Report rp_185cda4c49990d46 pass
This report disagrees with its peers.
three-areas kokiri-standing.draws_mean: -28.9% against peers' -0.6% three-areas kokiri-standing.frametime_p99_ms: -27.2% against peers' +0.6% three-areas market-standing.frametime_p99_ms: +1.8% against peers' -23.8% three-areas market-standing.hitch_count: +1.0% against peers' -85.7%
Machine
- Commit
- de65a6b46797cb803bd2438f2c5793139f1ee0c3
- Baseline
- a3565ac5b1991335058bdc204a77a9f39f14fc20
- App
- nightly-195-f9b6d598, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 5 230 w/ Radeon 760M Graphics
- gpu
- AMD Radeon 760M Graphics (RADV PHOENIX)
- tags
- linuxamdradvigpu
- driver
- 26.0.8
- ram_gb
- 16
- vram_mb
- 5,170
- gpu_vendor
- amd
- os_version
- Ubuntu 26.04.1 LTS (kernel 7.0.0)
Builds
main (baseline)
203.8 s warm
from a3565ac5b199
- lift
- 1.2 s
- read
- 12.2 s
- finish
- 16 s
- compile
- 94.6 s
- shaders
- 30.7 s
PR
88.6 s warm
Program cache: warm
Scenarios
three-areas
ok| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| run_hitch_count | 1,979.5 | 1,997.5 | +0.9% |
| run_frametime_max_ms | 1,132.41 | 1,250.66 | +10.4% |
| field-standing.fps_mean | 19.76 | 19.65 | −0.6% |
| kokiri-standing.fps_mean | 20.64 | 22.79 | +10.4% |
| market-standing.fps_mean | 17.1 | 17.3 | +1.1% |
| field-standing.draws_mean | 1,190.95 | 1,184.5 | −0.5% |
| field-standing.hitch_count | 185 | 186.5 | +0.8% |
| kokiri-standing.draws_mean | 938.4 | 667.4 | −28.9% |
| market-standing.draws_mean | 2,442.65 | 2,454.05 | +0.5% |
| kokiri-standing.hitch_count | 118 | 7 | −94.1% |
| market-standing.hitch_count | 342.5 | 346 | +1% |
| field-standing.stutter_count | 0 | 0 | ±0% |
| kokiri-standing.stutter_count | 0 | 0 | ±0% |
| market-standing.stutter_count | 1 | 0 | −100% |
| field-standing.frametime_max_ms | 88.14 | 89.03 | +1% |
| field-standing.frametime_p50_ms | 49.93 | 49.94 | +0% |
| field-standing.frametime_p99_ms | 81.02 | 81.72 | +0.9% |
| kokiri-standing.frametime_max_ms | 83.98 | 63.43 | −24.5% |
| kokiri-standing.frametime_p50_ms | 47.31 | 43.43 | −8.2% |
| kokiri-standing.frametime_p99_ms | 69.27 | 50.45 | −27.2% |
| market-standing.frametime_max_ms | 104.48 | 93.68 | −10.3% |
| market-standing.frametime_p50_ms | 56.55 | 56.17 | −0.7% |
| market-standing.frametime_p99_ms | 83.12 | 84.58 | +1.8% |
| field-standing.frametime_1pct_low_ms | 84.6 | 84.81 | +0.2% |
| kokiri-standing.frametime_1pct_low_ms | 76.35 | 58 | −24% |
| market-standing.frametime_1pct_low_ms | 93.78 | 89.79 | −4.3% |
| screenshot_diff | — | 0.39 | — |
Pictures against main: kokiri diff 0.7025 (main against itself 0.7), field diff 0.0294 (main against itself 0.023), market diff 0.0811 (main against itself 0.064)
Runs (4)
| Metric | main 0 | pr 1 | pr 2 | main 3 |
|---|---|---|---|---|
| hang | no | no | no | no |
| crashed | no | no | no | no |
| exit_code | 0 | 0 | 0 | 0 |
| run_hitch_count | 2,134 | 2,073 | 1,922 | 1,825 |
| run_frametime_max_ms | 1,172.58 | 1,469.59 | 1,031.73 | 1,092.23 |
| field-standing.fps_mean | 19.53 | 19.24 | 20.06 | 19.99 |
| kokiri-standing.fps_mean | 22.37 | 22.51 | 23.06 | 18.92 |
| market-standing.fps_mean | 17.35 | 17.34 | 17.25 | 16.85 |
| field-standing.draws_mean | 1,210.7 | 1,172.5 | 1,196.5 | 1,171.2 |
| field-standing.hitch_count | 227 | 233 | 140 | 143 |
| kokiri-standing.draws_mean | 681.3 | 665.1 | 669.7 | 1,195.5 |
| market-standing.draws_mean | 2,487.2 | 2,509.2 | 2,398.9 | 2,398.1 |
| kokiri-standing.hitch_count | 13 | 9 | 5 | 223 |
| market-standing.hitch_count | 352 | 349 | 343 | 333 |
| field-standing.stutter_count | 0 | 0 | 0 | 0 |
| kokiri-standing.stutter_count | 0 | 0 | 0 | 0 |
| market-standing.stutter_count | 0 | 0 | 0 | 2 |
| field-standing.frametime_max_ms | 86.97 | 89.19 | 88.87 | 89.3 |
| field-standing.frametime_p50_ms | 50.52 | 50.55 | 49.32 | 49.34 |
| field-standing.frametime_p99_ms | 80.09 | 84.96 | 78.48 | 81.95 |
| kokiri-standing.frametime_max_ms | 79.31 | 51.96 | 74.9 | 88.65 |
| kokiri-standing.frametime_p50_ms | 44.12 | 44.1 | 42.76 | 50.5 |
| kokiri-standing.frametime_p99_ms | 57.69 | 50.65 | 50.24 | 80.84 |
| market-standing.frametime_max_ms | 87.33 | 91.33 | 96.04 | 121.64 |
| market-standing.frametime_p50_ms | 55.8 | 55.37 | 56.98 | 57.3 |
| market-standing.frametime_p99_ms | 73.69 | 83.24 | 85.93 | 92.55 |
| field-standing.frametime_1pct_low_ms | 82.26 | 87.61 | 82.01 | 86.94 |
| kokiri-standing.frametime_1pct_low_ms | 67.86 | 51.29 | 64.7 | 84.83 |
| market-standing.frametime_1pct_low_ms | 80.01 | 87.16 | 92.43 | 107.55 |
| screenshot_diff | — | 0.08 | 0.7 | — |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| three-areas | crash | False | 0 | 0 | — | pass | |
| three-areas | kokiri-standing.fps_mean.min_delta_pct | 10 | 20.64 | 22.79 | +10.4% | pass | |
| three-areas | field-standing.fps_mean.min_delta_pct | 10 | 19.76 | 19.65 | −0.6% | pass | |
| three-areas | market-standing.fps_mean.min_delta_pct | 10 | 17.1 | 17.3 | +1.1% | pass | |
| three-areas | screenshot.max_diff | 0 | 0.7 | 0.7 | — | passover the limit, but main differs from itself by 0.7 here: no more than 1.5x that is the scene, not the PR | |
| three-areas | kokiri-standing.stutter_count.max_delta_pct | 20 | 0 | 0 | ±0% | pass | |
| three-areas | field-standing.stutter_count.max_delta_pct | 20 | 0 | 0 | ±0% | pass | |
| three-areas | market-standing.stutter_count.max_delta_pct | 20 | 1 | 0 | −100% | pass | |
| three-areas | run_hitch_count.max_delta_pct | 20 | 1,979.5 | 1,997.5 | +0.9% | pass | |
| three-areas | kokiri-standing.frametime_p99_ms.max_delta_pct | 15 | 69.27 | 50.45 | −27.2% | pass | |
| three-areas | field-standing.frametime_p99_ms.max_delta_pct | 15 | 81.02 | 81.72 | +0.9% | pass | |
| three-areas | market-standing.frametime_p99_ms.max_delta_pct | 15 | 83.12 | 84.58 | +1.8% | pass |
Log (PR side, end)
[hos Presentation Thread] vk: a frame: 0.62 MB unswizzled on the CPU in 0.76 ms [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x11791f0000 x2 0 x3 0x11791f0000 x4 0x654040) [hos sead::MainThread] nvn: GPU waits in 5 s: 96 sync waits (1416 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos Presentation Thread] vi: 6862 frames presented (21.0 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 40, over 40 65 [hos Presentation Thread] vk: 12 textures retired (1856 left, 2058 MB): budget 0, drawn over 0, dead targets 12 [hos sead::MainThread] nvn: CommandBufferWaitEvent #100000: event 0x100d6c8038 mode 0 value 69040 (now 69021) (lr 0x80661a48) [hos ModuleSystemWorker1] nvn: 750000 recordings made, 68487 live copies (20.9 MB), 2261 texture copies; 2 command buffers' segments (4.1 MB) [hos host] vk: replay reads of guest memory as submitted: 2300000 (1326784 pages from the captures) [hos sead::MainThread] barrier: 178245 looks: 30789 found the masks moved already, 61992 waited until they moved, 85464 for the whole 1 ms (a wait 707 us on average); 45382 wakes [hos AudioUserTaskThread] vcores: 48886 takes, 8191 waits (mean 192 us, longest 120.9 ms, 1 over HOS_VCORE_LOG_MS), 3840 kicks, 4041 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: the recording streams: 48 of 2 MB, the most one held 259 KB; 0 made on demand (0 MB kept now); c1 stages: at most 131 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2320000 (1341240 pages from the captures) [hos host] vk: texture #14028 0x10007bd9200 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 6888 (drawn at 6827) [hos host] vk: texture #14027 0x10007b49000 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 6889 (drawn at 6828) [hos sead::MainThread] vk: capture: a submit 0.54 ms (lock 0.01, scan 0.15 over 2877 ranges, 2973 MB), 231 pages written, 231 copied (0.9 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.076; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.067, bytes copied 0.000; 25 kept (226 MB), 2 spare buffers, 11504 texture pages copied (44 MB) [hos sead::MainThread] vk: late pages left to their reads (600 takes): 624 pages in 84 takes (624 kept with their capture), 168 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.08, writes collected 0.06 [hos Presentation Thread] vk: 11 textures retired (1902 left, 2157 MB): budget 0, drawn over 0, dead targets 11 [hos Presentation Thread] vk: 182 textures retired (1767 left, 1941 MB): budget 113, drawn over 0, dead targets 69 [hos ModuleSystemWorker2] nvn: CommandBufferSignalEvent #70000: event 0x100d6c8000 mode 0 value 69995 (lr 0x80291440) [hos host] vk: program picks: 3400749 kept (1405204 by the last picks' textures, a uniform buffer bound since), 13784 new, 1385466 with other textures (of 4800000) [hos host] vk: replay reads of guest memory as submitted: 2340000 (1354124 pages from the captures) [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos Presentation Thread] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos Presentation Thread] vk: 13 textures retired (1817 left, 2046 MB): budget 0, drawn over 0, dead targets 13 [hos sead::MainThread] vk: readbacks of GPU results: 2558 of 3000 waited for their write-back, 0.53 ms each; 105 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos sead::MainThread] vk: readbacks waited for their writer's part (RX_VK_READBACK_EARLY): 821, 0.77 ms each; 0 for their whole submission (writer not known); 410 parts ended after a readback's writer; 3 waited for their writer's submission to be recorded first, 5.11 ms each (0 of them past 250 ms: their whole submission) [hos sead::MainThread] vk: invalidates since the last readbacks line: 9861 kept their virtual core (nothing there to wait for), 2939 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: 2360000 (1368382 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 93 sync waits (1468 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos Presentation Thread] vk: 9 textures retired (1887 left, 2086 MB): budget 0, drawn over 0, dead targets 9 [hos Presentation Thread] vi: 6959 frames presented (19.4 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 22, over 40 75 [hos Presentation Thread] vk: a frame: 184 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 15.36, present 0.77, draw 8.59, descriptors 3.11, texture lookups 2.00, uploads 0.39, pipelines 0.31, programs 1.16, commands 3.39, dispatch 1.18, memory sync 0.78, queue submit 1.59, slot wait 0.11 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 6960 presents, 19.8 fps; a frame: 1226 draws (0 skipped), 109 dispatches, 153 passes, 176 barriers, 6 submits, 1.5 uploads (0.7 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1886 textures (2088 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 17.03 ms a frame (fences 0.00, timelines 17.03, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 429.3 full barriers recorded, 255.3 left out (nothing recorded since the one before), 17.7 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 61.9; 0x12: 81.8; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 39.0 ms a frame (the longest submission 28.7 ms); 9.6 textures made a frame: colour targets 4.3 (12.1 MB), depth 4.0 (14.8 MB), ASTC or BC 1.2 (0.4 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.56 MB unswizzled on the CPU in 0.24 ms [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2380000 (1381919 pages from the captures) [hos Presentation Thread] vk: 10 textures retired (1897 left, 2156 MB): budget 0, drawn over 0, dead targets 10 [hos Presentation Thread] vk: 8 textures retired (1893 left, 2085 MB): budget 0, drawn over 0, dead targets 8 [hos sead::MainThread] vk: capture: a submit 0.34 ms (lock 0.00, scan 0.16 over 2876 ranges, 2975 MB), 174 pages written, 174 copied (0.7 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.036; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.028, bytes copied 0.000; 25 kept (202 MB), 1 spare buffers, 8928 texture pages copied (34 MB) [hos sead::MainThread] vk: late pages left to their reads (600 takes): 621 pages in 83 takes (621 kept with their capture), 166 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos ModuleSystemWorker1] vcores: 51472 takes, 9099 waits (mean 174 us, longest 33.5 ms, 0 over HOS_VCORE_LOG_MS), 4361 kicks, 4513 yields, 0 starved grants, 0 escapes in 5 s [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.06 [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: replay reads of guest memory as submitted: 2400000 (1395242 pages from the captures) [hos Presentation Thread] vk: 1 textures retired (1905 left, 2112 MB): budget 0, drawn over 0, dead targets 1 [hos host] vk: replay reads of guest memory as submitted: 2420000 (1409974 pages from the captures) [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 78.5 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.0 ms and was never asked; the cores it may use now: core 1: it; [hos host] vk: texture #15497 0x10007bd9200 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 7026 (drawn at 6965) [hos Presentation Thread] vk: 8 textures retired (1928 left, 2140 MB): budget 0, drawn over 0, dead targets 8 [hos host] vk: texture #15496 0x10007b49000 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 7030 (drawn at 6965) [hos Presentation Thread] vk: render targets drawn over from another start, let go: 8953 so far (33669 MB), 8133 of them (30355 MB) between the passes [hos Presentation Thread] vk: 140 textures retired (1811 left, 2130 MB): budget 128, drawn over 0, dead targets 12 [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 82984 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos sead::MainThread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 sead::MainThread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos sead::MainThread] vk: read live, by pool: [hos Presentation Thread] vk: 73 textures retired (1784 left, 1964 MB): budget 3, drawn over 0, dead targets 70 [hos Presentation Thread] vk: replay reads of guest memory as submitted: 2440000 (1422815 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 101 sync waits (1372 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos Presentation Thread] vi: 7064 frames presented (21.0 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 38, over 40 67 [hos Presentation Thread] vk: capture: a submit 0.46 ms (lock 0.01, scan 0.16 over 2879 ranges, 2965 MB), 201 pages written, 201 copied (0.8 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.058; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.049, bytes copied 0.000; 24 kept (248 MB), 2 spare buffers, 6617 texture pages copied (25 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 609 pages in 82 takes (609 kept with their capture), 164 read on the CPU, 0 of them waited (0.00 ms in all); 6 still late; 0 late pages in a texture's storage waited at the take [hos Presentation Thread] vk: 4 textures retired (1790 left, 2011 MB): budget 0, drawn over 0, dead targets 4 [hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #105000: event 0x100d6c8038 mode 0 value 72840 (now 72821) (lr 0x80661a48) [hos Presentation Thread] vk: 17 textures retired (1800 left, 2101 MB): budget 0, drawn over 0, dead targets 17 [hos Presentation Thread] vk: a frame: 147 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 14.97, present 0.50, draw 8.09, descriptors 3.00, texture lookups 2.18, uploads 0.37, pipelines 0.28, programs 1.11, commands 3.14, dispatch 1.58, memory sync 0.68, queue submit 1.55, slot wait 0.10 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 7080 presents, 21.2 fps; a frame: 1020 draws (0 skipped), 106 dispatches, 154 passes, 175 barriers, 6 submits, 0.9 uploads (0.6 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1814 textures (2108 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 15.18 ms a frame (fences 0.00, timelines 15.18, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 417.1 full barriers recorded, 254.0 left out (nothing recorded since the one before), 18.5 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 60.4; 0x12: 82.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 36.4 ms a frame (the longest submission 27.0 ms); 8.9 textures made a frame: colour targets 4.3 (12.1 MB), depth 3.9 (15.1 MB), ASTC or BC 0.6 (0.3 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.49 MB unswizzled on the CPU in 0.20 ms [hos host] vk: replay reads of guest memory as submitted: 2460000 (1436841 pages from the captures) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 259 KB; 0 made on demand (0 MB kept now); c1 stages: at most 132 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: program picks: 3538863 kept (1444479 by the last picks' textures, a uniform buffer bound since), 13809 new, 1447327 with other textures (of 5000000) [hos aal::LowPrioWorkerThread] vcores: 51143 takes, 9402 waits (mean 189 us, longest 78.5 ms, 1 over HOS_VCORE_LOG_MS), 4464 kicks, 4615 yields, 0 starved grants, 0 escapes in 5 s [hos Presentation Thread] vk: 13 textures retired (1815 left, 2043 MB): budget 0, drawn over 0, dead targets 13 [hos host] vk: replay reads of guest memory as submitted: 2480000 (1451076 pages from the captures) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.05, writes collected 0.06 [hos Presentation Thread] vk: 17 textures retired (1844 left, 2090 MB): budget 0, drawn over 0, dead targets 17 [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 50.2 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.0 ms and was never asked; the cores it may use now: core 1: it; [hos Presentation Thread] vk: 51 textures retired (1834 left, 2129 MB): budget 40, drawn over 0, dead targets 11 [hos sead::MainThread] vk: readbacks of GPU results: 2626 of 3000 waited for their write-back, 0.46 ms each; 111 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos sead::MainThread] vk: readbacks waited for their writer's part (RX_VK_READBACK_EARLY): 827, 0.51 ms each; 0 for their whole submission (writer not known); 407 parts ended after a readback's writer; 2 waited for their writer's submission to be recorded first, 15.23 ms each (0 of them past 250 ms: their whole submission) [hos sead::MainThread] vk: invalidates since the last readbacks line: 9824 kept their virtual core (nothing there to wait for), 2976 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: 1 textures retired (1812 left, 1980 MB): budget 0, drawn over 0, dead targets 1 [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2500000 (1464038 pages from the captures) [hos Presentation Thread] vk: 14 textures retired (1812 left, 1969 MB): budget 0, drawn over 0, dead targets 14 [hos Presentation Thread] vk: capture: a submit 0.35 ms (lock 0.00, scan 0.16 over 2879 ranges, 2975 MB), 174 pages written, 174 copied (0.7 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.030; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.022, bytes copied 0.000; 25 kept (248 MB), 2 spare buffers, 7130 texture pages copied (27 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 639 pages in 85 takes (639 kept with their capture), 172 read on the CPU, 0 of them waited (0.00 ms in all); 6 still late; 0 late pages in a texture's storage waited at the take [hos host] vk: replay reads of guest memory as submitted: 2520000 (1478314 pages from the captures) [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: texture #16735 0x10007ab8e00 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 7163 (drawn at 7102) [hos Presentation Thread] vi: 7165 frames presented (20.2 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 2, 30-40 29, over 40 70 [hos sead::MainThread] nvn: GPU waits in 5 s: 97 sync waits (1447 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos Presentation Thread] vk: 25 textures retired (1886 left, 2084 MB): budget 0, drawn over 0, dead targets 25 [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 50.3 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 5.7 ms and was never asked; the cores it may use now: core 1: it; [hos host] vk: replay reads of guest memory as submitted: 2540000 (1491767 pages from the captures) [hos Presentation Thread] vk: 11 textures retired (1897 left, 2166 MB): budget 0, drawn over 0, dead targets 11 [hos sead::MainThread] nvn: CommandBufferSignalEvent #75000: event 0x100d6c8020 mode 0 value 75000 (lr 0x80664f14) [hos ModuleSystemWorker1] vcores: 50979 takes, 9782 waits (mean 207 us, longest 50.3 ms, 2 over HOS_VCORE_LOG_MS), 4608 kicks, 4810 yields, 0 starved grants, 0 escapes in 5 s [hos Presentation Thread] vk: 10 textures retired (1875 left, 2013 MB): budget 0, drawn over 0, dead targets 10 [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.06 [hos Presentation Thread] vk: memory: working set 4631 MB (peak 7239), private 1195 MB, staging 48 MB in 3 arenas, 43 made so far (68 ms) [hos Presentation Thread] vk: memory heaps: heap 0 (system): 18 blocks 344 MB, 29 allocations 274 MB; used 2608 of 2585 MB; heap 1 (device): 157 blocks 3076 MB, 1971 allocations 2546 MB; used 3384 of 4294 MB; [hos Presentation Thread] vk: image blocks: 1 blocks 32 MB, 6 images 31 MB; 2 free ranges, the largest 0 MB [hos Presentation Thread] vk: image blocks (render targets): 45 blocks 720 MB, 175 images 417 MB; 142 free ranges, the largest 16 MB [hos Presentation Thread] vk: image blocks (textures, compacted): 43 blocks 1376 MB, 1719 images 1202 MB; 436 free ranges, the largest 14 MB [hos Presentation Thread] vk: render target images: 6451 reused from the pool, 4353 made new, 4173 destroyed from it; it holds 11 (40 MB) [hos Presentation Thread] vk: VRAM: 3384 MB used of 4294 MB allowed (529 MB of it free in the blocks); textures 2132 MB (budget 2211 MB), 1891 textures [hos Presentation Thread] vk: budget: VRAM 3076 of 4294 MB (3384 MB by the driver, 307 MB unaccounted): textures 2132, blocks free 529, other buffers 278, staging 48, other images 46, target pool 40; RAM 2501 MB (the process's private memory 1195 MB): imports 2192, captures 256, capture table 35, capture spares 16, other buffers 2, others 0 [hos Presentation Thread] vk: textures: decoded ASTC 621 MB, rendered 900 MB (48 drawn in one frame, kept: 44491 KB), other 361 MB; used in the last 8 presents 1333 MB [hos Presentation Thread] vk: decoded ASTC used again: 72 textures (45 MB) copied from ones the game finalized, not decoded; 72 of those retired, 0 listed; 1196 MB of blocks hashed in 1452 ms [hos Presentation Thread] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos Presentation Thread] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos Presentation Thread] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos Presentation Thread] vk: 32 MB: 0x1159c17000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos Presentation Thread] vk: 31 MB: 0x111e3ae400 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago [hos Presentation Thread] vk: 21 MB: 0x10004543e00 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos Presentation Thread] vk: 14 MB: 0x100030a4200 1600x1600x1 x3 levels 1 NVN 0x32 rendered, last used 14 presents ago [hos Presentation Thread] vk: 14 MB: 0x10002d97a00 1600x1600x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos Presentation Thread] vk: finalized textures the GPU drew once, kept for being made again: 72 (15549 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); 140x42x1 NVN 0x25: 1 (22 KB); 154x98x1 NVN 0x1: 1 (14 KB); 165x112x1 NVN 0x1: 1 (18 KB); 198x40x1 NVN 0x25: 2 (61 KB); 204x106x1 NVN 0x1: 1 (21 KB); 242x40x1 NVN 0x25: 3 (113 KB); 244x44x1 NVN 0x25: 1 (41 KB); 260x260x1 NVN 0xd: 36 (6334 KB); [hos Presentation Thread] vk: status: 600 frames, the slowest 208.6 ms; VRAM 3.3 of 4.2 GB [hos Presentation Thread] 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: 20 program records loaded (21.7 ms), 3 new graphics pipelines, pipelines from the driver's cache 3, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos Presentation Thread] vk: program loads at create (play): 6026 queued, 6026 loaded (median 0.73 ms, 99th percentile 10.85 ms, worst 139.94 ms, 9500 ms and 1365.5 MB read in all); 8679 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 10841 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 1 itself and waited for 0 (0.9 ms); 2316 pipelines made at create taken by draws; 2767 create calls with nothing kept for their stages, 0 before the index; units 8793 (6026 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use [hos Presentation Thread] vk: module identifiers (play): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before) [hos Presentation Thread] vk: a frame: 184 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 1 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 14.75, present 0.57, draw 8.43, descriptors 2.95, texture lookups 1.60, uploads 0.28, pipelines 0.31, programs 1.15, commands 3.39, dispatch 1.16, memory sync 0.57, queue submit 1.60, slot wait 0.11 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 7200 presents, 20.7 fps; a frame: 1228 draws (0 skipped), 109 dispatches, 158 passes, 177 barriers, 6 submits, 1.1 uploads (0.5 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1892 textures (2135 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 16.31 ms a frame (fences 0.00, timelines 16.31, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 429.4 full barriers recorded, 256.9 left out (nothing recorded since the one before), 19.9 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 60.9; 0x12: 84.0; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 37.8 ms a frame (the longest submission 23.8 ms); 9.6 textures made a frame: colour targets 4.5 (13.1 MB), depth 4.2 (14.5 MB), ASTC or BC 0.9 (0.4 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.37 MB unswizzled on the CPU in 0.17 ms [hos host] vk: malloc: 3516 MB in arenas (2519 MB in use, 997 MB free, 0 MB of it at the tops), 18 MB mapped [hos host] vk: malloc_trim: 997 MB free in the arenas now, the process's private memory 1202 -> 1067 MB (36 ms) [hos Presentation Thread] vk: 13 textures retired (1874 left, 2003 MB): budget 0, drawn over 0, dead targets 13 [hos host] vk: replay reads of guest memory as submitted: 2560000 (1505199 pages from the captures) [hos host] vk: texture #17793 0x10006ca4a00 932x932 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (3 so far) [hos Presentation Thread] vk: queues ordered by their events: 42000 submissions stopped at a wait, 41992 went on once it was reached, 4 waits gone past; made to go by presents 1913, releases 0, waits for the replay 0, 50 ms 1 (stopped 149.44 ms at most); waits met 108683, not met 0; captures at a CPU event's wait 5133, 92 of them at a wait met on arrival [hos host] vk: replay reads of guest memory as submitted: 2580000 (1519718 pages from the captures) [hos host] vk: program picks: 3678822 kept (1485925 by the last picks' textures, a uniform buffer bound since), 13816 new, 1507361 with other textures (of 5200000) [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos Presentation Thread] vk: 9 textures retired (1907 left, 2100 MB): budget 0, drawn over 0, dead targets 9 [hos Presentation Thread] vk: capture: a submit 0.31 ms (lock 0.00, scan 0.15 over 2878 ranges, 2977 MB), 180 pages written, 180 copied (0.7 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.036; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.027, bytes copied 0.000; 24 kept (232 MB), 2 spare buffers, 8491 texture pages copied (33 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 621 pages in 83 takes (621 kept with their capture), 164 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos Presentation Thread] vk: 11 textures retired (1921 left, 2166 MB): budget 0, drawn over 0, dead targets 11 [hos ModuleSystemWorker5] nvn: 800000 recordings made, 68760 live copies (19.5 MB), 2926 texture copies; 6 command buffers' segments (4.3 MB) [hos rmbl::VibrationThread] hid: 45056 vibration values, strongest 0.00 since the last count [hos Presentation Thread] vk: 145 textures retired (1814 left, 1966 MB): budget 81, drawn over 0, dead targets 64 [hos host] vk: replay reads of guest memory as submitted: 2600000 (1532499 pages from the captures) [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 178.9 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.0 ms and was never asked; the cores it may use now: core 1: it; [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 59395 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vi: 7270 frames presented (21.0 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 3, 30-40 41, over 40 61 [hos sead::MainThread] nvn: GPU waits in 5 s: 101 sync waits (1436 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #110000: event 0x100d6c8038 mode 0 value 76640 (now 76621) (lr 0x80661a48) [hos Presentation Thread] vk: the recording streams: 48 of 2 MB, the most one held 259 KB; 0 made on demand (0 MB kept now); c1 stages: at most 132 a recording; 0 descriptor pools made when a recording's own ran out [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos ModuleSystemWorker1] vk: readbacks of GPU results: 2580 of 3000 waited for their write-back, 0.35 ms each; 86 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: readbacks waited for their writer's part (RX_VK_READBACK_EARLY): 821, 0.52 ms each; 0 for their whole submission (writer not known); 429 parts ended after a readback's writer; 3 waited for their writer's submission to be recorded first, 4.05 ms each (0 of them past 250 ms: their whole submission) [hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 10484 kept their virtual core (nothing there to wait for), 3084 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: 3 textures retired (1822 left, 2015 MB): budget 0, drawn over 0, dead targets 3 [hos Presentation Thread] vk: texture #18394 0x10006ca4a00 845x845 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (4 so far) [hos Presentation Thread] vk: 1 textures retired (1840 left, 2105 MB): budget 0, drawn over 0, dead targets 1 [hos BaseProcExecutor1] vcores: 51653 takes, 9351 waits (mean 213 us, longest 178.9 ms, 1 over HOS_VCORE_LOG_MS), 4447 kicks, 4579 yields, 0 starved grants, 0 escapes in 5 s [hos Presentation Thread] vk: replay reads of guest memory as submitted: 2620000 (1546585 pages from the captures) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.09, writes collected 0.06 [hos Presentation Thread] vk: 12 textures retired (1843 left, 2043 MB): budget 0, drawn over 0, dead targets 12 [hos host] vk: replay reads of guest memory as submitted: 2640000 (1560456 pages from the captures) [hos Presentation Thread] vk: 19 textures retired (1860 left, 2104 MB): budget 0, drawn over 0, dead targets 19 [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos Presentation Thread] vk: 85 textures retired (1805 left, 2124 MB): budget 73, drawn over 0, dead targets 12 [hos Presentation Thread] vk: a frame: 208 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 15.51, present 0.54, draw 8.61, descriptors 3.01, texture lookups 1.60, uploads 0.28, pipelines 0.32, programs 1.19, commands 3.44, dispatch 1.33, memory sync 1.00, queue submit 1.61, slot wait 0.11 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 7320 presents, 20.0 fps; a frame: 1316 draws (0 skipped), 112 dispatches, 160 passes, 179 barriers, 6 submits, 0.7 uploads (0.6 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1805 textures (2124 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 15.84 ms a frame (fences 0.00, timelines 15.84, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 428.4 full barriers recorded, 259.0 left out (nothing recorded since the one before), 20.5 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 62.1; 0x12: 84.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 39.2 ms a frame (the longest submission 29.7 ms); 9.3 textures made a frame: colour targets 4.6 (13.3 MB), depth 4.3 (14.9 MB), ASTC or BC 0.4 (0.2 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.53 MB unswizzled on the CPU in 0.22 ms [hos Presentation Thread] vk: capture: a submit 0.55 ms (lock 0.00, scan 0.17 over 2880 ranges, 2985 MB), 223 pages written, 223 copied (0.9 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.105; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.096, bytes copied 0.000; 24 kept (224 MB), 2 spare buffers, 15876 texture pages copied (62 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 612 pages in 81 takes (612 kept with their capture), 162 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos Presentation Thread] vk: 2 textures retired (1779 left, 1953 MB): budget 0, drawn over 0, dead targets 2 [hos host] vk: replay reads of guest memory as submitted: 2660000 (1573468 pages from the captures) [hos Presentation Thread] vk: 12 textures retired (1785 left, 1957 MB): budget 0, drawn over 0, dead targets 12 [hos sead::MainThread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos sead::MainThread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 sead::MainThread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos sead::MainThread] vk: read live, by pool: [hos host] vk: texture #19028 0x10006794a00 1100x1100 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (5 so far) [hos host] vk: replay reads of guest memory as submitted: 2680000 (1588009 pages from the captures) [hos Presentation Thread] vk: 1 textures retired (1823 left, 2029 MB): budget 0, drawn over 0, dead targets 1 [hos Presentation Thread] vi: 7372 frames presented (20.3 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 2, 30-40 31, over 40 69 [hos sead::MainThread] nvn: GPU waits in 5 s: 88 sync waits (1409 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: texture #18674 0x10007bd9200 384x384 x1 NVN 0x34 the GPU drew, finalized by the game, sampled again at frame 7374 (drawn at 7313) [hos Presentation Thread] vk: 23 textures retired (1846 left, 2086 MB): budget 0, drawn over 0, dead targets 23 [hos sead::MainThread] nvn: DrawMeshTasksIndirect: 180000 so far (x1 0x117db40020 x2 0 x3 0x117db40000 x4 0x44b040) [hos host] vk: replay reads of guest memory as submitted: 2700000 (1601506 pages from the captures) [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: program picks: 3817775 kept (1527579 by the last picks' textures, a uniform buffer bound since), 13820 new, 1568404 with other textures (of 5400000) [hos Presentation Thread] vk: 65 textures retired (1807 left, 2141 MB): budget 52, drawn over 0, dead targets 13 [hos BaseProcExecutor5] vcores: 50266 takes, 9293 waits (mean 220 us, longest 49.7 ms, 0 over HOS_VCORE_LOG_MS), 4389 kicks, 4560 yields, 0 starved grants, 0 escapes in 5 s [hos ModuleSystemWorker5] barrier: 198377 looks: 34537 found the masks moved already, 65548 waited until they moved, 98292 for the whole 1 ms (a wait 730 us on average); 48498 wakes [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.08, writes collected 0.06 [hos Presentation Thread] vk: texture #19545 0x10006794a00 421x421 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (6 so far) [hos Presentation Thread] vk: 10 textures retired (1785 left, 1991 MB): budget 0, drawn over 0, dead targets 10 [hos Presentation Thread] vk: capture: a submit 0.37 ms (lock 0.00, scan 0.16 over 2883 ranges, 2995 MB), 183 pages written, 183 copied (0.7 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.063; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.055, bytes copied 0.000; 24 kept (252 MB), 2 spare buffers, 17293 texture pages copied (67 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 615 pages in 82 takes (615 kept with their capture), 164 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos Presentation Thread] vk: 13 textures retired (1784 left, 1985 MB): budget 0, drawn over 0, dead targets 13 [hos Presentation Thread] vk: replay reads of guest memory as submitted: 2720000 (1614938 pages from the captures) [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: texture storage read as submitted (2001 times; 23801 pages from the copies, 0 of them rewritten in guest memory since their submit; 17293 pages kept, 489 spans, 1350 MB) [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 382.4 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 3.5 ms and was never asked; the cores it may use now: core 1: it; [hos Presentation Thread] vk: a frame: 154 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 14.27, present 0.53, draw 7.80, descriptors 2.83, texture lookups 1.63, uploads 0.34, pipelines 0.28, programs 1.06, commands 3.07, dispatch 1.14, memory sync 0.77, queue submit 1.61, slot wait 0.11 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 7440 presents, 21.2 fps; a frame: 1077 draws (0 skipped), 105 dispatches, 149 passes, 172 barriers, 6 submits, 1.0 uploads (0.6 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1797 textures (2020 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 14.35 ms a frame (fences 0.00, timelines 14.35, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 410.9 full barriers recorded, 250.2 left out (nothing recorded since the one before), 16.4 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 59.4; 0x12: 80.2; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 36.4 ms a frame (the longest submission 41.2 ms); 8.3 textures made a frame: colour targets 4.0 (11.1 MB), depth 3.6 (14.6 MB), ASTC or BC 0.7 (0.3 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.55 MB unswizzled on the CPU in 0.26 ms [hos host] vk: replay reads of guest memory as submitted: 2740000 (1629981 pages from the captures) [hos sead::MainThread] vk: readbacks of GPU results: 2568 of 3000 waited for their write-back, 0.36 ms each; 95 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos sead::MainThread] vk: readbacks waited for their writer's part (RX_VK_READBACK_EARLY): 828, 0.42 ms each; 0 for their whole submission (writer not known); 408 parts ended after a readback's writer; 5 waited for their writer's submission to be recorded first, 3.59 ms each (0 of them past 250 ms: their whole submission) [hos sead::MainThread] vk: invalidates since the last readbacks line: 10137 kept their virtual core (nothing there to wait for), 2919 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: texture #19910 0x100075a8a00 384x384 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (7 so far) [hos Presentation Thread] vk: 23 textures retired (1848 left, 2073 MB): budget 0, drawn over 0, dead targets 23 [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #80000: event 0x100d6c8028 mode 0 value 79999 (lr 0x80667410) [hos Presentation Thread] vk: 52 textures retired (1855 left, 2134 MB): budget 41, drawn over 0, dead targets 11 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 259 KB; 0 made on demand (0 MB kept now); c1 stages: at most 132 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 2760000 (1642937 pages from the captures) [hos Presentation Thread] vk: 1 textures retired (1834 left, 2002 MB): budget 0, drawn over 0, dead targets 1 [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 58.6 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.9 ms and was never asked; the cores it may use now: core 1: it; [hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #115000: event 0x100d6c8038 mode 0 value 80440 (now 80421) (lr 0x80661a48) [hos Presentation Thread] vi: 7475 frames presented (20.6 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 30, over 40 73 [hos sead::MainThread] nvn: GPU waits in 5 s: 95 sync waits (1291 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 80049 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vk: 18 textures retired (1829 left, 2009 MB): budget 0, drawn over 0, dead targets 18 [hos ModuleSystemWorker1] vcores: 52099 takes, 10076 waits (mean 308 us, longest 382.4 ms, 2 over HOS_VCORE_LOG_MS), 4802 kicks, 4988 yields, 0 starved grants, 0 escapes in 5 s [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.06 [hos host] vk: replay reads of guest memory as submitted: 2780000 (1656949 pages from the captures) [hos Presentation Thread] vk: 3 textures retired (1867 left, 2117 MB): budget 0, drawn over 0, dead targets 3 [hos Presentation Thread] vk: capture: a submit 0.43 ms (lock 0.00, scan 0.16 over 2882 ranges, 3009 MB), 209 pages written, 209 copied (0.8 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.090; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.081, bytes copied 0.000; 24 kept (232 MB), 2 spare buffers, 10341 texture pages copied (40 MB) [hos Presentation Thread] vk: late pages left to their reads (600 takes): 606 pages in 81 takes (606 kept with their capture), 162 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos sead::MainThread] nvn: EventSignal (CPU) #15000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c) [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos host] vk: texture #20482 0x10005e94800 1613x1613 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (8 so far) [hos Presentation Thread] vk: 21 textures retired (1873 left, 2060 MB): budget 0, drawn over 0, dead targets 21 [hos host] vk: replay reads of guest memory as submitted: 2800000 (1671201 pages from the captures) [hos Presentation Thread] vk: 13 textures retired (1892 left, 2120 MB): budget 0, drawn over 0, dead targets 13 [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 157.8 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.0 ms and was never asked; the cores it may use now: core 1: it; [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos sead::MainThread] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: replay reads of guest memory as submitted: 2820000 (1684078 pages from the captures) [hos Presentation Thread] vk: 18 textures retired (1877 left, 2063 MB): budget 0, drawn over 0, dead targets 18 [hos Presentation Thread] vk: a frame: 167 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 113 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 14.34, present 0.65, draw 8.24, descriptors 3.00, texture lookups 1.75, uploads 0.42, pipelines 0.28, programs 1.30, commands 3.08, dispatch 1.08, memory sync 0.89, queue submit 1.50, slot wait 0.10 [hos Presentation Thread] vk: a frame: mirrors 0 (0 MB): 0.00 MB synced in 0.0 copies, 0.00 MB written back [hos Presentation Thread] vk: 7560 presents, 20.4 fps; a frame: 1138 draws (0 skipped), 108 dispatches, 158 passes, 178 barriers, 6 submits, 1.2 uploads (0.6 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 13704 pipelines (1178 ms), 0 programs (10 failed), 1880 textures (2070 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 16.83 ms a frame (fences 0.00, timelines 16.83, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 430.7 full barriers recorded, 257.6 left out (nothing recorded since the one before), 19.5 pass starts ordered in their fragment stages only (draw passes after draw passes) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 61.7; 0x12: 83.8; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 37.5 ms a frame (the longest submission 21.3 ms); 10.2 textures made a frame: colour targets 4.8 (13.6 MB), depth 4.4 (15.1 MB), ASTC or BC 1.0 (0.5 MB), other 0.0 (0.0 MB) [hos Presentation Thread] vk: a frame: 0.41 MB unswizzled on the CPU in 0.20 ms [hos host] vk: texture #21037 0x10006ca4a00 826x826 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (9 so far) [hos host] vk: program picks: 3953092 kept (1565384 by the last picks' textures, a uniform buffer bound since), 13826 new, 1633081 with other textures (of 5600000) [hos host] vk: replay reads of guest memory as submitted: 2840000 (1698589 pages from the captures) [hos Presentation Thread] vi: 7578 frames presented (20.5 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 0, 15.5-17.8 0, 17.8-22 0, 22-30 1, 30-40 31, over 40 71 [hos sead::MainThread] nvn: GPU waits in 5 s: 97 sync waits (1449 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos Presentation Thread] vk: 26 textures retired (1920 left, 2104 MB): budget 0, drawn over 0, dead targets 26 [hos Presentation Thread] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: read live, by pool: [hos host] vk: capture: a submit 0.37 ms (lock 0.00, scan 0.17 over 2884 ranges, 3021 MB), 192 pages written, 192 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.041; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.033, bytes copied 0.000; 25 kept (256 MB), 1 spare buffers, 7454 texture pages copied (29 MB) [hos host] vk: late pages left to their reads (600 takes): 606 pages in 81 takes (606 kept with their capture), 162 read on the CPU, 0 of them waited (0.00 ms in all); 12 still late; 0 late pages in a texture's storage waited at the take [hos host] vk: replay reads of guest memory as submitted: 2860000 (1712593 pages from the captures) [hos Presentation Thread] vk: 114 textures retired (1837 left, 2081 MB): budget 101, drawn over 0, dead targets 13 [hos PreActorModelCompose] vcores: PreActorModelCompose (priority 26) waited 78.3 ms for a core: given by aglTextureDataMgr::Compaction (priority 25), which held it 0.0 ms and was never asked; the cores it may use now: core 1: it; [hos aal::LowPrioWorkerThread] vcores: 49717 takes, 9232 waits (mean 232 us, longest 157.8 ms, 2 over HOS_VCORE_LOG_MS), 4368 kicks, 4560 yields, 0 starved grants, 0 escapes in 5 s [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.05, writes collected 0.07 [hos Presentation Thread] vk: 12 textures retired (1854 left, 2165 MB): budget 0, drawn over 0, dead targets 12 [hos host] vk: texture #21442 0x10006a64e00 384x384 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (10 so far) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 2546 of 3000 waited for their write-back, 0.41 ms each; 93 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: readbacks waited for their writer's part (RX_VK_READBACK_EARLY): 826, 0.56 ms each; 0 for their whole submission (writer not known); 412 parts ended after a readback's writer; 4 waited for their writer's submission to be recorded first, 3.50 ms each (0 of them past 250 ms: their whole submission) [hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 10036 kept their virtual core (nothing there to wait for), 3020 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos ModuleSystemWorker2] vk: releases kept for stopped work: 10001 [hos host] vk: write-backs left out (600 submits): 0, 0.0 MB; 0 bindings followed, 0 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 0 dirty pages from their submits' captures, 0 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): 0 dispatches, 0 chunks; 0 syncs as copies (no table room) [hos host] vk: read live, by pool: [hos host] vk: imports: 60 live (2192 MB), 0 retired still imported (0 MB), 36 retired given back (1600 MB) [hos host] vk: replay reads of guest memory as submitted: 2880000 (1725599 pages from the captures) [hos Presentation Thread] vk: 1 textures retired (1838 left, 2050 MB): budget 0, drawn over 0, dead targets 1 [hos ModuleSystemWorker4] vk: texture slots registered again at another size: 400000 (of 571506 registrations; slot 8112 120x68 -> 480x270) [hos host] vk: texture #21686 0x10006ca4a00 847x847 NVN 0x34 evicted, made again over storage render targets took: uploaded from the game's memory (11 so far) [hos Presentation Thread] vk: render targets drawn over from another start, let go: 14002 so far (49941 MB), 12610 of them (45034 MB) between the passes [hos Presentation Thread] vk: 1 textures retired (1853 left, 2132 MB): budget 0, drawn over 0, dead targets 1 [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: 20 program records loaded (21.7 ms), 3 new graphics pipelines, pipelines from the driver's cache 3, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 6026 queued, 6026 loaded (median 0.73 ms, 99th percentile 10.85 ms, worst 139.94 ms, 9500 ms and 1365.5 MB read in all); 8679 programs (1809 of them compute variants without their code, 0 graphics programs no note names), 10841 graphics pipelines (0 not in a cache), 703 compute pipelines (36 not in a cache); a first use ran 1 itself and waited for 0 (0.9 ms); 2319 pipelines made at create taken by draws; 2767 create calls with nothing kept for their stages, 0 before the index; units 8793 (6026 ready, 0 loading), 14419 programs alive; 0 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (close): 739 known, 0 learned in this run; 703 compute pipelines made by them at a create call, 36 asked that way were in no cache (their code read, as before) [hos host] vk: indexed descriptor arrays (close): 1141 in 1141 of 19056 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 1141 texture (17-64: 1141); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4263 pools in the table now) [hos host] control: exiting [hos host] stop: close work done (a file the game was writing waited for, at most 3 s)