Report rp_b47b80f27c0c9ecd fail
Machine
- Commit
- 8ba0d0281b89c9b32abe3dce2ad1db1e2e365378
- Baseline
- 08994a9ee1b391bf35b29ddd41eede8b3f4defb4
- App
- nightly-191-38dff5fc, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 7 5800X3D 8-Core Processor
- gpu
- AMD Radeon RX 7900 XTX (RADV NAVI31)
- tags
- linuxamdradvdgpu
- driver
- 26.2.7
- ram_gb
- 64
- vram_mb
- 24,560
- gpu_vendor
- amd
- os_version
- Bazzite (kernel 7.3.4)
Builds
main (baseline)
54.9 s warm
from 08994a9ee1b3
- lift
- 0.6 s
- read
- 5.1 s
- finish
- 15.3 s
- compile
- 10.8 s
- shaders
- 16.6 s
PR
23.2 s warm
Program cache: warm
Scenarios
three-areas
ok| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| run_hitch_count | 41 | 126 | +207.3% |
| run_frametime_max_ms | 340.12 | 387.41 | +13.9% |
| field-standing.fps_mean | 84.88 | 103.96 | +22.5% |
| forest-standing.fps_mean | 77.62 | 110.78 | +42.7% |
| market-standing.fps_mean | 64.39 | 49.62 | −22.9% |
| field-after-turn.fps_mean | 81.86 | 112.31 | +37.2% |
| field-standing.draws_mean | 1,199.65 | 1,197.3 | −0.2% |
| field-standing.hitch_count | 0 | 0 | ±0% |
| forest-after-turn.fps_mean | 77.47 | 107.45 | +38.7% |
| forest-standing.draws_mean | 738.15 | 684.25 | −7.3% |
| market-after-turn.fps_mean | 89.52 | 103.52 | +15.6% |
| market-standing.draws_mean | 2,475.35 | 2,488.9 | +0.5% |
| field-after-turn.draws_mean | 775.1 | 762.7 | −1.6% |
| forest-standing.hitch_count | 0.5 | 0.5 | ±0% |
| market-standing.hitch_count | 2.5 | 47 | +1780% |
| field-after-turn.hitch_count | 0 | 0.5 | — |
| field-standing.stutter_count | 0 | 0 | ±0% |
| forest-after-turn.draws_mean | 726.75 | 768.6 | +5.8% |
| market-after-turn.draws_mean | 514.2 | 494.7 | −3.8% |
| forest-after-turn.hitch_count | 0 | 0 | ±0% |
| forest-standing.stutter_count | 0.5 | 0.5 | ±0% |
| market-after-turn.hitch_count | 0 | 0.5 | — |
| market-standing.stutter_count | 3.5 | 47 | +1242.9% |
| field-after-turn.stutter_count | 0 | 0.5 | — |
| field-standing.frametime_max_ms | 16.27 | 14.14 | −13.1% |
| field-standing.frametime_p50_ms | 11.55 | 9.6 | −16.9% |
| field-standing.frametime_p99_ms | 14.66 | 10.75 | −26.7% |
| forest-after-turn.stutter_count | 0 | 0 | ±0% |
| market-after-turn.stutter_count | 0 | 1 | — |
| forest-standing.frametime_max_ms | 42.36 | 38.63 | −8.8% |
| forest-standing.frametime_p50_ms | 13.09 | 8.96 | −31.5% |
| forest-standing.frametime_p99_ms | 15.46 | 11.1 | −28.2% |
| market-standing.frametime_max_ms | 71.4 | 67.32 | −5.7% |
| market-standing.frametime_p50_ms | 15.16 | 17.69 | +16.7% |
| market-standing.frametime_p99_ms | 19.93 | 65.32 | +227.7% |
| field-after-turn.frametime_max_ms | 15.4 | 35.49 | +130.5% |
| field-after-turn.frametime_p50_ms | 11.96 | 8.8 | −26.5% |
| field-after-turn.frametime_p99_ms | 14.67 | 9.94 | −32.2% |
| forest-after-turn.frametime_max_ms | 17 | 13.13 | −22.8% |
| forest-after-turn.frametime_p50_ms | 13.04 | 9.17 | −29.7% |
| forest-after-turn.frametime_p99_ms | 15.69 | 11.01 | −29.8% |
| market-after-turn.frametime_max_ms | 17.44 | 36.77 | +110.8% |
| market-after-turn.frametime_p50_ms | 11.08 | 9.47 | −14.5% |
| market-after-turn.frametime_p99_ms | 15.43 | 12.45 | −19.3% |
| field-standing.frametime_1pct_low_ms | 15.08 | 11.39 | −24.5% |
| forest-standing.frametime_1pct_low_ms | 17.54 | 13.22 | −24.6% |
| market-standing.frametime_1pct_low_ms | 32.03 | 66.21 | +106.7% |
| field-after-turn.frametime_1pct_low_ms | 14.94 | 11.95 | −20% |
| forest-after-turn.frametime_1pct_low_ms | 16.14 | 11.44 | −29.1% |
| market-after-turn.frametime_1pct_low_ms | 16.27 | 15.98 | −1.8% |
| screenshot_diff | — | 0.39 | — |
Pictures against main: forest diff 0.694 (main against itself 0.6943), field diff 0.0321 (main against itself 0.0291), market diff 0.1798 (main against itself 0.0684)
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 | 47 | 151 | 101 | 35 |
| run_frametime_max_ms | 379.6 | 415.58 | 359.25 | 300.63 |
| field-standing.fps_mean | 84.64 | 103.71 | 104.21 | 85.11 |
| forest-standing.fps_mean | 85.87 | 108.8 | 112.75 | 69.37 |
| market-standing.fps_mean | 64.59 | 46.48 | 52.76 | 64.19 |
| field-after-turn.fps_mean | 81.59 | 108.45 | 116.16 | 82.12 |
| field-standing.draws_mean | 1,202.5 | 1,197.1 | 1,197.5 | 1,196.8 |
| field-standing.hitch_count | 0 | 0 | 0 | 0 |
| forest-after-turn.fps_mean | 85.57 | 107.19 | 107.72 | 69.38 |
| forest-standing.draws_mean | 797.5 | 685.2 | 683.3 | 678.8 |
| market-after-turn.fps_mean | 91.01 | 106.67 | 100.36 | 88.02 |
| market-standing.draws_mean | 2,479.2 | 2,518.5 | 2,459.3 | 2,471.5 |
| field-after-turn.draws_mean | 769.2 | 787.5 | 737.9 | 781 |
| forest-standing.hitch_count | 1 | 0 | 1 | 0 |
| market-standing.hitch_count | 3 | 68 | 26 | 2 |
| field-after-turn.hitch_count | 0 | 1 | 0 | 0 |
| field-standing.stutter_count | 0 | 0 | 0 | 0 |
| forest-after-turn.draws_mean | 759.7 | 768.6 | 768.6 | 693.8 |
| market-after-turn.draws_mean | 510.8 | 505.2 | 484.2 | 517.6 |
| forest-after-turn.hitch_count | 0 | 0 | 0 | 0 |
| forest-standing.stutter_count | 1 | 0 | 1 | 0 |
| market-after-turn.hitch_count | 0 | 1 | 0 | 0 |
| market-standing.stutter_count | 4 | 68 | 26 | 3 |
| field-after-turn.stutter_count | 0 | 1 | 0 | 0 |
| field-standing.frametime_max_ms | 16.46 | 13.36 | 14.92 | 16.07 |
| field-standing.frametime_p50_ms | 11.63 | 9.65 | 9.55 | 11.47 |
| field-standing.frametime_p99_ms | 14.78 | 10.78 | 10.71 | 14.55 |
| forest-after-turn.stutter_count | 0 | 0 | 0 | 0 |
| market-after-turn.stutter_count | 0 | 2 | 0 | 0 |
| forest-standing.frametime_max_ms | 65.3 | 14.75 | 62.51 | 19.42 |
| forest-standing.frametime_p50_ms | 11.66 | 9.13 | 8.79 | 14.52 |
| forest-standing.frametime_p99_ms | 13.6 | 11.61 | 10.59 | 17.33 |
| market-standing.frametime_max_ms | 69.83 | 67.69 | 66.95 | 72.98 |
| market-standing.frametime_p50_ms | 15.11 | 17.89 | 17.49 | 15.21 |
| market-standing.frametime_p99_ms | 20.31 | 65.88 | 64.76 | 19.55 |
| field-after-turn.frametime_max_ms | 15.26 | 59.72 | 11.27 | 15.54 |
| field-after-turn.frametime_p50_ms | 12.09 | 9.08 | 8.52 | 11.84 |
| field-after-turn.frametime_p99_ms | 14.7 | 10.39 | 9.49 | 14.64 |
| forest-after-turn.frametime_max_ms | 16.3 | 12.45 | 13.82 | 17.71 |
| forest-after-turn.frametime_p50_ms | 11.56 | 9.18 | 9.16 | 14.52 |
| forest-after-turn.frametime_p99_ms | 14.08 | 11.57 | 10.46 | 17.3 |
| market-after-turn.frametime_max_ms | 17.84 | 55.9 | 17.63 | 17.05 |
| market-after-turn.frametime_p50_ms | 10.74 | 9.29 | 9.65 | 11.42 |
| market-after-turn.frametime_p99_ms | 15.23 | 12.12 | 12.79 | 15.63 |
| field-standing.frametime_1pct_low_ms | 15.23 | 11.41 | 11.36 | 14.92 |
| forest-standing.frametime_1pct_low_ms | 17 | 12.67 | 13.77 | 18.08 |
| market-standing.frametime_1pct_low_ms | 33.8 | 66.71 | 65.71 | 30.26 |
| field-after-turn.frametime_1pct_low_ms | 14.87 | 14.01 | 9.9 | 15 |
| forest-after-turn.frametime_1pct_low_ms | 14.78 | 11.8 | 11.09 | 17.51 |
| market-after-turn.frametime_1pct_low_ms | 16.43 | 18.2 | 13.75 | 16.11 |
| screenshot_diff | — | 0.69 | 0.08 | — |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| three-areas | crash | False | 0 | 0 | — | pass | |
| three-areas | forest-standing.fps_mean.min_delta_pct | 5 | 77.62 | 110.78 | +42.7% | pass | |
| three-areas | forest-after-turn.fps_mean.min_delta_pct | 5 | 77.47 | 107.45 | +38.7% | pass | |
| three-areas | field-standing.fps_mean.min_delta_pct | 5 | 84.88 | 103.96 | +22.5% | pass | |
| three-areas | field-after-turn.fps_mean.min_delta_pct | 5 | 81.86 | 112.31 | +37.2% | pass | |
| three-areas | market-standing.fps_mean.min_delta_pct | 5 | 64.39 | 49.62 | −22.9% | fail | |
| three-areas | market-after-turn.fps_mean.min_delta_pct | 5 | 89.52 | 103.52 | +15.6% | pass | |
| three-areas | screenshot.max_diff | 0.05 | 0.69 | 0.69 | — | fail | |
| three-areas | forest-standing.stutter_count.max_delta_pct | 50 | 0.5 | 0.5 | ±0% | pass | |
| three-areas | forest-after-turn.stutter_count.max_delta_pct | 50 | 0 | 0 | ±0% | pass | |
| three-areas | field-standing.stutter_count.max_delta_pct | 50 | 0 | 0 | ±0% | pass | |
| three-areas | field-after-turn.stutter_count.max_delta_pct | 50 | 0 | 0.5 | — | failthe baseline is 0 | |
| three-areas | market-standing.stutter_count.max_delta_pct | 50 | 3.5 | 47 | +1242.9% | fail | |
| three-areas | market-after-turn.stutter_count.max_delta_pct | 50 | 0 | 1 | — | failthe baseline is 0 | |
| three-areas | forest-standing.frametime_p99_ms.max_delta_pct | 15 | 15.46 | 11.1 | −28.2% | pass | |
| three-areas | forest-after-turn.frametime_p99_ms.max_delta_pct | 15 | 15.69 | 11.01 | −29.8% | pass | |
| three-areas | field-standing.frametime_p99_ms.max_delta_pct | 15 | 14.66 | 10.75 | −26.7% | pass | |
| three-areas | field-after-turn.frametime_p99_ms.max_delta_pct | 15 | 14.67 | 9.94 | −32.2% | pass | |
| three-areas | market-standing.frametime_p99_ms.max_delta_pct | 15 | 19.93 | 65.32 | +227.7% | fail | |
| three-areas | market-after-turn.frametime_p99_ms.max_delta_pct | 15 | 15.43 | 12.45 | −19.3% | pass |
Pictures of the failure
This report had 2 pictures of its failure (the last frame of a stuck step, or main's and the PR's picture where they differed too much). The farm keeps those for a day: they were deleted.
Log (PR side, end)
[hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 33.2; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 3.0 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.9 MB), ASTC or BC 0.0 (0.0 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.16 MB unswizzled on the CPU in 0.02 ms [hos host] vk: 2 textures retired (4586 left, 9018 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: 4 textures retired (4583 left, 9012 MB): budget 0, drawn over 4, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7560000 (4095914 pages from the captures) [hos sead::MainThread] nvn: CommandBufferSignalEvent #270000: event 0x100d6c8034 mode 0 value 269999 (lr 0x806616b0) [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 16512; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1827 dirty pages from their submits' captures, 54267 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): 1191 dispatches, 45359 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5786 runs, 942.4 MB compared; 107 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20227 in captures, 2 only in the collection, 55 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos host] vk: 1 textures retired (4584 left, 8998 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1018 ranges, 3304 MB), 175 pages written, 175 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (104 MB), 9 spare buffers, 7330 texture pages copied (28 MB) [hos host] vk: replay reads of guest memory as submitted: 7580000 (4109300 pages from the captures) [hos sead::MainThread] nvn: CommandBufferWaitEvent #395000: event 0x100d6c8010 mode 0 value 271035 (now 271016) (lr 0x80660fdc) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1789 dirty pages from their submits' captures, 54275 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): 1190 dispatches, 45344 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5790 runs, 941.4 MB compared; 101 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20190 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker4] vk: readbacks of GPU results: 981 of 3000 waited for their write-back, 0.14 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: 7919 kept their virtual core (nothing there to wait for), 2833 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, 5161 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.18, present 0.17, draw 2.28, descriptors 0.76, texture lookups 0.07, uploads 0.02, pipelines 0.07, programs 0.27, commands 1.02, dispatch 0.53, memory sync 0.23, queue submit 0.71, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 839.8 copies, 17.43 MB written back [hos host] vk: 27840 presents, 100.1 fps; a frame: 483 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4590 textures (9074 MB) [hos host] vk: host time in GPU resource waits: 2.15 ms a frame (fences 0.00, timelines 2.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.4 full barriers recorded, 219.6 left out (nothing recorded since the one before), 12.4 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: 33.2; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 2.8 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.7 MB), ASTC or BC 0.1 (0.2 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: replay reads of guest memory as submitted: 7600000 (4122650 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: 1 textures retired (4589 left, 9070 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: late pages' fix (600 recordings with one): of 677 captures with late pages 677 fixed (37.5 pages, 38.5 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 348 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 117 blocks (7488 KB); of the reads on the CPU, 0 waited for an earlier part's fix, 0 copied the page again instead (that part not waited for); the paths: reads on the CPU with the fix done 151, of an earlier recording 197, not recorded yet 0, of this part 0; pages fixed from stamps 24209, from snapshots 1186; the shadows: 324510 pages synced from captures, 320702 made known by it, 3808 left unknown because the replay or the collection wrote them since [hos host] vk: 2 textures retired (4587 left, 9042 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17160; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1847 dirty pages from their submits' captures, 54278 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): 1188 dispatches, 45375 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5782 runs, 941.4 MB compared; 110 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20236 in captures, 1 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos sead::MainThread] nvn: GPU waits in 5 s: 326 sync waits (518 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: 4 textures retired (4583 left, 8984 MB): budget 0, drawn over 4, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1018 ranges, 3298 MB), 177 pages written, 177 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.008; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 24 kept (84 MB), 11 spare buffers, 7108 texture pages copied (27 MB) [hos host] vk: replay reads of guest memory as submitted: 7620000 (4136032 pages from the captures) [hos host] vk: 1 textures retired (4582 left, 8980 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 2 textures retired (4581 left, 8986 MB): budget 0, drawn over 2, dead targets 0 [hos ModuleSystemWorker4] nvn: 2100000 recordings made, 68192 live copies (19.4 MB), 3380 texture copies; 4 command buffers' segments (4.2 MB) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1782 dirty pages from their submits' captures, 54505 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): 1190 dispatches, 45382 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5771 runs, 941.3 MB compared; 102 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20193 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 2 textures retired (4581 left, 8976 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7640000 (4149394 pages from the captures) [hos host] vk: 1 textures retired (4585 left, 9044 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.23, present 0.17, draw 2.29, descriptors 0.77, texture lookups 0.05, uploads 0.00, pipelines 0.07, programs 0.28, commands 1.02, dispatch 0.54, memory sync 0.25, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 840.2 copies, 17.44 MB written back [hos host] vk: 27960 presents, 100.4 fps; a frame: 483 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4585 textures (9044 MB) [hos host] vk: host time in GPU resource waits: 2.11 ms a frame (fences 0.00, timelines 2.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.7 full barriers recorded, 219.6 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 5.9 ms a frame (the longest submission 3.0 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.8 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 sead::MainThread] vk: readbacks of GPU results: 980 of 3000 waited for their write-back, 0.14 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos sead::MainThread] vk: invalidates since the last readbacks line: 8490 kept their virtual core (nothing there to wait for), 3030 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, 11842 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 1 textures retired (4585 left, 9054 MB): budget 0, drawn over 1, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1018 ranges, 3298 MB), 175 pages written, 175 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 24 kept (108 MB), 12 spare buffers, 6596 texture pages copied (25 MB) [hos host] vk: readback pages refreshed from guest memory: 4399067 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 7660000 (4162806 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: 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 135 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 17808; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1893 dirty pages from their submits' captures, 54251 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): 1188 dispatches, 45371 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5844 runs, 942.2 MB compared; 101 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20342 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos Presentation Thread] vi: 27982 frames presented (100.6 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 502, 15.5-17.8 1, 17.8-22 0, 22-30 0, 30-40 0, over 40 0 [hos ModuleSystemWorker3] nvn: DrawMeshTasksIndirect: 620000 so far (x1 0x117ccee000 x2 0x2 x3 0x117ccee000 x4 0x230040) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: 2 textures retired (4583 left, 9046 MB): budget 0, drawn over 2, dead targets 0 [hos sead::MainThread] nvn: CommandBufferWaitEvent #400000: event 0x100d6c8010 mode 0 value 274835 (now 274816) (lr 0x80660fdc) [hos host] vk: replay reads of guest memory as submitted: 7680000 (4176177 pages from the captures) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #275000: event 0x100d6c8040 mode 0 value 274999 (lr 0x806621e8) [hos host] vk: 2 textures retired (4581 left, 9017 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1815 dirty pages from their submits' captures, 54247 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): 1188 dispatches, 45365 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5861 runs, 942.5 MB compared; 105 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20192 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1018 ranges, 3276 MB), 168 pages written, 168 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (104 MB), 11 spare buffers, 6596 texture pages copied (25 MB) [hos host] vk: program picks: 10393551 kept (3794064 by the last picks' textures, a uniform buffer bound since), 58089 new, 4948359 with other textures (of 15400000) [hos host] vk: replay reads of guest memory as submitted: 7700000 (4189544 pages from the captures) [hos BaseProcExecutor4] vcores: 155542 takes, 32502 waits (mean 72 us, longest 11.9 ms, 0 over HOS_VCORE_LOG_MS), 14702 kicks, 14915 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.21, present 0.17, draw 2.23, descriptors 0.73, texture lookups 0.04, uploads 0.00, pipelines 0.07, programs 0.26, commands 1.01, dispatch 0.56, memory sync 0.24, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 840.9 copies, 17.46 MB written back [hos host] vk: 28080 presents, 101.0 fps; a frame: 483 draws (0 skipped), 79 dispatches, 134 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4586 textures (9068 MB) [hos host] vk: host time in GPU resource waits: 2.07 ms a frame (fences 0.00, timelines 2.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 387.9 full barriers recorded, 219.8 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 3.0 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.5 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: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 18456; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1774 dirty pages from their submits' captures, 54665 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): 1197 dispatches, 45628 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5894 runs, 943.1 MB compared; 105 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20326 in captures, 1 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 5192 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: render targets drawn over from another start, let go: 7603 so far (31345 MB), 6756 of them (28160 MB) between the passes [hos ModuleSystemWorker5] vk: readbacks of GPU results: 980 of 3000 waited for their write-back, 0.14 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker5] vk: invalidates since the last readbacks line: 8249 kept their virtual core (nothing there to wait for), 3015 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 7720000 (4202932 pages from the captures) [hos host] vk: 1 textures retired (4590 left, 9095 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: 4 textures retired (4586 left, 9037 MB): budget 0, drawn over 4, dead targets 0 [hos host] vk: 5 textures retired (4581 left, 8966 MB): budget 0, drawn over 5, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1155, 5665.4 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): 1733 dirty pages from their submits' captures, 55152 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): 1201 dispatches, 46054 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5966 runs, 959.8 MB compared; 106 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20588 in captures, 1 only in the collection, 55 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.04 over 1002 ranges, 3078 MB), 176 pages written, 176 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (110 MB), 11 spare buffers, 6596 texture pages copied (25 MB) [hos host] vk: replay reads of guest memory as submitted: 7740000 (4216286 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 7760000 (4229699 pages from the captures) [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19110; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1777 dirty pages from their submits' captures, 54245 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): 1191 dispatches, 45343 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5816 runs, 942.0 MB compared; 111 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20162 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: memory: working set 10400 MB (peak 11485), private 3588 MB, staging 80 MB in 5 arenas, 49 made so far (1 ms) [hos host] vk: memory heaps: heap 0 (system): 13 blocks 808 MB, 39 allocations 742 MB; used 3072 of 31951 MB; heap 1 (device): 341 blocks 11260 MB, 17689 allocations 10472 MB; used 12002 of 22635 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): 27 blocks 864 MB, 158 images 476 MB; 122 free ranges, the largest 28 MB [hos host] vk: image blocks (textures, compacted): 214 blocks 6848 MB, 4407 images 6759 MB; 1018 free ranges, the largest 19 MB [hos host] vk: render target images: 4166 reused from the pool, 4326 made new, 4162 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 12002 MB used of 22635 MB allowed (787 MB of it free in the blocks); textures 8984 MB (budget 11000 MB), 4585 textures [hos host] vk: budget: VRAM 11260 of 22635 MB (12002 MB by the driver, 741 MB unaccounted): textures 8984, mirrors 800, blocks free 787, shadows 332, other buffers 228, staging 80, other images 46; RAM 3016 MB (the process's private memory 3588 MB): imports 2240, capture spares 628, captures 96, capture table 34, other buffers 18, others 0 [hos host] vk: textures: decoded ASTC 5554 MB, rendered 1247 MB (40 drawn in one frame, kept: 36248 KB), other 1357 MB; used in the last 8 presents 1921 MB [hos host] vk: decoded ASTC used again: 81 textures (123 MB) copied from ones the game finalized, not decoded; 81 of those retired, 644 listed; 1122 MB of blocks hashed in 104 ms [hos host] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 5575 presents ago [hos host] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 5575 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0xa, last used 16901 presents ago [hos host] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1046 presents ago [hos host] vk: 54 MB: 0x100032c0400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 7707 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 72 (19423 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: 35 (6158 KB); [hos Presentation Thread] vk: presents after the CPU's signal (600): 486 waited for it, 1.46 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 17.6 ms; VRAM 11.7 of 22.1 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: 28 program records loaded (7.9 ms), 1 new graphics pipelines, pipelines from the driver's cache 1, from the start's cache 0, compiled 0; 1 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 6026 queued, 6026 loaded (median 0.16 ms, 99th percentile 3.02 ms, worst 16.81 ms, 1919 ms and 1447.6 MB read in all); 8970 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 0 itself and waited for 0 (0.0 ms); 2165 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 (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 host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.22, present 0.18, draw 2.24, descriptors 0.74, texture lookups 0.05, uploads 0.00, pipelines 0.07, programs 0.28, commands 1.01, dispatch 0.55, memory sync 0.25, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 840.1 copies, 17.45 MB written back [hos host] vk: 28200 presents, 99.8 fps; a frame: 483 draws (0 skipped), 79 dispatches, 134 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4585 textures (8984 MB) [hos host] vk: host time in GPU resource waits: 2.05 ms a frame (fences 0.00, timelines 2.05, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 387.2 full barriers recorded, 219.7 left out (nothing recorded since the one before), 12.4 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: 33.2; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 2.8 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.5 MB), ASTC or BC 0.1 (0.1 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 9.97 ms a frame): its jobs 4.77 ms a frame (submits 0.80, presents 0.18, others 3.79), idle 5.20; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 2.24 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); 573 captures at a CPU signal; the submits' waits read in 0.019 ms a frame; readbacks: 3000 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 4.20 ms after its hand-over (7.43 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 1.96 + 0.23 (the window's copy is in the idle), after it 1.61 + 0.21; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.02 ms of GPU time), after its last that reads it 1.00 (0.02 ms) [hos host] vk: frame ahead (600 presents): 4.13 parts a frame recorded in the signal's job, 56.1% of them took nothing that came with the signal; of the others, 1.81 a frame took pages of the signal's capture into a mirror (34.8 pages a frame) and 0.00 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 66 of 573 frames, its first three in 66 [hos host] vk: frame ahead, what came with the signal: 573 signals with a capture, each of 82.6 pages in 9.6 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any) [hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.65+0.14, 0.86+0.04, 0.10+0.02, 0.00+0.02, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00, 0.00+0.00 [hos host] vk: 2 textures retired (4584 left, 8991 MB): budget 0, drawn over 2, dead targets 0 [hos sead::MainThread] nvn: CommandBufferWaitEvent #405000: event 0x100d6c8010 mode 0 value 278635 (now 278616) (lr 0x80660fdc) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 7192 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 1002 ranges, 3084 MB), 178 pages written, 178 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.008; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.005, bytes copied 0.000; 25 kept (110 MB), 11 spare buffers, 6750 texture pages copied (26 MB) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 7780000 (4243063 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 979 of 3000 waited for their write-back, 0.14 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 8272 kept their virtual core (nothing there to wait for), 2992 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: readback pages refreshed from guest memory: 4473242 pages so far (0 held: may be written ahead in their submission) [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 135 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1817 dirty pages from their submits' captures, 54308 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): 1189 dispatches, 45354 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5792 runs, 941.4 MB compared; 104 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20158 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 2 textures retired (4584 left, 9011 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: 1 textures retired (4583 left, 8997 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7800000 (4256440 pages from the captures) [hos host] vk: 1 textures retired (4582 left, 8982 MB): budget 0, drawn over 1, dead targets 0 [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #280000: event 0x100d6c800c mode 0 value 280002 (lr 0x80660adc) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 19764; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1155, 5665.4 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): 1784 dirty pages from their submits' captures, 55230 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): 1210 dispatches, 46138 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5895 runs, 958.8 MB compared; 112 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20440 in captures, 3 only in the collection, 55 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos host] vk: 1 textures retired (4583 left, 8976 MB): budget 0, drawn over 1, dead targets 0 [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.01, scan 0.04 over 955 ranges, 2850 MB), 172 pages written, 172 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 6738 texture pages copied (26 MB) [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.18, present 0.17, draw 2.24, descriptors 0.73, texture lookups 0.04, uploads 0.00, pipelines 0.07, programs 0.27, commands 1.01, dispatch 0.53, memory sync 0.23, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 839.7 copies, 17.43 MB written back [hos host] vk: 28320 presents, 100.8 fps; a frame: 483 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4585 textures (8995 MB) [hos host] vk: host time in GPU resource waits: 2.09 ms a frame (fences 0.00, timelines 2.09, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.2 full barriers recorded, 219.6 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 5.9 ms a frame (the longest submission 2.9 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.5 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: 7820000 (4269830 pages from the captures) [hos host] vk: queues ordered by their events: 162000 submissions stopped at a wait, 160815 went on once it was reached, 1183 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 86 (stopped 50.07 ms at most); waits met 407071, not met 0; captures at a CPU event's wait 20292, 0 of them at a wait met on arrival [hos host] vk: 1 textures retired (4585 left, 9005 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2910 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1838 dirty pages from their submits' captures, 54287 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): 1188 dispatches, 45389 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5783 runs, 941.4 MB compared; 104 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20223 in captures, 1 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 2 textures retired (4585 left, 9015 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7840000 (4283178 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: 1 textures retired (4585 left, 9005 MB): budget 0, drawn over 1, dead targets 0 [hos ModuleSystemWorker2] nvn: 2150000 recordings made, 68152 live copies (19.2 MB), 3380 texture copies; 7 command buffers' segments (4.4 MB) [hos sead::MainThread] nvn: GPU waits in 5 s: 328 sync waits (535 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: 1 textures retired (4584 left, 8991 MB): budget 0, drawn over 1, dead targets 0 [hos ModuleSystemWorker4] vk: readbacks of GPU results: 968 of 3000 waited for their write-back, 0.15 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: 8454 kept their virtual core (nothing there to wait for), 3066 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 955 ranges, 2848 MB), 172 pages written, 172 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.006; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.003, bytes copied 0.000; 24 kept (84 MB), 12 spare buffers, 6442 texture pages copied (25 MB) [hos host] vk: replay reads of guest memory as submitted: 7860000 (4296593 pages from the captures) [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 20418; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1155, 5665.4 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): 1829 dirty pages from their submits' captures, 55165 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): 1209 dispatches, 46120 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5803 runs, 941.5 MB compared; 115 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20412 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos ModuleSystemWorker1] nvn: CommandBufferWaitEvent #410000: event 0x100d6c8010 mode 0 value 282435 (now 282416) (lr 0x80660fdc) [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.15, present 0.17, draw 2.25, descriptors 0.73, texture lookups 0.05, uploads 0.00, pipelines 0.07, programs 0.27, commands 1.02, dispatch 0.53, memory sync 0.21, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.05 MB synced in 839.1 copies, 17.43 MB written back [hos host] vk: 28440 presents, 100.9 fps; a frame: 483 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4584 textures (8991 MB) [hos host] vk: host time in GPU resource waits: 2.10 ms a frame (fences 0.00, timelines 2.10, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.6 full barriers recorded, 219.5 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 3.0 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.3 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: program picks: 10497753 kept (3806911 by the last picks' textures, a uniform buffer bound since), 58089 new, 5044157 with other textures (of 15600000) [hos host] vk: 1 textures retired (4585 left, 9015 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7880000 (4309961 pages from the captures) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1777 dirty pages from their submits' captures, 54216 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): 1190 dispatches, 45313 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5846 runs, 957.6 MB compared; 104 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20180 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 2 textures retired (4584 left, 8991 MB): budget 0, drawn over 2, dead targets 0 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 10279 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vi: 28486 frames presented (100.7 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 504, 15.5-17.8 0, 17.8-22 0, 22-30 0, 30-40 0, over 40 0 [hos host] vk: 1 textures retired (4583 left, 8986 MB): budget 0, drawn over 1, dead targets 0 [hos sead::MainThread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 955 ranges, 2848 MB), 178 pages written, 178 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.007; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.004, bytes copied 0.000; 25 kept (104 MB), 11 spare buffers, 6795 texture pages copied (26 MB) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 7900000 (4323338 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: readback pages refreshed from guest memory: 4546942 pages so far (0 held: may be written ahead in their submission) [hos sead::MainThread] nvn: DrawMeshTasksIndirect: 640000 so far (x1 0x117e3d8030 x2 0 x3 0x117e3d8000 x4 0x8b040) [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 135 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 21066; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1819 dirty pages from their submits' captures, 54161 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): 1191 dispatches, 45263 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5796 runs, 941.4 MB compared; 104 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20116 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 980 of 3000 waited for their write-back, 0.14 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker2] vk: invalidates since the last readbacks line: 8281 kept their virtual core (nothing there to wait for), 2983 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: 7920000 (4336715 pages from the captures) [hos sead::MainThread] nvn: CommandBufferSignalEvent #285000: event 0x100d6c8008 mode 0 value 284998 (lr 0x80660f34) [hos host] vk: 1 textures retired (4584 left, 9001 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.15, present 0.17, draw 2.29, descriptors 0.76, texture lookups 0.04, uploads 0.00, pipelines 0.07, programs 0.27, commands 1.03, dispatch 0.53, memory sync 0.23, queue submit 0.70, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 839.3 copies, 17.43 MB written back [hos host] vk: 28560 presents, 101.0 fps; a frame: 483 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.0 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4584 textures (9001 MB) [hos host] vk: host time in GPU resource waits: 2.11 ms a frame (fences 0.00, timelines 2.11, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.3 full barriers recorded, 219.6 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 6.0 ms a frame (the longest submission 2.9 ms); 0.0 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.0 (0.4 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: 1 textures retired (4583 left, 8986 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1952 dirty pages from their submits' captures, 54305 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): 1190 dispatches, 45371 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5799 runs, 942.4 MB compared; 103 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20180 in captures, 1 only in the collection, 55 only by the replay itself [hos host] vk: read live, by pool: [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 953 ranges, 2830 MB), 182 pages written, 182 copied (0.7 MB) [hos host] vk: a capture taken (ms): all 0.010; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 24 kept (102 MB), 12 spare buffers, 7375 texture pages copied (28 MB) [hos aal::LowPrioWorkerThread] vcores: 151795 takes, 32097 waits (mean 77 us, longest 11.8 ms, 0 over HOS_VCORE_LOG_MS), 14372 kicks, 14570 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: 1 textures retired (4583 left, 8976 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 7940000 (4350070 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 9662 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] nvn: CommandBufferWaitEvent #415000: event 0x100d6c8010 mode 0 value 286235 (now 286216) (lr 0x80660fdc) [hos host] vk: replay reads of guest memory as submitted: 7960000 (4363492 pages from the captures) [hos host] vk: late pages found at the replay (600 takes): 0 pages in 0 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: sparse mirrors: 53, 800 MB with memory of 1200 MB (399 MB spared); blocks given memory later 3805, given back 9634; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 21714; 556 binds (143.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 127 taken from the spares, 119 made new; 193 kept as spares, 0 destroyed; 66 spares now, 1132 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1853 dirty pages from their submits' captures, 54252 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): 1188 dispatches, 45364 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5779 runs, 941.4 MB compared; 108 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20195 in captures, 1 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 163 live (2240 MB), 0 retired still imported (0 MB), 21 retired given back (760 MB) [hos host] vk: 1 textures retired (4589 left, 9062 MB): budget 0, drawn over 1, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.08 ms (lock 0.00, scan 0.04 over 948 ranges, 2808 MB), 166 pages written, 166 copied (0.6 MB) [hos host] vk: a capture taken (ms): all 0.004; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.001, bytes copied 0.000; 25 kept (98 MB), 10 spare buffers, 7375 texture pages copied (28 MB) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 980 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: 7990 kept their virtual core (nothing there to wait for), 3018 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: 7980000 (4376859 pages from the captures) [hos host] vk: 1 textures retired (4589 left, 9062 MB): budget 0, drawn over 1, dead targets 0 [hos host] vk: 5 textures retired (4588 left, 8992 MB): budget 0, drawn over 5, dead targets 0 [hos host] vk: a frame: 28 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 54 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 4.21, present 0.17, draw 2.21, descriptors 0.74, texture lookups 0.05, uploads 0.00, pipelines 0.07, programs 0.27, commands 0.98, dispatch 0.55, memory sync 0.26, queue submit 0.69, slot wait 0.03 [hos host] vk: a frame: mirrors 246 (800 MB): 4.06 MB synced in 839.5 copies, 17.43 MB written back [hos host] vk: 28680 presents, 101.2 fps; a frame: 484 draws (0 skipped), 78 dispatches, 134 passes, 141 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.0 ms (recording slots only); 55041 pipelines (903 ms), 0 programs (10 failed), 4588 textures (8992 MB) [hos host] vk: host time in GPU resource waits: 1.99 ms a frame (fences 0.00, timelines 1.99, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 386.4 full barriers recorded, 219.6 left out (nothing recorded since the one before), 12.4 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: 33.1; 0x12: 75.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 5.9 ms a frame (the longest submission 2.9 ms); 0.1 textures made a frame: colour targets 0.0 (0.0 MB), depth 0.1 (0.8 MB), ASTC or BC 0.1 (0.0 MB), other 0.0 (0.0 MB) [hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: write-backs left out (600 submits): 1134, 5562.4 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): 1830 dirty pages from their submits' captures, 54222 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): 1190 dispatches, 45323 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 5782 runs, 941.3 MB compared; 103 pages read into the shadows; 332 MB of shadows; pages the shadows knew that the CPU wrote: 20149 in captures, 0 only in the collection, 54 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.03 [hos host] vk: render targets drawn over from another start, let go: 7603 so far (31345 MB), 6756 of them (28160 MB) between the passes [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: 28 program records loaded (7.9 ms), 1 new graphics pipelines, pipelines from the driver's cache 1, from the start's cache 0, compiled 0; 1 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 6026 queued, 6026 loaded (median 0.16 ms, 99th percentile 3.02 ms, worst 16.81 ms, 1919 ms and 1447.6 MB read in all); 8970 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 0 itself and waited for 0 (0.0 ms); 2165 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): 2631 in 2631 of 55777 program stages, 0 of them near a limit [hos host] vk: indexed descriptor arrays (close), fragment stages: 2631 texture (17-64: 2631); the longest 64 [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4256 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)