Beanstalk Longshot test farm
Menu

Report rp_28cd9c2a5d5a15aa fail

#1866 perf(vk): the recorder takes a whole part and submits it, so the render thread never waits at a part's end

windows+amd on Hidden tester,

This report disagrees with its peers.

three-areas field-after-turn.draws_mean: +34.8% against peers' -2.2%
three-areas field-after-turn.frametime_max_ms: -14.1% against peers' +20.3%
three-areas field-standing.frametime_max_ms: -35.1% against peers' +7.7%
three-areas kokiri-after-turn.draws_mean: -6.1% against peers' +88.5%
three-areas kokiri-after-turn.frametime_1pct_low_ms: -5.4% against peers' +21.9%
three-areas kokiri-after-turn.frametime_max_ms: -16.3% against peers' +17.6%
three-areas kokiri-after-turn.frametime_p50_ms: -4.7% against peers' +24.5%
three-areas kokiri-after-turn.frametime_p99_ms: -3.1% against peers' +23.4%
three-areas kokiri-standing.stutter_count: -100.0% against peers' +14.3%
three-areas run_frametime_max_ms: -97.9% against peers' +8.8%

Machine

Commit
f08644e37cd3ce2e6a4801195b6c39d7a2df9f7e
Baseline
89c3d21ea169ed46124e6c97acd90587f660b75a
App
nightly-195-f9b6d598, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 5 5600 6-Core Processor
gpu
AMD Radeon RX 9060 XT
tags
windowsamdamd-proprietarydgpu
driver
2.0.416
ram_gb
32
vram_mb
16,304
gpu_vendor
amd
os_version
Windows 10.0.26200

Builds

main (baseline)

2,042.7 s warm

from 89c3d21ea169

lift
154.3 s
read
2.6 s
finish
91.4 s
compile
1,740.9 s

PR

74.4 s warm

Program cache: warm

Scenarios

three-areas

ok
Metric (median)mainPRΔ
exit_code00±0%
run_hitch_count18.517.5−5.4%
log_forbidden_hits00±0%
log_expected_missing00±0%
run_frametime_max_ms14,587.25310.46−97.9%
field-standing.fps_mean91.4493.27+2%
kokiri-standing.fps_mean94.4897.13+2.8%
market-standing.fps_mean62.8465.39+4%
field-after-turn.fps_mean88.6887.94−0.8%
field-standing.draws_mean1,188.31,182.25−0.5%
field-standing.hitch_count00±0%
kokiri-after-turn.fps_mean96.06100.04+4.1%
kokiri-standing.draws_mean729.85742.1+1.7%
market-after-turn.fps_mean66.9772.78+8.7%
market-standing.draws_mean2,450.62,450.3−0%
field-after-turn.draws_mean938.21,264.6+34.8%
kokiri-standing.hitch_count00±0%
market-standing.hitch_count00±0%
field-after-turn.hitch_count00±0%
field-standing.stutter_count0.50−100%
kokiri-after-turn.draws_mean723678.7−6.1%
market-after-turn.draws_mean1,987.051,567.25−21.1%
kokiri-after-turn.hitch_count00±0%
kokiri-standing.stutter_count20−100%
market-after-turn.hitch_count00±0%
market-standing.stutter_count0.50.5±0%
field-after-turn.stutter_count00±0%
field-standing.frametime_max_ms21.3113.84−35.1%
field-standing.frametime_p50_ms10.9610.73−2.1%
field-standing.frametime_p99_ms13.8712.78−7.9%
kokiri-after-turn.stutter_count0.50−100%
market-after-turn.stutter_count00.5—
kokiri-standing.frametime_max_ms23.2418.98−18.4%
kokiri-standing.frametime_p50_ms10.410.14−2.6%
kokiri-standing.frametime_p99_ms13.7612.59−8.5%
market-standing.frametime_max_ms33.0329.97−9.3%
market-standing.frametime_p50_ms15.6215.09−3.4%
market-standing.frametime_p99_ms22.7720.31−10.8%
field-after-turn.frametime_max_ms17.8215.3−14.1%
field-after-turn.frametime_p50_ms11.1411.31+1.5%
field-after-turn.frametime_p99_ms14.1914.04−1%
kokiri-after-turn.frametime_max_ms18.4415.43−16.3%
kokiri-after-turn.frametime_p50_ms10.439.94−4.7%
kokiri-after-turn.frametime_p99_ms12.9612.55−3.1%
market-after-turn.frametime_max_ms24.5928.76+16.9%
market-after-turn.frametime_p50_ms14.7713.55−8.2%
market-after-turn.frametime_p99_ms20.318.44−9.2%
field-standing.frametime_1pct_low_ms15.1313.08−13.5%
kokiri-standing.frametime_1pct_low_ms15.9714.03−12.2%
market-standing.frametime_1pct_low_ms25.8623.02−11%
field-after-turn.frametime_1pct_low_ms14.914.57−2.2%
kokiri-after-turn.frametime_1pct_low_ms13.8613.12−5.4%
market-after-turn.frametime_1pct_low_ms21.7220.64−5%
screenshot_diff—0.12—

Pictures against main: kokiri diff 0.1287 (main against itself 0.127), field diff 0.0236 (main against itself 0.0183), market diff 0.083 (main against itself 0.1351)

Runs (4)
Metricmain 0pr 1pr 2main 3
hangnononono
crashednononono
exit_code0000
run_hitch_count16181721
log_forbidden_hits0000
log_expected_missing0000
run_frametime_max_ms400.68255.69365.2428,773.82
field-standing.fps_mean91.5493.7292.8291.33
kokiri-standing.fps_mean92.696.9397.3396.37
market-standing.fps_mean63.3265.8764.9162.37
field-after-turn.fps_mean86.2888.0287.8691.08
field-standing.draws_mean1,189.11,184.71,179.81,187.5
field-standing.hitch_count0000
kokiri-after-turn.fps_mean95.799.81100.2796.41
kokiri-standing.draws_mean732.8748.6735.6726.9
market-after-turn.fps_mean62.4370.5874.9771.51
market-standing.draws_mean2,504.82,4162,484.62,396.4
field-after-turn.draws_mean1,108.11,2621,267.2768.3
kokiri-standing.hitch_count0000
market-standing.hitch_count0000
field-after-turn.hitch_count0000
field-standing.stutter_count0001
kokiri-after-turn.draws_mean730.2675.4682715.8
market-after-turn.draws_mean2,343.31,776.61,357.91,630.8
kokiri-after-turn.hitch_count0000
kokiri-standing.stutter_count4000
market-after-turn.hitch_count0000
market-standing.stutter_count1010
field-after-turn.stutter_count0000
field-standing.frametime_max_ms19.9113.8913.7922.71
field-standing.frametime_p50_ms10.9510.6910.7710.98
field-standing.frametime_p99_ms13.1712.6512.914.57
kokiri-after-turn.stutter_count0001
market-after-turn.stutter_count0100
kokiri-standing.frametime_max_ms28.819.3618.5917.69
kokiri-standing.frametime_p50_ms10.5210.1610.1110.29
kokiri-standing.frametime_p99_ms15.0812.7412.4412.44
market-standing.frametime_max_ms36.1227.832.1329.95
market-standing.frametime_p50_ms15.614.9615.2215.65
market-standing.frametime_p99_ms21.5220.3220.2924.02
field-after-turn.frametime_max_ms16.0115.8314.7819.63
field-after-turn.frametime_p50_ms11.5211.311.3210.77
field-after-turn.frametime_p99_ms13.7714.4213.6714.62
kokiri-after-turn.frametime_max_ms13.8415.7715.0923.04
kokiri-after-turn.frametime_p50_ms10.459.979.9110.4
kokiri-after-turn.frametime_p99_ms12.9112.5612.5413
market-after-turn.frametime_max_ms25.8133.9623.5523.38
market-after-turn.frametime_p50_ms15.7913.9213.1813.75
market-after-turn.frametime_p99_ms22.1618.7918.0918.44
field-standing.frametime_1pct_low_ms14.0412.9313.2416.22
kokiri-standing.frametime_1pct_low_ms18.8414.0713.9813.09
market-standing.frametime_1pct_low_ms24.6122.1623.8827.12
field-after-turn.frametime_1pct_low_ms14.1115.114.0515.7
kokiri-after-turn.frametime_1pct_low_ms13.2713.0113.2214.46
market-after-turn.frametime_1pct_low_ms23.4321.1520.1320.01
screenshot_diff—0.130.1—

Rules

ScenarioCellRuleLimitmainPRΔ %Status
three-areascrashFalse00—pass
three-areaskokiri-standing.fps_mean.min_delta_pct1094.4897.13+2.8%pass
three-areaskokiri-after-turn.fps_mean.min_delta_pct1096.06100.04+4.1%pass
three-areasfield-standing.fps_mean.min_delta_pct1091.4493.27+2%pass
three-areasfield-after-turn.fps_mean.min_delta_pct1088.6887.94−0.8%pass
three-areasmarket-standing.fps_mean.min_delta_pct1062.8465.39+4%pass
three-areasmarket-after-turn.fps_mean.min_delta_pct1066.9772.78+8.7%pass
three-areasscreenshot.max_diff0.050.140.13—passover the limit, but main differs from itself by 0.1351 here: no more than 1.5x that is the scene, not the PR
three-areaskokiri-standing.stutter_count.max_delta_pct2020−100%pass
three-areaskokiri-after-turn.stutter_count.max_delta_pct200.50−100%pass
three-areasfield-standing.stutter_count.max_delta_pct200.50−100%pass
three-areasfield-after-turn.stutter_count.max_delta_pct2000±0%pass
three-areasmarket-standing.stutter_count.max_delta_pct200.50.5±0%pass
three-areasmarket-after-turn.stutter_count.max_delta_pct2000.5—failthe baseline is 0
three-areaskokiri-standing.frametime_p99_ms.max_delta_pct1513.7612.59−8.5%pass
three-areaskokiri-after-turn.frametime_p99_ms.max_delta_pct1512.9612.55−3.1%pass
three-areasfield-standing.frametime_p99_ms.max_delta_pct1513.8712.78−7.9%pass
three-areasfield-after-turn.frametime_p99_ms.max_delta_pct1514.1914.04−1%pass
three-areasmarket-standing.frametime_p99_ms.max_delta_pct1522.7720.31−10.8%pass
three-areasmarket-after-turn.frametime_p99_ms.max_delta_pct1520.318.44−9.2%pass
three-areaslog_forbidden_hits.max000—pass

Log (PR side, end)

[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 154 kept as spares, 0 destroyed; 39 spares now, 892 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 466 dirty pages from their submits' captures, 49883 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): 960 dispatches, 39401 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5427 runs, 783.3 MB compared; 52 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13205 in captures, 4 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.06
[hos host] vk: 3 textures retired (959 left, 2248 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7140000 (3877407 pages from the captures)
[hos host] vk: mirror of pool 0x7f79400000 (4 MB) given back: idle, 6003 submissions since its sync
[hos host] vk: 1 textures retired (958 left, 2237 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: late pages' fix (600 recordings with one): of 688 captures with late pages 688 fixed (67.4 pages, 68.0 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 22 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 576 blocks (36864 KB); of the reads on the CPU, 2 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 3, of an earlier recording 17, not recorded yet 0, of this part 0; pages fixed from stamps 45323, from snapshots 1038; the shadows: 502081 pages synced from captures, 491056 made known by it, 11025 left unknown because the replay or the collection wrote them since
[hos host] vk: 5 textures retired (956 left, 2244 MB): budget 5, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7160000 (3892262 pages from the captures)
[hos host] vk: a frame: 258 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.21, present 0.16, draw 4.68, descriptors 1.87, texture lookups 0.22, uploads 0.10, pipelines 0.24, programs 0.79, commands 1.42, dispatch 0.77, memory sync 0.47, queue submit 0.00, slot wait 0.17
[hos host] vk: a frame: mirrors 240 (928 MB): 4.51 MB synced in 901.6 copies, 17.81 MB written back
[hos host] vk: 21120 presents, 74.4 fps; a frame: 1383 draws (0 skipped), 102 dispatches, 136 passes, 144 barriers, 6 submits, 0.1 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 956 textures (2244 MB)
[hos host] vk: host time in GPU resource waits: 0.20 ms a frame (fences 0.03, timelines 0.17, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 344.0 full barriers recorded, 189.9 left out (nothing recorded since the one before), 16.1 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: 35.7; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.1 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (1.2 MB), ASTC or BC 0.1 (0.3 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.12 MB unswizzled on the CPU in 0.01 ms
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 887 ranges, 3686 MB), 228 pages written, 228 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.012, bytes copied 0.000; 24 kept (88 MB), 12 spare buffers, 9895 texture pages copied (38 MB)
[hos host] vk: mirror of pool 0x7f7fc00000 (8 MB) given back: idle, 6055 submissions since its sync
[hos host] vk: mirror of pool 0x7f82400000 (16 MB) given back: idle, 6030 submissions since its sync
[hos host] vk: mirror of pool 0x7fb7400000 (4 MB) given back: idle, 6030 submissions since its sync
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 757 dirty pages from their submits' captures, 50111 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): 968 dispatches, 39722 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5429 runs, 783.3 MB compared; 68 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13527 in captures, 1 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: mirror of pool 0x1043800000 (4 MB) given back: idle, 6057 submissions since its sync
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9469 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 7180000 (3907234 pages from the captures)
[hos host] vk: mirror of pool 0x7f79000000 (4 MB) given back: idle, 6062 submissions since its sync
[hos host] vk: mirror of pool 0x7f85800000 (4 MB) given back: idle, 6036 submissions since its sync
[hos host] vk: mirror of pool 0x7fbbc00000 (4 MB) given back: idle, 6034 submissions since its sync
[hos host] vk: mirror of pool 0x105dc00000 (4 MB) given back: idle, 6005 submissions since its sync
[hos host] vk: 163 mirrors given back (1443 MB in all); 905 MB of mirrors now, 44 MB of them idle and kept for what the GPU wrote there alone
[hos host] vk: mirror of pool 0x7f81c00000 (8 MB) given back: idle, 6055 submissions since its sync
[hos host] vk: mirror of pool 0x7fe1000000 (4 MB) given back: idle, 6043 submissions since its sync
[hos host] vk: mirror of pool 0x7facc00000 (8 MB) given back: idle, 6002 submissions since its sync
[hos host] vk: mirror of pool 0x7fffc00000 (4 MB) given back: idle, 6002 submissions since its sync
[hos host] vk: 1 textures retired (961 left, 2258 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7200000 (3921976 pages from the captures)
[hos host] vk: 1 textures retired (964 left, 2258 MB): budget 1, drawn over 0, dead targets 0
[hos ModuleSystemWorker3] nvn: 1800000 recordings made, 74814 live copies (21.6 MB), 3792 texture copies; 5 command buffers' segments (4.3 MB)
[hos host] vk: 3 textures retired (961 left, 2254 MB): budget 3, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7220000 (3936782 pages from the captures)
[hos host] vk: sparse mirrors: 73, 890 MB with memory of 1344 MB (453 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17706; 667 binds (71.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 167 kept as spares, 0 destroyed; 52 spares now, 968 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 503 dirty pages from their submits' captures, 50181 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): 971 dispatches, 39597 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5403 runs, 781.9 MB compared; 58 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13479 in captures, 0 only in the collection, 43 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: 6 textures retired (966 left, 2235 MB): budget 5, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7240000 (3951490 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #345000: event 0x100d6c8004 mode 0 value 244266 (now 244247) (lr 0x82c0326c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.06
[hos host] vk: program picks: 11056308 kept (4203512 by the last picks' textures, a uniform buffer bound since), 45490 new, 4298201 with other textures (of 15400000)
[hos host] vk: replay reads of guest memory as submitted: 7260000 (3966308 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.06 over 888 ranges, 3698 MB), 214 pages written, 214 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.006, bytes copied 0.000; 25 kept (96 MB), 11 spare buffers, 7728 texture pages copied (30 MB)
[hos host] vk: 2 textures retired (974 left, 2250 MB): budget 2, drawn over 0, 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: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 424 dirty pages from their submits' captures, 50287 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): 971 dispatches, 39660 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5371 runs, 784.0 MB compared; 65 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13420 in captures, 3 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 7280000 (3981274 pages from the captures)
[hos host] vk: commit limit near: 2301 MB of commit left (reserve 2560 MB); the textures' budget down to 1991 MB of their 2250 MB (RX_VK_COMMIT_RESERVE_MB)
[hos host] vk: 5 textures retired (969 left, 2235 MB): budget 5, drawn over 0, dead targets 0
[hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #245000: event 0x100d6c8030 mode 0 value 244999 (lr 0x806612a8)
[hos sead::MainThread] nvn: GPU waits in 5 s: 55 sync waits (30 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 560000 so far (x1 0x1179846000 x2 0 x3 0x1179846000 x4 0x654040)
[hos host] vk: 6 textures retired (963 left, 2233 MB): budget 6, drawn over 0, dead targets 0
[hos host] vk: a frame: 258 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.95, present 0.14, draw 4.64, descriptors 1.82, texture lookups 0.14, uploads 0.04, pipelines 0.24, programs 0.79, commands 1.43, dispatch 0.76, memory sync 0.43, queue submit 0.00, slot wait 0.16
[hos host] vk: a frame: mirrors 240 (890 MB): 4.50 MB synced in 900.4 copies, 17.80 MB written back
[hos host] vk: 21240 presents, 75.6 fps; a frame: 1381 draws (0 skipped), 101 dispatches, 136 passes, 144 barriers, 6 submits, 0.5 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 963 textures (2233 MB)
[hos host] vk: host time in GPU resource waits: 0.17 ms a frame (fences 0.03, 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: 343.7 full barriers recorded, 189.7 left out (nothing recorded since the one before), 16.2 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: 35.5; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.0 ms); 0.5 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.1 MB), ASTC or BC 0.5 (0.9 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1029 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: 9352 kept their virtual core (nothing there to wait for), 3192 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 3202 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 7300000 (3995978 pages from the captures)
[hos host] vk: 3 textures retired (960 left, 2232 MB): budget 3, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7320000 (4010869 pages from the captures)
[hos Presentation Thread] vi: 21265 frames presented (75.1 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 371, 15.5-17.8 3, 17.8-22 2, 22-30 0, 30-40 0, over 40 0
[hos host] vk: sparse mirrors: 73, 890 MB with memory of 1344 MB (453 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18234; 667 binds (71.6 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 167 kept as spares, 0 destroyed; 52 spares now, 968 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 543 dirty pages from their submits' captures, 50056 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): 966 dispatches, 39557 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5355 runs, 782.2 MB compared; 63 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13418 in captures, 3 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: replay reads of guest memory as submitted: 7340000 (4025581 pages from the captures)
[hos host] vk: 3 textures retired (962 left, 2258 MB): budget 3, drawn over 0, dead targets 0
[hos host] vk: readback pages refreshed from guest memory: 3917982 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 7360000 (4040398 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.06
[hos host] vk: 1 textures retired (962 left, 2258 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 266 KB; 0 made on demand (0 MB kept now); c1 stages: at most 116 a recording; 2 descriptor pools made when a recording's own ran out (2 slots' pools made whole); a recording's pool took at most 378 sets (ub 4216, sb 1968, cis 31660, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 903, 4429.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 736 dirty pages from their submits' captures, 48997 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): 955 dispatches, 38803 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5229 runs, 765.4 MB compared; 63 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13007 in captures, 2 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 7380000 (4055159 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 889 ranges, 3696 MB), 214 pages written, 214 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (90 MB), 11 spare buffers, 2413 texture pages copied (9 MB)
[hos host] vk: 10 textures retired (952 left, 2207 MB): budget 8, drawn over 2, dead targets 0
[hos host] vk: mirror of pool 0x7f85c00000 (4 MB) given back: idle, 6031 submissions since its sync
[hos host] vk: render targets drawn over from another start, let go: 7973 so far (31956 MB), 7340 of them (30112 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 7400000 (4069891 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: 1 textures retired (968 left, 2270 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: program picks: 11201744 kept (4238857 by the last picks' textures, a uniform buffer bound since), 45490 new, 4352765 with other textures (of 15600000)
[hos host] vk: replay reads of guest memory as submitted: 7420000 (4084728 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8950 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18756; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 610 dirty pages from their submits' captures, 50572 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): 984 dispatches, 39873 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5362 runs, 782.8 MB compared; 58 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 105 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13744 in captures, 4 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: 1 textures retired (968 left, 2270 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: a frame: 258 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.07, present 0.14, draw 4.86, descriptors 2.04, texture lookups 0.34, uploads 0.23, pipelines 0.24, programs 0.79, commands 1.43, dispatch 0.75, memory sync 0.45, queue submit 0.00, slot wait 0.16
[hos host] vk: a frame: mirrors 240 (890 MB): 4.51 MB synced in 900.4 copies, 17.78 MB written back
[hos host] vk: 21360 presents, 74.7 fps; a frame: 1382 draws (0 skipped), 101 dispatches, 136 passes, 144 barriers, 6 submits, 0.4 uploads (0.4 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 968 textures (2270 MB)
[hos host] vk: host time in GPU resource waits: 0.32 ms a frame (fences 0.03, timelines 0.29, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 342.8 full barriers recorded, 190.0 left out (nothing recorded since the one before), 16.2 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: 35.6; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.0 ms); 0.4 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.3 MB), ASTC or BC 0.4 (0.9 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.40 MB unswizzled on the CPU in 0.04 ms
[hos host] vk: replay reads of guest memory as submitted: 7440000 (4099460 pages from the captures)
[hos host] vk: 1 textures retired (967 left, 2270 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7460000 (4114373 pages from the captures)
[hos host] vk: 5 textures retired (963 left, 2247 MB): budget 5, drawn over 0, dead targets 0
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #350000: event 0x100d6c8004 mode 0 value 248066 (now 248047) (lr 0x82c0326c)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1016 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 ModuleSystemWorker3] vk: invalidates since the last readbacks line: 8793 kept their virtual core (nothing there to wait for), 2727 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 0.01, writes collected 0.06
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 955 dirty pages from their submits' captures, 49307 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): 955 dispatches, 39328 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5349 runs, 782.2 MB compared; 63 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13065 in captures, 4 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 2 textures retired (961 left, 2247 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7480000 (4129240 pages from the captures)
[hos host] vk: 1 textures retired (972 left, 2245 MB): budget 1, drawn over 0, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 890 ranges, 3716 MB), 229 pages written, 229 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.011, bytes copied 0.000; 25 kept (90 MB), 11 spare buffers, 7526 texture pages copied (29 MB)
[hos host] vk: replay reads of guest memory as submitted: 7500000 (4144075 pages from the captures)
[hos AudioFrameworkThread] vcores: 177717 takes, 32805 waits (mean 75 us, longest 16.3 ms, 0 over HOS_VCORE_LOG_MS), 16255 kicks, 16114 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 7520000 (4158878 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: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19284; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 616 dirty pages from their submits' captures, 50051 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): 968 dispatches, 39570 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5356 runs, 782.1 MB compared; 54 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13472 in captures, 4 only in the collection, 43 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: 1 textures retired (975 left, 2265 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7540000 (4173748 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6430 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 12 textures retired (963 left, 2258 MB): budget 12, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7560000 (4188499 pages from the captures)
[hos host] vk: program picks: 11347103 kept (4274241 by the last picks' textures, a uniform buffer bound since), 45491 new, 4407405 with other textures (of 15800000)
[hos host] vk: 2 textures retired (961 left, 2247 MB): budget 1, drawn over 1, dead targets 0
[hos host] vk: a frame: 258 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.09, present 0.14, draw 4.67, descriptors 1.85, texture lookups 0.16, uploads 0.07, pipelines 0.23, programs 0.78, commands 1.44, dispatch 0.77, memory sync 0.47, queue submit 0.00, slot wait 0.17
[hos host] vk: a frame: mirrors 240 (890 MB): 4.50 MB synced in 899.8 copies, 17.78 MB written back
[hos host] vk: 21480 presents, 75.1 fps; a frame: 1382 draws (0 skipped), 101 dispatches, 136 passes, 144 barriers, 6 submits, 0.2 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 961 textures (2247 MB)
[hos host] vk: host time in GPU resource waits: 0.26 ms a frame (fences 0.03, timelines 0.22, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 342.9 full barriers recorded, 189.9 left out (nothing recorded since the one before), 16.2 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: 35.6; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.1 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.1 MB), ASTC or BC 0.2 (0.2 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.07 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: write-backs left out (600 submits): 903, 4429.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 461 dirty pages from their submits' captures, 49621 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): 963 dispatches, 39033 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5277 runs, 765.0 MB compared; 62 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13490 in captures, 3 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 7580000 (4203326 pages from the captures)
[hos host] vk: 4 textures retired (957 left, 2232 MB): budget 4, drawn over 0, dead targets 0
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #250000: event 0x100d6c803c mode 0 value 249999 (lr 0x80661bfc)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.06
[hos host] vk: 1 textures retired (956 left, 2232 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7600000 (4218147 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 3991313 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 4 textures retired (957 left, 2246 MB): budget 4, drawn over 0, dead targets 0
[hos sead::MainThread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 891 ranges, 3708 MB), 214 pages written, 214 copied (0.8 MB)
[hos host] vk: a capture taken (ms): all 0.010; 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 (98 MB), 11 spare buffers, 7696 texture pages copied (30 MB)
[hos host] vk: 5 textures retired (952 left, 2231 MB): budget 5, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7620000 (4232899 pages from the captures)
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 266 KB; 0 made on demand (0 MB kept now); c1 stages: at most 116 a recording; 2 descriptor pools made when a recording's own ran out (2 slots' pools made whole); a recording's pool took at most 378 sets (ub 4216, sb 1968, cis 31660, si 0, utb 0, stb 0)
[hos host] vk: sparse mirrors: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19806; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 645 dirty pages from their submits' captures, 50080 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): 967 dispatches, 39621 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5419 runs, 783.0 MB compared; 57 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 106 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13477 in captures, 5 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos ModuleSystemWorker2] nvn: 1850000 recordings made, 74784 live copies (21.2 MB), 3792 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: 2 textures retired (963 left, 2235 MB): budget 1, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7640000 (4247748 pages from the captures)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1026 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 ModuleSystemWorker3] vk: invalidates since the last readbacks line: 8685 kept their virtual core (nothing there to wait for), 3091 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): 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: 7660000 (4262443 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6432 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 1 textures retired (962 left, 2235 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 233 dirty pages from their submits' captures, 50622 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): 972 dispatches, 39729 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5438 runs, 783.4 MB compared; 54 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 105 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13580 in captures, 1 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 7680000 (4277293 pages from the captures)
[hos host] vk: 3 textures retired (959 left, 2211 MB): budget 2, drawn over 1, dead targets 0
[hos host] vk: queues ordered by their events: 126000 submissions stopped at a wait, 125997 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 354698, not met 0; captures at a CPU event's wait 10139, 0 of them at a wait met on arrival
[hos host] vk: 6 textures retired (953 left, 2196 MB): budget 6, drawn over 0, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #355000: event 0x100d6c8004 mode 0 value 251866 (now 251847) (lr 0x82c0326c)
[hos host] vk: replay reads of guest memory as submitted: 7700000 (4292075 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.06
[hos host] vk: memory: working set 15495 MB (peak 15630), private 21525 MB, staging 64 MB in 4 arenas, 35 made so far (128 ms)
[hos host] vk: memory heaps: heap 0 (system): 14 blocks 880 MB, 39 allocations 798 MB; used 3248 of 15580 MB; heap 1 (device): 166 blocks 4835 MB, 15944 allocations 3675 MB; used 5836 of 15419 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 1 free ranges, the largest 0 MB
[hos host] vk: image blocks (render targets): 28 blocks 896 MB, 142 images 337 MB; 94 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 52 blocks 1664 MB, 806 images 1307 MB; 288 free ranges, the largest 32 MB
[hos host] vk: render target images: 4416 reused from the pool, 4914 made new, 4769 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 5836 MB used of 15419 MB allowed (1159 MB of it free in the blocks); textures 2196 MB (budget 1992 MB), 954 textures
[hos host] vk: budget: VRAM 4835 of 15419 MB (5836 MB by the driver, 1000 MB unaccounted): textures 2196, blocks free 1159, mirrors 890, shadows 304, other buffers 142, other images 78, staging 64; RAM 3192 MB (the process's private memory 21525 MB): imports 2360, capture spares 692, captures 96, capture table 34, other buffers 10, others 0
[hos host] vk: textures: decoded ASTC 989 MB, rendered 842 MB (51 drawn in one frame, kept: 37785 KB), other 210 MB; used in the last 8 presents 1957 MB
[hos host] vk: decoded ASTC used again: 423 textures (974 MB) copied from ones the game finalized, not decoded; 423 of those retired, 0 listed; 2006 MB of blocks hashed in 250 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 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:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   31 MB: 0x111cc23000 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk:   21 MB: 0x10006f14600 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   14 MB: 0x1005f37000 2560x1440x1 x1 levels 1 NVN 0x25 rendered, last used 3 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 74 (23649 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 host] vk: 1 textures retired (953 left, 2196 MB): budget 1, drawn over 0, dead targets 0
[hos Presentation Thread] vk: presents after the CPU's signal (600): 99 waited for it, 0.81 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 23.5 ms; VRAM 5.7 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: 47 program records loaded (49.8 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): 6232 queued, 6232 loaded (median 0.52 ms, 99th percentile 11.92 ms, worst 35.54 ms, 7712 ms and 1590.0 MB read in all); 9241 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 11156 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2037 pipelines made at create taken by draws; 2565 create calls with nothing kept for their stages, 0 before the index; units 8797 (6232 ready, 0 loading), 14428 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: program loads at create (play): 13302 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them)
[hos host] vk: module identifiers (play): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 257 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.07, present 0.15, draw 4.70, descriptors 1.87, texture lookups 0.19, uploads 0.09, pipelines 0.24, programs 0.79, commands 1.43, dispatch 0.79, memory sync 0.45, queue submit 0.00, slot wait 0.17
[hos host] vk: a frame: mirrors 240 (890 MB): 4.51 MB synced in 900.8 copies, 17.79 MB written back
[hos host] vk: 21600 presents, 74.9 fps; a frame: 1380 draws (0 skipped), 102 dispatches, 136 passes, 144 barriers, 6 submits, 0.2 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 953 textures (2196 MB)
[hos host] vk: host time in GPU resource waits: 0.22 ms a frame (fences 0.03, timelines 0.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 344.2 full barriers recorded, 189.8 left out (nothing recorded since the one before), 16.2 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: 35.6; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 3.0 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.2 (0.2 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.12 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: queues ordered by their events: 126148 submissions stopped at a wait, 126148 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 355223, not met 0; captures at a CPU event's wait 10143, 0 of them at a wait met on arrival
[hos host] vk: the render thread (600 presents, 13.35 ms a frame): its jobs 8.46 ms a frame (submits 6.88, presents 0.15, others 1.43), idle 4.88; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.40 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); 109 captures at a CPU signal; the submits' waits read in 0.044 ms a frame; readbacks: 734 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 7.51 ms after its hand-over (18.25 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 2.44 + 0.16 (the window's copy is in the idle), after it 3.17 + 0.54; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.05 ms of GPU time), after its last that reads it 1.00 (0.05 ms)
[hos host] vk: frame ahead (600 presents): 7.36 parts a frame recorded in the signal's job, 68.2% of them took nothing that came with the signal; of the others, 2.34 a frame took pages of the signal's capture into a mirror (52.6 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 19 of 109 frames, its first three in 19
[hos host] vk: frame ahead, what came with the signal: 109 signals with a capture, each of 103.7 pages in 10.7 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: 1.62+0.15, 0.31+0.09, 0.67+0.16, 0.33+0.05, 0.23+0.04, 0.01+0.02, 0.01+0.02, 0.00+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.06 over 890 ranges, 3700 MB), 213 pages written, 213 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 0.005, bytes copied 0.000; 25 kept (90 MB), 11 spare buffers, 6176 texture pages copied (24 MB)
[hos host] vk: 1 textures retired (953 left, 2196 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7720000 (4306792 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 55 sync waits (50 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: program picks: 11492831 kept (4309658 by the last picks' textures, a uniform buffer bound since), 45491 new, 4461677 with other textures (of 16000000)
[hos host] vk: sparse mirrors: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20334; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 327 dirty pages from their submits' captures, 50267 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): 970 dispatches, 39487 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5345 runs, 781.4 MB compared; 58 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 105 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13433 in captures, 2 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: 2 textures retired (951 left, 2196 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: 4 textures retired (949 left, 2217 MB): budget 4, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7740000 (4321567 pages from the captures)
[hos Presentation Thread] vi: 21641 frames presented (75.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 370, 15.5-17.8 3, 17.8-22 3, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 7760000 (4336300 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: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 621 dirty pages from their submits' captures, 49899 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): 963 dispatches, 39410 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5345 runs, 781.2 MB compared; 65 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 106 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13086 in captures, 3 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 7780000 (4351145 pages from the captures)
[hos host] vk: 1 textures retired (957 left, 2220 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4553 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 7800000 (4365844 pages from the captures)
[hos host] vk: 3 textures retired (956 left, 2220 MB): budget 3, drawn over 0, dead targets 0
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1014 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 ModuleSystemWorker2] vk: invalidates since the last readbacks line: 9132 kept their virtual core (nothing there to wait for), 2900 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 0.01, writes collected 0.06
[hos host] vk: 2 textures retired (954 left, 2220 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7820000 (4380702 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 891 ranges, 3676 MB), 227 pages written, 227 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.013; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 25 kept (148 MB), 10 spare buffers, 4694 texture pages copied (18 MB)
[hos host] vk: sparse mirrors: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20862; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 945, 4635.4 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 412 dirty pages from their submits' captures, 51267 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): 983 dispatches, 40386 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5353 runs, 783.0 MB compared; 70 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13755 in captures, 1 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: 2 textures retired (957 left, 2220 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7840000 (4395323 pages from the captures)
[hos host] vk: a frame: 259 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 111 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.99, present 0.14, draw 4.66, descriptors 1.84, texture lookups 0.14, uploads 0.03, pipelines 0.24, programs 0.79, commands 1.43, dispatch 0.77, memory sync 0.46, queue submit 0.00, slot wait 0.17
[hos host] vk: a frame: mirrors 240 (890 MB): 4.50 MB synced in 899.5 copies, 17.77 MB written back
[hos host] vk: 21720 presents, 74.7 fps; a frame: 1384 draws (0 skipped), 100 dispatches, 136 passes, 144 barriers, 6 submits, 0.4 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 53454 pipelines (28325 ms), 0 programs (10 failed), 957 textures (2220 MB)
[hos host] vk: host time in GPU resource waits: 0.18 ms a frame (fences 0.03, timelines 0.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 342.3 full barriers recorded, 189.9 left out (nothing recorded since the one before), 16.2 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: 35.6; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 7.0 ms a frame (the longest submission 2.8 ms); 0.4 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.3 MB), ASTC or BC 0.4 (0.7 MB), other 0.0 (0.0 MB)
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: readback pages refreshed from guest memory: 4064704 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 4 textures retired (954 left, 2211 MB): budget 4, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7860000 (4410147 pages from the captures)
[hos host] vk: 2 textures retired (965 left, 2248 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: the recording streams: 48 of 1 MB, the most one held 266 KB; 0 made on demand (0 MB kept now); c1 stages: at most 116 a recording; 2 descriptor pools made when a recording's own ran out (2 slots' pools made whole); a recording's pool took at most 378 sets (ub 4216, sb 1968, cis 31660, si 0, utb 0, stb 0)
[hos host] vk: write-backs left out (600 submits): 903, 4429.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 716 dirty pages from their submits' captures, 48914 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): 951 dispatches, 38754 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5357 runs, 782.2 MB compared; 60 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13112 in captures, 2 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 11638364 kept (4345042 by the last picks' textures, a uniform buffer bound since), 45491 new, 4516144 with other textures (of 16200000)
[hos host] vk: replay reads of guest memory as submitted: 7880000 (4425028 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #255000: event 0x100d6c8048 mode 0 value 254999 (lr 0x80666598)
[hos ModuleSystemWorker3] nvn: DrawMeshTasksIndirect: 580000 so far (x1 0x117cabc000 x2 0x2 x3 0x117cabc000 x4 0x230040)
[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: 8 textures retired (962 left, 2246 MB): budget 8, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 7900000 (4439823 pages from the captures)
[hos host] vk: 1 textures retired (962 left, 2246 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 12019 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 7920000 (4454637 pages from the captures)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #360000: event 0x100d6c8004 mode 0 value 255666 (now 255647) (lr 0x82c0326c)
[hos host] vk: sparse mirrors: 72, 890 MB with memory of 1340 MB (449 MB spared); blocks given memory later 4358, given back 10549; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 21390; 668 binds (71.7 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 115 taken from the spares, 125 made new; 168 kept as spares, 0 destroyed; 53 spares now, 972 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 924, 4532.3 MB; 29 bindings followed, 36 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 521 dirty pages from their submits' captures, 50207 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): 973 dispatches, 39626 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 5354 runs, 782.2 MB compared; 54 pages read into the shadows; 304 MB of shadows (65 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13409 in captures, 5 only in the collection, 44 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 162 live (2360 MB), 0 retired still imported (0 MB), 27 retired given back (780 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.06
[hos host] vk: 6 textures retired (959 left, 2223 MB): budget 6, drawn over 0, dead targets 0
[hos AudioFrameworkThread] vcores: 177697 takes, 32595 waits (mean 76 us, longest 14.4 ms, 0 over HOS_VCORE_LOG_MS), 16222 kicks, 16064 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.13 ms (lock 0.00, scan 0.06 over 889 ranges, 3682 MB), 221 pages written, 221 copied (0.9 MB)
[hos host] vk: a capture taken (ms): all 0.012; 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 (90 MB), 11 spare buffers, 6118 texture pages copied (23 MB)
[hos host] vk: replay reads of guest memory as submitted: 7940000 (4469369 pages from the captures)
[hos host] vk: 5 textures retired (956 left, 2209 MB): budget 4, drawn over 1, dead targets 0
[hos host] vk: recorder: 6281889 packets run in 10.0 s (busy 1.92 s, spun idle 0.13 s, slept 11396 times, 2644 of them under 200 us), 11 calls made directly (no room); 20769 batches over 748 frames (27.8 a frame, 302 packets a batch), 10230 parts ended and submitted by it; the render thread (the replay lock's holder) waited for it 97 times, 11.51 ms (0.1 times, 0.02 ms a frame); every thread 107 times, 12.00 ms in all, the longest 0.35 ms; vkDestroyImageView 74/10.17 ms (max 0.32), no ring room 11/0.76 ms (max 0.12), vmaFreeMemory 6/0.49 ms (max 0.25), vmaDestroyBuffer 2/0.36 ms (max 0.35), the queue's lock 7/0.12 ms (max 0.04), vkQueueBindSparse 6/0.10 ms (max 0.02)
[hos host] vk: recorder: of its busy 1.92 s, 0.50 s in parts' ends and submits (the longest 0.40 ms), 0.00 s of that blocked on the queue's lock (0 times, the longest 0.00 ms), so 0.50 s in the ends, submits and holds; 1.42 s running the other packets; 8398 packets a frame
[hos host] vk: replay reads of guest memory as submitted: 7960000 (4484187 pages from the captures)
[hos host] vk: commit limit near: 2373 MB of commit left (reserve 2560 MB); the textures' budget down to 2033 MB of their 2220 MB (RX_VK_COMMIT_RESERVE_MB)
[hos host] vk: 3 textures retired (955 left, 2217 MB): budget 3, drawn over 0, dead targets 0
[hos host] control: quit asked by a client
[hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 47 program records loaded (49.8 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 (close): 6232 queued, 6232 loaded (median 0.52 ms, 99th percentile 11.92 ms, worst 35.54 ms, 7712 ms and 1590.0 MB read in all); 9241 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 11156 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2037 pipelines made at create taken by draws; 2565 create calls with nothing kept for their stages, 0 before the index; units 8797 (6232 ready, 0 loading), 14428 programs alive; 0 noted graphics pipeline probes deferred to first use
[hos host] vk: program loads at create (close): 13302 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them)
[hos host] vk: module identifiers (close): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before)
[hos host] vk: indexed descriptor arrays (close): 2661 in 2661 of 52319 program stages, 0 of them near a limit
[hos host] vk: indexed descriptor arrays (close), fragment stages: 2661 texture (17-64: 2661); the longest 64
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4263 pools in the table now)
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)