Beanstalk Longshot test farm
Menu

Report rp_19c1d72dac8d0dfe fail

#1442 fix(vk): frame generation's fixed multipliers on the game's timeline under V-Sync On (FIFO) too

linux+amd on Alberania/agent-af6cf3,

This report disagrees with its peers.

market-framegen market.fps_mean: +65.3% against peers' -5.6%
market-framegen market.frametime_1pct_low_ms: -97.5% against peers' -0.3%
market-framegen market.frametime_max_ms: -97.3% against peers' -0.6%
market-framegen market.frametime_p99_ms: -97.7% against peers' -0.4%
market-framegen market.hitch_count: -100.0% against peers' +13.3%
market-framegen market.stutter_count: -100.0% against peers' +16.7%
market-framegen#1 market.fps_mean: +0.0% against peers' +32.6%
market-framegen#2 market.frametime_1pct_low_ms: +25.7% against peers' -0.0%
market-framegen#2 market.frametime_max_ms: +92.0% against peers' +0.5%
market-framegen#3 market.draws_mean: +58.4% against peers' -7.7%
market-framegen#3 market.fps_mean: -12.7% against peers' -44.1%
market-framegen#3 market.frametime_1pct_low_ms: +1244.9% against peers' -0.2%
market-framegen#3 market.frametime_max_ms: +4612.6% against peers' -0.4%

Machine

Commit
0c552c97714ad41922bb616e5328cf968fc73898
Baseline
67efc4d3e305eccf11052b456783a1898d47c23d
App
nightly-156-4ec688b0, attempt 1
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
AMD Radeon RX 7900 XTX (RADV NAVI31)
tags
linuxamdradvdgpu
driver
26.2.7
ram_gb
64
vram_mb
24,560
gpu_vendor
amd
os_version
Bazzite (kernel 7.3.4)

Builds

main (baseline)

0 s warm

from 67efc4d3e305

the base was built already

PR

74.3 s warm

Program cache: warm

Scenarios

market-framegen vsync=1, frame_generation=2

ok
Metric (median)mainPRΔ
exit_code00±0%
market.fps_mean36.2959.99+65.3%
market.draws_mean488489.8+0.4%
log_forbidden_hits00±0%
market.hitch_count130−100%
log_expected_missing00±0%
market.stutter_count150−100%
market.frametime_max_ms1,011.5527.15−97.3%
market.frametime_p50_ms16.4416.63+1.1%
market.frametime_p99_ms1,00223.48−97.7%
market.frametime_1pct_low_ms1,004.2824.61−97.5%
screenshot_diff—0.5—

Pictures against main: market diff 0.5044 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
market.fps_mean36.2959.99
market.draws_mean488489.8
log_forbidden_hits00
market.hitch_count130
log_expected_missing00
market.stutter_count150
market.frametime_max_ms1,011.5527.15
market.frametime_p50_ms16.4416.63
market.frametime_p99_ms1,00223.48
market.frametime_1pct_low_ms1,004.2824.61
screenshot_diff—0.5

market-framegen vsync=1, frame_generation=3

ok
Metric (median)mainPRΔ
exit_code00±0%
market.fps_mean6060.01+0%
market.draws_mean505.5511+1.1%
log_forbidden_hits00±0%
market.hitch_count00±0%
log_expected_missing00±0%
market.stutter_count00±0%
market.frametime_max_ms26.6126.3−1.1%
market.frametime_p50_ms16.6616.77+0.6%
market.frametime_p99_ms23.0823.09+0%
market.frametime_1pct_low_ms24.2223.87−1.5%
screenshot_diff—0.63—

Pictures against main: market diff 0.626 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
market.fps_mean6060.01
market.draws_mean505.5511
log_forbidden_hits00
market.hitch_count00
log_expected_missing00
market.stutter_count00
market.frametime_max_ms26.6126.3
market.frametime_p50_ms16.6616.77
market.frametime_p99_ms23.0823.09
market.frametime_1pct_low_ms24.2223.87
screenshot_diff—0.63

market-framegen vsync=0, frame_generation=2

ok
Metric (median)mainPRΔ
exit_code00±0%
market.fps_mean59.9960+0%
market.draws_mean524.6514.9−1.8%
log_forbidden_hits00±0%
market.hitch_count00±0%
log_expected_missing00±0%
market.stutter_count01—
market.frametime_max_ms20.8740.06+92%
market.frametime_p50_ms16.6716.71+0.3%
market.frametime_p99_ms19.6923.27+18.2%
market.frametime_1pct_low_ms20.1325.3+25.7%
screenshot_diff—0.66—

Pictures against main: market diff 0.6567 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
market.fps_mean59.9960
market.draws_mean524.6514.9
log_forbidden_hits00
market.hitch_count00
log_expected_missing00
market.stutter_count01
market.frametime_max_ms20.8740.06
market.frametime_p50_ms16.6716.71
market.frametime_p99_ms19.6923.27
market.frametime_1pct_low_ms20.1325.3
screenshot_diff—0.66

market-framegen vsync=0, frame_generation=3

ok
Metric (median)mainPRΔ
exit_code00±0%
market.fps_mean59.9652.37−12.7%
market.draws_mean522826.8+58.4%
log_forbidden_hits00±0%
market.hitch_count04—
log_expected_missing00±0%
market.stutter_count04—
market.frametime_max_ms21.321,004.6+4612.6%
market.frametime_p50_ms16.6916.84+0.9%
market.frametime_p99_ms19.5724.34+24.4%
market.frametime_1pct_low_ms20.04269.5+1244.9%
screenshot_diff—0.87—

Pictures against main: market diff 0.8704 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
market.fps_mean59.9652.37
market.draws_mean522826.8
log_forbidden_hits00
market.hitch_count04
log_expected_missing00
market.stutter_count04
market.frametime_max_ms21.321,004.6
market.frametime_p50_ms16.6916.84
market.frametime_p99_ms19.5724.34
market.frametime_1pct_low_ms20.04269.5
screenshot_diff—0.87

Rules

ScenarioCellRuleLimitmainPRΔ %Status
market-framegenvsync=1, frame_generation=2crashFalse00—pass
market-framegenvsync=1, frame_generation=2market.fps_mean.min_delta_pct1036.2959.99+65.3%pass
market-framegenvsync=1, frame_generation=2screenshot.max_diff0.1—0.5—fail
market-framegenvsync=1, frame_generation=2market.frametime_p99_ms.max_delta_pct151,00223.48−97.7%pass
market-framegenvsync=1, frame_generation=2log_forbidden_hits.max000—pass
market-framegenvsync=1, frame_generation=3crashFalse00—pass
market-framegenvsync=1, frame_generation=3market.fps_mean.min_delta_pct106060.01±0%pass
market-framegenvsync=1, frame_generation=3screenshot.max_diff0.1—0.63—fail
market-framegenvsync=1, frame_generation=3market.frametime_p99_ms.max_delta_pct1523.0823.09±0%pass
market-framegenvsync=1, frame_generation=3log_forbidden_hits.max000—pass
market-framegenvsync=0, frame_generation=2crashFalse00—pass
market-framegenvsync=0, frame_generation=2market.fps_mean.min_delta_pct1059.9960±0%pass
market-framegenvsync=0, frame_generation=2screenshot.max_diff0.1—0.66—fail
market-framegenvsync=0, frame_generation=2market.frametime_p99_ms.max_delta_pct1519.6923.27+18.2%fail
market-framegenvsync=0, frame_generation=2log_forbidden_hits.max000—pass
market-framegenvsync=0, frame_generation=3crashFalse00—pass
market-framegenvsync=0, frame_generation=3market.fps_mean.min_delta_pct1059.9652.37−12.7%fail
market-framegenvsync=0, frame_generation=3screenshot.max_diff0.1—0.87—fail
market-framegenvsync=0, frame_generation=3market.frametime_p99_ms.max_delta_pct1519.5724.34+24.4%fail
market-framegenvsync=0, frame_generation=3log_forbidden_hits.max000—pass

Log (PR side, end)

[hos host] vk:   read live, by pool:
[hos host] vk: 2 textures retired (5004 left, 7791 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: 1 textures retired (5003 left, 7789 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 10820000 (9361972 pages from the captures)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.32, present 0.41, draw 2.80, descriptors 1.33, texture lookups 0.44, uploads 0.36, pipelines 0.11, programs 0.37, commands 0.72, dispatch 0.53, memory sync 0.94, queue submit 0.97, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.22 MB synced in 1125.0 copies, 18.04 MB written back
[hos host] vk: 16560 presents, 60.0 fps; a frame: 826 draws (0 skipped), 101 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 5006 textures (7827 MB)
[hos host] vk: host time in GPU resource waits: 1.43 ms a frame (fences 0.00, timelines 1.43, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.0 full barriers recorded, 241.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.3 ms a frame (the longest submission 1.9 ms); 0.3 textures made a frame
[hos host] vk: a frame: 1.72 MB unswizzled on the CPU in 0.11 ms
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #360000: event 0x100d6c8024 mode 0 value 268354 (now 268335) (lr 0x80a47c2c)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 127349 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 1 textures retired (5006 left, 7827 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 989 dirty pages from their submits' captures, 73604 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: write-back diff (600 submits): 4980 runs, 721.4 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19678 in captures, 15 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: texture storage read as submitted (84001 times; 4256865 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: replay reads of guest memory as submitted: 10840000 (9379925 pages from the captures)
[hos host] vk: 5 textures retired (5001 left, 7818 MB): budget 0, drawn over 5, dead targets 0
[hos sead::MainThread] nvn: DrawMeshTasksIndirect: 540000 so far (x1 0x117db40020 x2 0 x3 0x117db40000 x4 0x44b040)
[hos host] vk: 9 textures retired (4992 left, 7802 MB): budget 0, drawn over 9, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos ModuleSystemWorker3] nvn: 2350000 recordings made, 72430 live copies (21.7 MB), 4947 texture copies; 3 command buffers' segments (4.1 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 28 sync waits (35 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: replay reads of guest memory as submitted: 10860000 (9397526 pages from the captures)
[hos host] vk: 1 textures retired (4995 left, 7850 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1178 of 3000 waited for their write-back, 0.19 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 host] vk: 3 textures retired (4993 left, 7825 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1027 dirty pages from their submits' captures, 74179 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: write-back diff (600 submits): 4974 runs, 720.7 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20174 in captures, 20 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: render targets drawn over from another start, let go: 29551 so far (105916 MB), 26626 of them (95713 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 10880000 (9415511 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 787 pages written, 787 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.095; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.090, bytes copied 0.000; 25 kept (150 MB), 8 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: 1 textures retired (4992 left, 7824 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 10900000 (9433427 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 5455369 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 8564868 kept (2316755 by the last picks' textures, a uniform buffer bound since), 14666 new, 4620465 with other textures (of 13200000)
[hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #270000: event 0x100d6c8010 mode 0 value 270002 (lr 0x80660bcc)
[hos host] vk: 2 textures retired (4990 left, 7799 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1017 dirty pages from their submits' captures, 73184 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: write-back diff (600 submits): 5112 runs, 740.8 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19664 in captures, 18 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos Presentation Thread] nvn: QueueSubmitCommands #100000: queue 0x10100d6aa020 (its #16661), 1 handles (lr 0x805282f4)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 115941 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 10920000 (9451077 pages from the captures)
[hos host] vk: 2 textures retired (4988 left, 7784 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.14, present 0.41, draw 2.71, descriptors 1.25, texture lookups 0.38, uploads 0.31, pipelines 0.11, programs 0.36, commands 0.71, dispatch 0.54, memory sync 0.86, queue submit 0.97, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.24 MB synced in 1126.1 copies, 18.06 MB written back
[hos host] vk: 16680 presents, 60.0 fps; a frame: 824 draws (0 skipped), 101 dispatches, 146 passes, 150 barriers, 6 submits, 0.7 uploads (1.4 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 4988 textures (7784 MB)
[hos host] vk: host time in GPU resource waits: 1.42 ms a frame (fences 0.00, timelines 1.42, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.1 full barriers recorded, 241.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.3 ms a frame (the longest submission 1.9 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.43 MB unswizzled on the CPU in 0.09 ms
[hos host] vk: texture storage read as submitted (86001 times; 4299361 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: replay reads of guest memory as submitted: 10940000 (9469046 pages from the captures)
[hos host] vk: 4 textures retired (4984 left, 7734 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1119 dirty pages from their submits' captures, 73502 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: write-back diff (600 submits): 4997 runs, 723.1 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19686 in captures, 17 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 10960000 (9486896 pages from the captures)
[hos host] vk: 4 textures retired (4981 left, 7697 MB): budget 0, drawn over 4, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 783 pages written, 783 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.093; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.088, bytes copied 0.000; 25 kept (168 MB), 8 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: replay reads of guest memory as submitted: 10980000 (9504683 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 675 KB; 0 made on demand (0 MB kept now); c1 stages: at most 252 a recording; 13 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1168 dirty pages from their submits' captures, 73959 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: write-back diff (600 submits): 5097 runs, 739.2 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20166 in captures, 16 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: replay reads of guest memory as submitted: 11000000 (9522631 pages from the captures)
[hos aglTextureDataMgr::Compaction] vcores: 169412 takes, 40483 waits (mean 98 us, longest 21.3 ms, 0 over HOS_VCORE_LOG_MS), 19576 kicks, 19579 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 16753 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 34, 15.5-17.8 223, 17.8-22 43, 22-30 0, 30-40 0, over 40 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 126091 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1117 of 3000 waited for their write-back, 0.20 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #365000: event 0x100d6c8024 mode 0 value 272154 (now 272135) (lr 0x80a47c2c)
[hos host] vk: replay reads of guest memory as submitted: 11020000 (9540625 pages from the captures)
[hos host] vk: texture storage read as submitted (88001 times; 4341785 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1076 dirty pages from their submits' captures, 73326 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: write-back diff (600 submits): 4996 runs, 724.7 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19733 in captures, 13 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 11040000 (9558234 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: memory: working set 9961 MB (peak 17369), private 3468 MB, staging 48 MB in 3 arenas, 38 made so far (0 ms)
[hos host] vk: memory heaps: heap 0 (system): 15 blocks 848 MB, 50 allocations 810 MB; used 2968 of 31926 MB; heap 1 (device): 321 blocks 10603 MB, 19869 allocations 9374 MB; used 11325 of 23413 MB;
[hos host] vk: image blocks: 4 blocks 128 MB, 12 images 97 MB; 5 free ranges, the largest 23 MB
[hos host] vk: image blocks (render targets): 32 blocks 1024 MB, 136 images 492 MB; 105 free ranges, the largest 26 MB
[hos host] vk: image blocks (textures, compacted): 188 blocks 6016 MB, 4836 images 5756 MB; 1377 free ranges, the largest 11 MB
[hos host] vk: render target images: 18055 reused from the pool, 13530 made new, 13388 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 11325 MB used of 23413 MB allowed (1228 MB of it free in the blocks); textures 7784 MB (budget 11000 MB), 4988 textures
[hos host] vk: textures: decoded ASTC 4083 MB, rendered 1082 MB (56 drawn in one frame, kept: 51742 KB), other 1770 MB; used in the last 8 presents 2007 MB
[hos host] vk: decoded ASTC used again: 2922 textures (5340 MB) copied from ones the game finalized, not decoded; 2922 of those retired, 538 listed; 1853 MB of blocks hashed in 253 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 14953 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 14953 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 0xa, last used 15319 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 1 presents ago
[hos host] vk:   54 MB: 0x10002d97a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1320 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 41 (13023 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 4 (151 KB); 260x260x1 NVN 0xd: 23 (4047 KB); 306x104x1 NVN 0x1: 4 (124 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 960x540x1 NVN 0x29: 2 (8100 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 90 waited for it, 23.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 1003.3 ms; VRAM 11.1 of 22.9 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: 108 program records loaded (121.9 ms), 55 new graphics pipelines, pipelines from the driver's cache 93, from the start's cache 0, compiled 28; 102 draws and dispatches left out, 35 waits (1406.8 ms)
[hos host] vk: program loads at create (play): 5089 queued, 5089 loaded (median 0.14 ms, 99th percentile 5.46 ms, worst 9.47 ms, 3976 ms and 1095.6 MB read in all); 7093 programs (1124 of them compute variants without their code, 0 graphics programs no note names), 9196 graphics pipelines (0 not in a cache), 592 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1945 pipelines made at create taken by draws; 3271 create calls with nothing kept for their stages, 0 before the index; units 8360 (5089 ready, 0 loading), 14505 programs alive
[hos host] vk: module identifiers (play): 658 known, 658 learned in this run; 0 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.29, present 0.40, draw 2.77, descriptors 1.30, texture lookups 0.44, uploads 0.37, pipelines 0.11, programs 0.37, commands 0.71, dispatch 0.53, memory sync 0.94, queue submit 0.96, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.24 MB synced in 1127.6 copies, 18.06 MB written back
[hos host] vk: 16800 presents, 60.0 fps; a frame: 825 draws (0 skipped), 101 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 4988 textures (7784 MB)
[hos host] vk: host time in GPU resource waits: 1.46 ms a frame (fences 0.00, timelines 1.46, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.3 full barriers recorded, 241.1 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.4 ms a frame (the longest submission 1.9 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.72 MB unswizzled on the CPU in 0.11 ms
[hos host] vk: the render thread's whole frames (600 presents): 2 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making
[hos host] vk: the render thread (600 presents, 19.88 ms a frame): its jobs 7.26 ms a frame (submits 6.02, presents 0.42, others 0.82), idle 12.62; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 167.30 jobs queued at a present); 0 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 0.00 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 91 captures at a CPU signal; the submits' waits read in 0.028 ms a frame; readbacks: 3000 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 7.29 ms after its hand-over (15.24 at most)
[hos host] vk: replay reads of guest memory as submitted: 11060000 (9576231 pages from the captures)
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1109 dirty pages from their submits' captures, 73847 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: write-back diff (600 submits): 4978 runs, 721.4 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20160 in captures, 18 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos Presentation Thread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 796 pages written, 796 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.096; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.091, bytes copied 0.000; 25 kept (168 MB), 7 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: 2 textures retired (4993 left, 7815 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 11080000 (9594178 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 21 sync waits (1023 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: texture 0x10009368a00 561x561x1 x1 levels 1 NVN 0x34 -> vk 126 (5000 textures, 7827 MB)
[hos host] vk: readback pages refreshed from guest memory: 5528938 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 11100000 (9611851 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 128976 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 921 dirty pages from their submits' captures, 72970 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: write-back diff (600 submits): 4985 runs, 721.3 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19656 in captures, 13 only in the collection, 39 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: texture storage read as submitted (90001 times; 4384291 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: 3 textures retired (5002 left, 7841 MB): budget 0, drawn over 3, dead targets 0
[hos host] vk: program picks: 8694515 kept (2350325 by the last picks' textures, a uniform buffer bound since), 14666 new, 4690818 with other textures (of 13400000)
[hos host] vk: replay reads of guest memory as submitted: 11120000 (9629831 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1131 dirty pages from their submits' captures, 72810 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: write-back diff (600 submits): 4986 runs, 720.8 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19676 in captures, 20 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: replay reads of guest memory as submitted: 11140000 (9647705 pages from the captures)
[hos host] vk: 1 textures retired (5001 left, 7829 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: 1 textures retired (5000 left, 7816 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #275000: event 0x100d6c8000 mode 0 value 274995 (lr 0x80291440)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1146 of 3000 waited for their write-back, 0.20 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 794 pages written, 794 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.099; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.094, bytes copied 0.000; 25 kept (372 MB), 5 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: replay reads of guest memory as submitted: 11160000 (9665431 pages from the captures)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.33, present 0.43, draw 2.79, descriptors 1.31, texture lookups 0.44, uploads 0.37, pipelines 0.12, programs 0.37, commands 0.71, dispatch 0.55, memory sync 0.93, queue submit 0.96, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.22 MB synced in 1125.0 copies, 18.03 MB written back
[hos host] vk: 16920 presents, 40.4 fps; a frame: 824 draws (0 skipped), 101 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 5000 textures (7816 MB)
[hos host] vk: host time in GPU resource waits: 9.80 ms a frame (fences 0.00, timelines 9.80, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.4 full barriers recorded, 241.3 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.4 ms a frame (the longest submission 1.9 ms); 0.3 textures made a frame
[hos host] vk: a frame: 1.72 MB unswizzled on the CPU in 0.11 ms
[hos host] vk: 1 textures retired (4999 left, 7814 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: texture 0x10008558800 1716x1716x1 x1 levels 1 NVN 0x34 -> vk 126 (5000 textures, 7827 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 675 KB; 0 made on demand (0 MB kept now); c1 stages: at most 252 a recording; 13 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1167 dirty pages from their submits' captures, 73977 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: write-back diff (600 submits): 5116 runs, 739.3 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19776 in captures, 15 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 4 textures retired (4998 left, 7791 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 11180000 (9683413 pages from the captures)
[hos host] vk: texture 0x1133327c00 512x512x1 x1 levels 10 NVN 0x7b -> vk 37 (ASTC decoded) (5000 textures, 7793 MB)
[hos host] vk: texture storage read as submitted (92001 times; 4426797 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos PreActorModelCompose] vcores: 113123 takes, 26324 waits (mean 105 us, longest 19.5 ms, 0 over HOS_VCORE_LOG_MS), 12588 kicks, 12668 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vi: 16951 frames presented (37.6 fps over the last 5.3 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 32, 15.5-17.8 142, 17.8-22 22, 22-30 0, 30-40 0, over 40 2
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 128288 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #370000: event 0x100d6c8024 mode 0 value 275954 (now 275935) (lr 0x80a47c2c)
[hos host] vk: replay reads of guest memory as submitted: 11200000 (9701276 pages from the captures)
[hos host] vk: texture 0x11321b0200 512x512x1 x1 levels 10 NVN 0x7b -> vk 37 (ASTC decoded) (5000 textures, 7793 MB)
[hos host] vk: texture 0x10008558800 1703x1703x1 x1 levels 1 NVN 0x34 -> vk 126 (5000 textures, 7816 MB)
[hos host] vk: upload over a drawn image: #39335 0x10001248800 480x270x1 x1 NVN 0x3f at present 16973 (texture frame 16974), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1131 dirty pages from their submits' captures, 73279 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: write-back diff (600 submits): 5027 runs, 722.1 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19812 in captures, 22 only in the collection, 39 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: 6 textures retired (4997 left, 7800 MB): budget 0, drawn over 6, dead targets 0
[hos ModuleSystemWorker5] nvn: 2400000 recordings made, 72507 live copies (21.8 MB), 4948 texture copies; 4 command buffers' segments (4.2 MB)
[hos host] vk: replay reads of guest memory as submitted: 11220000 (9719000 pages from the captures)
[hos host] vk: 5 textures retired (4992 left, 7791 MB): budget 0, drawn over 5, dead targets 0
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: 4 textures retired (4988 left, 7784 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: recorder: 3269176 packets run in 10.0 s (busy 0.82 s, spun idle 1.88 s, slept 5598 times, 1431 of them under 200 us), 0 calls made directly (no room); the replay waited for it 20391 times, 70.02 ms in all, the longest 0.47 ms; vkEndCommandBuffer 7217/38.71 ms (max 0.46), replay_mu unlock 5849/19.64 ms (max 0.46), vkResetDescriptorPool 7215/10.18 ms (max 0.10), vkDestroyImageView 110/1.50 ms (max 0.47)
[hos host] vk: replay reads of guest memory as submitted: 11240000 (9737044 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 786 pages written, 786 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.095; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.089, bytes copied 0.000; 25 kept (248 MB), 9 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1017 dirty pages from their submits' captures, 73911 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: write-back diff (600 submits): 5056 runs, 723.1 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19915 in captures, 16 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: 1 textures retired (4989 left, 7797 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 11260000 (9754881 pages from the captures)
[hos host] vk: texture storage read as submitted (94001 times; 4464953 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.33, present 0.42, draw 2.87, descriptors 1.35, texture lookups 0.44, uploads 0.36, pipelines 0.12, programs 0.39, commands 0.73, dispatch 0.54, memory sync 0.92, queue submit 0.98, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.25 MB synced in 1126.9 copies, 18.07 MB written back
[hos host] vk: 17040 presents, 40.4 fps; a frame: 825 draws (0 skipped), 102 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 4989 textures (7797 MB)
[hos host] vk: host time in GPU resource waits: 9.66 ms a frame (fences 0.00, timelines 9.66, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 505.9 full barriers recorded, 241.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.4 ms a frame (the longest submission 1.9 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.73 MB unswizzled on the CPU in 0.11 ms
[hos host] vk: replay reads of guest memory as submitted: 11280000 (9772624 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 5602184 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 1 textures retired (4988 left, 7795 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 124227 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 892 dirty pages from their submits' captures, 73253 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: write-back diff (600 submits): 5027 runs, 722.7 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20281 in captures, 19 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: 1 textures retired (4987 left, 7783 MB): budget 0, drawn over 1, dead targets 0
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1149 of 3000 waited for their write-back, 0.19 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 host] vk: replay reads of guest memory as submitted: 11300000 (9790636 pages from the captures)
[hos host] vk: replay reads of guest memory as submitted: 11320000 (9808532 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 25 sync waits (1027 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: program picks: 8824104 kept (2383824 by the last picks' textures, a uniform buffer bound since), 14666 new, 4761229 with other textures (of 13600000)
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1071 dirty pages from their submits' captures, 73844 from earlier ones', 9 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: write-back diff (600 submits): 5107 runs, 737.6 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19706 in captures, 20 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 9;
[hos host] vk: 2 textures retired (4986 left, 7759 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 11340000 (9826211 pages from the captures)
[hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 560000 so far (x1 0x1178b9a000 x2 0 x3 0x1178b9a000 x4 0x654040)
[hos Presentation Thread] vk: capture: a submit 0.27 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 787 pages written, 787 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.095; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.091, bytes copied 0.000; 25 kept (214 MB), 9 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: 1 textures retired (4985 left, 7747 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: texture storage read as submitted (96001 times; 4507471 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: replay reads of guest memory as submitted: 11360000 (9844200 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 675 KB; 0 made on demand (0 MB kept now); c1 stages: at most 252 a recording; 13 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1107 dirty pages from their submits' captures, 73148 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: write-back diff (600 submits): 4979 runs, 721.6 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19725 in captures, 17 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 124928 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 11380000 (9862090 pages from the captures)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.29, present 0.40, draw 2.79, descriptors 1.30, texture lookups 0.43, uploads 0.36, pipelines 0.11, programs 0.37, commands 0.72, dispatch 0.53, memory sync 0.92, queue submit 0.96, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.23 MB synced in 1126.1 copies, 18.03 MB written back
[hos host] vk: 17160 presents, 60.0 fps; a frame: 826 draws (0 skipped), 101 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 4985 textures (7747 MB)
[hos host] vk: host time in GPU resource waits: 1.49 ms a frame (fences 0.00, timelines 1.49, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 504.6 full barriers recorded, 241.2 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.4 ms a frame (the longest submission 1.9 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.72 MB unswizzled on the CPU in 0.11 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #375000: event 0x100d6c8024 mode 0 value 279754 (now 279735) (lr 0x80a47c2c)
[hos host] vk: 1 textures retired (4984 left, 7745 MB): budget 0, drawn over 1, dead targets 0
[hos sead::MainThread] nvn: CommandBufferSignalEvent #280000: event 0x100d6c8020 mode 0 value 280000 (lr 0x80664f14)
[hos host] vk: replay reads of guest memory as submitted: 11400000 (9879779 pages from the captures)
[hos host] vk: 1 textures retired (4983 left, 7733 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1166 dirty pages from their submits' captures, 73126 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: write-back diff (600 submits): 4965 runs, 721.2 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19692 in captures, 16 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: replay reads of guest memory as submitted: 11420000 (9897767 pages from the captures)
[hos host] vk: upload over a drawn image: #39345 0x1000134da00 1920x1080x1 x1 NVN 0x3f at present 17200 (texture frame 17201), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it
[hos host] vk: texture 0x1000134da00 1920x1080x1 x1 levels 1 NVN 0x3f (8640 KB of storage) re-uploaded (its memory was written; flags 0x8): a GPU write into its storage, 8640 KB of it, over what the GPU wrote (finalized since)
[hos host] vk: 2 textures retired (4986 left, 7770 MB): budget 0, drawn over 2, dead targets 0
[hos sead::MainThread] vk: capture: a submit 0.28 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 807 pages written, 807 copied (3.2 MB)
[hos host] vk: a capture taken (ms): all 0.101; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.096, bytes copied 0.000; 25 kept (168 MB), 6 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: texture storage read as submitted (98001 times; 4549989 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: replay reads of guest memory as submitted: 11440000 (9915582 pages from the captures)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1113 of 3000 waited for their write-back, 0.20 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 host] vk: render targets drawn over from another start, let go: 29551 so far (105916 MB), 26626 of them (95713 MB) between the passes
[hos host] vk: 1 textures retired (4986 left, 7770 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1068 dirty pages from their submits' captures, 73786 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: write-back diff (600 submits): 5001 runs, 722.7 MB compared; 74 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20176 in captures, 20 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: replay reads of guest memory as submitted: 11460000 (9933362 pages from the captures)
[hos aglTextureDataMgr::Compaction] vcores: 167095 takes, 41002 waits (mean 98 us, longest 19.5 ms, 0 over HOS_VCORE_LOG_MS), 19696 kicks, 19729 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 132008 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 5675842 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 3 textures retired (4983 left, 7733 MB): budget 0, drawn over 3, dead targets 0
[hos Presentation Thread] vi: 17253 frames presented (60.4 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 57, 15.5-17.8 200, 17.8-22 45, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 11480000 (9951360 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1196 dirty pages from their submits' captures, 73820 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: write-back diff (600 submits): 5137 runs, 741.9 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19809 in captures, 16 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 11500000 (9969298 pages from the captures)
[hos host] vk: a frame: 89 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 52 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.27, present 0.40, draw 2.84, descriptors 1.36, texture lookups 0.44, uploads 0.36, pipelines 0.11, programs 0.37, commands 0.72, dispatch 0.53, memory sync 0.93, queue submit 0.94, slot wait 0.04
[hos host] vk: a frame: mirrors 411 (915 MB): 7.24 MB synced in 1125.4 copies, 18.08 MB written back
[hos host] vk: 17280 presents, 60.0 fps; a frame: 825 draws (0 skipped), 102 dispatches, 146 passes, 150 barriers, 6 submits, 0.8 uploads (1.8 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 44215 pipelines (3812 ms), 0 programs (10 failed), 4985 textures (7758 MB)
[hos host] vk: host time in GPU resource waits: 1.48 ms a frame (fences 0.00, timelines 1.48, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 505.1 full barriers recorded, 241.0 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 6.4 ms a frame (the longest submission 1.9 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.72 MB unswizzled on the CPU in 0.11 ms
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos rmbl::VibrationThread] hid: 94208 vibration values, strongest 0.00 since the last count
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1161 dirty pages from their submits' captures, 72915 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: write-back diff (600 submits): 5063 runs, 723.9 MB compared; 78 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19881 in captures, 16 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: replay reads of guest memory as submitted: 11520000 (9987239 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.27 ms (lock 0.01, scan 0.04 over 847 ranges, 2620 MB), 783 pages written, 783 copied (3.1 MB)
[hos host] vk: a capture taken (ms): all 0.095; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.090, bytes copied 0.000; 25 kept (158 MB), 6 spare buffers, 9220 texture pages copied (36 MB)
[hos host] vk: ASTC texture #39999 0x1133327c00 512x512 x1 levels 10: the image of #39997 0x110cb55a00 (the same blocks, finalized by the game) copied, not decoded again (3000 so far, 5415 MB)
[hos host] vk: texture storage read as submitted (100001 times; 4592387 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[hos host] vk: replay reads of guest memory as submitted: 11540000 (10005206 pages from the captures)
[hos host] vk: program picks: 8953559 kept (2417455 by the last picks' textures, a uniform buffer bound since), 14666 new, 4831774 with other textures (of 13800000)
[hos host] vk: 4 textures retired (4988 left, 7752 MB): budget 0, drawn over 4, dead targets 0
[hos host] vk: queues ordered by their events: 114000 submissions stopped at a wait, 113956 went on once it was reached, 42 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 3 (stopped 51.94 ms at most); waits met 379288, not met 0; captures at a CPU event's wait 2933, 0 of them at a wait met on arrival
[hos host] vk: 1 textures retired (4987 left, 7740 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 675 KB; 0 made on demand (0 MB kept now); c1 stages: at most 252 a recording; 13 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 840, 4120.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1028 dirty pages from their submits' captures, 73280 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: write-back diff (600 submits): 5052 runs, 724.7 MB compared; 75 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 19845 in captures, 23 only in the collection, 40 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 11560000 (10022953 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 127476 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: 1 textures retired (4998 left, 7780 MB): budget 0, drawn over 1, dead targets 0
[hos host] vk: texture 0x10009368a00 595x595x1 x1 levels 1 NVN 0x34 -> vk 126 (5000 textures, 7795 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #380000: event 0x100d6c8024 mode 0 value 283554 (now 283535) (lr 0x80a47c2c)
[hos host] vk: replay reads of guest memory as submitted: 11580000 (10040982 pages from the captures)
[hos ModuleSystemWorker5] nvn: 2450000 recordings made, 72428 live copies (20.9 MB), 4948 texture copies; 7 command buffers' segments (4.4 MB)
[hos host] vk: 3 textures retired (5000 left, 7784 MB): budget 0, drawn over 3, dead targets 0
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1137 of 3000 waited for their write-back, 0.19 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 host] vk: 2 textures retired (4998 left, 7759 MB): budget 0, drawn over 2, dead targets 0
[hos host] vk: sparse mirrors: 57, 915 MB with memory of 1324 MB (409 MB spared); blocks given memory later 8009, given back 9940; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 902 binds (267.4 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 861, 4223.3 MB; 23 bindings followed, 34 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far
[hos host] vk: mirror syncs (600 submits): 1003 dirty pages from their submits' captures, 75434 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: write-back diff (600 submits): 5167 runs, 740.9 MB compared; 76 pages read into the shadows; 288 MB of shadows; pages the shadows knew that the CPU wrote: 20408 in captures, 16 only in the collection, 39 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 135 live (2096 MB), 0 retired still imported (0 MB), 81 retired given back (1132 MB)
[hos host] vk: texture 0x10009368a00 600x600x1 x1 levels 1 NVN 0x34 -> vk 126 (5000 textures, 7762 MB)
[hos host] vk: replay reads of guest memory as submitted: 11600000 (10058891 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 29 sync waits (40 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.05
[hos host] vk: texture storage read as submitted (102001 times; 4634899 pages from the copies, 0 of them rewritten in guest memory since their submit; 9220 pages kept, 16 spans, 72 MB)
[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: 108 program records loaded (121.9 ms), 55 new graphics pipelines, pipelines from the driver's cache 93, from the start's cache 0, compiled 28; 102 draws and dispatches left out, 35 waits (1406.8 ms)
[hos host] vk: memory: working set 9965 MB (peak 17369), private 3472 MB, staging 48 MB in 3 arenas, 38 made so far (0 ms)
[hos host] vk: memory heaps: heap 0 (system): 15 blocks 848 MB, 50 allocations 810 MB; used 2968 of 31926 MB; heap 1 (device): 321 blocks 10603 MB, 19883 allocations 9367 MB; used 11325 of 23413 MB;
[hos host] vk: image blocks: 4 blocks 128 MB, 12 images 97 MB; 5 free ranges, the largest 23 MB
[hos host] vk: image blocks (render targets): 32 blocks 1024 MB, 150 images 484 MB; 120 free ranges, the largest 32 MB
[hos host] vk: image blocks (textures, compacted): 188 blocks 6016 MB, 4836 images 5756 MB; 1377 free ranges, the largest 11 MB
[hos host] vk: render target images: 18057 reused from the pool, 13594 made new, 13438 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 11325 MB used of 23413 MB allowed (1236 MB of it free in the blocks); textures 7777 MB (budget 11000 MB), 5002 textures
[hos host] vk: textures: decoded ASTC 4083 MB, rendered 1071 MB (66 drawn in one frame, kept: 65425 KB), other 1770 MB; used in the last 8 presents 2016 MB
[hos host] vk: decoded ASTC used again: 3012 textures (5426 MB) copied from ones the game finalized, not decoded; 3012 of those retired, 538 listed; 1866 MB of blocks hashed in 256 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 15553 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 15553 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:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 15919 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10002d97a00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1920 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 41 (13023 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 4 (151 KB); 260x260x1 NVN 0xd: 23 (4047 KB); 306x104x1 NVN 0x1: 4 (124 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 960x540x1 NVN 0x29: 2 (8100 KB);
[hos host] vk: program loads at create (close): 5089 queued, 5089 loaded (median 0.14 ms, 99th percentile 5.46 ms, worst 9.47 ms, 3976 ms and 1095.6 MB read in all); 7093 programs (1124 of them compute variants without their code, 0 graphics programs no note names), 9196 graphics pipelines (0 not in a cache), 592 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1945 pipelines made at create taken by draws; 3271 create calls with nothing kept for their stages, 0 before the index; units 8360 (5089 ready, 0 loading), 14505 programs alive
[hos host] vk: module identifiers (close): 658 known, 658 learned in this run; 0 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before)
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4255 pools in the table now)
[hos host] vk: pipeline cache: play file 6 saved (839 KB): 16 pipelines, 12 from the driver's cache, 4 compiled; 7 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (the game's saves are not waited for)