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #300000: event 0x100d6c8044 mode 0 value 299999 (lr 0x802742f0)
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 23580; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 268 dirty pages from their submits' captures, 56420 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): 1188 dispatches, 45717 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5581 runs, 941.8 MB compared; 209 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18360 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos host] vk: 2 textures retired (2538 left, 4678 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 8140000 (4332497 pages from the captures)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 553 of 3000 waited for their write-back, 0.01 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8895 kept their virtual core (nothing there to wait for), 3137 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.04
[hos host] vk: late pages found at the replay (600 takes): 29 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found)
[hos host] vk: 2 textures retired (2538 left, 4678 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2029 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; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 132 dirty pages from their submits' captures, 57626 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): 1210 dispatches, 46556 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5689 runs, 959.3 MB compared; 214 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18896 in captures, 2 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 894 ranges, 3004 MB), 195 pages written, 195 copied (0.8 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 0.003, bytes copied 0.000; 25 kept (76 MB), 10 spare buffers, 3235 texture pages copied (12 MB)
[hos host] vk: replay reads of guest memory as submitted: 8160000 (4345162 pages from the captures)
[hos rmbl::VibrationThread] hid: 32768 vibration values, strongest 0.00 since the last count
[hos host] vk: 1 textures retired (2544 left, 4725 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.57, present 0.49, draw 2.31, descriptors 0.72, texture lookups 0.09, uploads 0.00, pipelines 0.08, programs 0.27, commands 1.06, dispatch 0.66, memory sync 0.25, queue submit 0.13, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 846.6 copies, 17.44 MB written back
[hos host] vk: 25440 presents, 118.4 fps; a frame: 481 draws (0 skipped), 77 dispatches, 127 passes, 142 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2544 textures (4725 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.01, timelines 0.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.6 full barriers recorded, 185.1 left out (nothing recorded since the one before), 13.3 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 34.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.7 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (1.1 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: 2 textures retired (2543 left, 4712 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: program picks: 12445189 kept (4521959 by the last picks' textures, a uniform buffer bound since), 2606 new, 5152204 with other textures (of 17600000)
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 24234; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 95 dirty pages from their submits' captures, 56568 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): 1188 dispatches, 45672 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5596 runs, 941.9 MB compared; 219 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18534 in captures, 4 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 14 sync waits (14 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 8180000 (4357839 pages from the captures)
[hos host] vk: 1 textures retired (2544 left, 4722 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #425000: event 0x100d6c802c mode 0 value 302406 (now 302387) (lr 0x8028c554)
[hos host] vk: 2 textures retired (2542 left, 4705 MB): budget 0, drawn over 2, dead targets 0
[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 host] vk: 3 textures retired (2541 left, 4700 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 265 KB; 0 made on demand (0 MB kept now); c1 stages: at most 90 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; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 238 dirty pages from their submits' captures, 57498 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): 1205 dispatches, 46516 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5595 runs, 941.9 MB compared; 217 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18921 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 885 ranges, 2972 MB), 193 pages written, 193 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.003; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (88 MB), 11 spare buffers, 3229 texture pages copied (12 MB)
[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: replay reads of guest memory as submitted: 8200000 (4370542 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 4943768 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 3 textures retired (2538 left, 4679 MB): budget 0, drawn over 3, dead targets 0
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 571 of 3000 waited for their write-back, 0.02 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 8766 kept their virtual core (nothing there to wait for), 3010 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: render targets drawn over from another start, let go: 6519 so far (26449 MB), 5838 of them (23524 MB) between the passes
[hos host] vk: 5 textures retired (2534 left, 4649 MB): budget 0, drawn over 5, dead targets 0
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.51, present 0.16, draw 2.28, descriptors 0.72, texture lookups 0.07, uploads 0.00, pipelines 0.07, programs 0.27, commands 1.04, dispatch 0.65, memory sync 0.29, queue submit 0.14, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 846.2 copies, 17.44 MB written back
[hos host] vk: 25560 presents, 124.0 fps; a frame: 481 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2535 textures (4659 MB)
[hos host] vk: host time in GPU resource waits: 0.07 ms a frame (fences 0.01, timelines 0.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.5 full barriers recorded, 184.8 left out (nothing recorded since the one before), 13.4 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.8; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.7 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.5 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 24888; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 169 dirty pages from their submits' captures, 56671 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): 1193 dispatches, 45763 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5673 runs, 958.2 MB compared; 210 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18680 in captures, 1 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 8220000 (4383199 pages from the captures)
[hos host] vk: 6 textures retired (2529 left, 4612 MB): budget 0, drawn over 6, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: 3 textures retired (2528 left, 4605 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: 3 textures retired (2525 left, 4580 MB): budget 0, drawn over 3, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #305000: event 0x100d6c8010 mode 0 value 305002 (lr 0x80660bcc)
[hos sead::MainThread] vk: capture: a submit 0.10 ms (lock 0.01, scan 0.04 over 854 ranges, 2854 MB), 201 pages written, 201 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, 2860 texture pages copied (11 MB)
[hos host] vk: replay reads of guest memory as submitted: 8240000 (4395885 pages from the captures)
[hos host] vk: 1 textures retired (2524 left, 4573 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 166 dirty pages from their submits' captures, 56706 from earlier ones', 85 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): 1189 dispatches, 45768 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5593 runs, 942.8 MB compared; 215 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18550 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 85;
[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: 1 textures retired (2524 left, 4573 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5339 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 1 textures retired (2524 left, 4576 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker2] nvn: 2150000 recordings made, 68733 live copies (19.9 MB), 3846 texture copies; 4 command buffers' segments (4.4 MB)
[hos host] vk: replay reads of guest memory as submitted: 8260000 (4408575 pages from the captures)
[hos Presentation Thread] vi: 25677 frames presented (120.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 602, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 1
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.46, present 0.15, draw 2.25, descriptors 0.70, texture lookups 0.07, uploads 0.00, pipelines 0.07, programs 0.26, commands 1.03, dispatch 0.65, memory sync 0.27, queue submit 0.15, slot wait 0.01
[hos host] vk: a frame: mirrors 252 (917 MB): 4.11 MB synced in 847.1 copies, 17.44 MB written back
[hos host] vk: 25680 presents, 125.0 fps; a frame: 482 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2527 textures (4598 MB)
[hos host] vk: host time in GPU resource waits: 0.07 ms a frame (fences 0.01, timelines 0.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.5 full barriers recorded, 184.8 left out (nothing recorded since the one before), 13.4 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.8; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.7 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.4 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #430000: event 0x100d6c802c mode 0 value 306206 (now 306187) (lr 0x8028c554)
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 25536; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 191 dirty pages from their submits' captures, 56509 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): 1188 dispatches, 45690 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5593 runs, 941.9 MB compared; 209 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18593 in captures, 4 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 598 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 1 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: 8562 kept their virtual core (nothing there to wait for), 2958 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: 1 textures retired (2528 left, 4602 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03
[hos host] vk: 1 textures retired (2535 left, 4653 MB): budget 0, drawn over 1, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 855 ranges, 2856 MB), 200 pages written, 200 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 (76 MB), 11 spare buffers, 3416 texture pages copied (13 MB)
[hos host] vk: replay reads of guest memory as submitted: 8280000 (4421230 pages from the captures)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 700000 so far (x1 0x117a4f2020 x2 0 x3 0x117a4f2000 x4 0xf33080)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 347 dirty pages from their submits' captures, 56335 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): 1188 dispatches, 45683 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5596 runs, 941.9 MB compared; 219 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18506 in captures, 1 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[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: 1 textures retired (2537 left, 4665 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6144 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 8300000 (4433900 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 265 KB; 0 made on demand (0 MB kept now); c1 stages: at most 90 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 26184; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 175 dirty pages from their submits' captures, 56616 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): 1188 dispatches, 45768 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5594 runs, 941.9 MB compared; 224 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18638 in captures, 1 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[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 21656 MB (peak 21884), private 12617 MB, staging 48 MB in 3 arenas, 46 made so far (16 ms)
[hos host] vk: memory heaps: heap 0 (device): 226 blocks 7334 MB, 17496 allocations 6230 MB; used 8106 of 10900 MB; heap 1 (system): 12 blocks 800 MB, 39 allocations 696 MB; used 3191 of 48166 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 5 images 16 MB; 1 free ranges, the largest 15 MB
[hos host] vk: image blocks (render targets): 32 blocks 1024 MB, 167 images 527 MB; 89 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 103 blocks 3296 MB, 2368 images 2990 MB; 1250 free ranges, the largest 24 MB
[hos host] vk: render target images: 3573 reused from the pool, 4752 made new, 4580 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 8106 MB used of 10900 MB allowed (1104 MB of it free in the blocks); textures 4696 MB (budget 7164 MB), 2545 textures
[hos host] vk: budget: VRAM 7334 of 10900 MB (8106 MB by the driver, 772 MB unaccounted): textures 4696, blocks free 1104, mirrors 917, shadows 380, other buffers 156, staging 48, other images 31; RAM 3101 MB (the process's private memory 12617 MB): imports 2372, capture spares 604, captures 86, capture table 33, other buffers 6, others 0
[hos host] vk: textures: decoded ASTC 2448 MB, rendered 1181 MB (41 drawn in one frame, kept: 32527 KB), other 698 MB; used in the last 8 presents 1954 MB
[hos host] vk: decoded ASTC used again: 96 textures (128 MB) copied from ones the game finalized, not decoded; 96 of those retired, 93 listed; 1107 MB of blocks hashed in 111 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 7192 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 7192 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1531 presents ago
[hos host] vk:   54 MB: 0x10002d97a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7192 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 72 (15549 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 140x42x1 NVN 0x25: 1 (22 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 36 (6334 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 29 waited for it, 0.73 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 47.8 ms; VRAM 7.9 of 10.6 GB
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.66, present 0.13, draw 2.30, descriptors 0.72, texture lookups 0.09, uploads 0.01, pipelines 0.08, programs 0.27, commands 1.04, dispatch 0.65, memory sync 0.26, queue submit 0.14, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 846.4 copies, 17.44 MB written back
[hos host] vk: 25800 presents, 125.1 fps; a frame: 483 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2545 textures (4696 MB)
[hos host] vk: host time in GPU resource waits: 0.10 ms a frame (fences 0.01, timelines 0.09, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.9 full barriers recorded, 184.9 left out (nothing recorded since the one before), 13.3 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.7; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.2 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (1.0 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread (600 presents, 8.20 ms a frame): its jobs 4.99 ms a frame (submits 4.46, presents 0.22, others 0.30), idle 3.21; the game waited for room at 1 presents, 39.03 ms each (0.07 a frame; 2.06 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); 37 captures at a CPU signal; the submits' waits read in 0.022 ms a frame; readbacks: 2988 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 4.53 ms after its hand-over (47.07 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 3.52 + 0.20 (the window's copy is in the idle), after it 0.91 + 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): 5.00 parts a frame recorded in the signal's job, 69.2% of them took nothing that came with the signal; of the others, 1.54 a frame took pages of the signal's capture into a mirror (22.5 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 37 frames, its first three in 5
[hos host] vk: frame ahead, what came with the signal: 37 signals with a capture, each of 58.5 pages in 6.0 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: 0.57+0.14, 0.22+0.04, 0.02+0.03, 0.01+0.02, 0.08+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: readback pages refreshed from guest memory: 5017655 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 3 textures retired (2542 left, 4674 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: 3 textures retired (2540 left, 4659 MB): budget 0, drawn over 3, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 855 ranges, 2860 MB), 199 pages written, 199 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 (88 MB), 8 spare buffers, 4358 texture pages copied (17 MB)
[hos host] vk: replay reads of guest memory as submitted: 8320000 (4446593 pages from the captures)
[hos host] vk: 2 textures retired (2538 left, 4642 MB): budget 0, drawn over 2, dead targets 0
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 636 of 3000 waited for their write-back, 0.01 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8740 kept their virtual core (nothing there to wait for), 3036 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: 1 textures retired (2538 left, 4642 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: program picks: 12551272 kept (4536435 by the last picks' textures, a uniform buffer bound since), 2606 new, 5246121 with other textures (of 17800000)
[hos host] vk: write-backs left out (600 submits): 1155, 5665.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 287 dirty pages from their submits' captures, 57485 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): 1205 dispatches, 46544 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5611 runs, 941.9 MB compared; 230 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18784 in captures, 0 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 1 textures retired (2539 left, 4650 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 1 textures retired (2538 left, 4642 MB): budget 0, drawn over 1, dead targets 0
[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: 8340000 (4459278 pages from the captures)
[hos host] vk: 1 textures retired (2538 left, 4640 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4533 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #310000: event 0x100d6c8014 mode 0 value 310000 (lr 0x802915c8)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #435000: event 0x100d6c802c mode 0 value 310006 (now 309987) (lr 0x8028c554)
[hos host] vk: 1 textures retired (2541 left, 4662 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.04
[hos host] vk: 1 textures retired (2540 left, 4654 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 26838; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 167 dirty pages from their submits' captures, 56609 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): 1194 dispatches, 45741 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5671 runs, 959.1 MB compared; 225 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18487 in captures, 1 only in the collection, 55 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos BaseProcExecutor1] vcores: 189513 takes, 47070 waits (mean 86 us, longest 20.5 ms, 0 over HOS_VCORE_LOG_MS), 22062 kicks, 21526 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 8360000 (4471950 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.10 ms (lock 0.00, scan 0.04 over 853 ranges, 2858 MB), 197 pages written, 197 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 (82 MB), 11 spare buffers, 3838 texture pages copied (14 MB)
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.75, present 0.14, draw 2.34, descriptors 0.76, texture lookups 0.09, uploads 0.00, pipelines 0.08, programs 0.27, commands 1.06, dispatch 0.65, memory sync 0.27, queue submit 0.14, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.11 MB synced in 846.8 copies, 17.44 MB written back
[hos host] vk: 25920 presents, 122.4 fps; a frame: 483 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2545 textures (4679 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.01, timelines 0.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.7 full barriers recorded, 185.0 left out (nothing recorded since the one before), 13.4 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.9; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.3 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.7 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: 2 textures retired (2543 left, 4665 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: queues ordered by their events: 156000 submissions stopped at a wait, 155985 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 50.06 ms at most); waits met 436167, not met 0; captures at a CPU event's wait 14875, 0 of them at a wait met on arrival
[hos host] vk: 1 textures retired (2542 left, 4655 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 167 dirty pages from their submits' captures, 56497 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): 1188 dispatches, 45656 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5599 runs, 941.9 MB compared; 220 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18598 in captures, 3 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 3 textures retired (2541 left, 4650 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 8380000 (4484616 pages from the captures)
[hos host] vk: slow present: 16.1 ms:
[hos host] vk: 1 textures retired (2541 left, 4650 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 1 textures retired (2540 left, 4640 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 614 of 3000 waited for their write-back, 0.02 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 8574 kept their virtual core (nothing there to wait for), 2946 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: late pages found at the replay (600 takes): 29 pages in 1 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, 3330 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: 3 textures retired (2539 left, 4633 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 27486; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 318 dirty pages from their submits' captures, 56389 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): 1188 dispatches, 45689 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5595 runs, 941.9 MB compared; 206 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18495 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos host] vk: replay reads of guest memory as submitted: 8400000 (4497279 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 847 ranges, 2838 MB), 191 pages written, 191 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.003; 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 (82 MB), 11 spare buffers, 2783 texture pages copied (10 MB)
[hos host] vk: 1 textures retired (2540 left, 4640 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 1 textures retired (2540 left, 4643 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.65, present 0.27, draw 2.31, descriptors 0.73, texture lookups 0.07, uploads 0.00, pipelines 0.07, programs 0.28, commands 1.05, dispatch 0.65, memory sync 0.26, queue submit 0.13, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 845.8 copies, 17.44 MB written back
[hos host] vk: 26040 presents, 123.5 fps; a frame: 483 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2540 textures (4643 MB)
[hos host] vk: host time in GPU resource waits: 0.12 ms a frame (fences 0.01, timelines 0.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 300.5 full barriers recorded, 185.0 left out (nothing recorded since the one before), 13.4 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.9; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.3 ms a frame (the longest submission 1.2 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.5 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: texture slots registered again at another size: 1000000 (of 1243236 registrations; slot 15635 512x512 -> 1920x1080)
[hos host] vk: replay reads of guest memory as submitted: 8420000 (4509956 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 265 KB; 0 made on demand (0 MB kept now); c1 stages: at most 90 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 110 dirty pages from their submits' captures, 57009 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, 45931 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5593 runs, 941.9 MB compared; 231 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18416 in captures, 1 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 2 textures retired (2544 left, 4675 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: readback pages refreshed from guest memory: 5091811 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 1 textures retired (2544 left, 4672 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #440000: event 0x100d6c802c mode 0 value 313806 (now 313787) (lr 0x8028c554)
[hos sead::MainThread] nvn: GPU waits in 5 s: 23 sync waits (20 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: 3 textures retired (2542 left, 4657 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.04
[hos host] vk: 1 textures retired (2542 left, 4657 MB): budget 0, drawn over 1, dead targets 0
[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: 1 textures retired (2541 left, 4650 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 8440000 (4522631 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 248 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 847 ranges, 2838 MB), 188 pages written, 188 copied (0.7 MB)
[hos host] vk: a capture taken (ms): all 0.004; 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 (88 MB), 11 spare buffers, 2907 texture pages copied (11 MB)
[hos host] vk: sparse mirrors: 59, 917 MB with memory of 1408 MB (490 MB spared); blocks given memory later 4747, given back 11609; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 28134; 656 binds (242.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 137 taken from the spares, 115 made new; 193 kept as spares, 0 destroyed; 56 spares now, 1040 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 753 dirty pages from their submits' captures, 55505 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): 1175 dispatches, 45349 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5581 runs, 941.8 MB compared; 191 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18731 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 151 live (2372 MB), 0 retired still imported (0 MB), 28 retired given back (912 MB)
[hos host] vk: 2 textures retired (2539 left, 4633 MB): budget 0, drawn over 2, dead targets 0
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 742 of 3000 waited for their write-back, 0.01 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 ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8759 kept their virtual core (nothing there to wait for), 3017 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: 2 textures retired (2541 left, 4650 MB): budget 0, drawn over 2, dead targets 0
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #315000: event 0x100d6c8020 mode 0 value 315000 (lr 0x80664f14)
[hos ModuleSystemWorker1] nvn: 2200000 recordings made, 68663 live copies (19.4 MB), 3847 texture copies; 3 command buffers' segments (4.1 MB)
[hos host] vk: render targets drawn over from another start, let go: 6519 so far (26449 MB), 5838 of them (23524 MB) between the passes
[hos host] vk: 2 textures retired (2539 left, 4636 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 8460000 (4535310 pages from the captures)
[hos host] vk: a frame: 37 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.61, present 0.14, draw 2.30, descriptors 0.74, texture lookups 0.08, uploads 0.00, pipelines 0.07, programs 0.27, commands 1.04, dispatch 0.65, memory sync 0.26, queue submit 0.14, slot wait 0.02
[hos host] vk: a frame: mirrors 252 (917 MB): 4.10 MB synced in 845.1 copies, 17.44 MB written back
[hos host] vk: 26160 presents, 122.5 fps; a frame: 481 draws (0 skipped), 77 dispatches, 127 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 37386 pipelines (4493868 ms), 0 programs (0 failed), 2539 textures (4636 MB)
[hos host] vk: host time in GPU resource waits: 0.15 ms a frame (fences 0.01, timelines 0.14, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 301.2 full barriers recorded, 185.0 left out (nothing recorded since the one before), 13.3 pass starts ordered in their fragment stages only (draw passes after draw passes)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.9; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 3.8 ms a frame (the longest submission 2.9 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.8 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26164 (texture frame 26165), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26167 (texture frame 26168), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: write-backs left out (600 submits): 1134, 5562.4 MB; 34 bindings followed, 42 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 383 dirty pages from their submits' captures, 56242 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): 1188 dispatches, 45628 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5588 runs, 941.9 MB compared; 194 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 18683 in captures, 2 only in the collection, 54 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26170 (texture frame 26171), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26173 (texture frame 26174), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26176 (texture frame 26177), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: 3 textures retired (2538 left, 4628 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26179 (texture frame 26180), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26190 (texture frame 26191), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: upload over a drawn image: #12300 0x100010e0400 960x540x1 x1 NVN 0x3f at present 26193 (texture frame 26194), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] control: quit asked by a client
[hos host] vk: indexed descriptor arrays (close): 2610 in 2610 of 52174 program stages, 0 of them near a limit
[hos host] vk: indexed descriptor arrays (close), fragment stages: 2610 texture (17-64: 2610); the longest 64
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4255 pools in the table now)
[hos host] vk: pipeline cache: play file 16 saved (3363 KB): 13 pipelines, 13 from the driver's cache, 0 compiled; 5 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)