Report rp_f6c52862f071f12f fail
This report disagrees with its peers.
field-and-market market.frametime_max_ms: -22.6% against peers' +9.0% field-and-market market.stutter_count: -24.4% against peers' -50.0% field-and-market run_frametime_max_ms: -51.7% against peers' -16.6%
Machine
- Commit
- ef200041a7500f51d086fdf12c92b38243c71e65
- Baseline
- ed9495bbbed762e654bfa268214de8e10d03ec9a
- App
- nightly-211-845707b2, attempt 7
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 5 5600X 6-Core Processor
- gpu
- AMD Radeon RX 6600 (RADV NAVI23)
- tags
- linuxamdradvdgpu
- driver
- 26.2.6
- ram_gb
- 64
- vram_mb
- 8,176
- gpu_vendor
- amd
- os_version
- EndeavourOS (kernel 7.3.4)
Builds
main (baseline)
1,848.9 s cold
from ed9495bbbed7
- lift
- 151.1 s
- read
- 4.3 s
- finish
- 37.9 s
- compile
- 871.6 s
- shaders
- 783 s
PR
27.3 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 | 96.31 | 91.73 | −4.8% |
| market.fps_mean | 37.77 | 41.22 | +9.1% |
| run_hitch_count | 204 | 192 | −5.9% |
| field.draws_mean | 676.4 | 678.5 | +0.3% |
| field.hitch_count | 5 | 2 | −60% |
| market.draws_mean | 2,456.1 | 2,476.2 | +0.8% |
| log_forbidden_hits | 0 | 0 | ±0% |
| market.hitch_count | 114 | 91 | −20.2% |
| field.stutter_count | 7 | 5 | −28.6% |
| log_expected_missing | 2 | 2 | ±0% |
| market.stutter_count | 123 | 93 | −24.4% |
| run_frametime_max_ms | 2,679.91 | 1,293.34 | −51.7% |
| field.frametime_max_ms | 62.93 | 61.61 | −2.1% |
| field.frametime_p50_ms | 10.13 | 10.67 | +5.3% |
| field.frametime_p99_ms | 13.92 | 16.21 | +16.5% |
| market.frametime_max_ms | 104.07 | 80.55 | −22.6% |
| market.frametime_p50_ms | 17.8 | 17.81 | +0.1% |
| market.frametime_p99_ms | 76.06 | 72.89 | −4.2% |
| field.frametime_1pct_low_ms | 29.1 | 24.25 | −16.7% |
| market.frametime_1pct_low_ms | 84.23 | 76.27 | −9.5% |
| screenshot_diff | — | 0.05 | — |
Pictures against the switch off: field diff 0.0468 (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 | 96.31 | 91.73 |
| market.fps_mean | 37.77 | 41.22 |
| run_hitch_count | 204 | 192 |
| field.draws_mean | 676.4 | 678.5 |
| field.hitch_count | 5 | 2 |
| market.draws_mean | 2,456.1 | 2,476.2 |
| log_forbidden_hits | 0 | 0 |
| market.hitch_count | 114 | 91 |
| field.stutter_count | 7 | 5 |
| log_expected_missing | 2 | 2 |
| market.stutter_count | 123 | 93 |
| run_frametime_max_ms | 2,679.91 | 1,293.34 |
| field.frametime_max_ms | 62.93 | 61.61 |
| field.frametime_p50_ms | 10.13 | 10.67 |
| field.frametime_p99_ms | 13.92 | 16.21 |
| market.frametime_max_ms | 104.07 | 80.55 |
| market.frametime_p50_ms | 17.8 | 17.81 |
| market.frametime_p99_ms | 76.06 | 72.89 |
| field.frametime_1pct_low_ms | 29.1 | 24.25 |
| market.frametime_1pct_low_ms | 84.23 | 76.27 |
| screenshot_diff | — | 0.05 |
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 | 96.31 | 91.73 | −4.8% | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | market.fps_mean.min_delta_pct | 10 | 37.77 | 41.22 | +9.1% | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | screenshot.max_diff | 0.05 | — | 0.05 | — | pass |
| field-and-market | RX_VK_ACQUIRE_AHEAD=1 (PR only) | field.frametime_p99_ms.max_delta_pct | 10 | 13.92 | 16.21 | +16.5% | 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 | 76.06 | 72.89 | −4.2% | 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 |
Log (PR side, end)
[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 7842 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.28, present 0.19, draw 7.85, descriptors 2.40, texture lookups 0.08, uploads 0.00, pipelines 0.32, programs 1.10, commands 3.54, dispatch 1.13, memory sync 0.39, queue submit 1.36, slot wait 0.15 [hos host] vk: a frame: mirrors 235 (971 MB): 5.10 MB synced in 980.7 copies, 18.20 MB written back [hos host] vk: 31920 presents, 47.6 fps; a frame: 2442 draws (38 skipped), 123 dispatches, 119 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2343 pipelines (249 ms), 1357 programs (10 failed), 2214 textures (2920 MB) [hos host] vk: host time in GPU resource waits: 7.54 ms a frame (fences 0.00, timelines 7.54, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 425.7 full barriers recorded, 249.1 left out (nothing recorded since the one before), 16.1 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: 41.1; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 11.0 ms a frame (the longest submission 5.3 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: mirror of pool 0x7f9dc00000 (4 MB) given back: idle, 6051 submissions since its sync [hos host] vk: mirror of pool 0x7fbec00000 (4 MB) given back: idle, 6051 submissions since its sync [hos host] vk: mirror of pool 0x7f91400000 (12 MB) given back: idle, 6049 submissions since its sync [hos host] vk: mirror of pool 0x7fbcc00000 (4 MB) given back: idle, 6049 submissions since its sync [hos ModuleSystemWorker4] nvn: 1100000 recordings made, 63610 live copies (21.9 MB), 1021 texture copies; 6 command buffers' segments (4.4 MB) [hos host] vk: mirror of pool 0x7fe2400000 (4 MB) given back: idle, 6018 submissions since its sync [hos host] vk: sparse mirrors: 76, 953 MB with memory of 1224 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 395 binds (185.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 159 kept as spares, 0 destroyed; 33 spares now, 1208 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4106 dirty pages from their submits' captures, 38985 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): 801 dispatches, 32404 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5271 runs, 618.6 MB compared; 84 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12897 in captures, 2 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: replay reads of guest memory as submitted: 1780000 (889465 pages from the captures) [hos sead::MainThread] nvn: CommandBufferWaitEvent #205000: event 0x100d6c8048 mode 0 value 98174 (now 98155) (lr 0x806661f8) [hos host] vk: in play: compute 09cc9a93a2d7dd81 (09cc9a93a2d7dd81 0000000000000000), inputs 0000000000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants [hos host] vk: in play: graphics 2617da75ccd7f311 (5f73d498e6000238 62a339dfd2622657), inputs 0000000000000000, outputs 00 00 00 00 00 00 00 00, 0 other variants [hos host] vk: mirror of pool 0x7f7c000000 (4 MB) given back: idle, 6025 submissions since its sync [hos host] vk: 160 mirrors given back (1693 MB in all); 949 MB of mirrors now, 44 MB of them idle and kept for what the GPU wrote there alone [hos host] vk: replay reads of guest memory as submitted: 1800000 (902652 pages from the captures) [hos host] vk: program picks: 2638928 kept (721378 by the last picks' textures, a uniform buffer bound since), 39473 new, 1321598 with other textures (of 4000000) [hos host] vk: replay reads of guest memory as submitted: 1820000 (915757 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 19171 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4066 dirty pages from their submits' captures, 39066 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): 797 dispatches, 32472 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5161 runs, 600.6 MB compared; 87 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12968 in captures, 3 only in the collection, 21 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] vk: capture: a submit 0.17 ms (lock 0.00, scan 0.05 over 1060 ranges, 3517 MB), 228 pages written, 228 copied (0.9 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; 25 kept (112 MB), 5 spare buffers, 5681 texture pages copied (22 MB) [hos host] vk: replay reads of guest memory as submitted: 1840000 (928965 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 1860000 (941987 pages from the captures) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 714, 3502.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4378 dirty pages from their submits' captures, 39984 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): 811 dispatches, 33360 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5246 runs, 601.9 MB compared; 74 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13391 in captures, 1 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.04 [hos host] vk: queues ordered by their events: 126000 submissions stopped at a wait, 124974 went on once it was reached, 1024 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 81 (stopped 50.25 ms at most); waits met 205587, not met 0; captures at a CPU event's wait 14599, 0 of them at a wait met on arrival [hos host] vk: replay reads of guest memory as submitted: 1880000 (955211 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 1900000 (968449 pages from the captures) [hos ModuleSystemWorker4] vk: readbacks of GPU results: 916 of 3000 waited for their write-back, 0.10 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: 8403 kept their virtual core (nothing there to wait for), 2861 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: readback pages refreshed from guest memory: 1439974 pages so far (0 held: may be written ahead in their submission) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 231 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 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 247 sets (ub 2816, sb 1334, cis 13516, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3263 dirty pages from their submits' captures, 39952 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): 804 dispatches, 32495 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5301 runs, 617.7 MB compared; 102 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12977 in captures, 3 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #100000: event 0x100d6c8000 mode 0 value 99999 (lr 0x80291440) [hos rmbl::VibrationThread] vcores: 83673 takes, 16236 waits (mean 105 us, longest 24.9 ms, 0 over HOS_VCORE_LOG_MS), 7242 kicks, 7516 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 1920000 (981543 pages from the captures) [hos host] vk: program picks: 2789581 kept (776712 by the last picks' textures, a uniform buffer bound since), 39473 new, 1370945 with other textures (of 4200000) [hos host] vk: a frame: 397 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos host] vk: a frame: 1.2 draws left out (not ready), 0.01 waits for shaders or pipelines (0.0 ms); translation 7847 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.29, present 0.18, draw 8.46, descriptors 2.54, texture lookups 0.08, uploads 0.00, pipelines 0.33, programs 1.19, commands 3.85, dispatch 1.36, memory sync 0.37, queue submit 1.50, slot wait 0.12 [hos host] vk: a frame: mirrors 235 (949 MB): 5.10 MB synced in 982.7 copies, 18.21 MB written back [hos host] vk: 32040 presents, 42.3 fps; a frame: 2445 draws (38 skipped), 124 dispatches, 119 passes, 151 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2346 pipelines (250 ms), 1359 programs (10 failed), 2218 textures (2921 MB) [hos host] vk: host time in GPU resource waits: 9.63 ms a frame (fences 0.00, timelines 9.63, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 427.7 full barriers recorded, 250.7 left out (nothing recorded since the one before), 16.2 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: 42.6; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 10.5 ms a frame (the longest submission 5.6 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] vi: 32044 frames presented (44.8 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 29, 15.5-17.8 114, 17.8-22 51, 22-30 10, 30-40 1, over 40 20 [hos sead::MainThread] nvn: GPU waits in 5 s: 218 sync waits (1709 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 1940000 (994800 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.05 over 1059 ranges, 3519 MB), 223 pages written, 223 copied (0.9 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; 24 kept (112 MB), 5 spare buffers, 7221 texture pages copied (28 MB) [hos host] vk: late pages found at the replay (600 takes): 134 pages in 37 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3726 dirty pages from their submits' captures, 39168 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): 795 dispatches, 32340 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5146 runs, 600.3 MB compared; 93 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12853 in captures, 2 only in the collection, 25 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: replay reads of guest memory as submitted: 1960000 (1008048 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 1980000 (1021303 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2000000 (1034548 pages from the captures) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3915 dirty pages from their submits' captures, 38955 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): 801 dispatches, 32376 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5130 runs, 601.1 MB compared; 98 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12877 in captures, 3 only in the collection, 20 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 0.04, writes collected 0.04 [hos host] vk: replay reads of guest memory as submitted: 2020000 (1047861 pages from the captures) [hos host] vk: program picks: 2940098 kept (832277 by the last picks' textures, a uniform buffer bound since), 39473 new, 1420428 with other textures (of 4400000) [hos host] vk: replay reads of guest memory as submitted: 2040000 (1061118 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 14027 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4189 dirty pages from their submits' captures, 38706 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): 794 dispatches, 32374 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5121 runs, 600.3 MB compared; 87 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12954 in captures, 3 only in the collection, 20 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #210000: event 0x100d6c8048 mode 0 value 101974 (now 101955) (lr 0x806661f8) [hos host] vk: replay reads of guest memory as submitted: 2060000 (1074379 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.17 ms (lock 0.00, scan 0.06 over 1059 ranges, 3519 MB), 231 pages written, 231 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.029; 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 (88 MB), 5 spare buffers, 8531 texture pages copied (33 MB) [hos host] vk: late pages' fix (600 recordings with one): of 609 captures with late pages 605 fixed (77.6 pages, 78.3 fixes a capture), waited as before: 0 no pool, 4 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; 108 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 864 blocks (55296 KB); of the reads on the CPU, 5 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 12, of an earlier recording 91, not recorded yet 0, of this part 0; pages fixed from stamps 46076, from snapshots 861; the shadows: 180532 pages synced from captures, 179631 made known by it, 901 left unknown because the replay or the collection wrote them since [hos host] vk: replay reads of guest memory as submitted: 2080000 (1087624 pages from the captures) [hos host] vk: a frame: 406 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 7847 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 15.15, present 0.19, draw 8.86, descriptors 2.64, texture lookups 0.14, uploads 0.01, pipelines 0.35, programs 1.21, commands 4.12, dispatch 1.41, memory sync 0.47, queue submit 1.60, slot wait 0.12 [hos host] vk: a frame: mirrors 235 (949 MB): 5.07 MB synced in 980.3 copies, 18.19 MB written back [hos host] vk: 32160 presents, 40.2 fps; a frame: 2453 draws (38 skipped), 124 dispatches, 118 passes, 152 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2346 pipelines (250 ms), 1359 programs (10 failed), 2226 textures (2922 MB) [hos host] vk: host time in GPU resource waits: 10.69 ms a frame (fences 0.00, timelines 10.69, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 428.0 full barriers recorded, 252.0 left out (nothing recorded since the one before), 15.0 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: 43.5; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 10.7 ms a frame (the longest submission 6.1 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 (0.0 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: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3427 dirty pages from their submits' captures, 39332 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): 795 dispatches, 32327 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5117 runs, 599.9 MB compared; 110 pages read into the shadows; 272 MB of shadows (57 MB of pages known, in 106 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13320 in captures, 4 only in the collection, 22 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker3] vk: readbacks of GPU results: 898 of 3000 waited for their write-back, 0.12 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: 8126 kept their virtual core (nothing there to wait for), 3138 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: 2100000 (1100824 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2120000 (1114102 pages from the captures) [hos ModuleSystemWorker5] nvn: 1150000 recordings made, 63630 live copies (21.9 MB), 1021 texture copies; 7 command buffers' segments (4.4 MB) [hos host] vk: readback pages refreshed from guest memory: 1513435 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 2140000 (1127150 pages from the captures) [hos host] vk: program picks: 3090686 kept (888096 by the last picks' textures, a uniform buffer bound since), 39473 new, 1469840 with other textures (of 4600000) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 231 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 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 247 sets (ub 2816, sb 1334, cis 13516, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3199 dirty pages from their submits' captures, 39826 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): 803 dispatches, 32427 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5132 runs, 600.2 MB compared; 93 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12489 in captures, 3 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.04 [hos host] vk: replay reads of guest memory as submitted: 2160000 (1140284 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 151 pages in 36 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 2180000 (1153322 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.19 ms (lock 0.00, scan 0.06 over 1060 ranges, 3521 MB), 225 pages written, 225 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.025; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.011, bytes copied 0.000; 24 kept (86 MB), 5 spare buffers, 4173 texture pages copied (16 MB) [hos host] vk: write-backs left out (600 submits): 714, 3502.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3957 dirty pages from their submits' captures, 40022 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): 813 dispatches, 33217 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5291 runs, 617.8 MB compared; 89 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13300 in captures, 2 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos BaseProcExecutor0] vcores: 74723 takes, 13943 waits (mean 107 us, longest 16.4 ms, 0 over HOS_VCORE_LOG_MS), 6223 kicks, 6508 yields, 0 starved grants, 0 escapes in 5 s [hos BaseProcExecutor2] sync: object cache (HOS_OBJ_CACHE=16384 a thread, 44 made): 12687600 lookups, 93371 missed (0.74 %) [hos host] vk: replay reads of guest memory as submitted: 2200000 (1166387 pages from the captures) [hos Presentation Thread] vi: 32243 frames presented (39.7 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 22, 15.5-17.8 85, 17.8-22 51, 22-30 13, 30-40 2, over 40 26 [hos sead::MainThread] nvn: GPU waits in 5 s: 188 sync waits (1946 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 2220000 (1179411 pages from the captures) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4027 dirty pages from their submits' captures, 38938 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): 812 dispatches, 32348 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5138 runs, 601.3 MB compared; 88 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12939 in captures, 2 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: replay reads of guest memory as submitted: 2240000 (1192503 pages from the captures) [hos host] vk: program picks: 3241193 kept (943460 by the last picks' textures, a uniform buffer bound since), 39473 new, 1519333 with other textures (of 4800000) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 15680 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: a frame: 397 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 7847 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.55, present 0.17, draw 8.59, descriptors 2.63, texture lookups 0.14, uploads 0.03, pipelines 0.34, programs 1.19, commands 3.90, dispatch 1.49, memory sync 0.44, queue submit 1.52, slot wait 0.13 [hos host] vk: a frame: mirrors 235 (949 MB): 5.08 MB synced in 979.7 copies, 18.19 MB written back [hos host] vk: 32280 presents, 40.1 fps; a frame: 2431 draws (38 skipped), 124 dispatches, 117 passes, 152 barriers, 6 submits, 0.3 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2346 pipelines (250 ms), 1359 programs (10 failed), 2250 textures (2929 MB) [hos host] vk: host time in GPU resource waits: 10.61 ms a frame (fences 0.00, timelines 10.61, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 427.5 full barriers recorded, 251.8 left out (nothing recorded since the one before), 14.4 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: 43.6; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 11.0 ms a frame (the longest submission 5.9 ms); 0.3 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.0 MB), ASTC or BC 0.3 (0.1 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.05 MB unswizzled on the CPU in 0.01 ms [hos host] vk: replay reads of guest memory as submitted: 2260000 (1205597 pages from the captures) [hos sead::MainThread] nvn: CommandBufferSignalEvent #105000: event 0x100d6c8010 mode 0 value 105000 (lr 0x80660adc) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3473 dirty pages from their submits' captures, 39429 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): 800 dispatches, 32357 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5142 runs, 600.3 MB compared; 200 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12917 in captures, 5 only in the collection, 25 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2280000 (1218647 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.04 [hos host] vk: render targets drawn over from another start, let go: 1235 so far (4717 MB), 1106 of them (4056 MB) between the passes [hos ModuleSystemWorker1] vk: readbacks of GPU results: 908 of 3000 waited for their write-back, 0.13 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: 8484 kept their virtual core (nothing there to wait for), 3036 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: 2300000 (1231716 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.21 ms (lock 0.00, scan 0.06 over 1061 ranges, 3533 MB), 228 pages written, 228 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.029; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.012, bytes copied 0.000; 25 kept (106 MB), 6 spare buffers, 5323 texture pages copied (20 MB) [hos rmbl::VibrationThread] hid: 24576 vibration values, strongest 0.00 since the last count [hos host] vk: replay reads of guest memory as submitted: 2320000 (1244765 pages from the captures) [hos host] vk: sparse mirrors: 75, 949 MB with memory of 1220 MB (270 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 396 binds (185.5 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 160 kept as spares, 0 destroyed; 34 spares now, 1212 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 714, 3502.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3889 dirty pages from their submits' captures, 40192 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): 816 dispatches, 33236 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5357 runs, 618.7 MB compared; 78 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13316 in captures, 1 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #215000: event 0x100d6c8048 mode 0 value 105774 (now 105755) (lr 0x806661f8) [hos host] vk: replay reads of guest memory as submitted: 2340000 (1257798 pages from the captures) [hos host] vk: program picks: 3391908 kept (999061 by the last picks' textures, a uniform buffer bound since), 39473 new, 1568618 with other textures (of 5000000) [hos host] vk: readback pages refreshed from guest memory: 1586527 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 2360000 (1270858 pages from the captures) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 231 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 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 247 sets (ub 2816, sb 1334, cis 13516, si 0, utb 0, stb 0) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4266 dirty pages from their submits' captures, 38575 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): 793 dispatches, 32272 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5182 runs, 601.2 MB compared; 80 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12965 in captures, 2 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2380000 (1283952 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 315 pages in 31 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 2400000 (1297052 pages from the captures) [hos host] vk: mirror of pool 0x7fb2000000 (40 MB) given back: idle, 6040 submissions since its sync [hos host] vk: sparse mirrors: 74, 917 MB with memory of 1180 MB (262 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 397 binds (186.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 161 kept as spares, 0 destroyed; 35 spares now, 1252 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3635 dirty pages from their submits' captures, 39095 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): 794 dispatches, 32273 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5158 runs, 601.5 MB compared; 94 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12892 in captures, 4 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05 [hos sead::MainThread] vk: capture: a submit 0.22 ms (lock 0.00, scan 0.05 over 1062 ranges, 3537 MB), 235 pages written, 235 copied (0.9 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 0.016, bytes copied 0.000; 25 kept (90 MB), 7 spare buffers, 5988 texture pages copied (23 MB) [hos host] vk: memory: working set 8344 MB (peak 8347), private 1605 MB, staging 32 MB in 2 arenas, 46 made so far (7 ms) [hos host] vk: memory heaps: heap 0 (system): 8 blocks 176 MB, 35 allocations 132 MB; used 2132 of 31627 MB; heap 1 (device): 185 blocks 4853 MB, 17978 allocations 4457 MB; used 5094 of 6239 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 2 free ranges, the largest 0 MB [hos host] vk: image blocks (render targets): 23 blocks 368 MB, 116 images 209 MB; 60 free ranges, the largest 16 MB [hos host] vk: image blocks (textures, compacted): 46 blocks 1472 MB, 2126 images 1457 MB; 195 free ranges, the largest 2 MB [hos host] vk: render target images: 599 reused from the pool, 1087 made new, 964 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 5094 MB used of 6239 MB allowed (396 MB of it free in the blocks); textures 2929 MB (budget 2993 MB), 2255 textures [hos host] vk: budget: VRAM 4853 of 6239 MB (5094 MB by the driver, 240 MB unaccounted): textures 2929, mirrors 917, blocks free 396, shadows 272, other buffers 227, other images 78, staging 32; RAM 2114 MB (the process's private memory 1605 MB): imports 1948, captures 94, capture table 34, capture spares 32, other buffers 6, others 0 [hos host] vk: textures: decoded ASTC 1114 MB, rendered 847 MB (50 drawn in one frame, kept: 33877 KB), other 546 MB; used in the last 8 presents 1421 MB [hos host] vk: decoded ASTC used again: 48 textures (150 MB) copied from ones the game finalized, not decoded; 48 of those retired, 35 listed; 865 MB of blocks hashed in 88 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 2250 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 2250 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 37 MB: 0x10f8843e00 1800x1380x1 x8 levels 1 NVN 0x6, last used 2250 presents ago [hos host] vk: 32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 31 MB: 0x111aa73800 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 70 (15505 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: 36 (6334 KB); 262x104x1 NVN 0x1: 3 (79 KB); [hos host] vk: malloc: 1986 MB in arenas (1173 MB in use, 812 MB free, 2 MB of it at the tops), 20 MB mapped [hos Presentation Thread] vk: presents after the CPU's signal (600): 595 waited for it, 8.93 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: malloc_trim: 809 MB free in the arenas now, the process's private memory 1605 -> 1335 MB (13 ms) [hos host] vk: status: 600 frames, the slowest 80.4 ms; VRAM 5.0 of 6.1 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: 0 program records loaded (0.0 ms), 1876 new graphics pipelines, pipelines from the driver's cache 2033, from the start's cache 0, compiled 120; 5607 draws and dispatches left out, 1222 waits (6808.2 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: 402 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 7847 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 15.95, present 0.20, draw 9.62, descriptors 3.01, texture lookups 0.09, uploads 0.00, pipelines 0.37, programs 1.26, commands 4.44, dispatch 1.41, memory sync 0.54, queue submit 1.74, slot wait 0.17 [hos host] vk: a frame: mirrors 235 (917 MB): 5.07 MB synced in 977.9 copies, 18.21 MB written back [hos host] vk: 32400 presents, 39.9 fps; a frame: 2434 draws (38 skipped), 125 dispatches, 117 passes, 152 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.2 ms (recording slots only); 2346 pipelines (250 ms), 1359 programs (10 failed), 2255 textures (2929 MB) [hos host] vk: host time in GPU resource waits: 9.23 ms a frame (fences 0.00, timelines 9.23, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 427.9 full barriers recorded, 251.8 left out (nothing recorded since the one before), 14.4 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: 43.7; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 11.5 ms a frame (the longest submission 4.7 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: queues ordered by their events: 129488 submissions stopped at a wait, 127792 went on once it was reached, 1696 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 129 (stopped 50.25 ms at most); waits met 214931, not met 0; captures at a CPU event's wait 14997, 0 of them at a wait met on arrival [hos host] vk: the render thread (600 presents, 23.89 ms a frame): its jobs 13.23 ms a frame (submits 1.16, presents 0.20, others 11.88), idle 10.66; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.30 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); 598 captures at a CPU signal; the submits' waits read in 0.054 ms a frame; readbacks: 2995 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 13.35 ms after its hand-over (51.29 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 1.49 + 0.21 (the window's copy is in the idle), after it 10.65 + 0.59; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.08 ms of GPU time), after its last that reads it 1.00 (0.08 ms) [hos host] vk: frame ahead (600 presents): 11.07 parts a frame recorded in the signal's job, 72.3% of them took nothing that came with the signal; of the others, 3.06 a frame took pages of the signal's capture into a mirror (130.4 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 536 frames, its first three in 4 [hos host] vk: frame ahead, what came with the signal: 598 signals with a capture, each of 213.8 pages in 11.0 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: 1.69+0.18, 0.67+0.04, 0.84+0.10, 0.96+0.12, 0.39+0.04, 0.32+0.02, 0.27+0.02, 0.44+0.02, 2.09+0.02, 2.88+0.02, 0.10+0.01, 0.00+0.00 [hos host] vk: replay reads of guest memory as submitted: 2420000 (1310097 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2440000 (1323175 pages from the captures) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3835 dirty pages from their submits' captures, 38915 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): 796 dispatches, 32251 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5128 runs, 600.3 MB compared; 87 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12921 in captures, 3 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: program picks: 3542694 kept (1054752 by the last picks' textures, a uniform buffer bound since), 39473 new, 1617832 with other textures (of 5200000) [hos host] vk: replay reads of guest memory as submitted: 2460000 (1336190 pages from the captures) [hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 200000 so far (x1 0x117ccee020 x2 0 x3 0x117ccee000 x4 0x230040) [hos nn.npln.Callback] vcores: 79106 takes, 14253 waits (mean 114 us, longest 15.7 ms, 0 over HOS_VCORE_LOG_MS), 6335 kicks, 6591 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 2480000 (1349254 pages from the captures) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 913 of 3000 waited for their write-back, 0.13 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: 8260 kept their virtual core (nothing there to wait for), 3004 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 27859 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vi: 32451 frames presented (41.6 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 18, 15.5-17.8 84, 17.8-22 61, 22-30 18, 30-40 8, over 40 19 [hos sead::MainThread] nvn: GPU waits in 5 s: 197 sync waits (1609 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 2500000 (1362257 pages from the captures) [hos host] vk: sparse mirrors: 74, 917 MB with memory of 1180 MB (262 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 397 binds (186.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 161 kept as spares, 0 destroyed; 35 spares now, 1252 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4091 dirty pages from their submits' captures, 38928 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): 797 dispatches, 32295 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5147 runs, 600.5 MB compared; 79 pages read into the shadows; 272 MB of shadows (57 MB of pages known, in 106 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13319 in captures, 1 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos host] vk: replay reads of guest memory as submitted: 2520000 (1375397 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.23 ms (lock 0.00, scan 0.05 over 1062 ranges, 3537 MB), 241 pages written, 241 copied (0.9 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 0.018, bytes copied 0.000; 24 kept (96 MB), 7 spare buffers, 6500 texture pages copied (25 MB) [hos host] vk: replay reads of guest memory as submitted: 2540000 (1388433 pages from the captures) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 3944 dirty pages from their submits' captures, 38863 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): 795 dispatches, 32291 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5130 runs, 600.2 MB compared; 93 pages read into the shadows; 272 MB of shadows (59 MB of pages known, in 108 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 12579 in captures, 3 only in the collection, 31 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 0.03, writes collected 0.04 [hos sead::MainThread] nvn: EventSignal (CPU) #65000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c) [hos host] vk: replay reads of guest memory as submitted: 2560000 (1401455 pages from the captures) [hos host] vk: program picks: 3693560 kept (1110601 by the last picks' textures, a uniform buffer bound since), 39473 new, 1666966 with other textures (of 5400000) [hos host] vk: a frame: 406 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 7847 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.37, present 0.20, draw 7.81, descriptors 2.36, texture lookups 0.07, uploads 0.00, pipelines 0.31, programs 1.11, commands 3.53, dispatch 1.11, memory sync 0.44, queue submit 1.43, slot wait 0.15 [hos host] vk: a frame: mirrors 235 (917 MB): 5.07 MB synced in 977.4 copies, 18.19 MB written back [hos host] vk: 32520 presents, 47.7 fps; a frame: 2440 draws (38 skipped), 123 dispatches, 117 passes, 150 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 2346 pipelines (250 ms), 1359 programs (10 failed), 2255 textures (2929 MB) [hos host] vk: host time in GPU resource waits: 6.79 ms a frame (fences 0.00, timelines 6.79, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: skips a frame by vk_draw.cpp line: 8722: 38.0 [hos host] vk: a frame: 425.8 full barriers recorded, 249.5 left out (nothing recorded since the one before), 14.4 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: 41.4; 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, 0.0 from 0.0 batches at the game's barriers (0.0 converted in them; 0.0 dropped after a write, 0.0 the ring came round), 38.0 left as they are (no mesh shaders); scans ended at a barrier 0.0, an op 0.0, the end 0.0, full 0.0; the draws batched by a scan right after an op that ended the one before, by op: none [hos host] vk: GPU time 10.1 ms a frame (the longest submission 4.6 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: replay reads of guest memory as submitted: 2580000 (1414541 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 1659213 pages so far (0 held: may be written ahead in their submission) [hos host] vk: the recording streams: 48 of 1 MB, the most one held 231 KB; 0 made on demand (0 MB kept now); c1 stages: at most 87 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 247 sets (ub 2816, sb 1334, cis 13516, si 0, utb 0, stb 0) [hos host] vk: sparse mirrors: 74, 917 MB with memory of 1180 MB (262 MB spared); blocks given memory later 3579, given back 10381; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 648; 397 binds (186.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 126 taken from the spares, 109 made new; 161 kept as spares, 0 destroyed; 35 spares now, 1252 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 693, 3399.3 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 4576 dirty pages from their submits' captures, 38707 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): 805 dispatches, 32499 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5142 runs, 600.6 MB compared; 67 pages read into the shadows; 272 MB of shadows (58 MB of pages known, in 107 MB of 1 MB parts); pages the shadows knew that the CPU wrote: 13260 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 147 live (1948 MB), 0 retired still imported (0 MB), 39 retired given back (1340 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #220000: event 0x100d6c8048 mode 0 value 109574 (now 109555) (lr 0x806661f8) [hos host] vk: replay reads of guest memory as submitted: 2600000 (1427571 pages from the captures) [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), 1876 new graphics pipelines, pipelines from the driver's cache 2033, from the start's cache 0, compiled 120; 5607 draws and dispatches left out, 1222 waits (6808.2 ms) [hos host] vk: replay reads of guest memory as submitted: 2620000 (1440702 pages from the captures) [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): 97 in 97 of 2726 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 97 texture (17-64: 97); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4259 pools in the table now) [hos host] vk: late pages found at the replay (600 takes): 115 pages in 31 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #110000: event 0x100d6c8008 mode 0 value 109995 (lr 0x80660f34) [hos host] vk: pipeline cache: play file 5 saved (21 KB): 3 pipelines, 3 from the driver's cache, 0 compiled; 0 more from the start's cache [hos host] control: exiting [hos host] stop: close work done (a file the game was writing waited for, at most 3 s)