Report rp_72c9a7fa004d23aa fail
This report disagrees with its peers.
field-and-market field.frametime_max_ms: -18.4% against peers' +20.0% field-and-market market.hitch_count: -100.0% against peers' +0.0%
Machine
- Commit
- ef200041a7500f51d086fdf12c92b38243c71e65
- Baseline
- ed9495bbbed762e654bfa268214de8e10d03ec9a
- App
- nightly-211-845707b2, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 7 7800X3D 8-Core Processor
- gpu
- NVIDIA GeForce RTX 5080
- tags
- linuxnvidianvidia-proprietarydgpu
- driver
- 620.73.4
- ram_gb
- 32
- vram_mb
- 16,303
- gpu_vendor
- nvidia
- os_version
- CachyOS (kernel 7.3.5)
Builds
main (baseline)
1,401.1 s cold
from ed9495bbbed7
- lift
- 88.4 s
- read
- 2.6 s
- finish
- 11.3 s
- compile
- 968.7 s
- shaders
- 329.9 s
PR
28 s warm
Program cache: warm
Scenarios
field-and-market RX_VK_ACQUIRE_AHEAD=1 (PR only)
ok
| Metric (median) | switch off | switch on | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| field.fps_mean | 161.18 | 169.07 | +4.9% |
| market.fps_mean | 112.83 | 111.96 | −0.8% |
| run_hitch_count | 36 | 37 | +2.8% |
| field.draws_mean | 736.6 | 720 | −2.3% |
| field.hitch_count | 0 | 0 | ±0% |
| market.draws_mean | 2,487.8 | 2,534.3 | +1.9% |
| log_forbidden_hits | 0 | 0 | ±0% |
| market.hitch_count | 1 | 0 | −100% |
| field.stutter_count | 2 | 0 | −100% |
| log_expected_missing | 2 | 2 | ±0% |
| market.stutter_count | 4 | 3 | −25% |
| run_frametime_max_ms | 3,548.45 | 3,534.43 | −0.4% |
| field.frametime_max_ms | 13.54 | 11.04 | −18.4% |
| field.frametime_p50_ms | 6.15 | 5.9 | −4.1% |
| field.frametime_p99_ms | 7.84 | 6.89 | −12.2% |
| market.frametime_max_ms | 50.55 | 21.61 | −57.3% |
| market.frametime_p50_ms | 8.37 | 8.49 | +1.4% |
| market.frametime_p99_ms | 13.55 | 13.43 | −0.9% |
| field.frametime_1pct_low_ms | 9.13 | 7.29 | −20.2% |
| market.frametime_1pct_low_ms | 16.66 | 15.12 | −9.2% |
| screenshot_diff | — | 0.12 | — |
Pictures against the switch off: field diff 0.1163 (switch off against itself ), market diff 0 (switch off against itself )
Runs (2)
| Metric | off 0 | on 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| field.fps_mean | 161.18 | 169.07 |
| market.fps_mean | 112.83 | 111.96 |
| run_hitch_count | 36 | 37 |
| field.draws_mean | 736.6 | 720 |
| field.hitch_count | 0 | 0 |
| market.draws_mean | 2,487.8 | 2,534.3 |
| log_forbidden_hits | 0 | 0 |
| market.hitch_count | 1 | 0 |
| field.stutter_count | 2 | 0 |
| log_expected_missing | 2 | 2 |
| market.stutter_count | 4 | 3 |
| run_frametime_max_ms | 3,548.45 | 3,534.43 |
| field.frametime_max_ms | 13.54 | 11.04 |
| field.frametime_p50_ms | 6.15 | 5.9 |
| field.frametime_p99_ms | 7.84 | 6.89 |
| market.frametime_max_ms | 50.55 | 21.61 |
| market.frametime_p50_ms | 8.37 | 8.49 |
| market.frametime_p99_ms | 13.55 | 13.43 |
| field.frametime_1pct_low_ms | 9.13 | 7.29 |
| market.frametime_1pct_low_ms | 16.66 | 15.12 |
| screenshot_diff | — | 0.12 |
Rules
| Scenario | Cell | Rule | Limit | switch off | switch on | Δ % | Status |
|---|---|---|---|---|---|---|---|
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | crash | False | 0 | 0 | — | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | field.fps_mean.min_delta_pct | 10 | 161.18 | 169.07 | +4.9% | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | market.fps_mean.min_delta_pct | 10 | 112.83 | 111.96 | −0.8% | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | screenshot.max_diff | 0.05 | — | 0.12 | — | fail |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | field.frametime_p99_ms.max_delta_pct | 10 | 7.84 | 6.89 | −12.2% | inconclusiveneed two usable starts per side (baseline: 1, PR: 1) |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | market.frametime_p99_ms.max_delta_pct | 10 | 13.55 | 13.43 | −0.9% | inconclusiveneed two usable starts per side (baseline: 1, PR: 1) |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | log_forbidden_hits.max | 0 | 0 | 0 | — | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | log_expected_missing.max | 0 | 2 | 2 | — | 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: program loads at create (play): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 8793 create calls with nothing kept for their stages, 0 before the index; units 8793 (0 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: program loads at create (play): 0 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): 0 known, 0 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: 414 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.15, present 0.11, draw 3.95, descriptors 1.51, texture lookups 0.05, uploads 0.00, pipelines 0.21, programs 0.62, commands 1.33, dispatch 0.42, memory sync 0.27, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 202 (908 MB): 5.02 MB synced in 977.2 copies, 18.12 MB written back [hos host] vk: 16800 presents, 119.5 fps; a frame: 2512 draws (0 skipped), 118 dispatches, 123 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3027 textures (6353 MB) [hos host] vk: host time in GPU resource waits: 0.72 ms a frame (fences 0.01, 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: 381.2 full barriers recorded, 214.6 left out (nothing recorded since the one before), 15.2 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: 32.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.5, an op 2001.5, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 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: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 8.47 ms a frame): its jobs 6.43 ms a frame (submits 2.31, presents 0.11, others 4.01), idle 2.05; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.14 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); 420 captures at a CPU signal; the submits' waits read in 0.051 ms a frame; readbacks: 2480 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 5.83 ms after its hand-over (8.01 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 0.67 + 0.26 (the window's copy is in the idle), after it 1.69 + 0.69; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms) [hos host] vk: frame ahead (600 presents): 10.12 parts a frame recorded in the signal's job, 71.9% of them took nothing that came with the signal; of the others, 2.84 a frame took pages of the signal's capture into a mirror (128.8 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 10 of 420 frames, its first three in 10 [hos host] vk: frame ahead, what came with the signal: 420 signals with a capture, each of 180.9 pages in 8.8 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any) [hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.72+0.20, 0.05+0.05, 0.28+0.10, 0.45+0.14, 0.12+0.06, 0.02+0.04, 0.01+0.03, 0.01+0.03, 0.01+0.03, 0.01+0.02, 0.00+0.01, 0.00+0.00 [hos host] vk: sparse mirrors: 78, 908 MB with memory of 1520 MB (611 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 12030; 405 binds (55.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 91 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 33 spares now, 876 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 3605.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3675 dirty pages from their submits' captures, 41389 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, 34241 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5001 runs, 632.5 MB compared; 81 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10949 in captures, 0 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 4780000 (2574210 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1140 ranges, 3087 MB), 215 pages written, 215 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (164 MB), 11 spare buffers, 5360 texture pages copied (20 MB) [hos host] vk: program picks: 6979561 kept (2251812 by the last picks' textures, a uniform buffer bound since), 3385 new, 3017053 with other textures (of 10000000) [hos host] vk: replay reads of guest memory as submitted: 4800000 (2587135 pages from the captures) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 955 of 3000 waited for their write-back, 0.04 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 8063 kept their virtual core (nothing there to wait for), 2945 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: 4820000 (2600039 pages from the captures) [hos ModuleSystemWorker2] nvn: 1250000 recordings made, 64543 live copies (21.9 MB), 1033 texture copies; 6 command buffers' segments (4.3 MB) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 237 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 126 sets (ub 1405, sb 670, cis 3910, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 714, 3502.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2932 dirty pages from their submits' captures, 41399 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): 861 dispatches, 33625 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4871 runs, 616.5 MB compared; 99 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10759 in captures, 0 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: 4840000 (2612980 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 4860000 (2625969 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: shadow staging (600 takes): 0 shadow copies from staging, 5280 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: sparse mirrors: 78, 908 MB with memory of 1520 MB (611 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 12450; 405 binds (55.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 91 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 33 spares now, 876 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 756, 3708.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3002 dirty pages from their submits' captures, 42504 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): 876 dispatches, 34774 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5173 runs, 652.2 MB compared; 82 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10872 in captures, 0 only in the collection, 36 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 4880000 (2638913 pages from the captures) [hos ModuleSystemWorker2] nvn: CommandBufferWaitEvent #225000: event 0x100d6c8008 mode 0 value 151868 (now 151849) (lr 0x8027944c) [hos host] vk: program picks: 7130851 kept (2307534 by the last picks' textures, a uniform buffer bound since), 3385 new, 3065763 with other textures (of 10200000) [hos host] vk: replay reads of guest memory as submitted: 4900000 (2651917 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1138 ranges, 3071 MB), 225 pages written, 225 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 24 kept (156 MB), 12 spare buffers, 5869 texture pages copied (22 MB) [hos host] vk: readback pages refreshed from guest memory: 2491173 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 0.01, writes collected 0.03 [hos host] vk: replay reads of guest memory as submitted: 4920000 (2664865 pages from the captures) [hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4238 dirty pages from their submits' captures, 44747 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): 946 dispatches, 37331 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5610 runs, 690.5 MB compared; 61 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11731 in captures, 0 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: late pages' fix (600 recordings with one): of 657 captures with late pages 657 fixed (85.1 pages, 85.5 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; 0 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 576 blocks (36864 KB); of the reads on the CPU, 0 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 0, of an earlier recording 0, not recorded yet 0, of this part 0; pages fixed from stamps 54722, from snapshots 1198; the shadows: 228921 pages synced from captures, 222500 made known by it, 6421 left unknown because the replay or the collection wrote them since [hos host] vk: a frame: 401 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.05, present 0.12, draw 3.86, descriptors 1.47, texture lookups 0.06, uploads 0.01, pipelines 0.19, programs 0.62, commands 1.30, dispatch 0.41, memory sync 0.27, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 202 (908 MB): 5.02 MB synced in 977.9 copies, 18.14 MB written back [hos host] vk: 16920 presents, 119.6 fps; a frame: 2490 draws (0 skipped), 118 dispatches, 123 passes, 141 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3043 textures (6360 MB) [hos host] vk: host time in GPU resource waits: 0.66 ms a frame (fences 0.01, timelines 0.65, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 380.4 full barriers recorded, 214.4 left out (nothing recorded since the one before), 15.3 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: 32.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.1 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.5, an op 1979.8, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 ms); 0.2 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.2 (0.3 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.04 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 4940000 (2677724 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 4960000 (2690669 pages from the captures) [hos host] vk: sparse mirrors: 78, 908 MB with memory of 1520 MB (611 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 12912; 405 binds (55.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 91 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 33 spares now, 876 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2929 dirty pages from their submits' captures, 46885 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): 964 dispatches, 38033 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5737 runs, 707.9 MB compared; 64 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12096 in captures, 1 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 4980000 (2703561 pages from the captures) [hos Presentation Thread] vi: 16964 frames presented (118.7 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 594, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0 [hos ModuleSystemWorker3] vk: readbacks of GPU results: 986 of 3000 waited for their write-back, 0.06 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: 8416 kept their virtual core (nothing there to wait for), 3104 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: program picks: 7281048 kept (2362551 by the last picks' textures, a uniform buffer bound since), 3385 new, 3115566 with other textures (of 10400000) [hos host] vk: replay reads of guest memory as submitted: 5000000 (2716450 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1131 ranges, 3013 MB), 228 pages written, 228 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 24 kept (158 MB), 12 spare buffers, 7197 texture pages copied (28 MB) [hos host] vk: replay reads of guest memory as submitted: 5020000 (2729334 pages from the captures) [hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3151 dirty pages from their submits' captures, 45022 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): 939 dispatches, 36651 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5458 runs, 673.3 MB compared; 76 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11706 in captures, 0 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04 [hos host] vk: replay reads of guest memory as submitted: 5040000 (2742185 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 5060000 (2755093 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: shadow staging (600 takes): 0 shadow copies from staging, 9052 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 237 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 126 sets (ub 1405, sb 670, cis 3910, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 13362; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2359 dirty pages from their submits' captures, 46933 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): 946 dispatches, 37685 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5589 runs, 690.4 MB compared; 70 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11641 in captures, 1 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 5080000 (2768026 pages from the captures) [hos SceneLowPriority] vcores: 170594 takes, 39991 waits (mean 77 us, longest 12.6 ms, 0 over HOS_VCORE_LOG_MS), 17587 kicks, 17671 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: a frame: 383 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.03, present 0.11, draw 3.84, descriptors 1.45, texture lookups 0.04, uploads 0.00, pipelines 0.20, programs 0.62, commands 1.31, dispatch 0.41, memory sync 0.29, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 203 (919 MB): 5.10 MB synced in 977.8 copies, 18.17 MB written back [hos host] vk: 17040 presents, 118.1 fps; a frame: 2452 draws (0 skipped), 118 dispatches, 123 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3049 textures (6363 MB) [hos host] vk: host time in GPU resource waits: 0.69 ms a frame (fences 0.01, timelines 0.68, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 378.5 full barriers recorded, 214.2 left out (nothing recorded since the one before), 15.2 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: 32.1; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.6, an op 1947.8, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 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: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: program picks: 7431758 kept (2418008 by the last picks' textures, a uniform buffer bound since), 3385 new, 3164856 with other textures (of 10600000) [hos host] vk: replay reads of guest memory as submitted: 5100000 (2780929 pages from the captures) [hos sead::MainThread] nvn: CommandBufferSignalEvent #155000: event 0x100d6c8044 mode 0 value 154999 (lr 0x802742f0) [hos host] vk: replay reads of guest memory as submitted: 5120000 (2793876 pages from the captures) [hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3279 dirty pages from their submits' captures, 44375 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): 921 dispatches, 36348 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5587 runs, 690.4 MB compared; 63 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11448 in captures, 1 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.05 over 1134 ranges, 3005 MB), 228 pages written, 228 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (150 MB), 10 spare buffers, 7709 texture pages copied (30 MB) [hos host] vk: replay reads of guest memory as submitted: 5140000 (2806841 pages from the captures) [hos host] vk: queues ordered by their events: 90000 submissions stopped at a wait, 89998 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 229966, not met 0; captures at a CPU event's wait 7962, 0 of them at a wait met on arrival [hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #230000: event 0x100d6c8008 mode 0 value 155668 (now 155649) (lr 0x8027944c) [hos host] vk: readback pages refreshed from guest memory: 2564460 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 5160000 (2819736 pages from the captures) [hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 360000 so far (x1 0x11791f0000 x2 0x2 x3 0x11791f0000 x4 0x654040) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 13812; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2927 dirty pages from their submits' captures, 44667 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): 916 dispatches, 36260 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5406 runs, 671.7 MB compared; 82 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11486 in captures, 0 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 973 of 3000 waited for their write-back, 0.06 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: 8526 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: 5180000 (2832631 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 5200000 (2845609 pages from the captures) [hos host] vk: program picks: 7582448 kept (2473352 by the last picks' textures, a uniform buffer bound since), 3385 new, 3214166 with other textures (of 10800000) [hos sead::MainThread] nvn: GPU waits in 5 s: 437 sync waits (193 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: write-backs left out (600 submits): 819, 4017.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3053 dirty pages from their submits' captures, 46870 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): 961 dispatches, 38081 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5665 runs, 691.4 MB compared; 66 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12119 in captures, 2 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 5220000 (2858571 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 5240000 (2871482 pages from the captures) [hos host] vk: a frame: 389 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.01, present 0.10, draw 3.85, descriptors 1.46, texture lookups 0.04, uploads 0.00, pipelines 0.20, programs 0.62, commands 1.30, dispatch 0.41, memory sync 0.29, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 203 (919 MB): 5.01 MB synced in 978.2 copies, 18.18 MB written back [hos host] vk: 17160 presents, 118.5 fps; a frame: 2451 draws (0 skipped), 119 dispatches, 123 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3051 textures (6363 MB) [hos host] vk: host time in GPU resource waits: 0.62 ms a frame (fences 0.01, timelines 0.61, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 379.2 full barriers recorded, 214.2 left out (nothing recorded since the one before), 15.2 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: 32.1; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.0 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.6, an op 1939.5, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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 Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.04 over 1109 ranges, 2867 MB), 215 pages written, 215 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.008; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 24 kept (162 MB), 12 spare buffers, 7334 texture pages copied (28 MB) [hos host] vk: replay reads of guest memory as submitted: 5260000 (2884385 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: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 14274; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2860 dirty pages from their submits' captures, 45804 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): 941 dispatches, 37129 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5749 runs, 709.2 MB compared; 54 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11755 in captures, 0 only in the collection, 39 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: render targets drawn over from another start, let go: 1166 so far (4667 MB), 1041 of them (4334 MB) between the passes [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 10753 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 5280000 (2897317 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 5300000 (2910278 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.04 [hos host] vk: program picks: 7733062 kept (2528488 by the last picks' textures, a uniform buffer bound since), 3385 new, 3263552 with other textures (of 11000000) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 237 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 126 sets (ub 1405, sb 670, cis 3910, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3750 dirty pages from their submits' captures, 43957 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): 922 dispatches, 36270 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5486 runs, 672.8 MB compared; 74 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11584 in captures, 0 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 5320000 (2923174 pages from the captures) [hos ModuleSystemWorker4] nvn: 1300000 recordings made, 64599 live copies (22.8 MB), 1033 texture copies; 3 command buffers' segments (4.1 MB) [hos host] vk: replay reads of guest memory as submitted: 5340000 (2936167 pages from the captures) [hos host] vk: recorder: 18848337 packets run in 10.0 s (busy 2.78 s, spun idle 0.23 s, slept 21156 times, 7995 of them under 200 us), 0 calls made directly (no room); 39692 batches over 1181 frames (33.6 a frame, 475 packets a batch), 19448 parts ended and submitted by it; the render thread (the replay lock's holder) waited for it 13 times, 1.24 ms (0.0 times, 0.00 ms a frame); every thread 280 times, 7.93 ms in all, the longest 1.30 ms; the queue's lock 250/3.90 ms (max 1.30), a part's submit 17/2.80 ms (max 0.77), vkDestroyImageView 8/0.95 ms (max 0.30), vkQueueBindSparse 3/0.17 ms (max 0.17), vmaFreeMemory 2/0.11 ms (max 0.11) [hos host] vk: recorder: of its busy 2.78 s, 0.30 s in parts' ends and submits (the longest 1.55 ms), 0.00 s of that blocked on the queue's lock (0 times, the longest 0.00 ms), so 0.30 s in the ends, submits and holds; 2.48 s running the other packets; 15960 packets a frame [hos BaseProcExecutor2] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 43 made): 33709765 lookups, 255104 missed (0.76 %) [hos host] vk: replay reads of guest memory as submitted: 5360000 (2949098 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 978 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 ModuleSystemWorker2] vk: invalidates since the last readbacks line: 8093 kept their virtual core (nothing there to wait for), 2915 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 14706; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 3605.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2950 dirty pages from their submits' captures, 42151 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): 865 dispatches, 34233 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5066 runs, 633.5 MB compared; 89 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10948 in captures, 1 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1096 ranges, 2803 MB), 224 pages written, 224 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (148 MB), 11 spare buffers, 7466 texture pages copied (29 MB) [hos host] vk: replay reads of guest memory as submitted: 5380000 (2962010 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 2637788 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 5400000 (2974907 pages from the captures) [hos host] vk: program picks: 7884773 kept (2584448 by the last picks' textures, a uniform buffer bound since), 3385 new, 3311841 with other textures (of 11200000) [hos host] vk: a frame: 412 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.03, present 0.10, draw 3.84, descriptors 1.45, texture lookups 0.04, uploads 0.00, pipelines 0.20, programs 0.61, commands 1.32, dispatch 0.41, memory sync 0.27, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 203 (919 MB): 5.03 MB synced in 978.4 copies, 18.15 MB written back [hos host] vk: 17280 presents, 119.9 fps; a frame: 2508 draws (0 skipped), 120 dispatches, 123 passes, 140 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3051 textures (6363 MB) [hos host] vk: host time in GPU resource waits: 0.67 ms a frame (fences 0.01, timelines 0.66, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 382.6 full barriers recorded, 214.1 left out (nothing recorded since the one before), 15.2 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: 32.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.1 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.5, an op 1997.9, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.2 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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: write-backs left out (600 submits): 714, 3502.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3403 dirty pages from their submits' captures, 41008 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): 860 dispatches, 33649 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4927 runs, 617.4 MB compared; 79 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11024 in captures, 0 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] nvn: CommandBufferWaitEvent #235000: event 0x100d6c8008 mode 0 value 159468 (now 159449) (lr 0x8027944c) [hos host] vk: replay reads of guest memory as submitted: 5420000 (2987859 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: replay reads of guest memory as submitted: 5440000 (3000777 pages from the captures) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #160000: event 0x100d6c8004 mode 0 value 159999 (lr 0x80291504) [hos host] vk: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 15120; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 735, 3605.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2428 dirty pages from their submits' captures, 42375 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): 859 dispatches, 34074 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5041 runs, 634.1 MB compared; 102 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10891 in captures, 0 only in the collection, 35 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 5460000 (3013662 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: replay reads of guest memory as submitted: 5480000 (3026545 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 12532 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1087 ranges, 2773 MB), 235 pages written, 235 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.011; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (162 MB), 10 spare buffers, 7978 texture pages copied (31 MB) [hos host] vk: replay reads of guest memory as submitted: 5500000 (3039464 pages from the captures) [hos host] vk: write-backs left out (600 submits): 735, 3605.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2772 dirty pages from their submits' captures, 41678 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): 854 dispatches, 33886 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5035 runs, 634.0 MB compared; 90 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 10653 in captures, 0 only in the collection, 34 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: program picks: 8036426 kept (2640559 by the last picks' textures, a uniform buffer bound since), 3385 new, 3360188 with other textures (of 11400000) [hos host] vk: replay reads of guest memory as submitted: 5520000 (3052396 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 5540000 (3065289 pages from the captures) [hos ModuleSystemWorker5] vk: readbacks of GPU results: 954 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 ModuleSystemWorker5] vk: invalidates since the last readbacks line: 8515 kept their virtual core (nothing there to wait for), 3005 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 237 KB; 0 made on demand (0 MB kept now); c1 stages: at most 95 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 126 sets (ub 1405, sb 670, cis 3910, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 79, 919 MB with memory of 1536 MB (616 MB spared); blocks given memory later 3653, given back 10503; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 15552; 406 binds (55.3 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 92 taken from the spares, 111 made new; 124 kept as spares, 0 destroyed; 32 spares now, 860 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 777, 3811.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3294 dirty pages from their submits' captures, 44835 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): 936 dispatches, 36636 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5442 runs, 672.2 MB compared; 57 pages read into the shadows; 372 MB of shadows (114 MB of pages known, in 157 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11947 in captures, 0 only in the collection, 37 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 130 live (2128 MB), 0 retired still imported (0 MB), 43 retired given back (924 MB) [hos host] vk: replay reads of guest memory as submitted: 5560000 (3078229 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: memory: working set 12231 MB (peak 12328), private 3005 MB, staging 144 MB in 9 arenas, 27 made so far (10 ms) [hos host] vk: memory heaps: heap 0 (device): 260 blocks 8578 MB, 18513 allocations 8004 MB; used 8684 of 13835 MB; heap 1 (system): 21 blocks 928 MB, 39 allocations 866 MB; used 3073 of 23769 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): 18 blocks 576 MB, 118 images 233 MB; 55 free ranges, the largest 32 MB [hos host] vk: image blocks (textures, compacted): 143 blocks 4576 MB, 2915 images 4527 MB; 1382 free ranges, the largest 21 MB [hos host] vk: render target images: 518 reused from the pool, 958 made new, 831 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 8684 MB used of 13835 MB allowed (573 MB of it free in the blocks); textures 6363 MB (budget 10539 MB), 3051 textures [hos host] vk: budget: VRAM 8578 of 13835 MB (8684 MB by the driver, 106 MB unaccounted): textures 6363, mirrors 919, blocks free 573, shadows 372, staging 144, other buffers 142, other images 63; RAM 3027 MB (the process's private memory 3005 MB): imports 2128, capture spares 698, captures 158, capture table 33, other buffers 10, others 0 [hos host] vk: textures: decoded ASTC 3884 MB, rendered 1154 MB (53 drawn in one frame, kept: 38279 KB), other 957 MB; used in the last 8 presents 2202 MB [hos host] vk: decoded ASTC used again: 29 textures (71 MB) copied from ones the game finalized, not decoded; 29 of those retired, 106 listed; 763 MB of blocks hashed in 40 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 4486 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 4486 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 10440 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x1000105fc00 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 9033 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 68 (15153 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); 114x121x1 NVN 0x1: 1 (13 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 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); 260x260x1 NVN 0xd: 34 (5982 KB); 262x104x1 NVN 0x1: 3 (79 KB); [hos Presentation Thread] vk: presents after the CPU's signal (600): 356 waited for it, 0.45 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 13.1 ms; VRAM 8.5 of 13.5 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: 0 program records loaded (0.0 ms), 1853 new graphics pipelines, pipelines from the driver's cache 572, from the start's cache 34, compiled 1390; 280128 draws and dispatches left out, 1218 waits (5854.8 ms) [hos host] vk: program loads at create (play): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 8793 create calls with nothing kept for their stages, 0 before the index; units 8793 (0 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: program loads at create (play): 0 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): 0 known, 0 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: 415 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 6606 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 6.15, present 0.10, draw 3.94, descriptors 1.48, texture lookups 0.04, uploads 0.00, pipelines 0.20, programs 0.63, commands 1.35, dispatch 0.41, memory sync 0.27, queue submit 0.00, slot wait 0.02 [hos host] vk: a frame: mirrors 203 (919 MB): 5.02 MB synced in 976.9 copies, 18.14 MB written back [hos host] vk: 17400 presents, 117.4 fps; a frame: 2512 draws (0 skipped), 119 dispatches, 123 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 2052 pipelines (238155 ms), 1361 programs (0 failed), 3051 textures (6363 MB) [hos host] vk: host time in GPU resource waits: 0.60 ms a frame (fences 0.01, timelines 0.59, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 381.8 full barriers recorded, 214.3 left out (nothing recorded since the one before), 15.2 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: 32.1; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: a frame: indirect mesh draws' arguments (RX_VK_MESH_CONV=2): 0.0 converted one by one, 34.1 from 24.0 batches at the game's barriers (38.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 0.0 left as they are (no mesh shaders); scans ended at a barrier 131.7, an op 1993.9, the end 7.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: 4: 2.0; 5: 20.0; 48: 6.0; [hos host] vk: GPU time 5.1 ms a frame (the longest submission 1.8 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.0 (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, 8.43 ms a frame): its jobs 6.27 ms a frame (submits 2.31, presents 0.11, others 3.85), idle 2.16; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.19 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); 412 captures at a CPU signal; the submits' waits read in 0.051 ms a frame; readbacks: 2335 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 5.67 ms after its hand-over (9.84 at most) [hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 0.68 + 0.26 (the window's copy is in the idle), after it 1.69 + 0.67; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms) [hos host] vk: frame ahead (600 presents): 9.63 parts a frame recorded in the signal's job, 70.5% of them took nothing that came with the signal; of the others, 2.84 a frame took pages of the signal's capture into a mirror (121.7 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 7 of 412 frames, its first three in 7 [hos host] vk: frame ahead, what came with the signal: 412 signals with a capture, each of 172.2 pages in 8.6 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any) [hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.71+0.20, 0.05+0.05, 0.29+0.11, 0.48+0.13, 0.11+0.06, 0.01+0.03, 0.01+0.03, 0.01+0.03, 0.01+0.03, 0.00+0.01, 0.00+0.00, 0.00+0.00 [hos host] vk: replay reads of guest memory as submitted: 5580000 (3091152 pages from the captures) [hos host] vk: write-backs left out (600 submits): 798, 3914.3 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3332 dirty pages from their submits' captures, 44802 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): 926 dispatches, 36771 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5582 runs, 690.3 MB compared; 58 pages read into the shadows; 372 MB of shadows (115 MB of pages known, in 158 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 11570 in captures, 0 only in the collection, 38 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 5600000 (3104000 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.04 over 1087 ranges, 2773 MB), 225 pages written, 225 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (150 MB), 10 spare buffers, 7978 texture pages copied (31 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: 0 program records loaded (0.0 ms), 1853 new graphics pipelines, pipelines from the driver's cache 572, from the start's cache 34, compiled 1390; 280128 draws and dispatches left out, 1218 waits (5854.8 ms) [hos host] vk: program loads at create (close): 0 queued, 0 loaded (median 0.00 ms, 99th percentile 0.00 ms, worst 0.00 ms, 0 ms and 0.0 MB read in all); 0 programs (0 of them compute variants without their code, 0 graphics programs no note names), 0 graphics pipelines (0 not in a cache), 0 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 0 pipelines made at create taken by draws; 8793 create calls with nothing kept for their stages, 0 before the index; units 8793 (0 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: program loads at create (close): 0 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): 0 known, 0 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): 116 in 116 of 2636 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 116 texture (17-64: 116); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4258 pools in the table now) [hos host] vk: program picks: 8187470 kept (2696151 by the last picks' textures, a uniform buffer bound since), 3385 new, 3409144 with other textures (of 11600000) [hos host] vk: pipeline cache: play file 11 saved (2126 KB): 1 pipelines, 0 from the driver's cache, 1 compiled; 0 more from the start's cache [hos host] control: exiting [hos host] stop: close work done (a file the game was writing waited for, at most 3 s)

