Beanstalk Longshot test farm
Menu

Report rp_e5373935df9cb509 pass

#1462 fix(vk): a finalized render target goes once the game has written over its storage

vram8gb on Hidden tester,

Machine

Commit
1c09f9d120b2f28618b563d5797706d84879555b
Baseline
645d58e682a02aff8af7de5c098404b44073c9a2
App
nightly-160-32a4fa8a, attempt 1
Game build
e0f3ccfa
os
windows
cpu
AMD Ryzen 5 5600X3D 6-Core Processor
gpu
NVIDIA GeForce RTX 3070
tags
windowsnvidianvidia-proprietarydgpu
driver
621.24.0
ram_gb
32
vram_mb
8,017
gpu_vendor
nvidia
os_version
Windows 10.0.26200

Builds

main (baseline)

614.5 s warm

from 645d58e682a0

lift
3.1 s
read
376.1 s
finish
151.8 s
compile
77 s

PR

158.4 s warm

Program cache: warm

Scenarios

field-retention

ok
Metric (median)mainPRΔ
exit_code00±0%
deku.hitch_count00±0%
deku.vram_mean_mb4,519.54,528+0.2%
deku.vram_peak_mb4,5644,640+1.7%
field.hitch_count00±0%
deku.stutter_count01—
field.vram_mean_mb4,5614,563+0%
field.vram_peak_mb4,5614,563+0%
log_forbidden_hits00±0%
field.stutter_count10−100%
log_expected_missing00±0%
deku.frametime_max_ms32.4136.21+11.7%
deku.frametime_p50_ms16.5116.44−0.4%
deku.frametime_p99_ms25.5124.24−4.9%
field.frametime_max_ms47.9226.65−44.4%
field.frametime_p50_ms16.6916.65−0.3%
field.frametime_p99_ms19.8819.89+0%
deku.frametime_1pct_low_ms27.7427.37−1.3%
field.frametime_1pct_low_ms23.9421.17−11.6%
screenshot_diff—0—

Pictures against main: field-after-laps diff 0 (main against itself ), deku-interior diff 0 (main against itself )

Runs (2)
Metricmain 0pr 1
hangnono
crashednono
exit_code00
deku.hitch_count00
deku.vram_mean_mb4,519.54,528
deku.vram_peak_mb4,5644,640
field.hitch_count00
deku.stutter_count01
field.vram_mean_mb4,5614,563
field.vram_peak_mb4,5614,563
log_forbidden_hits00
field.stutter_count10
log_expected_missing00
deku.frametime_max_ms32.4136.21
deku.frametime_p50_ms16.5116.44
deku.frametime_p99_ms25.5124.24
field.frametime_max_ms47.9226.65
field.frametime_p50_ms16.6916.65
field.frametime_p99_ms19.8819.89
deku.frametime_1pct_low_ms27.7427.37
field.frametime_1pct_low_ms23.9421.17
screenshot_diff—0

Rules

ScenarioCellRuleLimitmainPRΔ %Status
field-retentioncrashFalse00—pass
field-retentionscreenshot.max_diff0.03—0—pass
field-retentionfield.vram_peak_mb.max_delta_pct104,5614,563±0%pass
field-retentiondeku.vram_peak_mb.max_delta_pct104,5644,640+1.7%pass
field-retentionfield.frametime_p99_ms.max_delta_pct2019.8819.89±0%pass
field-retentiondeku.frametime_p99_ms.max_delta_pct2025.5124.24−4.9%pass
field-retentionlog_forbidden_hits.max000—pass

Log (PR side, end)

[hos sead::MainThread] nvn: CommandBufferWaitEvent #195000: event 0x1005a88000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos host] vk: replay reads of guest memory as submitted: 3600000 (1690159 pages from the captures)
[hos host] vk: sparse mirrors: 52, 780 MB with memory of 1092 MB (311 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1138 dirty pages from their submits' captures, 92915 from earlier ones', 11 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4177 runs, 665.9 MB compared; 80 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18127 in captures, 22 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool: 0x1057000000 (4 MB, captured, state 2): 6; 0x1042000000 (4 MB, captured, state 2): 5;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos Presentation Thread] vk: capture: a submit 0.34 ms (lock 0.01, scan 0.03 over 348 ranges, 3395 MB), 655 pages written, 655 copied (2.6 MB)
[hos host] vk: a capture taken (ms): all 0.116; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.112, bytes copied 0.000; 25 kept (138 MB), 4 spare buffers, 18679 texture pages copied (72 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 101475 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 952 dirty pages from their submits' captures, 93057 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4206 runs, 666.1 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18620 in captures, 14 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3620000 (1699661 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.13, writes collected 0.04
[hos host] vk: program picks: 7019438 kept (3230457 by the last picks' textures, a uniform buffer bound since), 3246 new, 2177315 with other textures (of 9200000)
[hos ModuleSystemWorker4] vcores: 236466 takes, 27664 waits (mean 41 us, longest 5.1 ms, 0 over HOS_VCORE_LOG_MS), 14380 kicks, 14238 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: memory: working set 12391 MB (peak 12786), private 18208 MB, staging 128 MB in 8 arenas, 99 made so far (22 ms)
[hos host] vk: memory heaps: heap 0 (device): 155 blocks 3755 MB, 13815 allocations 3228 MB; used 4416 of 7249 MB; heap 1 (system): 11 blocks 224 MB, 35 allocations 180 MB; used 2574 of 15577 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 256 MB, 120 images 150 MB; 51 free ranges, the largest 16 MB
[hos host] vk: image blocks (textures, compacted): 30 blocks 960 MB, 978 images 915 MB; 394 free ranges, the largest 18 MB
[hos host] vk: render target images: 701 reused from the pool, 3115 made new, 2992 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 4416 MB used of 5200 MB allowed (527 MB of it free in the blocks); textures 1829 MB (budget 1888 MB), 1105 textures
[hos host] vk: textures: decoded ASTC 811 MB, rendered 376 MB (66 drawn in one frame, kept: 23683 KB), other 410 MB; used in the last 8 presents 1128 MB
[hos host] vk: decoded ASTC used again: 242 textures (590 MB) copied from ones the game finalized, not decoded; 242 of those retired, 87 listed; 2863 MB of blocks hashed in 326 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:   47 MB: 0x10de96f000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago
[hos host] vk:   37 MB: 0x1109f38e00 1800x1380x1 x8 levels 1 NVN 0x6, last used 849 presents ago
[hos host] vk:   24 MB: 0x111b11f600 5072x5056x1 x1 levels 1 NVN 0x4b, last used 1 presents ago
[hos host] vk:   23 MB: 0x10cd345e00 1536x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 572 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 38 (10131 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 4 (151 KB); 260x260x1 NVN 0xd: 17 (2991 KB); 306x104x1 NVN 0x1: 4 (124 KB); 360x202x1 NVN 0x25: 2 (568 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 720x405x1 NVN 0x29: 2 (4556 KB); 720x405x1 NVN 0x34: 1 (1139 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 47 waited for it, 7.38 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 230.5 ms; VRAM 4.3 of 5.1 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: 103 program records loaded (31.1 ms), 8 new graphics pipelines, pipelines from the driver's cache 21, from the start's cache 0, compiled 122; 3572 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5728 queued, 5728 loaded (median 3.55 ms, 99th percentile 21.45 ms, worst 53.12 ms, 28717 ms and 1173.9 MB read in all); 7812 programs (1404 of them compute variants without their code, 0 graphics programs no note names), 9331 graphics pipelines (0 not in a cache), 173 compute pipelines (562 not in a cache); a first use ran 25 itself and waited for 0 (61.7 ms); 1643 pipelines made at create taken by draws; 2694 create calls with nothing kept for their stages, 0 before the index; units 8422 (5728 ready, 0 loading), 13918 programs alive
[hos host] vk: module identifiers (play): 811 known, 811 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: 16 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 7.06, present 0.18, draw 3.36, descriptors 1.59, texture lookups 0.23, uploads 0.15, pipelines 0.11, programs 0.41, commands 1.02, dispatch 0.63, memory sync 0.96, queue submit 0.51, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.77 MB synced in 1290.7 copies, 15.99 MB written back
[hos host] vk: 10200 presents, 60.0 fps; a frame: 799 draws (0 skipped), 84 dispatches, 202 passes, 148 barriers, 6 submits, 0.9 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1105 textures (1829 MB)
[hos host] vk: host time in GPU resource waits: 0.74 ms a frame (fences 0.03, timelines 0.71, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 461.5 full barriers recorded, 199.7 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.0 ms a frame (the longest submission 3.9 ms); 0.9 textures made a frame
[hos host] vk: a frame: 0.10 MB unswizzled on the CPU in 0.01 ms
[hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 8 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, 18.61 ms a frame): its jobs 9.23 ms a frame (submits 7.81, presents 0.30, others 1.12), idle 9.38; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 163.55 jobs queued at a present); 8 catch-ups (a finish, a texture read back, a write-back not recorded yet: 0), 28.57 ms each; 0 presents held for the CPU's signal, 0.00 ms each (0 let go by RX_VK_HOLD_MS); 51 captures at a CPU signal; the submits' waits read in 0.024 ms a frame; readbacks: 2388 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 9.23 ms after its hand-over (204.27 at most)
[hos ModuleSystemWorker3] nvn: DrawMeshTasks: 360000 so far (x1 0 x2 0x10 x3 0x18e01ead x4 0x2c0)
[hos host] vk: recorder: 3813728 packets run in 10.0 s (busy 1.31 s, spun idle 2.80 s, slept 4561 times, 1254 of them under 200 us), 0 calls made directly (no room); the replay waited for it 24188 times, 115.57 ms in all, the longest 0.60 ms; vkEndCommandBuffer 8545/57.98 ms (max 0.60), replay_mu unlock 7095/37.77 ms (max 0.22), vkResetDescriptorPool 8545/19.66 ms (max 0.11), vkDestroyImageView 3/0.16 ms (max 0.06)
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1154 dirty pages from their submits' captures, 94366 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4544 runs, 657.0 MB compared; 71 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19197 in captures, 20 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos Presentation Thread] vi: 10236 frames presented (59.8 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 76, 15.5-17.8 152, 17.8-22 68, 22-30 4, 30-40 0, over 40 0
[hos host] vk: replay reads of guest memory as submitted: 3640000 (1709172 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 3103653 pages so far (0 held: may be written ahead in their submission)
[hos Presentation Thread] vk: capture: a submit 0.35 ms (lock 0.01, scan 0.03 over 347 ranges, 3457 MB), 673 pages written, 673 copied (2.6 MB)
[hos host] vk: a capture taken (ms): all 0.134; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.129, bytes copied 0.000; 25 kept (138 MB), 5 spare buffers, 15556 texture pages copied (60 MB)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #145000: event 0x100c318038 mode 0 value 144999 (lr 0x8066189c)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 112606 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: write-backs left out (600 submits): 779, 3510.8 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1086 dirty pages from their submits' captures, 92459 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4317 runs, 667.4 MB compared; 65 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18766 in captures, 13 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1057000000 (4 MB, captured, state 2): 1;
[hos host] vk: 28 textures retired (1095 left, 1952 MB): budget 28, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 3660000 (1718715 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.15, writes collected 0.04
[hos sead::MainThread] vk: readbacks of GPU results: 1575 of 3000 waited for their write-back, 0.08 ms each; 0 looked at the stopped queues first, 3 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: 65 textures retired (1033 left, 1945 MB): budget 65, drawn over 0, dead targets 0; GPU-drawn with no copy kept: 0 live, 1 finalized, 0 MB
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 644 KB; 0 made on demand (0 MB kept now); c1 stages: at most 121 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 817, 3682.0 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1033 dirty pages from their submits' captures, 94287 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4082 runs, 664.5 MB compared; 65 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18676 in captures, 14 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: a frame: 15 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 7.43, present 0.20, draw 3.54, descriptors 1.78, texture lookups 0.44, uploads 0.37, pipelines 0.11, programs 0.42, commands 1.01, dispatch 0.62, memory sync 1.16, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.80 MB synced in 1293.7 copies, 15.99 MB written back
[hos host] vk: 10320 presents, 60.0 fps; a frame: 798 draws (0 skipped), 86 dispatches, 203 passes, 148 barriers, 6 submits, 0.2 uploads (1.5 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 1.05 ms a frame (fences 0.03, timelines 1.02, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 462.3 full barriers recorded, 199.8 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.1 ms a frame (the longest submission 4.0 ms); 0.2 textures made a frame
[hos host] vk: a frame: 1.50 MB unswizzled on the CPU in 0.14 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #200000: event 0x1005a88000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos host] vk: replay reads of guest memory as submitted: 3680000 (1728503 pages from the captures)
[hos sead::MainThread] nvn: GPU waits in 5 s: 14 sync waits (52 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos Presentation Thread] vk: capture: a submit 0.36 ms (lock 0.01, scan 0.04 over 349 ranges, 3505 MB), 680 pages written, 680 copied (2.7 MB)
[hos host] vk: a capture taken (ms): all 0.145; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.140, bytes copied 0.000; 25 kept (138 MB), 7 spare buffers, 23909 texture pages copied (93 MB)
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 984 dirty pages from their submits' captures, 93009 from earlier ones', 2 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4269 runs, 680.4 MB compared; 65 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18326 in captures, 7 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 2;
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 115804 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3700000 (1737799 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.16, writes collected 0.04
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1056 dirty pages from their submits' captures, 93414 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4088 runs, 650.1 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18605 in captures, 16 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos ModuleSystemWorker1] nvn: 1300000 recordings made, 29256 live copies (8.0 MB), 870 texture copies; 6 command buffers' segments (4.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 3720000 (1747158 pages from the captures)
[hos host] vk: program picks: 7159965 kept (3321767 by the last picks' textures, a uniform buffer bound since), 3246 new, 2236788 with other textures (of 9400000)
[hos host] vk: write-backs left out (600 submits): 779, 3510.8 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 828 dirty pages from their submits' captures, 93278 from earlier ones', 3 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4622 runs, 672.0 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19555 in captures, 10 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 3;
[hos host] vk: a frame: 15 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 7.15, present 0.16, draw 3.21, descriptors 1.42, texture lookups 0.05, uploads 0.00, pipelines 0.11, programs 0.42, commands 1.02, dispatch 0.64, memory sync 1.18, queue submit 0.47, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.79 MB synced in 1291.6 copies, 16.01 MB written back
[hos host] vk: 10440 presents, 60.0 fps; a frame: 799 draws (0 skipped), 87 dispatches, 203 passes, 148 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.79 ms a frame (fences 0.03, timelines 0.76, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 463.8 full barriers recorded, 199.7 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.1 ms a frame (the longest submission 3.7 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos Presentation Thread] vk: capture: a submit 0.39 ms (lock 0.01, scan 0.04 over 349 ranges, 3505 MB), 737 pages written, 737 copied (2.9 MB)
[hos host] vk: a capture taken (ms): all 0.160; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.154, bytes copied 0.000; 25 kept (124 MB), 4 spare buffers, 12500 texture pages copied (48 MB)
[hos host] vk:   (its written part: 0 of 0 KB readable, 460 bytes not zero; levels L0)
[hos host] vk: texture 0x10e5d0f600 5072x5056x1 x1 levels 1 NVN 0x4b (25043 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk:   (its written part: 0 of 0 KB readable, 460 bytes not zero; levels L0)
[hos host] vk: texture 0x10e5d0f600 5072x5056x1 x1 levels 1 NVN 0x4b (25043 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: readback pages refreshed from guest memory: 3164968 pages so far (0 held: may be written ahead in their submission)
[hos host] vk:   (its written part: 0 of 0 KB readable, 460 bytes not zero; levels L0)
[hos host] vk: texture 0x10e5d0f600 5072x5056x1 x1 levels 1 NVN 0x4b (25043 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 0 KB of it
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 155133 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker4] vk: readbacks of GPU results: 1620 of 3000 waited for their write-back, 0.09 ms each; 0 looked at the stopped queues first, 2 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 3740000 (1756593 pages from the captures)
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 954 dirty pages from their submits' captures, 93149 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4335 runs, 667.7 MB compared; 61 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18427 in captures, 11 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.13, writes collected 0.04
[hos ModuleSystemWorker1] vcores: 248695 takes, 29129 waits (mean 40 us, longest 6.9 ms, 0 over HOS_VCORE_LOG_MS), 15218 kicks, 15106 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #150000: event 0x100c318044 mode 0 value 149999 (lr 0x802742f0)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 644 KB; 0 made on demand (0 MB kept now); c1 stages: at most 121 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 817, 3682.0 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 960 dirty pages from their submits' captures, 94231 from earlier ones', 4 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4143 runs, 664.6 MB compared; 67 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19212 in captures, 11 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 4;
[hos sead::MainThread] nvn: CommandBufferWaitEvent #205000: event 0x1005a88000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos host] vk: replay reads of guest memory as submitted: 3760000 (1765965 pages from the captures)
[hos Presentation Thread] vi: 10537 frames presented (60.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 103, 15.5-17.8 124, 17.8-22 66, 22-30 7, 30-40 1, over 40 0
[hos host] vk: render targets drawn over from another start, let go: 3443 so far (5525 MB), 3259 of them (5224 MB) between the passes
[hos Presentation Thread] vk: capture: a submit 0.34 ms (lock 0.01, scan 0.03 over 350 ranges, 3509 MB), 686 pages written, 686 copied (2.7 MB)
[hos host] vk: a capture taken (ms): all 0.124; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.119, bytes copied 0.000; 25 kept (138 MB), 7 spare buffers, 6879 texture pages copied (26 MB)
[hos host] vk: a frame: 16 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 6.92, present 0.17, draw 3.24, descriptors 1.48, texture lookups 0.13, uploads 0.07, pipelines 0.12, programs 0.41, commands 1.01, dispatch 0.61, memory sync 0.98, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.76 MB synced in 1289.0 copies, 15.97 MB written back
[hos host] vk: 10560 presents, 60.0 fps; a frame: 800 draws (0 skipped), 84 dispatches, 203 passes, 148 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.58 ms a frame (fences 0.03, timelines 0.55, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 459.8 full barriers recorded, 199.6 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.0 ms a frame (the longest submission 4.0 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 124114 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 779, 3510.8 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 998 dirty pages from their submits' captures, 92357 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4117 runs, 666.4 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18276 in captures, 7 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: replay reads of guest memory as submitted: 3780000 (1775351 pages from the captures)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.13, writes collected 0.04
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1084 dirty pages from their submits' captures, 91874 from earlier ones', 3 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4234 runs, 667.3 MB compared; 62 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18168 in captures, 19 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 3;
[hos host] vk: replay reads of guest memory as submitted: 3800000 (1784906 pages from the captures)
[hos host] vk: queues ordered by their events: 66000 submissions stopped at a wait, 65982 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 52.41 ms at most); waits met 207640, not met 0; captures at a CPU event's wait 2642, 0 of them at a wait met on arrival
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 954 dirty pages from their submits' captures, 94346 from earlier ones', 14 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4532 runs, 670.8 MB compared; 62 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19450 in captures, 11 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1064400000 (8 MB, captured, state 2): 14;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 12 sync waits (6 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos Presentation Thread] vk: capture: a submit 0.35 ms (lock 0.01, scan 0.04 over 350 ranges, 3509 MB), 705 pages written, 705 copied (2.8 MB)
[hos host] vk: a capture taken (ms): all 0.130; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.125, bytes copied 0.000; 25 kept (140 MB), 5 spare buffers, 6879 texture pages copied (26 MB)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1589 of 3000 waited for their write-back, 0.06 ms each; 0 looked at the stopped queues first, 2 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 132186 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: readback pages refreshed from guest memory: 3226767 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3820000 (1794442 pages from the captures)
[hos host] vk: program picks: 7300503 kept (3412958 by the last picks' textures, a uniform buffer bound since), 3246 new, 2296250 with other textures (of 9600000)
[hos host] vk: a frame: 17 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 7.03, present 0.16, draw 3.24, descriptors 1.46, texture lookups 0.13, uploads 0.07, pipelines 0.11, programs 0.40, commands 1.04, dispatch 0.65, memory sync 1.00, queue submit 0.49, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.81 MB synced in 1294.7 copies, 16.05 MB written back
[hos host] vk: 10680 presents, 60.1 fps; a frame: 800 draws (0 skipped), 89 dispatches, 203 passes, 148 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.65 ms a frame (fences 0.03, timelines 0.62, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 465.7 full barriers recorded, 199.7 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.2 ms a frame (the longest submission 3.9 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos rmbl::VibrationThread] hid: 36864 vibration values, strongest 0.00 since the last count
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1040 dirty pages from their submits' captures, 93544 from earlier ones', 5 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4414 runs, 669.9 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18873 in captures, 16 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 5;
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.14, writes collected 0.04
[hos host] vk: replay reads of guest memory as submitted: 3840000 (1803997 pages from the captures)
[hos sead::MainThread] nvn: CommandBufferWaitEvent #210000: event 0x1005a88000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 644 KB; 0 made on demand (0 MB kept now); c1 stages: at most 121 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 936 dirty pages from their submits' captures, 93515 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4176 runs, 666.9 MB compared; 63 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18708 in captures, 16 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1057000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos sead::MainThread] vk: capture: a submit 0.36 ms (lock 0.01, scan 0.04 over 350 ranges, 3511 MB), 714 pages written, 714 copied (2.8 MB)
[hos host] vk: a capture taken (ms): all 0.136; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.131, bytes copied 0.000; 25 kept (138 MB), 3 spare buffers, 7450 texture pages copied (29 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 131539 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3860000 (1813557 pages from the captures)
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1025 dirty pages from their submits' captures, 93241 from earlier ones', 3 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4056 runs, 664.6 MB compared; 63 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18220 in captures, 8 only in the collection, 41 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 3;
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #155000: event 0x100c318010 mode 0 value 155002 (lr 0x80660bcc)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.14, writes collected 0.04
[hos BaseProcExecutor1] vcores: 240248 takes, 28112 waits (mean 42 us, longest 6.8 ms, 0 over HOS_VCORE_LOG_MS), 14765 kicks, 14645 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: memory: working set 12293 MB (peak 12786), private 18240 MB, staging 128 MB in 8 arenas, 101 made so far (22 ms)
[hos host] vk: memory heaps: heap 0 (device): 162 blocks 3979 MB, 13743 allocations 3344 MB; used 4640 of 7249 MB; heap 1 (system): 11 blocks 208 MB, 33 allocations 164 MB; used 2558 of 15577 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 256 MB, 119 images 149 MB; 50 free ranges, the largest 16 MB
[hos host] vk: image blocks (textures, compacted): 37 blocks 1184 MB, 907 images 1032 MB; 411 free ranges, the largest 16 MB
[hos host] vk: render target images: 701 reused from the pool, 3115 made new, 2993 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 4640 MB used of 5200 MB allowed (635 MB of it free in the blocks); textures 1945 MB (budget 1952 MB), 1033 textures
[hos host] vk: textures: decoded ASTC 802 MB, rendered 376 MB (66 drawn in one frame, kept: 23683 KB), other 544 MB; used in the last 8 presents 1128 MB
[hos host] vk: decoded ASTC used again: 287 textures (712 MB) copied from ones the game finalized, not decoded; 287 of those retired, 82 listed; 2943 MB of blocks hashed in 350 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:   47 MB: 0x10de96f000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1 presents ago
[hos host] vk:   37 MB: 0x1109f38e00 1800x1380x1 x8 levels 1 NVN 0x6, last used 1449 presents ago
[hos host] vk:   24 MB: 0x10e5d0f600 5072x5056x1 x1 levels 1 NVN 0x4b, last used 1 presents ago
[hos host] vk:   24 MB: 0x1130e00200 5072x5056x1 x1 levels 1 NVN 0x4b, last used 492 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 38 (10131 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 4 (151 KB); 260x260x1 NVN 0xd: 17 (2991 KB); 306x104x1 NVN 0x1: 4 (124 KB); 360x202x1 NVN 0x25: 2 (568 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 720x405x1 NVN 0x29: 2 (4556 KB); 720x405x1 NVN 0x34: 1 (1139 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 33 waited for it, 1.38 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 36.3 ms; VRAM 4.5 of 5.1 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: 103 program records loaded (31.1 ms), 8 new graphics pipelines, pipelines from the driver's cache 21, from the start's cache 0, compiled 122; 3572 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (play): 5728 queued, 5728 loaded (median 3.55 ms, 99th percentile 21.45 ms, worst 53.12 ms, 28717 ms and 1173.9 MB read in all); 7812 programs (1404 of them compute variants without their code, 0 graphics programs no note names), 9331 graphics pipelines (0 not in a cache), 173 compute pipelines (562 not in a cache); a first use ran 25 itself and waited for 0 (61.7 ms); 1643 pipelines made at create taken by draws; 2694 create calls with nothing kept for their stages, 0 before the index; units 8422 (5728 ready, 0 loading), 13918 programs alive
[hos host] vk: module identifiers (play): 811 known, 811 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: 16 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 6.96, present 0.17, draw 3.19, descriptors 1.46, texture lookups 0.14, uploads 0.08, pipelines 0.11, programs 0.41, commands 0.99, dispatch 0.60, memory sync 1.10, queue submit 0.47, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.77 MB synced in 1289.0 copies, 15.97 MB written back
[hos host] vk: 10800 presents, 59.4 fps; a frame: 800 draws (0 skipped), 83 dispatches, 203 passes, 148 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.65 ms a frame (fences 0.03, timelines 0.62, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 459.7 full barriers recorded, 199.4 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 8.9 ms a frame (the longest submission 3.8 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: queues ordered by their events: 67176 submissions stopped at a wait, 67162 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 52.41 ms at most); waits met 211814, not met 0; captures at a CPU event's wait 2653, 0 of them at a wait met on arrival
[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, 16.69 ms a frame): its jobs 7.75 ms a frame (submits 7.14, presents 0.18, others 0.42), idle 8.94; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 160.82 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); 38 captures at a CPU signal; the submits' waits read in 0.024 ms a frame; readbacks: 2400 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 7.77 ms after its hand-over (24.43 at most)
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1071 dirty pages from their submits' captures, 93146 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4260 runs, 666.6 MB compared; 63 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18671 in captures, 13 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: recorder: 3794374 packets run in 10.0 s (busy 1.28 s, spun idle 2.80 s, slept 4494 times, 1230 of them under 200 us), 0 calls made directly (no room); the replay waited for it 24391 times, 110.22 ms in all, the longest 0.48 ms; vkEndCommandBuffer 8584/55.06 ms (max 0.48), replay_mu unlock 7223/36.28 ms (max 0.21), vkResetDescriptorPool 8584/18.88 ms (max 0.13)
[hos host] vk: replay reads of guest memory as submitted: 3880000 (1823014 pages from the captures)
[hos Presentation Thread] vi: 10837 frames presented (59.9 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 94, 15.5-17.8 118, 17.8-22 86, 22-30 2, 30-40 0, over 40 0
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1602 of 3000 waited for their write-back, 0.07 ms each; 0 looked at the stopped queues first, 2 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos sead::MainThread] vk: capture: a submit 0.36 ms (lock 0.01, scan 0.04 over 350 ranges, 3511 MB), 730 pages written, 730 copied (2.9 MB)
[hos host] vk: a capture taken (ms): all 0.141; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.135, bytes copied 0.000; 25 kept (122 MB), 2 spare buffers, 7450 texture pages copied (29 MB)
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 992 dirty pages from their submits' captures, 93934 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4466 runs, 669.7 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19321 in captures, 9 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1057000000 (4 MB, captured, state 2): 1;
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 152752 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3900000 (1832496 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 3287998 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.14, writes collected 0.04
[hos host] vk: sparse mirrors: 50, 780 MB with memory of 1084 MB (304 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1317 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 876 dirty pages from their submits' captures, 93948 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4495 runs, 670.5 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19012 in captures, 16 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: replay reads of guest memory as submitted: 3920000 (1842100 pages from the captures)
[hos host] vk: program picks: 7440886 kept (3504326 by the last picks' textures, a uniform buffer bound since), 3246 new, 2355867 with other textures (of 9800000)
[hos host] vk: a frame: 15 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 6.93, present 0.18, draw 3.22, descriptors 1.48, texture lookups 0.12, uploads 0.06, pipelines 0.11, programs 0.40, commands 1.00, dispatch 0.62, memory sync 1.05, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 495 (780 MB): 8.82 MB synced in 1294.2 copies, 16.03 MB written back
[hos host] vk: 10920 presents, 60.5 fps; a frame: 800 draws (0 skipped), 88 dispatches, 204 passes, 148 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.63 ms a frame (fences 0.03, timelines 0.60, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 465.6 full barriers recorded, 199.6 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.2 ms a frame (the longest submission 4.1 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos sead::MainThread] nvn: CommandBufferWaitEvent #215000: event 0x1005a88000 mode 0 value 1 (now 0) (lr 0x802eb444)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 644 KB; 0 made on demand (0 MB kept now); c1 stages: at most 121 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1009 dirty pages from their submits' captures, 93557 from earlier ones', 4 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4114 runs, 663.0 MB compared; 62 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18690 in captures, 5 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 4;
[hos Presentation Thread] vk: capture: a submit 0.35 ms (lock 0.01, scan 0.03 over 350 ranges, 3511 MB), 707 pages written, 707 copied (2.8 MB)
[hos host] vk: a capture taken (ms): all 0.130; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.126, bytes copied 0.000; 25 kept (140 MB), 4 spare buffers, 7450 texture pages copied (29 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 14 sync waits (9 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 130444 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3940000 (1851732 pages from the captures)
[hos host] vk: sparse mirrors: 51, 780 MB with memory of 1088 MB (307 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1318 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 779, 3510.8 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1053 dirty pages from their submits' captures, 92136 from earlier ones', 4 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4134 runs, 651.9 MB compared; 63 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18558 in captures, 11 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 4;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.13, writes collected 0.04
[hos ModuleSystemWorker2] nvn: 1350000 recordings made, 29264 live copies (8.2 MB), 870 texture copies; 5 command buffers' segments (4.3 MB)
[hos host] vk: replay reads of guest memory as submitted: 3960000 (1861063 pages from the captures)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1612 of 3000 waited for their write-back, 0.05 ms each; 0 looked at the stopped queues first, 3 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1042 dirty pages from their submits' captures, 92083 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4258 runs, 666.5 MB compared; 62 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 18217 in captures, 17 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool:
[hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 380000 so far (x1 0x117b93e000 x2 0 x3 0x117b93e000 x4 0x230040)
[hos host] vk: a frame: 15 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 6.83, present 0.17, draw 3.12, descriptors 1.42, texture lookups 0.10, uploads 0.05, pipelines 0.11, programs 0.39, commands 0.98, dispatch 0.60, memory sync 1.03, queue submit 0.48, slot wait 0.05
[hos host] vk: a frame: mirrors 496 (780 MB): 8.77 MB synced in 1287.3 copies, 15.96 MB written back
[hos host] vk: 11040 presents, 60.0 fps; a frame: 803 draws (0 skipped), 84 dispatches, 203 passes, 148 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 42422 pipelines (5690402 ms), 0 programs (0 failed), 1033 textures (1945 MB)
[hos host] vk: host time in GPU resource waits: 0.45 ms a frame (fences 0.03, timelines 0.42, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 460.9 full barriers recorded, 199.7 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: 3.0; 0x8: 3.0; 0x9: 1.0; 0x10: 2.0; 0x11: 43.0; 0x12: 71.5; 0x13: 2.0; 0x21: 4.0; 0x28: 14.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 9.0 ms a frame (the longest submission 3.9 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #160000: event 0x100c318008 mode 0 value 159997 (lr 0x80291504)
[hos sead::MainThread] vk: capture: a submit 0.35 ms (lock 0.01, scan 0.03 over 350 ranges, 3511 MB), 706 pages written, 706 copied (2.8 MB)
[hos host] vk: a capture taken (ms): all 0.133; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.128, bytes copied 0.000; 25 kept (122 MB), 2 spare buffers, 7450 texture pages copied (29 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 136021 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3980000 (1870366 pages from the captures)
[hos host] vk: sparse mirrors: 51, 780 MB with memory of 1088 MB (307 MB spared); blocks given memory later 24028, given back 32020; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 80; 1318 binds (243.9 ms); 0 made whole for want of memory
[hos host] vk: write-backs left out (600 submits): 798, 3596.4 MB; 46 bindings followed, 41 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 3285 so far
[hos host] vk: mirror syncs (600 submits): 1068 dirty pages from their submits' captures, 94381 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE)
[hos host] vk: write-back diff (600 submits): 4448 runs, 669.9 MB compared; 64 pages read into the shadows; 312 MB of shadows; pages the shadows knew that the CPU wrote: 19288 in captures, 11 only in the collection, 42 only by the replay itself
[hos host] vk:   read live, by pool: 0x1042000000 (4 MB, captured, state 2): 1;
[hos host] vk: imports: 174 live (2220 MB), 0 retired still imported (0 MB), 98 retired given back (3144 MB)
[hos host] control: quit asked by a client
[hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 103 program records loaded (31.1 ms), 8 new graphics pipelines, pipelines from the driver's cache 21, from the start's cache 0, compiled 122; 3572 draws and dispatches left out, 0 waits (0.0 ms)
[hos host] vk: program loads at create (close): 5728 queued, 5728 loaded (median 3.55 ms, 99th percentile 21.45 ms, worst 53.12 ms, 28717 ms and 1173.9 MB read in all); 7812 programs (1404 of them compute variants without their code, 0 graphics programs no note names), 9331 graphics pipelines (0 not in a cache), 173 compute pipelines (562 not in a cache); a first use ran 25 itself and waited for 0 (61.7 ms); 1643 pipelines made at create taken by draws; 2694 create calls with nothing kept for their stages, 0 before the index; units 8422 (5728 ready, 0 loading), 13918 programs alive
[hos host] vk: module identifiers (close): 811 known, 811 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 (4341 pools in the table now)
[hos host] vk: pipeline cache: play file 6 saved (2216 KB): 15 pipelines, 1 from the driver's cache, 14 compiled; 14 more from the start's cache
[hos host] control: exiting
[hos host] stop: close work done (the game's saves are not waited for)