Beanstalk Longshot test farm
Menu

Report rp_b854f1dd81aaa143 pass

#1574 perf(vk): RX_VK_ACQUIRE_AHEAD=1 asks for the window's next image right after a present, so the render thread no longer waits for it (off by default)

nvidia on jabbaxipil/Blaine,

This report disagrees with its peers.

field-acquire-ahead field.frametime_1pct_low_ms: +5.4% against peers' +31.4%
field-acquire-ahead field.frametime_max_ms: +43.7% against peers' +9.4%
field-default field.frametime_max_ms: +9.5% against peers' +35.8%

Machine

Commit
2f24a499ca2a8fc708008cdb350c09fea17e9ea0
Baseline
430eef4f2cc94e398b06d0daeb585a679d3ebcda
App
nightly-166-e4316243, attempt 7
Game build
e0f3ccfa
os
linux
cpu
AMD Ryzen 7 5800X3D 8-Core Processor
gpu
NVIDIA GeForce RTX 4070
tags
linuxnvidianvidia-proprietarydgpu
driver
615.71.9
ram_gb
64
vram_mb
12,282
gpu_vendor
nvidia
os_version
Ubuntu 26.04.1 LTS (kernel 7.0.0)

Builds

main (baseline)

0 s warm

from 430eef4f2cc9

the base was built already

PR

82.4 s warm

Program cache: warm

Scenarios

field-default

ok
Metric (median)mainPRΔ
exit_code00±0%
field.fps_mean59.9959.99±0%
field.draws_mean1,194.41,192.1−0.2%
field.hitch_count00±0%
log_forbidden_hits00±0%
field.stutter_count00±0%
log_expected_missing00±0%
field.frametime_max_ms23.9426.23+9.5%
field.frametime_p50_ms16.7316.61−0.7%
field.frametime_p99_ms18.9118.96+0.3%
field.frametime_1pct_low_ms19.7220.01+1.5%
screenshot_diff—0—

Pictures against main: field-default diff 0 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
field.fps_mean59.9959.99
field.draws_mean1,194.41,192.1
field.hitch_count00
log_forbidden_hits00
field.stutter_count00
log_expected_missing00
field.frametime_max_ms23.9426.23
field.frametime_p50_ms16.7316.61
field.frametime_p99_ms18.9118.96
field.frametime_1pct_low_ms19.7220.01
screenshot_diff—0

field-acquire-ahead RX_VK_ACQUIRE_AHEAD=1 (PR only)

ok
Metric (median)mainPRΔ
exit_code00±0%
field.fps_mean59.9960+0%
field.draws_mean1,196.21,194.4−0.2%
field.hitch_count00±0%
log_forbidden_hits00±0%
field.stutter_count01—
log_expected_missing00±0%
field.frametime_max_ms23.934.34+43.7%
field.frametime_p50_ms16.6216.71+0.5%
field.frametime_p99_ms18.5918.92+1.8%
field.frametime_1pct_low_ms19.3620.41+5.4%
screenshot_diff—0—

Pictures against main: field-ahead diff 0 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
field.fps_mean59.9960
field.draws_mean1,196.21,194.4
field.hitch_count00
log_forbidden_hits00
field.stutter_count01
log_expected_missing00
field.frametime_max_ms23.934.34
field.frametime_p50_ms16.6216.71
field.frametime_p99_ms18.5918.92
field.frametime_1pct_low_ms19.3620.41
screenshot_diff—0

Rules

ScenarioCellRuleLimitmainPRΔ %Status
field-defaultcrashFalse00—pass
field-defaultfield.fps_mean.min_delta_pct059.9959.99±0%pass
field-defaultscreenshot.max_diff0.05—0—pass
field-defaultlog_forbidden_hits.max000—pass
field-acquire-aheadRX_VK_ACQUIRE_AHEAD=1 (PR only)crashFalse00—pass
field-acquire-aheadRX_VK_ACQUIRE_AHEAD=1 (PR only)field.fps_mean.min_delta_pct059.9960±0%pass
field-acquire-aheadRX_VK_ACQUIRE_AHEAD=1 (PR only)screenshot.max_diff0.05—0—pass
field-acquire-aheadRX_VK_ACQUIRE_AHEAD=1 (PR only)log_forbidden_hits.max000—pass

Log (PR side, end)

[hos Presentation Thread] vi: 12232 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: program picks: 10591373 kept (4823525 by the last picks' textures, a uniform buffer bound since), 1598 new, 3407028 with other textures (of 14000000)
[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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.55, present 0.12, draw 2.48, descriptors 0.99, texture lookups 0.04, uploads 0.00, pipelines 0.12, programs 0.33, commands 0.80, dispatch 0.55, memory sync 0.30, queue submit 0.19, slot wait 0.03
[hos host] vk: a frame: mirrors 134 (849 MB): 5.98 MB synced in 918.7 copies, 18.42 MB written back
[hos host] vk: 12240 presents, 60.0 fps; a frame: 1196 draws (0 skipped), 146 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.28 ms a frame (fences 0.02, timelines 0.27, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 404.5 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 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 recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 69 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1076 dirty pages from their submits' captures, 72692 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): 1352 dispatches, 44629 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8362 runs, 884.1 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26471 in captures, 4 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 24;
[hos sead::MainThread] nvn: CommandBufferSignalEvent #205000: event 0x100d6c8028 mode 0 value 204999 (lr 0x80667410)
[hos host] vk: render targets drawn over from another start, let go: 603 so far (1261 MB), 526 of them (1082 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 4200000 (1626086 pages from the captures)
[hos ModuleSystemWorker1] tex: the game's texture heap: 194 compaction rounds asked for in 10800 frames without one running
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 226 binds (84.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 73 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1174 dirty pages from their submits' captures, 72457 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): 1351 dispatches, 44681 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8337 runs, 883.7 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26507 in captures, 2 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #275000: event 0x100d6c8008 mode 0 value 205827 (now 205808) (lr 0x8027944c)
[hos host] vk: readback pages refreshed from guest memory: 3105518 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker1] vcores: 108445 takes, 13584 waits (mean 37 us, longest 3.3 ms, 0 over HOS_VCORE_LOG_MS), 5831 kicks, 5723 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 311 pages written, 311 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker4] nvn: 1300000 recordings made, 43664 live copies (15.7 MB), 429 texture copies; 3 command buffers' segments (4.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 4220000 (1633335 pages from the captures)
[hos host] vk: recorder: 4798475 packets run in 10.0 s (busy 0.97 s, spun idle 2.04 s, slept 4310 times, 682 of them under 200 us), 0 calls made directly (no room); the replay waited for it 22193 times, 69.96 ms in all, the longest 0.22 ms; vkEndCommandBuffer 7514/36.92 ms (max 0.13), replay_mu unlock 7203/18.16 ms (max 0.07), vkResetDescriptorPool 7475/14.88 ms (max 0.22), vkQueueBindSparse 1/0.00 ms (max 0.00)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1547 of 3000 waited for their write-back, 0.03 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: 1461 kept their virtual core (nothing there to wait for), 3147 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, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1115 dirty pages from their submits' captures, 72868 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): 1350 dispatches, 44658 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8301 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26460 in captures, 0 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.57, present 0.12, draw 2.46, descriptors 0.99, texture lookups 0.03, uploads 0.00, pipelines 0.12, programs 0.33, commands 0.79, dispatch 0.54, memory sync 0.37, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 134 (849 MB): 6.02 MB synced in 919.9 copies, 18.41 MB written back
[hos host] vk: 12360 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.29 ms a frame (fences 0.01, timelines 0.28, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.4 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4240000 (1640598 pages from the captures)
[hos host] vk: program picks: 10742011 kept (4890924 by the last picks' textures, a uniform buffer bound since), 1598 new, 3456390 with other textures (of 14200000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 226 binds (84.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 73 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 912 dirty pages from their submits' captures, 72792 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): 1350 dispatches, 44578 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8296 runs, 882.2 MB compared; 77 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26438 in captures, 2 only in the collection, 47 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 314 pages written, 314 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 4260000 (1647873 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1233 dirty pages from their submits' captures, 72467 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): 1346 dispatches, 44624 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8298 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26433 in captures, 2 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.53, present 0.12, draw 2.46, descriptors 0.97, texture lookups 0.04, uploads 0.00, pipelines 0.12, programs 0.33, commands 0.80, dispatch 0.54, memory sync 0.32, queue submit 0.18, slot wait 0.03
[hos host] vk: a frame: mirrors 134 (849 MB): 6.00 MB synced in 918.5 copies, 18.40 MB written back
[hos host] vk: 12480 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.37 ms a frame (fences 0.02, timelines 0.35, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.3 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4280000 (1655100 pages from the captures)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 69 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 226 binds (84.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 73 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1084 dirty pages from their submits' captures, 72883 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): 1350 dispatches, 44627 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8302 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26425 in captures, 2 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos sead::MainThread] nvn: EventSignal (CPU) #25000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #280000: event 0x100d6c8008 mode 0 value 209627 (now 209608) (lr 0x8027944c)
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1546 of 3000 waited for their write-back, 0.04 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: 1198 kept their virtual core (nothing there to wait for), 2642 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 313 pages written, 313 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #210000: event 0x100d6c8034 mode 0 value 209999 (lr 0x806616b0)
[hos Presentation Thread] vi: 12533 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 560000 so far (x1 0x11789aa000 x2 0x1 x3 0x11789aa000 x4 0x4040)
[hos host] vk: replay reads of guest memory as submitted: 4300000 (1662298 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1255 dirty pages from their submits' captures, 72290 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): 1350 dispatches, 44591 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8302 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26446 in captures, 0 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: program picks: 10893036 kept (4958141 by the last picks' textures, a uniform buffer bound since), 1598 new, 3505365 with other textures (of 14400000)
[hos host] vk: readback pages refreshed from guest memory: 3173530 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 226 binds (84.0 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 73 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1268 dirty pages from their submits' captures, 72329 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): 1350 dispatches, 44644 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8302 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26455 in captures, 0 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: replay reads of guest memory as submitted: 4320000 (1669942 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos host] vk: memory: working set 18724 MB (peak 19443), private 10461 MB, staging 32 MB in 2 arenas, 20 made so far (10 ms)
[hos host] vk: memory heaps: heap 0 (device): 211 blocks 7017 MB, 15833 allocations 6200 MB; used 8054 of 10974 MB; heap 1 (system): 14 blocks 776 MB, 40 allocations 674 MB; used 2488 of 48166 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 5 images 16 MB; 1 free ranges, the largest 15 MB
[hos host] vk: image blocks (render targets): 16 blocks 512 MB, 107 images 248 MB; 52 free ranges, the largest 30 MB
[hos host] vk: image blocks (textures, compacted): 98 blocks 3136 MB, 1869 images 3093 MB; 987 free ranges, the largest 4 MB
[hos host] vk: render target images: 218 reused from the pool, 496 made new, 382 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 8054 MB used of 10974 MB allowed (816 MB of it free in the blocks); textures 4780 MB (budget 7164 MB), 1991 textures
[hos host] vk: textures: decoded ASTC 2935 MB, rendered 957 MB (90 drawn in one frame, kept: 40125 KB), other 602 MB; used in the last 8 presents 1329 MB
[hos host] vk: decoded ASTC used again: 180 textures (649 MB) copied from ones the game finalized, not decoded; 180 of those retired, 547 listed; 840 MB of blocks hashed in 88 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 10919 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10002ff0200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 10762 presents ago
[hos host] vk:   54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 10919 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (351 KB): 260x260x1 NVN 0xd: 2 (351 KB);
[hos host] vk: malloc: 11456 MB in arenas (10031 MB in use, 1425 MB free, 0 MB of it at the tops), 6 MB mapped
[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 19.0 ms; VRAM 7.9 of 10.7 GB
[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 0 ms in all, 1 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.55, present 0.14, draw 2.47, descriptors 1.00, texture lookups 0.03, uploads 0.00, pipelines 0.12, programs 0.34, commands 0.79, dispatch 0.54, memory sync 0.33, queue submit 0.18, slot wait 0.03
[hos host] vk: a frame: mirrors 134 (849 MB): 5.99 MB synced in 918.5 copies, 18.40 MB written back
[hos host] vk: 12600 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.34 ms a frame (fences 0.02, timelines 0.32, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.1 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 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 4.96 ms a frame (submits 4.75, presents 0.13, others 0.08), idle 11.71; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 112.24 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 0.028 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 4.98 ms after its hand-over (7.12 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 9.14 + 0.34 (the window's copy is in the idle), after it 0.32 + 0.27; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 6.20 parts a frame recorded in the signal's job, 71.0% of them took nothing that came with the signal; of the others, 1.80 a frame took pages of the signal's capture into a mirror (8.0 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 9.0 pages in 3.8 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: 0.25+0.08, 0.01+0.02, 0.01+0.06, 0.01+0.05, 0.01+0.03, 0.01+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos host] vk: malloc_trim: 1425 MB free in the arenas now, the process's private memory 10461 -> 10452 MB (22 ms)
[hos tera::FileResourceMgr] vcores: 108753 takes, 13427 waits (mean 37 us, longest 3.7 ms, 0 over HOS_VCORE_LOG_MS), 5824 kicks, 5760 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 314 pages written, 314 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1153 dirty pages from their submits' captures, 72233 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): 1350 dispatches, 44574 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8306 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26440 in captures, 1 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: 4340000 (1677384 pages from the captures)
[hos host] vk: mirror of pool 0x7f6b000000 (12 MB) given back: idle, 6025 submissions since its sync
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1550 of 3000 waited for their write-back, 0.04 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos ModuleSystemWorker4] vk: invalidates since the last readbacks line: 1441 kept their virtual core (nothing there to wait for), 3167 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: sparse mirrors: 60, 838 MB with memory of 1192 MB (353 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 227 binds (84.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 52 spares now, 1032 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1123 dirty pages from their submits' captures, 71734 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): 1350 dispatches, 44486 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8300 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26366 in captures, 5 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos host] vk: program picks: 11043744 kept (5025556 by the last picks' textures, a uniform buffer bound since), 1598 new, 3554657 with other textures (of 14600000)
[hos host] vk: replay reads of guest memory as submitted: 4360000 (1684837 pages from the captures)
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #285000: event 0x100d6c8008 mode 0 value 213427 (now 213408) (lr 0x8027944c)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 314 pages written, 314 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 11 spare buffers, 0 texture pages copied (0 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.61, present 0.12, draw 2.54, descriptors 1.03, texture lookups 0.04, uploads 0.00, pipelines 0.12, programs 0.34, commands 0.83, dispatch 0.55, memory sync 0.36, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 134 (838 MB): 5.96 MB synced in 917.2 copies, 18.40 MB written back
[hos host] vk: 12720 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.37 ms a frame (fences 0.01, timelines 0.36, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.2 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 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 recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 69 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1177 dirty pages from their submits' captures, 72219 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): 1350 dispatches, 44562 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8303 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26431 in captures, 2 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: 4380000 (1692309 pages from the captures)
[hos host] vk: sparse mirrors: 60, 838 MB with memory of 1192 MB (353 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 227 binds (84.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 52 spares now, 1032 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1125 dirty pages from their submits' captures, 71649 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): 1347 dispatches, 44275 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8212 runs, 881.6 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26419 in captures, 3 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #215000: event 0x100d6c8018 mode 0 value 214989 (lr 0x802911b8)
[hos host] vk: readback pages refreshed from guest memory: 3241152 pages so far (0 held: may be written ahead in their submission)
[hos rmbl::VibrationThread] hid: 40960 vibration values, strongest 0.00 since the last count
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos sead::MainThread] nvn: 1350000 recordings made, 43664 live copies (14.6 MB), 429 texture copies; 2 command buffers' segments (4.1 MB)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 310 pages written, 310 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 4400000 (1699800 pages from the captures)
[hos host] vk: queues ordered by their events: 84000 submissions stopped at a wait, 83998 went on once it was reached, 0 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 0 (stopped 0.00 ms at most); waits met 287816, not met 0; captures at a CPU event's wait 487, 0 of them at a wait met on arrival
[hos Presentation Thread] vi: 12833 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 300, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 883 dirty pages from their submits' captures, 72154 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): 1350 dispatches, 44520 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8233 runs, 867.4 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26419 in captures, 2 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.58, present 0.13, draw 2.51, descriptors 1.00, texture lookups 0.03, uploads 0.00, pipelines 0.12, programs 0.34, commands 0.82, dispatch 0.54, memory sync 0.32, queue submit 0.17, slot wait 0.05
[hos host] vk: a frame: mirrors 134 (838 MB): 5.95 MB synced in 917.1 copies, 18.40 MB written back
[hos host] vk: 12840 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.39 ms a frame (fences 0.02, timelines 0.37, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.4 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 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: program picks: 11194451 kept (5092836 by the last picks' textures, a uniform buffer bound since), 1598 new, 3603950 with other textures (of 14800000)
[hos ModuleSystemWorker1] vk: readbacks of GPU results: 1549 of 3000 waited for their write-back, 0.04 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: 1496 kept their virtual core (nothing there to wait for), 3112 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: render targets drawn over from another start, let go: 603 so far (1261 MB), 526 of them (1082 MB) between the passes
[hos host] vk: replay reads of guest memory as submitted: 4420000 (1707422 pages from the captures)
[hos host] vk: sparse mirrors: 60, 838 MB with memory of 1192 MB (353 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 227 binds (84.1 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 22 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 52 spares now, 1032 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 957 dirty pages from their submits' captures, 72577 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): 1344 dispatches, 44472 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8299 runs, 883.2 MB compared; 77 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 25879 in captures, 2 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool: 0x1065800000 (8 MB, captured, state 2): 24;
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #290000: event 0x100d6c8008 mode 0 value 217227 (now 217208) (lr 0x8027944c)
[hos nn.npln.Callback] vcores: 108206 takes, 13221 waits (mean 37 us, longest 3.1 ms, 0 over HOS_VCORE_LOG_MS), 5845 kicks, 5720 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 313 pages written, 313 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: replay reads of guest memory as submitted: 4440000 (1714631 pages from the captures)
[hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 580000 so far (x1 0x117ccee000 x2 0 x3 0x117ccee000 x4 0x230040)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 912 dirty pages from their submits' captures, 72713 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): 1350 dispatches, 44595 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8303 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26456 in captures, 1 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: recorder: 4772063 packets run in 10.0 s (busy 0.96 s, spun idle 2.04 s, slept 4294 times, 676 of them under 200 us), 0 calls made directly (no room); the replay waited for it 22176 times, 70.29 ms in all, the longest 0.25 ms; vkEndCommandBuffer 7507/36.70 ms (max 0.18), replay_mu unlock 7202/18.05 ms (max 0.25), vkResetDescriptorPool 7467/15.54 ms (max 0.21)
[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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.62, present 0.12, draw 2.49, descriptors 1.00, texture lookups 0.04, uploads 0.00, pipelines 0.12, programs 0.33, commands 0.81, dispatch 0.55, memory sync 0.38, queue submit 0.18, slot wait 0.02
[hos host] vk: a frame: mirrors 135 (849 MB): 6.10 MB synced in 918.4 copies, 18.40 MB written back
[hos host] vk: 12960 presents, 60.0 fps; a frame: 1194 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.45 ms a frame (fences 0.01, timelines 0.44, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.4 full barriers recorded, 173.3 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: 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 6.6 ms a frame (the longest submission 2.9 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 recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 69 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 228 binds (84.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1013 dirty pages from their submits' captures, 71946 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): 1335 dispatches, 44086 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8301 runs, 883.2 MB compared; 81 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26432 in captures, 2 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: replay reads of guest memory as submitted: 4460000 (1721886 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.06
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 314 pages written, 314 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: program picks: 11344956 kept (5160304 by the last picks' textures, a uniform buffer bound since), 1598 new, 3653445 with other textures (of 15000000)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1201 dirty pages from their submits' captures, 72734 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): 1350 dispatches, 44593 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8304 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26448 in captures, 0 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: 4480000 (1729121 pages from the captures)
[hos ModuleSystemWorker5] vk: readbacks of GPU results: 1543 of 3000 waited for their write-back, 0.05 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 1317 kept their virtual core (nothing there to wait for), 2779 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos host] vk: readback pages refreshed from guest memory: 3308800 pages so far (0 held: may be written ahead in their submission)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #220000: event 0x100d6c800c mode 0 value 220002 (lr 0x80660adc)
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 228 binds (84.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1200 dirty pages from their submits' captures, 72138 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): 1350 dispatches, 44519 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8300 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26429 in captures, 3 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.60, present 0.12, draw 2.49, descriptors 1.00, texture lookups 0.03, uploads 0.00, pipelines 0.12, programs 0.33, commands 0.80, dispatch 0.54, memory sync 0.34, queue submit 0.19, slot wait 0.03
[hos host] vk: a frame: mirrors 135 (849 MB): 6.00 MB synced in 917.7 copies, 18.40 MB written back
[hos host] vk: 13080 presents, 60.0 fps; a frame: 1194 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.41 ms a frame (fences 0.02, timelines 0.39, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.4 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: replay reads of guest memory as submitted: 4500000 (1736376 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos sead::MainThread] nvn: CommandBufferWaitEvent #295000: event 0x100d6c8008 mode 0 value 221027 (now 221008) (lr 0x8027944c)
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 313 pages written, 313 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 12 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1139 dirty pages from their submits' captures, 72772 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): 1350 dispatches, 44639 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8299 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26474 in captures, 0 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos Presentation Thread] vi: 13134 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 301, 17.8-22 0, 22-30 0, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 4520000 (1743577 pages from the captures)
[hos host] vk: sparse mirrors: 61, 849 MB with memory of 1204 MB (354 MB spared); blocks given memory later 1188, given back 4451; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 228 binds (84.3 ms); 0 made whole for want of memory
[hos host] vk: sparse mirrors' buffers: 23 taken from the spares, 112 made new; 74 kept as spares, 0 destroyed; 51 spares now, 1020 MB of address space (RX_VK_SPARSE_SPARE_MB=4096)
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1146 dirty pages from their submits' captures, 72660 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): 1350 dispatches, 44604 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8300 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26457 in captures, 1 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 111 live (1692 MB), 0 retired still imported (0 MB), 20 retired given back (728 MB)
[hos host] vk: program picks: 11495448 kept (5227639 by the last picks' textures, a uniform buffer bound since), 1598 new, 3702953 with other textures (of 15200000)
[hos host] vk: replay reads of guest memory as submitted: 4540000 (1751296 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.00, writes collected 0.05
[hos host] vk: memory: working set 18724 MB (peak 19443), private 10460 MB, staging 32 MB in 2 arenas, 20 made so far (10 ms)
[hos host] vk: memory heaps: heap 0 (device): 211 blocks 7017 MB, 15833 allocations 6200 MB; used 8054 of 10974 MB; heap 1 (system): 14 blocks 776 MB, 40 allocations 674 MB; used 2488 of 48166 MB;
[hos host] vk: image blocks: 1 blocks 32 MB, 5 images 16 MB; 1 free ranges, the largest 15 MB
[hos host] vk: image blocks (render targets): 16 blocks 512 MB, 107 images 248 MB; 52 free ranges, the largest 30 MB
[hos host] vk: image blocks (textures, compacted): 98 blocks 3136 MB, 1869 images 3093 MB; 987 free ranges, the largest 4 MB
[hos host] vk: render target images: 218 reused from the pool, 496 made new, 382 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 8054 MB used of 10974 MB allowed (816 MB of it free in the blocks); textures 4780 MB (budget 7164 MB), 1991 textures
[hos host] vk: textures: decoded ASTC 2935 MB, rendered 957 MB (90 drawn in one frame, kept: 40125 KB), other 602 MB; used in the last 8 presents 1329 MB
[hos host] vk: decoded ASTC used again: 180 textures (649 MB) copied from ones the game finalized, not decoded; 180 of those retired, 547 listed; 840 MB of blocks hashed in 88 ms
[hos host] vk:   288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 11519 presents ago
[hos host] vk:   214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk:   214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk:   64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk:   64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x10002ff0200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 11362 presents ago
[hos host] vk:   54 MB: 0x10002fb3c00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk:   54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 11519 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 2 (351 KB): 260x260x1 NVN 0xd: 2 (351 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 4 waited for it, 0.10 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 18.8 ms; VRAM 7.9 of 10.7 GB
[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 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 4.54, present 0.13, draw 2.55, descriptors 1.03, texture lookups 0.03, uploads 0.00, pipelines 0.12, programs 0.34, commands 0.83, dispatch 0.54, memory sync 0.32, queue submit 0.18, slot wait 0.04
[hos host] vk: a frame: mirrors 135 (849 MB): 5.99 MB synced in 918.0 copies, 18.40 MB written back
[hos host] vk: 13200 presents, 60.0 fps; a frame: 1192 draws (0 skipped), 145 dispatches, 146 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); 32485 pipelines (4038777 ms), 0 programs (0 failed), 1991 textures (4780 MB)
[hos host] vk: host time in GPU resource waits: 0.35 ms a frame (fences 0.02, timelines 0.33, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 403.4 full barriers recorded, 173.4 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 6.6 ms a frame (the longest submission 2.9 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, 16.66 ms a frame): its jobs 4.96 ms a frame (submits 4.73, presents 0.13, others 0.10), idle 11.71; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 112.24 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); 7 captures at a CPU signal; the submits' waits read in 0.029 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 4.97 ms after its hand-over (7.17 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 9.15 + 0.34 (the window's copy is in the idle), after it 0.32 + 0.27; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms)
[hos host] vk: frame ahead (600 presents): 6.57 parts a frame recorded in the signal's job, 78.3% of them took nothing that came with the signal; of the others, 1.43 a frame took pages of the signal's capture into a mirror (2.9 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 7 frames, its first three in 0
[hos host] vk: frame ahead, what came with the signal: 7 signals with a capture, each of 3.9 pages in 2.6 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: 0.24+0.08, 0.02+0.02, 0.01+0.07, 0.01+0.05, 0.01+0.03, 0.01+0.02, 0.01+0.01, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00
[hos ModuleSystemWorker2] vk: readbacks of GPU results: 1551 of 3000 waited for their write-back, 0.04 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: 1587 kept their virtual core (nothing there to wait for), 3533 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept)
[hos BaseProcExecutor3] vcores: 109070 takes, 13729 waits (mean 34 us, longest 4.0 ms, 0 over HOS_VCORE_LOG_MS), 6044 kicks, 5960 yields, 0 starved grants, 0 escapes in 5 s
[hos Presentation Thread] vk: capture: a submit 0.12 ms (lock 0.00, scan 0.04 over 1014 ranges, 2108 MB), 313 pages written, 313 copied (1.2 MB)
[hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.002, bytes copied 0.000; 25 kept (74 MB), 11 spare buffers, 0 texture pages copied (0 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 69 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 1152, 5244.2 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far
[hos host] vk: mirror syncs (600 submits): 1118 dirty pages from their submits' captures, 71861 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): 1350 dispatches, 44507 chunks; 0 syncs as copies (no table room)
[hos host] vk: write-back diff (600 submits): 8302 runs, 883.2 MB compared; 78 pages read into the shadows; 352 MB of shadows; pages the shadows knew that the CPU wrote: 26405 in captures, 3 only in the collection, 48 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] control: quit asked by a client
[hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4302 pools in the table now)
[hos host] vk: pipeline cache: play file 7 saved (4399 KB): 25 pipelines, 25 from the driver's cache, 0 compiled; 0 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (a file the game was writing waited for, at most 3 s)