Beanstalk Longshot test farm
Menu

Report rp_3043e2ab95b4174d pass

#1552 WIP: fix(vk): the fixed shares' fallback upscale gets an edge pass and FSR 1 EASU

windows+amd on Razytos/agent-d8f902,

This report disagrees with its peers.

outlines-and-fps forest.stutter_count: -100.0% against peers' +0.0%

Machine

Commit
ff0eec7ffb669b9252da34c3e95e6667c1e1cd13
Baseline
79d4a143622f5272f09f66ac57a28d775cfc4ae2
App
nightly-166-e4316243, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
AMD Radeon RX 9070 XT
tags
windowsamdamd-proprietarydgpu
driver
2.0.416
ram_gb
32
vram_mb
16,304
gpu_vendor
amd
os_version
Windows 10.0.26300

Builds

main (baseline)

2,568.1 s warm

from 79d4a143622f

lift
94.5 s
read
562.3 s
finish
802.4 s
compile
1,102.1 s

PR

175 s warm

Program cache: warm

Scenarios

outlines-and-fps resolution=4

ok
Metric (median)mainPRΔ
exit_code00±0%
field.fps_mean60.0160.04+0%
forest.fps_mean5958.41−1%
field.draws_mean1,187.11,178.4−0.7%
field.hitch_count00±0%
forest.draws_mean765.3830.5+8.5%
forest.hitch_count00±0%
field.stutter_count00±0%
forest.stutter_count10−100%
field.frametime_max_ms24.4420.54−16%
field.frametime_p50_ms16.6516.67+0.1%
field.frametime_p99_ms19.5819.42−0.8%
forest.frametime_max_ms35.6129.85−16.2%
forest.frametime_p50_ms16.6216.65+0.2%
forest.frametime_p99_ms22.5621.59−4.3%
field.frametime_1pct_low_ms21.2219.76−6.9%
forest.frametime_1pct_low_ms25.5823.87−6.7%
screenshot_diff—0.05—

Pictures against main: forest-outline diff 0.0526 (main against itself ), field-outline diff 0.0257 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
field.fps_mean60.0160.04
forest.fps_mean5958.41
field.draws_mean1,187.11,178.4
field.hitch_count00
forest.draws_mean765.3830.5
forest.hitch_count00
field.stutter_count00
forest.stutter_count10
field.frametime_max_ms24.4420.54
field.frametime_p50_ms16.6516.67
field.frametime_p99_ms19.5819.42
forest.frametime_max_ms35.6129.85
forest.frametime_p50_ms16.6216.65
forest.frametime_p99_ms22.5621.59
field.frametime_1pct_low_ms21.2219.76
forest.frametime_1pct_low_ms25.5823.87
screenshot_diff—0.05

outlines-and-fps resolution=3

ok
Metric (median)mainPRΔ
exit_code00±0%
field.fps_mean6060±0%
forest.fps_mean59.9760+0.1%
field.draws_mean1,187.21,169.1−1.5%
field.hitch_count00±0%
forest.draws_mean757.1751.4−0.8%
forest.hitch_count00±0%
field.stutter_count00±0%
forest.stutter_count00±0%
field.frametime_max_ms23.2228.99+24.8%
field.frametime_p50_ms16.6616.7+0.2%
field.frametime_p99_ms19.719.7+0%
forest.frametime_max_ms21.421.24−0.7%
forest.frametime_p50_ms16.6816.64−0.2%
forest.frametime_p99_ms19.4419.3−0.7%
field.frametime_1pct_low_ms20.521.23+3.6%
forest.frametime_1pct_low_ms19.8819.91+0.2%
screenshot_diff—0.13—

Pictures against main: forest-outline diff 0.1264 (main against itself ), field-outline diff 0.0309 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
field.fps_mean6060
forest.fps_mean59.9760
field.draws_mean1,187.21,169.1
field.hitch_count00
forest.draws_mean757.1751.4
forest.hitch_count00
field.stutter_count00
forest.stutter_count00
field.frametime_max_ms23.2228.99
field.frametime_p50_ms16.6616.7
field.frametime_p99_ms19.719.7
forest.frametime_max_ms21.421.24
forest.frametime_p50_ms16.6816.64
forest.frametime_p99_ms19.4419.3
field.frametime_1pct_low_ms20.521.23
forest.frametime_1pct_low_ms19.8819.91
screenshot_diff—0.13

Rules

ScenarioCellRuleLimitmainPRΔ %Status
outlines-and-fpsresolution=4crashFalse00—pass
outlines-and-fpsresolution=4forest.fps_mean.min_delta_pct105958.41−1%pass
outlines-and-fpsresolution=4field.fps_mean.min_delta_pct1060.0160.04±0%pass
outlines-and-fpsresolution=4screenshot.max_diff0.15—0.05—pass
outlines-and-fpsresolution=4forest.frametime_p99_ms.max_delta_pct1522.5621.59−4.3%pass
outlines-and-fpsresolution=4field.frametime_p99_ms.max_delta_pct1519.5819.42−0.8%pass
outlines-and-fpsresolution=3crashFalse00—pass
outlines-and-fpsresolution=3forest.fps_mean.min_delta_pct1059.9760+0.1%pass
outlines-and-fpsresolution=3field.fps_mean.min_delta_pct106060±0%pass
outlines-and-fpsresolution=3screenshot.max_diff0.15—0.13—pass
outlines-and-fpsresolution=3forest.frametime_p99_ms.max_delta_pct1519.4419.3−0.7%pass
outlines-and-fpsresolution=3field.frametime_p99_ms.max_delta_pct1519.719.7±0%pass

Log (PR side, end)

[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 11.23 + 0.41 (the window's copy is in the idle), after it 1.17 + 0.68; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 22.95 (0.03 ms)
[hos host] vk: frame ahead (600 presents): 3.12 parts a frame recorded in the signal's job, 61.3% of them took nothing that came with the signal; of the others, 1.17 a frame took pages of the signal's capture into a mirror (288.6 pages a frame) and 0.06 pages read as guest memory had them (128.8 pages a frame); a frame's first part took nothing in 68 of 96 frames, its first three in 68
[hos host] vk: frame ahead, what came with the signal: 96 signals with a capture, each of 582.7 pages in 9.4 pools; between a frame's last submit and that signal 0.44 texture and sampler registrations, 0.35 releases and 0.00 other CPU signals a signal (7 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.52+0.12, 0.07+0.03, 0.17+0.04, 0.04+0.02, 0.19+0.09, 0.06+0.10, 0.04+0.07, 0.00+0.06, 0.00+0.02, 0.01+0.01, 0.02+0.00, 0.04+0.12
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7072 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 60, 1030 MB with memory of 1340 MB (309 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 835 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 229 kept as spares, 0 destroyed; 85 spares now, 1372 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1277 dirty pages from their submits' captures, 94811 from earlier ones', 24 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): 1530 dispatches, 58933 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8009 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23702 in captures, 7 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool: 0x1064400000 (8 MB, captured, state 2): 24;
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos Presentation Thread] vi: 7208 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 2, 15.5-17.8 293, 17.8-22 4, 22-30 1, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 2600000 (1132378 pages from the captures)
[hos sead::MainThread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 432 ranges, 3561 MB), 359 pages written, 359 copied (1.4 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 0.006, bytes copied 0.000; 25 kept (130 MB), 7 spare buffers, 4766 texture pages copied (18 MB)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1248 dirty pages from their submits' captures, 94917 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): 1527 dispatches, 58920 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8017 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23719 in captures, 12 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos AudioFrameworkThread] vcores: 220921 takes, 23149 waits (mean 25 us, longest 3.1 ms, 0 over HOS_VCORE_LOG_MS), 12632 kicks, 12432 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2620000 (1139390 pages from the captures)
[hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #140000: event 0x100c318028 mode 0 value 102303 (now 102284) (lr 0x80a47c2c)
[hos host] vk: recorder: 3965636 packets run in 10.0 s (busy 1.10 s, spun idle 3.18 s, slept 3742 times, 855 of them under 200 us), 0 calls made directly (no room); the replay waited for it 22027 times, 86.64 ms in all, the longest 0.18 ms; vkResetDescriptorPool 7473/46.08 ms (max 0.14), vkEndCommandBuffer 7473/21.21 ms (max 0.13), replay_mu unlock 7077/19.13 ms (max 0.10), vkQueueBindSparse 3/0.20 ms (max 0.18), vkDestroyImageView 1/0.01 ms (max 0.01)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 375 KB; 0 made on demand (0 MB kept now); c1 stages: at most 159 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1267 dirty pages from their submits' captures, 94897 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): 1526 dispatches, 58884 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8015 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23686 in captures, 10 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4078 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.68, present 0.11, draw 3.68, descriptors 1.49, texture lookups 0.05, uploads 0.00, pipelines 0.18, programs 0.44, commands 1.24, dispatch 0.80, memory sync 0.32, queue submit 0.47, slot wait 0.26
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.83 MB synced in 1208.4 copies, 24.10 MB written back
[hos host] vk: 7320 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 756 textures (1834 MB)
[hos host] vk: host time in GPU resource waits: 0.21 ms a frame (fences 0.03, timelines 0.18, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.4 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 2640000 (1146360 pages from the captures)
[hos host] vk: program picks: 4316628 kept (1956714 by the last picks' textures, a uniform buffer bound since), 19835 new, 1463536 with other textures (of 5800000)
[hos sead::MainThread] vk: capture: a submit 0.16 ms (lock 0.02, scan 0.04 over 432 ranges, 3563 MB), 366 pages written, 366 copied (1.4 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 0.010, bytes copied 0.000; 25 kept (138 MB), 7 spare buffers, 4949 texture pages copied (19 MB)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1450 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker5] vk: invalidates since the last readbacks line: 1189 kept their virtual core (nothing there to wait for), 2907 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1176 dirty pages from their submits' captures, 94961 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): 1526 dispatches, 58880 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8016 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23703 in captures, 10 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2660000 (1153392 pages from the captures)
[hos host] vk: render targets drawn over from another start, let go: 1688 so far (1594 MB), 1462 of them (1395 MB) between the passes
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1371 dirty pages from their submits' captures, 94798 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): 1530 dispatches, 58946 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8018 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23767 in captures, 13 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8922 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1521993 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 2680000 (1160448 pages from the captures)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #105000: event 0x100c318024 mode 0 value 105000 (lr 0x80665068)
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 432 ranges, 3563 MB), 359 pages written, 359 copied (1.4 MB)
[hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 25 kept (142 MB), 11 spare buffers, 5462 texture pages copied (21 MB)
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.61, present 0.10, draw 3.71, descriptors 1.52, texture lookups 0.04, uploads 0.00, pipelines 0.18, programs 0.46, commands 1.23, dispatch 0.78, memory sync 0.32, queue submit 0.47, slot wait 0.25
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.82 MB synced in 1208.3 copies, 24.10 MB written back
[hos host] vk: 7440 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 756 textures (1834 MB)
[hos host] vk: host time in GPU resource waits: 0.10 ms a frame (fences 0.03, timelines 0.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.5 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1331 dirty pages from their submits' captures, 94812 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): 1527 dispatches, 58873 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8013 runs, 1150.6 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23695 in captures, 15 only in the collection, 47 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2700000 (1167409 pages from the captures)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #145000: event 0x100c318028 mode 0 value 106103 (now 106084) (lr 0x80a47c2c)
[hos ModuleSystemWorker4] nvn: DrawMeshTasks: 260000 so far (x1 0 x2 0x10 x3 0x108b342540 x4 0x40)
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1200 dirty pages from their submits' captures, 95043 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): 1525 dispatches, 58873 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8021 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23711 in captures, 11 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: program picks: 4468288 kept (2024127 by the last picks' textures, a uniform buffer bound since), 19992 new, 1511719 with other textures (of 6000000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos sead::MainThread] nvn: EventSignal (CPU) #15000: event 0x1005a88004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9334 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vi: 7508 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 292, 17.8-22 7, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1436 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 ModuleSystemWorker1] vk: invalidates since the last readbacks line: 1370 kept their virtual core (nothing there to wait for), 2982 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: replay reads of guest memory as submitted: 2720000 (1174818 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 432 ranges, 3563 MB), 361 pages written, 361 copied (1.4 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 0.008, bytes copied 0.000; 25 kept (142 MB), 9 spare buffers, 5462 texture pages copied (21 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 375 KB; 0 made on demand (0 MB kept now); c1 stages: at most 159 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1118 dirty pages from their submits' captures, 94417 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): 1522 dispatches, 58724 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8004 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23685 in captures, 15 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.65, present 0.09, draw 3.71, descriptors 1.49, texture lookups 0.05, uploads 0.01, pipelines 0.18, programs 0.46, commands 1.25, dispatch 0.80, memory sync 0.33, queue submit 0.46, slot wait 0.26
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.81 MB synced in 1207.4 copies, 24.10 MB written back
[hos host] vk: 7560 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 762 textures (1841 MB)
[hos host] vk: host time in GPU resource waits: 0.14 ms a frame (fences 0.03, timelines 0.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.4 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos BaseProcExecutor2] vcores: 209190 takes, 22269 waits (mean 27 us, longest 5.1 ms, 0 over HOS_VCORE_LOG_MS), 12233 kicks, 12013 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker1] nvn: 950000 recordings made, 57963 live copies (14.2 MB), 842 texture copies; 7 command buffers' segments (4.4 MB)
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1187 dirty pages from their submits' captures, 94573 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): 1526 dispatches, 58882 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8018 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23737 in captures, 8 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: replay reads of guest memory as submitted: 2740000 (1181954 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 6243 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1266 dirty pages from their submits' captures, 94424 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): 1525 dispatches, 58889 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8015 runs, 1151.0 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23755 in captures, 11 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 433 ranges, 3569 MB), 362 pages written, 362 copied (1.4 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 0.008, bytes copied 0.000; 25 kept (144 MB), 8 spare buffers, 5496 texture pages copied (21 MB)
[hos host] vk: replay reads of guest memory as submitted: 2760000 (1189049 pages from the captures)
[hos host] vk: program picks: 4619687 kept (2091510 by the last picks' textures, a uniform buffer bound since), 20149 new, 1560163 with other textures (of 6200000)
[hos host] vk: readback pages refreshed from guest memory: 1589700 pages so far (0 held: may be written ahead in their submission)
[hos rmbl::VibrationThread] hid: 24576 vibration values, strongest 0.00 since the last count
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.56, present 0.10, draw 3.66, descriptors 1.50, texture lookups 0.04, uploads 0.00, pipelines 0.18, programs 0.44, commands 1.22, dispatch 0.79, memory sync 0.31, queue submit 0.47, slot wait 0.25
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.79 MB synced in 1207.5 copies, 24.10 MB written back
[hos host] vk: 7680 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 764 textures (1841 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.03, timelines 0.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.1 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1160 dirty pages from their submits' captures, 94499 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): 1526 dispatches, 58854 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8019 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23690 in captures, 9 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #150000: event 0x100c318028 mode 0 value 109903 (now 109884) (lr 0x80a47c2c)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1459 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 ModuleSystemWorker2] vk: invalidates since the last readbacks line: 1400 kept their virtual core (nothing there to wait for), 2952 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos sead::MainThread] nvn: CommandBufferSignalEvent #110000: event 0x100c31802c mode 0 value 109999 (lr 0x80667688)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: replay reads of guest memory as submitted: 2780000 (1196210 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4230 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1235 dirty pages from their submits' captures, 94375 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): 1528 dispatches, 58844 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8012 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23708 in captures, 11 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 433 ranges, 3569 MB), 364 pages written, 364 copied (1.4 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 0.009, bytes copied 0.000; 25 kept (114 MB), 8 spare buffers, 5496 texture pages copied (21 MB)
[hos host] vk: replay reads of guest memory as submitted: 2800000 (1203330 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 375 KB; 0 made on demand (0 MB kept now); c1 stages: at most 159 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1175 dirty pages from their submits' captures, 94449 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): 1527 dispatches, 58806 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8019 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23696 in captures, 9 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: queues ordered by their events: 48000 submissions stopped at a wait, 47984 went on once it was reached, 14 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.26 ms at most); waits met 152411, not met 0; captures at a CPU event's wait 1534, 0 of them at a wait met on arrival
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: memory: working set 16215 MB (peak 16215), private 21977 MB, staging 256 MB in 16 arenas, 38 made so far (102 ms)
[hos host] vk: memory heaps: heap 0 (system): 17 blocks 864 MB, 39 allocations 788 MB; used 3176 of 15571 MB; heap 1 (device): 127 blocks 4085 MB, 17174 allocations 3593 MB; used 5136 of 15419 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 6 images 23 MB; 2 free ranges, the largest 4 MB
[hos host] vk: image blocks (render targets): 10 blocks 320 MB, 108 images 144 MB; 58 free ranges, the largest 23 MB
[hos host] vk: image blocks (textures, compacted): 27 blocks 864 MB, 649 images 835 MB; 118 free ranges, the largest 8 MB
[hos host] vk: render target images: 865 reused from the pool, 1025 made new, 913 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 5136 MB used of 15419 MB allowed (491 MB of it free in the blocks); textures 1841 MB (budget 11000 MB), 764 textures
[hos host] vk: textures: decoded ASTC 839 MB, rendered 414 MB (97 drawn in one frame, kept: 50019 KB), other 265 MB; used in the last 8 presents 1202 MB
[hos host] vk: decoded ASTC used again: 318 textures (1268 MB) copied from ones the game finalized, not decoded; 318 of those retired, 7 listed; 1640 MB of blocks hashed in 198 ms
[hos host] vk:   214 MB: 0x10a4772c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a0efa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x11361ac000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113b7bd000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10001646400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1088 presents ago
[hos host] vk:   54 MB: 0x100014ddc00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   37 MB: 0x110791f000 1800x1380x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk:   21 MB: 0x10005006800 2400x2400x1 x1 levels 1 NVN 0x34, last used 800 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 9 (854 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 2 (75 KB); 260x260x1 NVN 0xd: 4 (703 KB); 306x104x1 NVN 0x1: 1 (31 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 4 waited for it, 0.07 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 21.1 ms; VRAM 5.0 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: 30 program records loaded (56.1 ms), 8 new graphics pipelines, pipelines from the driver's cache 68, from the start's cache 0, compiled 5; 45 draws and dispatches left out, 4 waits (451.6 ms)
[hos host] vk: program loads at create (play): 5123 queued, 5123 loaded (median 0.61 ms, 99th percentile 4.36 ms, worst 27.72 ms, 4793 ms and 1076.8 MB read in all); 6952 programs (1152 of them compute variants without their code, 0 graphics programs no note names), 8752 graphics pipelines (0 not in a cache), 627 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1476 pipelines made at create taken by draws; 2639 create calls with nothing kept for their stages, 0 before the index; units 7762 (5123 ready, 0 loading), 13438 programs alive
[hos host] vk: module identifiers (play): 692 known, 692 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: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.63, present 0.10, draw 3.68, descriptors 1.48, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.46, commands 1.23, dispatch 0.78, memory sync 0.36, queue submit 0.46, slot wait 0.25
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.79 MB synced in 1207.0 copies, 24.10 MB written back
[hos host] vk: 7800 presents, 59.9 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 764 textures (1841 MB)
[hos host] vk: host time in GPU resource waits: 0.14 ms a frame (fences 0.03, timelines 0.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.4 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 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, 16.67 ms a frame): its jobs 7.18 ms a frame (submits 6.98, presents 0.10, others 0.10), idle 9.49; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 112.83 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); 5 captures at a CPU signal; the submits' waits read in 0.030 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 7.20 ms after its hand-over (9.84 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 10.22 + 0.35 (the window's copy is in the idle), after it 0.73 + 0.21; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.01 ms of GPU time), after its last that reads it 1.00 (0.01 ms)
[hos host] vk: frame ahead (600 presents): 6.80 parts a frame recorded in the signal's job, 67.6% of them took nothing that came with the signal; of the others, 2.20 a frame took pages of the signal's capture into a mirror (6.2 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 0 of 5 frames, its first three in 0
[hos host] vk: frame ahead, what came with the signal: 5 signals with a capture, each of 8.4 pages in 6.2 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any)
[hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.54+0.12, 0.01+0.01, 0.01+0.02, 0.03+0.02, 0.13+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, 0.00+0.00
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 16273 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 2820000 (1210629 pages from the captures)
[hos host] vk: program picks: 4771352 kept (2158917 by the last picks' textures, a uniform buffer bound since), 20306 new, 1608341 with other textures (of 6400000)
[hos Presentation Thread] vi: 7809 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 1, 15.5-17.8 295, 17.8-22 5, 22-30 0, 30-40 0, over 40 0
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1171 dirty pages from their submits' captures, 95063 from earlier ones', 24 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): 1527 dispatches, 58901 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8015 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23687 in captures, 9 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool: 0x1064400000 (8 MB, captured, state 2): 24;
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 433 ranges, 3569 MB), 371 pages written, 371 copied (1.5 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 0.014, bytes copied 0.000; 25 kept (128 MB), 8 spare buffers, 6093 texture pages copied (23 MB)
[hos host] vk: replay reads of guest memory as submitted: 2840000 (1217650 pages from the captures)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1438 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 ModuleSystemWorker2] vk: invalidates since the last readbacks line: 1482 kept their virtual core (nothing there to wait for), 3126 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos nn.npln.Worker] vcores: 208326 takes, 22430 waits (mean 25 us, longest 2.8 ms, 0 over HOS_VCORE_LOG_MS), 12139 kicks, 11952 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1281 dirty pages from their submits' captures, 94851 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): 1526 dispatches, 58848 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8018 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23712 in captures, 10 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 280000 so far (x1 0x117cbdb050 x2 0 x3 0x117cbdb040 x4 0x44b040)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #155000: event 0x100c318028 mode 0 value 113703 (now 113684) (lr 0x80a47c2c)
[hos host] vk: recorder: 3893252 packets run in 10.0 s (busy 1.05 s, spun idle 3.12 s, slept 3580 times, 744 of them under 200 us), 0 calls made directly (no room); the replay waited for it 22209 times, 78.20 ms in all, the longest 0.10 ms; vkResetDescriptorPool 7505/43.06 ms (max 0.09), vkEndCommandBuffer 7505/19.39 ms (max 0.07), replay_mu unlock 7199/15.76 ms (max 0.10)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 4090 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 1657443 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 2860000 (1224679 pages from the captures)
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.53, present 0.10, draw 3.67, descriptors 1.49, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.44, commands 1.24, dispatch 0.78, memory sync 0.32, queue submit 0.46, slot wait 0.25
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.82 MB synced in 1207.5 copies, 24.10 MB written back
[hos host] vk: 7920 presents, 60.1 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 764 textures (1841 MB)
[hos host] vk: host time in GPU resource waits: 0.11 ms a frame (fences 0.02, timelines 0.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.4 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1119 dirty pages from their submits' captures, 94990 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): 1521 dispatches, 58844 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 7869 runs, 1127.7 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23661 in captures, 14 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 433 ranges, 3569 MB), 364 pages written, 364 copied (1.4 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 0.009, bytes copied 0.000; 25 kept (130 MB), 7 spare buffers, 6092 texture pages copied (23 MB)
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #115000: event 0x100c318038 mode 0 value 114999 (lr 0x8066189c)
[hos host] vk: program picks: 4923192 kept (2226379 by the last picks' textures, a uniform buffer bound since), 20463 new, 1656344 with other textures (of 6600000)
[hos host] vk: replay reads of guest memory as submitted: 2880000 (1231689 pages from the captures)
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1425 dirty pages from their submits' captures, 94829 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): 1529 dispatches, 58947 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8020 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23750 in captures, 8 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: render targets drawn over from another start, let go: 1688 so far (1594 MB), 1462 of them (1395 MB) between the passes
[hos sead::MainThread] nvn: GPU waits in 5 s: 1 sync waits (1 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 0.03, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 23850 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 2900000 (1238700 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 375 KB; 0 made on demand (0 MB kept now); c1 stages: at most 159 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1128, 4841.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1231 dirty pages from their submits' captures, 93003 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): 1503 dispatches, 57581 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8011 runs, 1151.1 MB compared; 77 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23204 in captures, 16 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1439 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 ModuleSystemWorker1] vk: invalidates since the last readbacks line: 1396 kept their virtual core (nothing there to wait for), 2956 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: capture: a submit 0.17 ms (lock 0.01, scan 0.04 over 434 ranges, 3571 MB), 387 pages written, 387 copied (1.5 MB)
[hos host] vk: a capture taken (ms): all 0.027; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.024, bytes copied 0.000; 25 kept (122 MB), 9 spare buffers, 9881 texture pages copied (38 MB)
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.59, present 0.09, draw 3.64, descriptors 1.49, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.44, commands 1.21, dispatch 0.79, memory sync 0.39, queue submit 0.45, slot wait 0.24
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.83 MB synced in 1206.8 copies, 24.10 MB written back
[hos host] vk: 8040 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 768 textures (1842 MB)
[hos host] vk: host time in GPU resource waits: 0.22 ms a frame (fences 0.02, 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: 400.5 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.4 ms a frame (the longest submission 3.6 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1195 dirty pages from their submits' captures, 95051 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): 1526 dispatches, 58744 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8018 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23680 in captures, 15 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos host] vk: replay reads of guest memory as submitted: 2920000 (1245685 pages from the captures)
[hos ModuleSystemWorker5] nvn: 1000000 recordings made, 57974 live copies (15.5 MB), 842 texture copies; 2 command buffers' segments (4.1 MB)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #160000: event 0x100c318028 mode 0 value 117503 (now 117484) (lr 0x80a47c2c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8079 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos Presentation Thread] vi: 8110 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 3, 15.5-17.8 293, 17.8-22 5, 22-30 0, 30-40 0, over 40 0
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1161 dirty pages from their submits' captures, 94899 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): 1524 dispatches, 58709 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8014 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23676 in captures, 13 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 5074708 kept (2293723 by the last picks' textures, a uniform buffer bound since), 20620 new, 1704671 with other textures (of 6800000)
[hos host] vk: replay reads of guest memory as submitted: 2940000 (1253109 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.16 ms (lock 0.01, scan 0.04 over 434 ranges, 3571 MB), 358 pages written, 358 copied (1.4 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 0.008, bytes copied 0.000; 25 kept (100 MB), 8 spare buffers, 1995 texture pages copied (7 MB)
[hos host] vk: readback pages refreshed from guest memory: 1724954 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a frame: 125 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 93 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 6.51, present 0.10, draw 3.64, descriptors 1.49, texture lookups 0.04, uploads 0.00, pipelines 0.17, programs 0.45, commands 1.22, dispatch 0.78, memory sync 0.32, queue submit 0.45, slot wait 0.24
[hos host] vk: a frame: mirrors 289 (1011 MB): 7.81 MB synced in 1204.5 copies, 24.10 MB written back
[hos host] vk: 8160 presents, 60.0 fps; a frame: 1180 draws (0 skipped), 145 dispatches, 142 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 41765 pipelines (25513 ms), 0 programs (12 failed), 768 textures (1842 MB)
[hos host] vk: host time in GPU resource waits: 0.09 ms a frame (fences 0.03, timelines 0.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 400.3 full barriers recorded, 174.4 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: sparse mirrors: 58, 1011 MB with memory of 1304 MB (293 MB spared); blocks given memory later 15462, given back 13705; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 837 binds (341.8 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 144 taken from the spares, 145 made new; 231 kept as spares, 0 destroyed; 87 spares now, 1408 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 4944.4 MB; 32 bindings followed, 35 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1256 dirty pages from their submits' captures, 94483 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): 1529 dispatches, 58717 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8020 runs, 1151.1 MB compared; 78 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 23737 in captures, 9 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 139 live (2024 MB), 16 retired still imported (272 MB), 45 retired given back (892 MB)
[hos tera::FileResourceMgr] vcores: 210410 takes, 22814 waits (mean 26 us, longest 3.0 ms, 0 over HOS_VCORE_LOG_MS), 12466 kicks, 12263 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 2960000 (1260270 pages from the captures)
[hos ModuleSystemWorker5] tex: the game's texture heap: 129 compaction rounds asked for in 7200 frames without one running
[hos host] vk: slow present: 15.6 ms:
[hos host] vk: present 8191 written to <home>\AppData\Local\<user>\data\jobs\jb_2505e84d188607ea\runs\outlines-and-fps-g0-01-pr\shots/outlines-and-fps-c1-pr-01-field-outline.png (the control bridge)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.04
[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: 30 program records loaded (56.1 ms), 8 new graphics pipelines, pipelines from the driver's cache 68, from the start's cache 0, compiled 5; 45 draws and dispatches left out, 4 waits (451.6 ms)
[hos host] vk: program loads at create (close): 5123 queued, 5123 loaded (median 0.61 ms, 99th percentile 4.36 ms, worst 27.72 ms, 4793 ms and 1076.8 MB read in all); 6952 programs (1152 of them compute variants without their code, 0 graphics programs no note names), 8752 graphics pipelines (0 not in a cache), 627 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1476 pipelines made at create taken by draws; 2639 create calls with nothing kept for their stages, 0 before the index; units 7762 (5123 ready, 0 loading), 13438 programs alive
[hos host] vk: module identifiers (close): 692 known, 692 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 (4304 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)