Report rp_4206b88c1f2b0e74 fail
This report disagrees with its peers.
child-market market.frametime_max_ms: +37.1% against peers' +7.9% child-market market.hitch_count: -9.1% against peers' +166.7% child-market run_frametime_max_ms: -7.2% against peers' +31.4% child-market run_hitch_count: +7.1% against peers' +83.3%
Machine
- Commit
- dae496fd7d0ee978d5726959da7faa5606dd675b
- Baseline
- 89c3d21ea169ed46124e6c97acd90587f660b75a
- App
- nightly-199-9b041be6, attempt 1
- Game build
e0f3ccfa- os
- windows
- cpu
- AMD Ryzen 9 5900X 12-Core Processor
- gpu
- AMD Radeon RX 9070 XT
- tags
- windowsamdamd-proprietarydgpu
- driver
- 2.0.416
- ram_gb
- 32
- vram_mb
- 16,304
- gpu_vendor
- amd
- os_version
- Windows 10.0.26300
Builds
main (baseline)
0 s warm
from 1780fbe0cec8
the PR's pack goes over the base this PC had (the PR's history holds it): no main build
PR
1,723.4 s warm
- lift
- 113.2 s
- read
- 2.4 s
- finish
- 28.2 s
- compile
- 1,572.6 s
Program cache: warm
Scenarios
child-market HOS_NVN_FRAME_OVERLAP=1 (PR only)
ok
| Metric (median) | switch off | switch on | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| market.fps_mean | 51.67 | 55.46 | +7.3% |
| run_hitch_count | 14 | 15 | +7.1% |
| market.draws_mean | 2,493.8 | 2,487.6 | −0.2% |
| market.hitch_count | 11 | 10 | −9.1% |
| market.stutter_count | 26 | 27 | +3.8% |
| run_frametime_max_ms | 362.36 | 336.09 | −7.2% |
| market.frametime_max_ms | 91.39 | 125.31 | +37.1% |
| market.frametime_p50_ms | 19.09 | 17.68 | −7.4% |
| market.frametime_p99_ms | 29.07 | 26.23 | −9.8% |
| market.frametime_1pct_low_ms | 41.68 | 37.12 | −10.9% |
| screenshot_diff | — | 0.13 | — |
Pictures against the switch off: market 5 s diff 0.0967 (switch off against itself ), market 30 s diff 0.0659 (switch off against itself ), market 60 s diff 0.1291 (switch off against itself ), market 110 s diff 0.1035 (switch off against itself )
Runs (2)
| Metric | off 0 | on 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| market.fps_mean | 51.67 | 55.46 |
| run_hitch_count | 14 | 15 |
| market.draws_mean | 2,493.8 | 2,487.6 |
| market.hitch_count | 11 | 10 |
| market.stutter_count | 26 | 27 |
| run_frametime_max_ms | 362.36 | 336.09 |
| market.frametime_max_ms | 91.39 | 125.31 |
| market.frametime_p50_ms | 19.09 | 17.68 |
| market.frametime_p99_ms | 29.07 | 26.23 |
| market.frametime_1pct_low_ms | 41.68 | 37.12 |
| screenshot_diff | — | 0.13 |
Rules
| Scenario | Cell | Rule | Limit | switch off | switch on | Δ % | Status |
|---|---|---|---|---|---|---|---|
| child-market | HOS_NVN_FRAME_OVERLAP=1 (PR only) | crash | False | 0 | 0 | — | pass |
| child-market | HOS_NVN_FRAME_OVERLAP=1 (PR only) | market.fps_mean.min_delta_pct | 0 | 51.67 | 55.46 | +7.3% | pass |
| child-market | HOS_NVN_FRAME_OVERLAP=1 (PR only) | screenshot.max_diff | 0.05 | — | 0.13 | — | fail |
Pictures of the failure
The last frame of a step that got stuck, or main's and the PR's picture where they differed more than the plan allows; shrunk, and kept a day: until .
Log (PR side, end)
[hos host] vk: mirror syncs' pass (600 submits): 844 dispatches, 33531 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4866 runs, 2198.4 MB compared; 96 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10833 in captures, 4 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: program picks: 11663883 kept (4196466 by the last picks' textures, a uniform buffer bound since), 28980 new, 3907136 with other textures (of 15600000) [hos host] vk: replay reads of guest memory as submitted: 8220000 (5505443 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.05 over 1095 ranges, 2520 MB), 206 pages written, 206 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.010, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 7031 texture pages copied (27 MB) [hos host] vk: replay reads of guest memory as submitted: 8240000 (5518856 pages from the captures) [hos host] vk: mirror of pool 0x7f72000000 (4 MB) given back: idle, 6041 submissions since its sync [hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 240000 so far (x1 0x1178b9a000 x2 0 x3 0x1178b9a000 x4 0x654040) [hos host] vk: replay reads of guest memory as submitted: 8260000 (5532243 pages from the captures) [hos host] vk: sparse mirrors: 75, 920 MB with memory of 1372 MB (451 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 325 binds (19.8 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 63 taken from the spares, 98 made new; 86 kept as spares, 0 destroyed; 23 spares now, 388 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2713 dirty pages from their submits' captures, 41570 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): 841 dispatches, 33460 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4721 runs, 2138.2 MB compared; 97 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10839 in captures, 11 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: mirror of pool 0x7f9d000000 (4 MB) given back: idle, 6017 submissions since its sync [hos host] vk: replay reads of guest memory as submitted: 8280000 (5545647 pages from the captures) [hos ModuleSystemWorker5] nvn: CommandBufferSignalEvent #125000: event 0x100d6c8000 mode 0 value 124999 (lr 0x80291440) [hos sead::MainThread] nvn: GPU waits in 5 s: 190 sync waits (272 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 8300000 (5559137 pages from the captures) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 182 KB; 0 made on demand (0 MB kept now); c1 stages: at most 91 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 62 sets (ub 865, sb 469, cis 3799, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 756, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2738 dirty pages from their submits' captures, 42841 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): 863 dispatches, 34420 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4939 runs, 2201.7 MB compared; 88 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11082 in captures, 3 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker4] vk: readbacks of GPU results: 1014 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: 8896 kept their virtual core (nothing there to wait for), 3136 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.07 [hos host] vk: replay reads of guest memory as submitted: 8320000 (5572727 pages from the captures) [hos host] vk: program picks: 11815058 kept (4252064 by the last picks' textures, a uniform buffer bound since), 28980 new, 3955961 with other textures (of 15800000) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.05 over 1097 ranges, 2524 MB), 214 pages written, 214 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.031; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.017, bytes copied 0.000; 25 kept (112 MB), 10 spare buffers, 7172 texture pages copied (28 MB) [hos host] vk: replay reads of guest memory as submitted: 8340000 (5586401 pages from the captures) [hos host] vk: a frame: 408 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.01, present 0.23, draw 7.27, descriptors 2.79, texture lookups 0.09, uploads 0.00, pipelines 0.35, programs 1.36, commands 2.23, dispatch 0.93, memory sync 0.59, queue submit 0.41, slot wait 0.26 [hos host] vk: a frame: mirrors 161 (917 MB): 4.94 MB synced in 955.6 copies, 61.13 MB written back [hos host] vk: 12720 presents, 55.7 fps; a frame: 2488 draws (0 skipped), 123 dispatches, 141 passes, 150 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3039 textures (5658 MB) [hos host] vk: host time in GPU resource waits: 1.53 ms a frame (fences 0.03, timelines 1.50, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 379.6 full barriers recorded, 200.1 left out (nothing recorded since the one before), 16.3 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 42.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.1 ms a frame (the longest submission 4.2 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.0 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: sparse mirrors: 75, 920 MB with memory of 1372 MB (451 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 327 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 64 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 23 spares now, 388 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 777, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2863 dirty pages from their submits' captures, 43824 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): 886 dispatches, 35352 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5180 runs, 2262.2 MB compared; 59 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11435 in captures, 4 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: replay reads of guest memory as submitted: 8360000 (5600096 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 8380000 (5613544 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 2604034 pages so far (0 held: may be written ahead in their submission) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 20346 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 8400000 (5626949 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: write-backs left out (600 submits): 756, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2865 dirty pages from their submits' captures, 42660 from earlier ones', 0 from guest memory as it was at the replay; 24 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): 859 dispatches, 34454 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5097 runs, 2204.6 MB compared; 63 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11057 in captures, 7 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: slow present: 18.9 ms: [hos host] vk: replay reads of guest memory as submitted: 8420000 (5640429 pages from the captures) [hos host] vk: present 12774 written to <data>\jobs\jb_fa26809ba77be16a\runs\child-market-g0-01-pr\shots/child-market-c0-pr-01-market_110s.png (the control bridge) [hos Presentation Thread] vi: 12783 frames presented (55.2 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 26, 15.5-17.8 110, 17.8-22 131, 22-30 8, 30-40 1, over 40 0 [hos host] vk: program picks: 11965177 kept (4307806 by the last picks' textures, a uniform buffer bound since), 28980 new, 4005842 with other textures (of 16000000) [hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1101 ranges, 2528 MB), 200 pages written, 200 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.022; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.009, bytes copied 0.000; 24 kept (96 MB), 12 spare buffers, 6742 texture pages copied (26 MB) [hos host] vk: replay reads of guest memory as submitted: 8440000 (5653880 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.06 [hos host] vk: sparse mirrors: 75, 920 MB with memory of 1372 MB (451 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 327 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 64 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 23 spares now, 388 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 3491 dirty pages from their submits' captures, 41395 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): 850 dispatches, 33781 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4915 runs, 2141.2 MB compared; 85 pages read into the shadows; 260 MB of shadows (129 MB of pages known, in 152 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11008 in captures, 13 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: replay reads of guest memory as submitted: 8460000 (5667248 pages from the captures) [hos sead::MainThread] nvn: 1150000 recordings made, 74412 live copies (22.9 MB), 490 texture copies; 7 command buffers' segments (4.5 MB) [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #185000: event 0x100d6c8044 mode 0 value 127486 (now 127448) (lr 0x80274390) [hos host] vk: queues ordered by their events: 72000 submissions stopped at a wait, 71998 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 185045, not met 0; captures at a CPU event's wait 8075, 0 of them at a wait met on arrival [hos host] vk: replay reads of guest memory as submitted: 8480000 (5680708 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 8500000 (5694098 pages from the captures) [hos host] vk: write-backs left out (600 submits): 756, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 3423 dirty pages from their submits' captures, 41927 from earlier ones', 0 from guest memory as it was at the replay; 24 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): 853 dispatches, 34254 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5090 runs, 2203.0 MB compared; 68 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10941 in captures, 13 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a frame: 392 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.67, present 0.39, draw 7.66, descriptors 3.17, texture lookups 0.19, uploads 0.05, pipelines 0.34, programs 1.34, commands 2.25, dispatch 0.94, memory sync 0.60, queue submit 0.41, slot wait 0.26 [hos host] vk: a frame: mirrors 162 (920 MB): 4.98 MB synced in 957.3 copies, 61.19 MB written back [hos host] vk: 12840 presents, 54.0 fps; a frame: 2464 draws (0 skipped), 124 dispatches, 141 passes, 151 barriers, 6 submits, 0.4 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3060 textures (5674 MB) [hos host] vk: host time in GPU resource waits: 2.26 ms a frame (fences 0.03, timelines 2.23, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 381.7 full barriers recorded, 200.4 left out (nothing recorded since the one before), 16.4 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 42.3; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.4 ms a frame (the longest submission 4.2 ms); 0.4 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.4 (0.5 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.12 MB unswizzled on the CPU in 0.01 ms [hos ModuleSystemWorker1] vk: readbacks of GPU results: 997 of 3000 waited for their write-back, 0.05 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: 8668 kept their virtual core (nothing there to wait for), 2852 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: replay reads of guest memory as submitted: 8520000 (5707534 pages from the captures) [hos host] vk: program picks: 12116451 kept (4363540 by the last picks' textures, a uniform buffer bound since), 28980 new, 4054568 with other textures (of 16200000) [hos host] vk: replay reads of guest memory as submitted: 8540000 (5720966 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1102 ranges, 2518 MB), 207 pages written, 207 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.030; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.015, bytes copied 0.000; 25 kept (98 MB), 11 spare buffers, 6329 texture pages copied (24 MB) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 182 KB; 0 made on demand (0 MB kept now); c1 stages: at most 92 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 62 sets (ub 865, sb 469, cis 3799, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 75, 920 MB with memory of 1372 MB (451 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 327 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 64 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 23 spares now, 388 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2621 dirty pages from their submits' captures, 41837 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): 836 dispatches, 33530 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4790 runs, 2138.3 MB compared; 85 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10956 in captures, 11 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos BaseProcExecutor1] vcores: 132936 takes, 22031 waits (mean 89 us, longest 13.4 ms, 0 over HOS_VCORE_LOG_MS), 10957 kicks, 11030 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 8560000 (5734516 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 8580000 (5747926 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.06 [hos host] vk: recorder: 7470185 packets run in 10.0 s (busy 1.53 s, spun idle 5.40 s, slept 4912 times, 2747 of them under 200 us), 0 calls made directly (no room); the replay waited for it 25910 times, 110.70 ms in all, the longest 0.40 ms; vkResetDescriptorPool 9328/58.71 ms (max 0.33), vkEndCommandBuffer 9378/30.46 ms (max 0.35), replay_mu unlock 6986/19.65 ms (max 0.40), vmaInvalidateAllocation 217/1.87 ms (max 0.18), vkQueueBindSparse 1/0.00 ms (max 0.00) [hos host] vk: write-backs left out (600 submits): 714, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 3365 dirty pages from their submits' captures, 39893 from earlier ones', 0 from guest memory as it was at the replay; 24 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): 817 dispatches, 32565 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4639 runs, 2078.7 MB compared; 92 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10602 in captures, 10 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8600000 (5761607 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 14948 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 8620000 (5775331 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 2676866 pages so far (0 held: may be written ahead in their submission) [hos host] vk: late pages found at the replay (600 takes): 91 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 8640000 (5788996 pages from the captures) [hos host] vk: program picks: 12267809 kept (4419643 by the last picks' textures, a uniform buffer bound since), 28980 new, 4103210 with other textures (of 16400000) [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #130000: event 0x100d6c8010 mode 0 value 130000 (lr 0x80660adc) [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 3130 dirty pages from their submits' captures, 41457 from earlier ones', 0 from guest memory as it was at the replay; 24 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): 838 dispatches, 33551 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4744 runs, 2138.5 MB compared; 97 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10824 in captures, 3 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.05 over 1102 ranges, 2512 MB), 192 pages written, 192 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.019; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 24 kept (92 MB), 12 spare buffers, 6064 texture pages copied (23 MB) [hos host] vk: replay reads of guest memory as submitted: 8660000 (5802697 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 207 sync waits (359 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: a frame: 419 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.36, present 0.23, draw 7.80, descriptors 3.30, texture lookups 0.10, uploads 0.00, pipelines 0.34, programs 1.39, commands 2.24, dispatch 0.92, memory sync 0.56, queue submit 0.42, slot wait 0.27 [hos host] vk: a frame: mirrors 163 (923 MB): 5.00 MB synced in 957.5 copies, 61.11 MB written back [hos host] vk: 12960 presents, 54.9 fps; a frame: 2532 draws (0 skipped), 124 dispatches, 141 passes, 151 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3066 textures (5678 MB) [hos host] vk: host time in GPU resource waits: 1.74 ms a frame (fences 0.03, timelines 1.71, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 382.0 full barriers recorded, 200.7 left out (nothing recorded since the one before), 16.3 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 42.1; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.5 ms a frame (the longest submission 4.1 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 8680000 (5816447 pages from the captures) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2763 dirty pages from their submits' captures, 41886 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): 840 dispatches, 33671 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4752 runs, 2137.4 MB compared; 96 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10827 in captures, 8 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8700000 (5830093 pages from the captures) [hos host] vk: render targets drawn over from another start, let go: 454 so far (1243 MB), 418 of them (1130 MB) between the passes [hos sead::MainThread] vk: readbacks of GPU results: 1021 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 sead::MainThread] vk: invalidates since the last readbacks line: 8270 kept their virtual core (nothing there to wait for), 2994 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: replay reads of guest memory as submitted: 8720000 (5843790 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.06 [hos host] vk: replay reads of guest memory as submitted: 8740000 (5857444 pages from the captures) [hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #190000: event 0x100d6c8044 mode 0 value 131286 (now 131248) (lr 0x80274390) [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 714, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2933 dirty pages from their submits' captures, 41143 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): 837 dispatches, 33047 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4643 runs, 2078.5 MB compared; 87 pages read into the shadows; 260 MB of shadows (129 MB of pages known, in 152 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10905 in captures, 6 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: program picks: 12419504 kept (4475634 by the last picks' textures, a uniform buffer bound since), 28980 new, 4151515 with other textures (of 16600000) [hos host] vk: replay reads of guest memory as submitted: 8760000 (5871135 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.05 over 1103 ranges, 2512 MB), 206 pages written, 206 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.011, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 6023 texture pages copied (23 MB) [hos host] vk: replay reads of guest memory as submitted: 8780000 (5884786 pages from the captures) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 182 KB; 0 made on demand (0 MB kept now); c1 stages: at most 92 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 62 sets (ub 865, sb 469, cis 3799, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 777, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2845 dirty pages from their submits' captures, 43674 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): 879 dispatches, 35312 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5260 runs, 2263.9 MB compared; 62 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 154 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11199 in captures, 8 only in the collection, 36 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8800000 (5898501 pages from the captures) [hos Presentation Thread] vi: 13057 frames presented (54.8 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 25, 15.5-17.8 88, 17.8-22 148, 22-30 13, 30-40 0, over 40 0 [hos host] vk: replay reads of guest memory as submitted: 8820000 (5912143 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 10688 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 8840000 (5925811 pages from the captures) [hos host] vk: a frame: 398 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.34, present 0.24, draw 7.75, descriptors 3.26, texture lookups 0.13, uploads 0.02, pipelines 0.35, programs 1.35, commands 2.24, dispatch 0.95, memory sync 0.56, queue submit 0.42, slot wait 0.27 [hos host] vk: a frame: mirrors 163 (923 MB): 4.98 MB synced in 962.1 copies, 61.16 MB written back [hos host] vk: 13080 presents, 55.1 fps; a frame: 2494 draws (0 skipped), 124 dispatches, 141 passes, 151 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3074 textures (5682 MB) [hos host] vk: host time in GPU resource waits: 1.58 ms a frame (fences 0.03, timelines 1.55, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 381.3 full barriers recorded, 200.3 left out (nothing recorded since the one before), 16.3 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 42.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.3 ms a frame (the longest submission 4.0 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.01 ms [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 756, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2925 dirty pages from their submits' captures, 42965 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): 863 dispatches, 34623 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5094 runs, 2204.0 MB compared; 64 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11239 in captures, 7 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: program picks: 12569613 kept (4530882 by the last picks' textures, a uniform buffer bound since), 28980 new, 4201406 with other textures (of 16800000) [hos host] vk: replay reads of guest memory as submitted: 8860000 (5939457 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.06 [hos host] vk: readback pages refreshed from guest memory: 2750173 pages so far (0 held: may be written ahead in their submission) [hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.05 over 1104 ranges, 2502 MB), 202 pages written, 202 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.010, bytes copied 0.000; 25 kept (106 MB), 11 spare buffers, 5319 texture pages copied (20 MB) [hos host] vk: replay reads of guest memory as submitted: 8880000 (5952883 pages from the captures) [hos host] vk: late pages' fix (600 recordings with one): of 653 captures with late pages 653 fixed (80.5 pages, 80.9 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 289 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 390 blocks (24960 KB); of the reads on the CPU, 2 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 48, of an earlier recording 239, not recorded yet 0, of this part 0; pages fixed from stamps 51421, from snapshots 1178; the shadows: 227185 pages synced from captures, 222296 made known by it, 4889 left unknown because the replay or the collection wrote them since [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2862 dirty pages from their submits' captures, 42348 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): 849 dispatches, 34036 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4969 runs, 2141.9 MB compared; 72 pages read into the shadows; 260 MB of shadows (130 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11199 in captures, 8 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 8900000 (5966305 pages from the captures) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 1006 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 ModuleSystemWorker3] vk: invalidates since the last readbacks line: 8777 kept their virtual core (nothing there to wait for), 2999 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: replay reads of guest memory as submitted: 8920000 (5979701 pages from the captures) [hos sead::MainThread] vcores: 135147 takes, 22502 waits (mean 99 us, longest 15.0 ms, 0 over HOS_VCORE_LOG_MS), 11049 kicks, 11102 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 8940000 (5993096 pages from the captures) [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 756, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2547 dirty pages from their submits' captures, 42605 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): 851 dispatches, 34251 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5147 runs, 2203.9 MB compared; 70 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10838 in captures, 9 only in the collection, 36 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: replay reads of guest memory as submitted: 8960000 (6006594 pages from the captures) [hos host] vk: program picks: 12720270 kept (4586173 by the last picks' textures, a uniform buffer bound since), 28980 new, 4250749 with other textures (of 17000000) [hos ModuleSystemWorker2] nvn: 1200000 recordings made, 74442 live copies (23.0 MB), 490 texture copies; 6 command buffers' segments (4.3 MB) [hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 260000 so far (x1 0x1178aa8000 x2 0 x3 0x1178aa8000 x4 0xf0040) [hos host] vk: replay reads of guest memory as submitted: 8980000 (6020196 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.05 over 1105 ranges, 2494 MB), 202 pages written, 202 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.021; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (108 MB), 11 spare buffers, 4957 texture pages copied (19 MB) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2722 dirty pages from their submits' captures, 41974 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): 839 dispatches, 33732 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4881 runs, 2140.4 MB compared; 86 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10889 in captures, 4 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 9000000 (6033983 pages from the captures) [hos host] vk: memory: working set 14537 MB (peak 14563), private 23699 MB, staging 32 MB in 2 arenas, 21 made so far (55 ms) [hos host] vk: memory heaps: heap 0 (system): 14 blocks 680 MB, 39 allocations 594 MB; used 2456 of 15565 MB; heap 1 (device): 236 blocks 7696 MB, 18412 allocations 7107 MB; used 8846 of 15419 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 1 free ranges, the largest 0 MB [hos host] vk: image blocks (render targets): 17 blocks 544 MB, 103 images 265 MB; 56 free ranges, the largest 31 MB [hos host] vk: image blocks (textures, compacted): 125 blocks 4000 MB, 2959 images 3871 MB; 510 free ranges, the largest 20 MB [hos host] vk: render target images: 242 reused from the pool, 393 made new, 285 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 8846 MB used of 15419 MB allowed (589 MB of it free in the blocks); textures 5682 MB (budget 11000 MB), 3078 textures [hos host] vk: budget: VRAM 7696 of 15419 MB (8846 MB by the driver, 1149 MB unaccounted): textures 5682, mirrors 923, blocks free 589, shadows 260, other buffers 130, other images 78, staging 32; RAM 2386 MB (the process's private memory 23699 MB): imports 1760, capture spares 460, captures 130, capture table 32, other buffers 4, others 0 [hos host] vk: textures: decoded ASTC 3402 MB, rendered 925 MB (52 drawn in one frame, kept: 45982 KB), other 705 MB; used in the last 8 presents 2177 MB [hos host] vk: decoded ASTC used again: 715 textures (1287 MB) copied from ones the game finalized, not decoded; 715 of those retired, 274 listed; 883 MB of blocks hashed in 158 ms [hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 7772 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 7772 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: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 8011 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x10002ac7800 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7987 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 56 (12562 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 50x57x1 NVN 0x25: 1 (11 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 101x34x1 NVN 0x25: 1 (13 KB); 101x48x1 NVN 0x25: 1 (18 KB); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x98x1 NVN 0x1: 1 (15 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.06 [hos Presentation Thread] vk: presents after the CPU's signal (600): 434 waited for it, 1.70 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: HOS_NVN_FRAME_OVERLAP (600 presents): 432 frames recorded from the limiter's wait, 1.0 recordings held each; released at the CPU's signal that met the wait 432 (early: never); the bound reached 0 times, 0 submits left to the release by it; 0 presents made in a hold (their recordings held); not begun 0 at the wait (-), 0 at its job (-); the windows 175.6 pages each, 0 in a texture's storage; the guard: 0 of their pages read by the replay in the hold (not as submitted), 0 reads in the hold whose bytes they changed (as submitted or not; of 0 touching them; 0 not kept; 0 pointer tables changed only in words that are not GPU addresses; 0 changed by the replay's own later write in the hold, 0 at the release), 0 of 0 pages its syncs copied from guest memory written again before the next wait; the events: 432 early values, 432 met by the CPU's signal, 0 signals of another value left them held, 0 never signalled [hos host] vk: HOS_NVN_FRAME_OVERLAP (600 presents): 433 limiter's waits armed (no frame waiting for the signal at their start), 432 of them begun at a later submit, 1 disarmed by the CPU's signal; 0 times told the switch is off; 432 holds begun with other queues stopped at waits for the GPU; 432 released at the signal from inside their recording [hos host] vk: HOS_NVN_FRAME_OVERLAP (600 presents): the held work's own GPU writes: 2794 pages left to the mirrors by the window's sync, 0 taken from a capture of the CPU's; the guard's pages read in the hold, 0 of them: [hos host] vk: status: 600 frames, the slowest 33.9 ms; VRAM 8.6 of 15.1 GB [hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 2 program records loaded (2.2 ms), 0 new graphics pipelines, pipelines from the driver's cache 66, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 5717 queued, 5717 loaded (median 0.53 ms, 99th percentile 5.39 ms, worst 20.95 ms, 5455 ms and 1328.3 MB read in all); 7909 programs (1124 of them compute variants without their code, 0 graphics programs no note names), 10652 graphics pipelines (0 not in a cache), 563 compute pipelines (28 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1354 pipelines made at create taken by draws; 2516 create calls with nothing kept for their stages, 0 before the index; units 8233 (5717 ready, 0 loading), 14313 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: program loads at create (play): 12434 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them) [hos host] vk: module identifiers (play): 657 known, 657 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: 399 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.16, present 0.24, draw 7.77, descriptors 3.23, texture lookups 0.11, uploads 0.00, pipelines 0.35, programs 1.36, commands 2.28, dispatch 0.92, memory sync 0.58, queue submit 0.41, slot wait 0.26 [hos host] vk: a frame: mirrors 163 (923 MB): 4.97 MB synced in 961.7 copies, 61.19 MB written back [hos host] vk: 13200 presents, 55.6 fps; a frame: 2499 draws (0 skipped), 126 dispatches, 141 passes, 150 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3078 textures (5682 MB) [hos host] vk: host time in GPU resource waits: 1.23 ms a frame (fences 0.03, timelines 1.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 382.8 full barriers recorded, 200.3 left out (nothing recorded since the one before), 16.3 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.9; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.2 ms a frame (the longest submission 3.8 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.1 (0.0 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 18.17 ms a frame): its jobs 14.09 ms a frame (submits 4.49, presents 0.28, others 9.32), idle 4.07; the game waited for room at 1 presents, 12.32 ms each (0.02 a frame; 2.37 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); 447 captures at a CPU signal; the submits' waits read in 0.059 ms a frame; readbacks: 2572 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 11.74 ms after its hand-over (33.23 at most) [hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 2.07 + 0.14 (the window's copy is in the idle), after it 3.88 + 0.48; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.03 ms of GPU time), after its last that reads it 1.00 (0.03 ms) [hos host] vk: frame ahead (600 presents): 9.27 parts a frame recorded in the signal's job, 78.4% of them took nothing that came with the signal; of the others, 2.00 a frame took pages of the signal's capture into a mirror (9.8 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 4 of 15 frames, its first three in 4 [hos host] vk: frame ahead, what came with the signal: 447 signals with a capture, each of 10.0 pages in 0.4 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: 0.70+0.09, 0.60+0.03, 0.64+0.09, 0.56+0.15, 0.48+0.04, 0.50+0.02, 0.28+0.02, 0.07+0.02, 0.03+0.02, 0.03+0.01, 0.00+0.00, 0.00+0.00 [hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #135000: event 0x100d6c801c mode 0 value 135000 (lr 0x802915c8) [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #195000: event 0x100d6c8044 mode 0 value 135086 (now 135048) (lr 0x80274390) [hos host] vk: replay reads of guest memory as submitted: 9020000 (6047505 pages from the captures) [hos rmbl::VibrationThread] hid: 28672 vibration values, strongest 0.00 since the last count [hos host] vk: the recording streams: 48 of 1 MB, the most one held 182 KB; 0 made on demand (0 MB kept now); c1 stages: at most 92 a recording; 0 descriptor pools made when a recording's own ran out (0 slots' pools made whole); a recording's pool took at most 62 sets (ub 865, sb 469, cis 3799, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2983 dirty pages from their submits' captures, 41747 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): 835 dispatches, 33683 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4677 runs, 2078.0 MB compared; 101 pages read into the shadows; 260 MB of shadows (129 MB of pages known, in 152 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10900 in captures, 4 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 13340 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 9040000 (6061241 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 191 sync waits (265 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: late pages found at the replay (600 takes): 1 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 9060000 (6074874 pages from the captures) [hos host] vk: program picks: 12871856 kept (4642291 by the last picks' textures, a uniform buffer bound since), 28980 new, 4299163 with other textures (of 17200000) [hos host] vk: replay reads of guest memory as submitted: 9080000 (6088422 pages from the captures) [hos host] vk: write-backs left out (600 submits): 714, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2655 dirty pages from their submits' captures, 41217 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): 834 dispatches, 32974 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4777 runs, 2138.7 MB compared; 104 pages read into the shadows; 260 MB of shadows (129 MB of pages known, in 152 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10831 in captures, 3 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 9100000 (6101974 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.05 over 1105 ranges, 2484 MB), 207 pages written, 207 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.010, bytes copied 0.000; 25 kept (92 MB), 10 spare buffers, 4866 texture pages copied (19 MB) [hos host] vk: readback pages refreshed from guest memory: 2823272 pages so far (0 held: may be written ahead in their submission) [hos ModuleSystemWorker4] vk: readbacks of GPU results: 1027 of 3000 waited for their write-back, 0.02 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker4] vk: invalidates since the last readbacks line: 8807 kept their virtual core (nothing there to wait for), 2969 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: replay reads of guest memory as submitted: 9120000 (6115381 pages from the captures) [hos host] vk: texture slots registered again at another size: 600000 (of 795370 registrations; slot 12532 3072x3072 -> 60x33) [hos host] vk: sparse mirrors: 76, 923 MB with memory of 1376 MB (452 MB spared); blocks given memory later 2538, given back 6414; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 328 binds (19.9 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 65 taken from the spares, 98 made new; 87 kept as spares, 0 destroyed; 22 spares now, 384 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 0.0 MB; 23 bindings followed, 21 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 2611 dirty pages from their submits' captures, 41407 from earlier ones', 0 from guest memory as it was at the replay; 24 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): 826 dispatches, 33288 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4744 runs, 2138.4 MB compared; 89 pages read into the shadows; 260 MB of shadows (131 MB of pages known, in 153 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10546 in captures, 6 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 107 live (1760 MB), 0 retired still imported (0 MB), 18 retired given back (384 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.06 [hos host] vk: replay reads of guest memory as submitted: 9140000 (6128791 pages from the captures) [hos ModuleSystemWorker5] barrier: 169691 looks: 55003 found the masks moved already, 110539 waited until they moved, 4149 for the whole 1 ms (a wait 390 us on average); 132424 wakes [hos host] vk: replay reads of guest memory as submitted: 9160000 (6142319 pages from the captures) [hos host] vk: a frame: 421 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 158 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.34, present 0.24, draw 7.85, descriptors 3.27, texture lookups 0.18, uploads 0.05, pipelines 0.36, programs 1.38, commands 2.27, dispatch 0.92, memory sync 0.56, queue submit 0.42, slot wait 0.27 [hos host] vk: a frame: mirrors 163 (923 MB): 4.98 MB synced in 960.2 copies, 61.10 MB written back [hos host] vk: 13320 presents, 56.0 fps; a frame: 2548 draws (0 skipped), 124 dispatches, 141 passes, 150 barriers, 6 submits, 0.4 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 48728 pipelines (32411 ms), 0 programs (10 failed), 3091 textures (5685 MB) [hos host] vk: host time in GPU resource waits: 1.34 ms a frame (fences 0.03, timelines 1.30, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 382.6 full barriers recorded, 200.5 left out (nothing recorded since the one before), 16.3 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.9; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 12.1 ms a frame (the longest submission 3.9 ms); 0.4 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.4 (0.9 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms [hos host] vk: program picks: 13023394 kept (4698233 by the last picks' textures, a uniform buffer bound since), 28980 new, 4347625 with other textures (of 17400000) [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: 2 program records loaded (2.2 ms), 0 new graphics pipelines, pipelines from the driver's cache 66, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 5717 queued, 5717 loaded (median 0.53 ms, 99th percentile 5.39 ms, worst 20.95 ms, 5455 ms and 1328.3 MB read in all); 7909 programs (1124 of them compute variants without their code, 0 graphics programs no note names), 10652 graphics pipelines (0 not in a cache), 563 compute pipelines (28 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 1354 pipelines made at create taken by draws; 2516 create calls with nothing kept for their stages, 0 before the index; units 8233 (5717 ready, 0 loading), 14313 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: program loads at create (close): 12434 shader modules let go once their programs' noted pipelines were built, 0 programs' modules made again for a new pipeline state (RX_VK_DROP_LOADED_MODULES=0 keeps them) [hos host] vk: module identifiers (close): 657 known, 657 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: indexed descriptor arrays (close): 2661 in 2661 of 52309 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 2661 texture (17-64: 2661); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4265 pools in the table now) [hos host] control: exiting [hos host] stop: close work done (a file the game was writing waited for, at most 3 s)

