Report rp_dabcf9c0a1af5264 fail
Machine
- Commit
- 3569b8da6a4f90bc036bbb40cb52993b865b0a39
- Baseline
- 09cbdd979eacfbd0c83e27fad7e50380985af02d
- App
- nightly-172-736563c0, attempt 1
- Game build
e0f3ccfa- os
- windows
- cpu
- AMD Ryzen 5 5600X3D 6-Core Processor
- gpu
- NVIDIA GeForce RTX 3070
- tags
- windowsnvidianvidia-proprietarydgpu
- driver
- 621.24.0
- ram_gb
- 32
- vram_mb
- 8,017
- gpu_vendor
- nvidia
- os_version
- Windows 10.0.26200
Builds
PR
163.5 s warm
Program cache: warm
Scenarios
forest-market RX_VK_PRESENT_THREAD=0
ok
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| forest.fps_mean | 59.94 | 59.78 | −0.3% |
| market.fps_mean | 60.05 | 59.18 | −1.4% |
| forest.draws_mean | 772.5 | 749.3 | −3% |
| market.draws_mean | 2,473.4 | 2,547.2 | +3% |
| forest.hitch_count | 0 | 0 | ±0% |
| market.hitch_count | 0 | 0 | ±0% |
| forest.stutter_count | 0 | 0 | ±0% |
| market.stutter_count | 0 | 0 | ±0% |
| forest.frametime_max_ms | 24.29 | 20.46 | −15.8% |
| forest.frametime_p50_ms | 16.65 | 16.62 | −0.2% |
| forest.frametime_p99_ms | 20.03 | 19.02 | −5% |
| market.frametime_max_ms | 29.41 | 29.02 | −1.4% |
| market.frametime_p50_ms | 16.59 | 16.63 | +0.2% |
| market.frametime_p99_ms | 21.15 | 23.37 | +10.5% |
| forest.frametime_1pct_low_ms | 21.71 | 19.42 | −10.6% |
| market.frametime_1pct_low_ms | 22.58 | 25.42 | +12.6% |
| screenshot_diff | — | 0.11 | — |
Pictures against main: forest diff 0.1083 (main against itself ), market diff 0.1113 (main against itself )
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| forest.fps_mean | 59.94 | 59.78 |
| market.fps_mean | 60.05 | 59.18 |
| forest.draws_mean | 772.5 | 749.3 |
| market.draws_mean | 2,473.4 | 2,547.2 |
| forest.hitch_count | 0 | 0 |
| market.hitch_count | 0 | 0 |
| forest.stutter_count | 0 | 0 |
| market.stutter_count | 0 | 0 |
| forest.frametime_max_ms | 24.29 | 20.46 |
| forest.frametime_p50_ms | 16.65 | 16.62 |
| forest.frametime_p99_ms | 20.03 | 19.02 |
| market.frametime_max_ms | 29.41 | 29.02 |
| market.frametime_p50_ms | 16.59 | 16.63 |
| market.frametime_p99_ms | 21.15 | 23.37 |
| forest.frametime_1pct_low_ms | 21.71 | 19.42 |
| market.frametime_1pct_low_ms | 22.58 | 25.42 |
| screenshot_diff | — | 0.11 |
forest-market RX_VK_PRESENT_THREAD=1
ok
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| forest.fps_mean | 59.51 | 59.73 | +0.4% |
| market.fps_mean | 57.96 | 59.64 | +2.9% |
| forest.draws_mean | 666.9 | 666.4 | −0.1% |
| market.draws_mean | 2,516 | 2,469.1 | −1.9% |
| forest.hitch_count | 0 | 0 | ±0% |
| market.hitch_count | 0 | 0 | ±0% |
| forest.stutter_count | 0 | 0 | ±0% |
| market.stutter_count | 0 | 0 | ±0% |
| forest.frametime_max_ms | 27.36 | 26.93 | −1.6% |
| forest.frametime_p50_ms | 16.61 | 16.56 | −0.3% |
| forest.frametime_p99_ms | 20.14 | 19.56 | −2.9% |
| market.frametime_max_ms | 23.73 | 25.72 | +8.4% |
| market.frametime_p50_ms | 17 | 16.52 | −2.8% |
| market.frametime_p99_ms | 21.79 | 21.87 | +0.3% |
| forest.frametime_1pct_low_ms | 21.59 | 20.57 | −4.7% |
| market.frametime_1pct_low_ms | 22.49 | 23.16 | +3% |
| screenshot_diff | — | 0.13 | — |
Pictures against main: forest diff 0.0756 (main against itself ), market diff 0.1274 (main against itself )
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| forest.fps_mean | 59.51 | 59.73 |
| market.fps_mean | 57.96 | 59.64 |
| forest.draws_mean | 666.9 | 666.4 |
| market.draws_mean | 2,516 | 2,469.1 |
| forest.hitch_count | 0 | 0 |
| market.hitch_count | 0 | 0 |
| forest.stutter_count | 0 | 0 |
| market.stutter_count | 0 | 0 |
| forest.frametime_max_ms | 27.36 | 26.93 |
| forest.frametime_p50_ms | 16.61 | 16.56 |
| forest.frametime_p99_ms | 20.14 | 19.56 |
| market.frametime_max_ms | 23.73 | 25.72 |
| market.frametime_p50_ms | 17 | 16.52 |
| market.frametime_p99_ms | 21.79 | 21.87 |
| forest.frametime_1pct_low_ms | 21.59 | 20.57 |
| market.frametime_1pct_low_ms | 22.49 | 23.16 |
| screenshot_diff | — | 0.13 |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| forest-market | RX_VK_PRESENT_THREAD=0 | crash | False | 0 | 0 | — | pass |
| forest-market | RX_VK_PRESENT_THREAD=0 | forest.fps_mean.min_delta_pct | 10 | 59.94 | 59.78 | −0.3% | pass |
| forest-market | RX_VK_PRESENT_THREAD=0 | market.fps_mean.min_delta_pct | 10 | 60.05 | 59.18 | −1.4% | pass |
| forest-market | RX_VK_PRESENT_THREAD=0 | screenshot.max_diff | 0.1 | — | 0.11 | — | fail |
| forest-market | RX_VK_PRESENT_THREAD=0 | forest.frametime_p99_ms.max_delta_pct | 15 | 20.03 | 19.02 | −5% | pass |
| forest-market | RX_VK_PRESENT_THREAD=0 | market.frametime_p99_ms.max_delta_pct | 15 | 21.15 | 23.37 | +10.5% | pass |
| forest-market | RX_VK_PRESENT_THREAD=1 | crash | False | 0 | 0 | — | pass |
| forest-market | RX_VK_PRESENT_THREAD=1 | forest.fps_mean.min_delta_pct | 10 | 59.51 | 59.73 | +0.4% | pass |
| forest-market | RX_VK_PRESENT_THREAD=1 | market.fps_mean.min_delta_pct | 10 | 57.96 | 59.64 | +2.9% | pass |
| forest-market | RX_VK_PRESENT_THREAD=1 | screenshot.max_diff | 0.1 | — | 0.13 | — | fail |
| forest-market | RX_VK_PRESENT_THREAD=1 | forest.frametime_p99_ms.max_delta_pct | 15 | 20.14 | 19.56 | −2.9% | pass |
| forest-market | RX_VK_PRESENT_THREAD=1 | market.frametime_p99_ms.max_delta_pct | 15 | 21.79 | 21.87 | +0.3% | 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: replay reads of guest memory as submitted: 1740000 (1048782 pages from the captures) [hos host] vk: sparse mirrors: 75, 917 MB with memory of 1440 MB (522 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 255 binds (49.0 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 26 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 26 spares now, 304 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1167 dirty pages from their submits' captures, 38428 from earlier ones', 1 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): 818 dispatches, 29868 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4391 runs, 573.5 MB compared; 86 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9622 in captures, 1 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: 0x7fd8000000 (4 MB, captured, state 2): 1; [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1089 ranges, 3228 MB), 226 pages written, 226 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.018; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.008, bytes copied 0.000; 25 kept (112 MB), 11 spare buffers, 5305 texture pages copied (20 MB) [hos host] vk: replay reads of guest memory as submitted: 1760000 (1062056 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.06 [hos host] vk: replay reads of guest memory as submitted: 1780000 (1075298 pages from the captures) [hos ModuleSystemWorker1] vcores: 135643 takes, 23973 waits (mean 88 us, longest 18.5 ms, 0 over HOS_VCORE_LOG_MS), 12422 kicks, 12346 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: program picks: 2188845 kept (725595 by the last picks' textures, a uniform buffer bound since), 1608 new, 1009546 with other textures (of 3200000) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1605 dirty pages from their submits' captures, 37367 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): 810 dispatches, 29230 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4271 runs, 558.3 MB compared; 82 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9639 in captures, 0 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 1800000 (1088585 pages from the captures) [hos host] vk: (its written part: 2 of 2 KB readable, 2040 bytes not zero; levels L0) [hos host] vk: texture 0x10ae7d3800 512x512x1 x1 levels 10 NVN 0x7b (236 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 2 KB of it [hos host] vk: (its written part: 2 of 2 KB readable, 2040 bytes not zero; levels L0) [hos host] vk: texture 0x10ae7d3800 512x512x1 x1 levels 10 NVN 0x7b (236 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 2 KB of it [hos host] vk: replay reads of guest memory as submitted: 1820000 (1101778 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 23774 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 3 pages in 3 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 289 KB; 0 made on demand (0 MB kept now); c1 stages: at most 180 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 888 dirty pages from their submits' captures, 38009 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): 807 dispatches, 29478 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4429 runs, 576.9 MB compared; 89 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9661 in captures, 1 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: replay reads of guest memory as submitted: 1840000 (1114994 pages from the captures) [hos ModuleSystemWorker5] vk: readbacks of GPU results: 1264 of 3000 waited for their write-back, 0.11 ms each; 0 looked at the stopped queues first, 2 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: 9007 kept their virtual core (nothing there to wait for), 3025 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: a frame: 390 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.42, present 0.18, draw 8.30, descriptors 3.04, texture lookups 0.07, uploads 0.00, pipelines 0.41, programs 1.25, commands 2.97, dispatch 0.88, memory sync 0.54, queue submit 0.78, slot wait 0.07 [hos host] vk: a frame: mirrors 128 (917 MB): 4.84 MB synced in 932.0 copies, 18.11 MB written back [hos host] vk: 4560 presents, 59.3 fps; a frame: 2448 draws (0 skipped), 123 dispatches, 147 passes, 150 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2242 textures (3018 MB) [hos host] vk: host time in GPU resource waits: 1.45 ms a frame (fences 0.04, timelines 1.41, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 408.5 full barriers recorded, 201.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.6 ms a frame (the longest submission 3.1 ms); 0.1 textures made a frame [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: 1860000 (1128236 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 762518 pages so far (0 held: may be written ahead in their submission) [hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 100000 so far (x1 0x117b93e010 x2 0 x3 0x117b93e000 x4 0x230040) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1474 dirty pages from their submits' captures, 36909 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): 798 dispatches, 28904 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4315 runs, 559.2 MB compared; 86 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9402 in captures, 0 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos sead::MainThread] nvn: GPU waits in 5 s: 150 sync waits (136 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1089 ranges, 3228 MB), 242 pages written, 242 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.032; 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 (120 MB), 10 spare buffers, 9977 texture pages copied (38 MB) [hos host] vk: replay reads of guest memory as submitted: 1880000 (1141433 pages from the captures) [hos host] vk: program picks: 2338719 kept (777373 by the last picks' textures, a uniform buffer bound since), 1610 new, 1059670 with other textures (of 3400000) [hos host] vk: replay reads of guest memory as submitted: 1900000 (1154603 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.04, writes collected 0.05 [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1439 dirty pages from their submits' captures, 38260 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 812 dispatches, 29875 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4322 runs, 557.5 MB compared; 80 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9409 in captures, 0 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: replay reads of guest memory as submitted: 1920000 (1167828 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 1940000 (1181013 pages from the captures) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1460 dirty pages from their submits' captures, 36933 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): 798 dispatches, 28949 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4420 runs, 575.1 MB compared; 83 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9362 in captures, 2 only in the collection, 27 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 1960000 (1194182 pages from the captures) [hos host] vk: (its written part: 2 of 2 KB readable, 112 bytes not zero; levels L6 L7 L8 L9) [hos host] vk: texture 0x10cbcf6a00 576x576x1 x1 levels 10 NVN 0x8c (187 KB of storage) re-uploaded (its memory was written; flags 0): what the CPU wrote, 2 KB of it [hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #70000: event 0x100c31801c mode 0 value 48695 (now 48676) (lr 0x80295158) [hos host] vk: replay reads of guest memory as submitted: 1980000 (1207396 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8718 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 4 pages in 4 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1380 dirty pages from their submits' captures, 38197 from earlier ones', 1 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): 807 dispatches, 29802 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4421 runs, 574.0 MB compared; 102 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9633 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: 0x7fd8000000 (4 MB, captured, state 2): 1; [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: program picks: 2488112 kept (828945 by the last picks' textures, a uniform buffer bound since), 1610 new, 1110277 with other textures (of 3600000) [hos Presentation Thread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1092 ranges, 3234 MB), 224 pages written, 224 copied (0.9 MB) [hos Presentation Thread] vi: 4671 frames presented (59.9 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 73, 15.5-17.8 163, 17.8-22 61, 22-30 3, 30-40 0, over 40 0 [hos host] vk: a capture taken (ms): all 0.021; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.011, bytes copied 0.000; 24 kept (100 MB), 12 spare buffers, 2871 texture pages copied (11 MB) [hos host] vk: replay reads of guest memory as submitted: 2000000 (1220620 pages from the captures) [hos host] vk: a frame: 388 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.43, present 0.18, draw 8.69, descriptors 3.17, texture lookups 0.09, uploads 0.01, pipelines 0.43, programs 1.31, commands 3.12, dispatch 0.89, memory sync 0.47, queue submit 0.74, slot wait 0.07 [hos host] vk: a frame: mirrors 128 (917 MB): 4.84 MB synced in 932.2 copies, 18.08 MB written back [hos host] vk: 4680 presents, 59.9 fps; a frame: 2451 draws (0 skipped), 124 dispatches, 147 passes, 150 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2249 textures (3020 MB) [hos host] vk: host time in GPU resource waits: 1.48 ms a frame (fences 0.04, timelines 1.44, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 409.8 full barriers recorded, 201.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.1 textures made a frame [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: 2020000 (1233789 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.06 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 289 KB; 0 made on demand (0 MB kept now); c1 stages: at most 180 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 884 dirty pages from their submits' captures, 38515 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): 810 dispatches, 29776 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4260 runs, 557.5 MB compared; 82 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9638 in captures, 2 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2040000 (1247016 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1264 of 3000 waited for their write-back, 0.11 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: 8643 kept their virtual core (nothing there to wait for), 2877 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: 2060000 (1260182 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 835067 pages so far (0 held: may be written ahead in their submission) [hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #50000: event 0x100c31800c mode 0 value 50002 (lr 0x80660adc) [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1876 dirty pages from their submits' captures, 36748 from earlier ones', 0 from guest memory as it was at the replay; 24 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 800 dispatches, 28944 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4391 runs, 574.5 MB compared; 89 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9315 in captures, 0 only in the collection, 28 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: replay reads of guest memory as submitted: 2080000 (1273335 pages from the captures) [hos host] vk: program picks: 2637606 kept (880630 by the last picks' textures, a uniform buffer bound since), 1610 new, 1160783 with other textures (of 3800000) [hos host] vk: replay reads of guest memory as submitted: 2100000 (1286558 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1092 ranges, 3238 MB), 221 pages written, 221 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.016; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.007, bytes copied 0.000; 25 kept (128 MB), 11 spare buffers, 3142 texture pages copied (12 MB) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1285 dirty pages from their submits' captures, 38205 from earlier ones', 1 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 813 dispatches, 29810 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4395 runs, 573.5 MB compared; 85 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9601 in captures, 1 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: 0x7fd8000000 (4 MB, captured, state 2): 1; [hos host] vk: replay reads of guest memory as submitted: 2120000 (1299742 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2140000 (1312929 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8112 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 5 pages in 5 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1449 dirty pages from their submits' captures, 37513 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): 806 dispatches, 29208 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4246 runs, 557.5 MB compared; 83 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9628 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: memory: working set 12965 MB (peak 13008), private 19128 MB, staging 224 MB in 14 arenas, 36 made so far (22 ms) [hos host] vk: memory heaps: heap 0 (device): 195 blocks 5217 MB, 17226 allocations 4690 MB; used 5593 of 7074 MB; heap 1 (system): 18 blocks 660 MB, 39 allocations 616 MB; used 2452 of 15577 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 5 images 16 MB; 1 free ranges, the largest 15 MB [hos host] vk: image blocks (render targets): 23 blocks 368 MB, 101 images 191 MB; 54 free ranges, the largest 16 MB [hos host] vk: image blocks (textures, compacted): 59 blocks 1888 MB, 2143 images 1678 MB; 990 free ranges, the largest 31 MB [hos host] vk: render target images: 256 reused from the pool, 352 made new, 246 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 5593 MB used of 7074 MB allowed (527 MB of it free in the blocks); textures 3023 MB (budget 3087 MB), 2255 textures [hos host] vk: budget: VRAM 5217 of 7074 MB (5593 MB by the driver, 375 MB unaccounted): textures 3023, mirrors 917, blocks free 527, shadows 336, staging 224, other buffers 156, other images 31; RAM 2347 MB (the process's private memory 19128 MB): imports 1700, capture spares 506, captures 100, capture table 31, other buffers 10, others 0 [hos host] vk: textures: decoded ASTC 1367 MB, rendered 784 MB (90 drawn in one frame, kept: 55157 KB), other 490 MB; used in the last 8 presents 1383 MB [hos host] vk: decoded ASTC used again: 77 textures (43 MB) copied from ones the game finalized, not decoded; 77 of those retired, 104 listed; 716 MB of blocks hashed in 82 ms [hos host] vk: 288 MB: 0x114682a000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 214 MB: 0x10a0efa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1326 presents ago [hos host] vk: 214 MB: 0x10a4772c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1326 presents ago [hos host] vk: 64 MB: 0x113b7bd000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 64 MB: 0x11361ac000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 47 MB: 0x10c18e9000 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1326 presents ago [hos host] vk: 47 MB: 0x10ae982400 3072x3072x1 x1 levels 12 NVN 0x7b ASTC, last used 1326 presents ago [hos host] vk: 32 MB: 0x115882b000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 18 (2993 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 260x260x1 NVN 0xd: 17 (2991 KB); [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05 [hos Presentation Thread] vk: presents after the CPU's signal (600): 257 waited for it, 1.06 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 23.7 ms; VRAM 5.5 of 6.9 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: 85 program records loaded (5.4 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 21; 247 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 5340 queued, 5340 loaded (median 4.32 ms, 99th percentile 21.99 ms, worst 47.07 ms, 29850 ms and 1170.1 MB read in all); 7464 programs (1631 of them compute variants without their code, 0 graphics programs no note names), 9555 graphics pipelines (0 not in a cache), 363 compute pipelines (305 not in a cache); a first use ran 20 itself and waited for 1 (112.6 ms); 1343 pipelines made at create taken by draws; 2893 create calls with nothing kept for their stages, 0 before the index; units 8233 (5340 ready, 0 loading), 14313 programs alive; 18 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (play): 669 known, 0 learned in this run; 363 compute pipelines made by them at a create call, 305 asked that way were in no cache (their code read, as before) [hos host] vk: a frame: 384 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.32, present 0.21, draw 8.46, descriptors 3.10, texture lookups 0.08, uploads 0.01, pipelines 0.43, programs 1.26, commands 3.03, dispatch 0.86, memory sync 0.45, queue submit 0.78, slot wait 0.07 [hos host] vk: a frame: mirrors 128 (917 MB): 4.83 MB synced in 931.4 copies, 18.06 MB written back [hos host] vk: 4800 presents, 59.6 fps; a frame: 2446 draws (0 skipped), 123 dispatches, 147 passes, 150 barriers, 6 submits, 0.2 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2255 textures (3023 MB) [hos host] vk: host time in GPU resource waits: 1.42 ms a frame (fences 0.04, timelines 1.38, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 407.9 full barriers recorded, 201.5 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.6 ms a frame (the longest submission 2.8 ms); 0.2 textures made a frame [hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: the render thread (600 presents, 16.73 ms a frame): its jobs 14.20 ms a frame (submits 8.01, presents 0.19, others 6.00), idle 2.53; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 1.43 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); 285 captures at a CPU signal; the submits' waits read in 0.063 ms a frame; readbacks: 1841 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 13.02 ms after its hand-over (18.63 at most) [hos host] vk: frame overlap (600 presents): the GPU between recordings, ms a frame, idle + in the next one's uploads: up to a frame's first recording with a draw 2.36 + 0.28 (the window's copy is in the idle), after it 3.95 + 0.46; after a frame's last recording that reads or writes the game's memory come 1.00 recordings (0.03 ms of GPU time), after its last that reads it 1.00 (0.03 ms) [hos host] vk: frame ahead (600 presents): 12.48 parts a frame recorded in the signal's job, 84.2% of them took nothing that came with the signal; of the others, 1.97 a frame took pages of the signal's capture into a mirror (75.0 pages a frame) and 0.01 pages read as guest memory had them (0.0 pages a frame); a frame's first part took nothing in 20 of 285 frames, its first three in 20 [hos host] vk: frame ahead, what came with the signal: 285 signals with a capture, each of 131.2 pages in 9.8 pools; between a frame's last submit and that signal 0.00 texture and sampler registrations, 0.00 releases and 0.00 other CPU signals a signal (0 of them with any) [hos host] vk: frame overlap, by place: idle + uploads before a frame's 2nd to 12th recording with a draw, then all later ones: 0.50+0.04, 0.46+0.03, 0.43+0.02, 0.75+0.06, 0.91+0.09, 0.29+0.05, 0.21+0.05, 0.02+0.02, 0.04+0.02, 0.07+0.02, 0.22+0.03, 0.06+0.03 [hos host] vk: replay reads of guest memory as submitted: 2160000 (1326111 pages from the captures) [hos BaseProcExecutor2] vcores: 134338 takes, 24444 waits (mean 90 us, longest 18.4 ms, 0 over HOS_VCORE_LOG_MS), 12593 kicks, 12503 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 2180000 (1339279 pages from the captures) [hos host] vk: recorder: 10146061 packets run in 10.0 s (busy 2.51 s, spun idle 5.77 s, slept 3493 times, 1862 of them under 200 us), 0 calls made directly (no room); the replay waited for it 30202 times, 158.93 ms in all, the longest 0.41 ms; vkEndCommandBuffer 11379/88.23 ms (max 0.40), replay_mu unlock 7450/35.52 ms (max 0.41), vkResetDescriptorPool 11329/35.07 ms (max 0.19), vmaInvalidateAllocation 44/0.10 ms (max 0.02) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1625 dirty pages from their submits' captures, 37350 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 795 dispatches, 29404 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4378 runs, 573.5 MB compared; 75 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9309 in captures, 0 only in the collection, 29 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: program picks: 2787200 kept (932440 by the last picks' textures, a uniform buffer bound since), 1610 new, 1211189 with other textures (of 4000000) [hos host] vk: replay reads of guest memory as submitted: 2200000 (1352503 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2220000 (1365694 pages from the captures) [hos ModuleSystemWorker4] nvn: 600000 recordings made, 77364 live copies (23.4 MB), 503 texture copies; 5 command buffers' segments (4.3 MB) [hos Presentation Thread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1092 ranges, 3238 MB), 231 pages written, 231 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.023; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.014, bytes copied 0.000; 24 kept (106 MB), 12 spare buffers, 6890 texture pages copied (26 MB) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 289 KB; 0 made on demand (0 MB kept now); c1 stages: at most 180 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1682 dirty pages from their submits' captures, 36722 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): 794 dispatches, 28876 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4261 runs, 557.5 MB compared; 93 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9346 in captures, 1 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #75000: event 0x100c318018 mode 0 value 52494 (now 52475) (lr 0x80295158) [hos ModuleSystemWorker3] vk: readbacks of GPU results: 1288 of 3000 waited for their write-back, 0.12 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker3] vk: invalidates since the last readbacks line: 9037 kept their virtual core (nothing there to wait for), 2995 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: 2240000 (1378868 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 146 sync waits (145 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: replay reads of guest memory as submitted: 2260000 (1392074 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 908157 pages so far (0 held: may be written ahead in their submission) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1075 dirty pages from their submits' captures, 38411 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): 818 dispatches, 29759 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4390 runs, 573.5 MB compared; 72 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9631 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2280000 (1405393 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05 [hos host] vk: program picks: 2936582 kept (984299 by the last picks' textures, a uniform buffer bound since), 1610 new, 1261807 with other textures (of 4200000) [hos host] vk: replay reads of guest memory as submitted: 2300000 (1418615 pages from the captures) [hos host] vk: a frame: 384 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.51, present 0.19, draw 8.65, descriptors 3.16, texture lookups 0.08, uploads 0.01, pipelines 0.43, programs 1.32, commands 3.09, dispatch 0.89, memory sync 0.49, queue submit 0.75, slot wait 0.07 [hos host] vk: a frame: mirrors 128 (917 MB): 4.83 MB synced in 930.2 copies, 18.06 MB written back [hos host] vk: 4920 presents, 59.9 fps; a frame: 2446 draws (0 skipped), 123 dispatches, 147 passes, 150 barriers, 6 submits, 0.1 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2262 textures (3025 MB) [hos host] vk: host time in GPU resource waits: 1.50 ms a frame (fences 0.04, timelines 1.46, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 407.5 full barriers recorded, 201.6 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.1 textures made a frame [hos host] vk: a frame: 0.01 MB unswizzled on the CPU in 0.00 ms [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 256 binds (49.1 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 52 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1700 dirty pages from their submits' captures, 37251 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): 809 dispatches, 29200 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4265 runs, 557.5 MB compared; 78 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9628 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 15908 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 3 pages in 3 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 2320000 (1431921 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2340000 (1445148 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1094 ranges, 3244 MB), 226 pages written, 226 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.019; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.010, bytes copied 0.000; 25 kept (122 MB), 10 spare buffers, 6890 texture pages copied (26 MB) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1113 dirty pages from their submits' captures, 37881 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 804 dispatches, 29534 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4372 runs, 574.5 MB compared; 87 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9347 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2360000 (1458351 pages from the captures) [hos host] vk: mirror of pool 0x103cc00000 (4 MB) given back: idle, 6029 submissions since its sync [hos Presentation Thread] vi: 4969 frames presented (59.5 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 69, 15.5-17.8 155, 17.8-22 73, 22-30 1, 30-40 0, over 40 0 [hos host] vk: render targets drawn over from another start, let go: 418 so far (1107 MB), 377 of them (964 MB) between the passes [hos host] vk: replay reads of guest memory as submitted: 2380000 (1471603 pages from the captures) [hos host] vk: sparse mirrors: 75, 917 MB with memory of 1440 MB (522 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 257 binds (49.2 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 27 taken from the spares, 101 made new; 53 kept as spares, 0 destroyed; 26 spares now, 304 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1751 dirty pages from their submits' captures, 37899 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): 814 dispatches, 29811 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4256 runs, 556.5 MB compared; 78 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9624 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: program picks: 3085764 kept (1035905 by the last picks' textures, a uniform buffer bound since), 1610 new, 1312625 with other textures (of 4400000) [hos host] vk: replay reads of guest memory as submitted: 2400000 (1484878 pages from the captures) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #55000: event 0x100c318010 mode 0 value 55000 (lr 0x80660bcc) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.05 [hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1005a88004 mode 0 value 1 (lr 0x8348c78c) [hos host] vk: replay reads of guest memory as submitted: 2420000 (1498120 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1294 of 3000 waited for their write-back, 0.11 ms each; 0 looked at the stopped queues first, 3 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: 8873 kept their virtual core (nothing there to wait for), 2903 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 289 KB; 0 made on demand (0 MB kept now); c1 stages: at most 180 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 830 dirty pages from their submits' captures, 37483 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 795 dispatches, 28914 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4399 runs, 574.8 MB compared; 80 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9634 in captures, 3 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2440000 (1511342 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2460000 (1524635 pages from the captures) [hos ModuleSystemWorker2] barrier: 71495 looks: 22343 found the masks moved already, 39433 waited until they moved, 9719 for the whole 1 ms (a wait 606 us on average); 54896 wakes [hos host] vk: a frame: 390 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.29, present 0.18, draw 8.42, descriptors 3.11, texture lookups 0.12, uploads 0.03, pipelines 0.42, programs 1.28, commands 2.97, dispatch 0.88, memory sync 0.44, queue submit 0.74, slot wait 0.07 [hos host] vk: a frame: mirrors 129 (917 MB): 4.83 MB synced in 931.4 copies, 18.10 MB written back [hos host] vk: 5040 presents, 60.1 fps; a frame: 2445 draws (0 skipped), 123 dispatches, 147 passes, 150 barriers, 6 submits, 0.3 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2273 textures (3027 MB) [hos host] vk: host time in GPU resource waits: 1.33 ms a frame (fences 0.04, timelines 1.29, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 407.9 full barriers recorded, 201.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.3 textures made a frame [hos host] vk: a frame: 0.02 MB unswizzled on the CPU in 0.00 ms [hos sead::MainThread] vk: capture: a submit 0.14 ms (lock 0.00, scan 0.06 over 1094 ranges, 3256 MB), 217 pages written, 217 copied (0.8 MB) [hos host] vk: a capture taken (ms): all 0.015; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.006, bytes copied 0.000; 25 kept (100 MB), 11 spare buffers, 7122 texture pages copied (27 MB) [hos host] vk: readback pages refreshed from guest memory: 981494 pages so far (0 held: may be written ahead in their submission) [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 258 binds (49.2 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 28 taken from the spares, 101 made new; 53 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1671 dirty pages from their submits' captures, 37879 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): 810 dispatches, 29781 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4461 runs, 578.1 MB compared; 69 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9342 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 8060 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 2 pages in 2 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: replay reads of guest memory as submitted: 2480000 (1537931 pages from the captures) [hos sead::MainThread] nvn: CommandBufferWaitEvent #80000: event 0x100c318018 mode 0 value 56294 (now 56275) (lr 0x80295158) [hos host] vk: program picks: 3235489 kept (1087427 by the last picks' textures, a uniform buffer bound since), 1611 new, 1362899 with other textures (of 4600000) [hos host] vk: replay reads of guest memory as submitted: 2500000 (1551103 pages from the captures) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 863 dirty pages from their submits' captures, 37968 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): 807 dispatches, 29175 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4318 runs, 558.5 MB compared; 89 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9677 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2520000 (1564354 pages from the captures) [hos host] vk: late pages' fix (600 recordings with one): of 728 captures with late pages 728 fixed (73.9 pages, 73.9 fixes a capture), waited as before: 0 no pool, 0 no stamps or shadow yet, 0 stamps too new, 0 whole copies, 0 in place or unknown, 0 a page's earlier fix not recorded yet, 0 other; 58 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 105 blocks (6720 KB); of the reads on the CPU, 4 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 36, of an earlier recording 18, not recorded yet 0, of this part 0; pages fixed from stamps 52698, from snapshots 1102; the shadows: 243116 pages synced from captures, 239841 made known by it, 3275 left unknown because the replay or the collection wrote them since [hos host] vk: replay reads of guest memory as submitted: 2540000 (1577504 pages from the captures) [hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 120000 so far (x1 0x117cbdb070 x2 0 x3 0x117cbdb040 x4 0x44b040) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.03, writes collected 0.05 [hos ModuleSystemWorker2] vcores: 135167 takes, 24236 waits (mean 88 us, longest 18.7 ms, 0 over HOS_VCORE_LOG_MS), 12539 kicks, 12462 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 258 binds (49.2 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 28 taken from the spares, 101 made new; 53 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1473 dirty pages from their submits' captures, 37773 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 801 dispatches, 29580 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4433 runs, 575.2 MB compared; 79 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9389 in captures, 0 only in the collection, 31 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: replay reads of guest memory as submitted: 2560000 (1590718 pages from the captures) [hos host] vk: replay reads of guest memory as submitted: 2580000 (1603844 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.15 ms (lock 0.00, scan 0.06 over 1094 ranges, 3266 MB), 238 pages written, 238 copied (0.9 MB) [hos host] vk: a capture taken (ms): all 0.027; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.017, bytes copied 0.000; 25 kept (106 MB), 10 spare buffers, 5460 texture pages copied (21 MB) [hos host] vk: write-backs left out (600 submits): 672, 3296.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 976 dirty pages from their submits' captures, 38578 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): 814 dispatches, 29839 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4413 runs, 574.0 MB compared; 75 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9694 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: program picks: 3384840 kept (1139116 by the last picks' textures, a uniform buffer bound since), 1611 new, 1413548 with other textures (of 4800000) [hos host] vk: replay reads of guest memory as submitted: 2600000 (1617064 pages from the captures) [hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29984 went on once it was reached, 14 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.00 ms at most); waits met 82274, not met 0; captures at a CPU event's wait 2789, 0 of them at a wait met on arrival [hos host] vk: a frame: 388 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 0 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.28, present 0.18, draw 8.63, descriptors 3.16, texture lookups 0.10, uploads 0.03, pipelines 0.42, programs 1.29, commands 3.13, dispatch 0.85, memory sync 0.49, queue submit 0.74, slot wait 0.07 [hos host] vk: a frame: mirrors 129 (917 MB): 4.83 MB synced in 932.1 copies, 18.08 MB written back [hos host] vk: 5160 presents, 59.5 fps; a frame: 2451 draws (0 skipped), 124 dispatches, 147 passes, 150 barriers, 6 submits, 0.4 uploads (0.0 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 42581 pipelines (6528153 ms), 0 programs (0 failed), 2294 textures (3031 MB) [hos host] vk: host time in GPU resource waits: 1.23 ms a frame (fences 0.04, timelines 1.19, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 408.5 full barriers recorded, 201.7 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 41.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 9.7 ms a frame (the longest submission 2.8 ms); 0.4 textures made a frame [hos host] vk: a frame: 0.03 MB unswizzled on the CPU in 0.00 ms [hos host] vk: replay reads of guest memory as submitted: 2620000 (1630267 pages from the captures) [hos ModuleSystemWorker4] vk: readbacks of GPU results: 1325 of 3000 waited for their write-back, 0.10 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker4] vk: invalidates since the last readbacks line: 9166 kept their virtual core (nothing there to wait for), 3122 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, 14680 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: late pages found at the replay (600 takes): 1 pages in 1 takes (RX_VK_LATE_AT_REPLAY=0: only the ones the capture found) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 289 KB; 0 made on demand (0 MB kept now); c1 stages: at most 180 a recording; 0 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 76, 917 MB with memory of 1444 MB (526 MB spared); blocks given memory later 1018, given back 5088; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 258 binds (49.2 ms); 0 made whole for want of memory [hos host] vk: sparse mirrors' buffers: 28 taken from the spares, 101 made new; 53 kept as spares, 0 destroyed; 25 spares now, 300 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos host] vk: write-backs left out (600 submits): 651, 3193.2 MB; 28 bindings followed, 40 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 0 so far [hos host] vk: mirror syncs (600 submits): 1339 dirty pages from their submits' captures, 37612 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos host] vk: mirror syncs' pass (600 submits): 811 dispatches, 29236 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 4272 runs, 557.6 MB compared; 81 pages read into the shadows; 336 MB of shadows; pages the shadows knew that the CPU wrote: 9646 in captures, 0 only in the collection, 30 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 103 live (1700 MB), 0 retired still imported (0 MB), 23 retired given back (460 MB) [hos host] vk: replay reads of guest memory as submitted: 2640000 (1643435 pages from the captures) [hos host] vk: slow present: 17.2 ms: [hos sead::MainThread] nvn: GPU waits in 5 s: 132 sync waits (129 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: present 5181 written to F:\<user>\data\jobs\jb_c0cc1fb54b4fc1ac\runs\forest-market-g1-01-pr\shots/forest-market-c1-pr-01-market.png (the control bridge) [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: 85 program records loaded (5.4 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 21; 247 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 5340 queued, 5340 loaded (median 4.32 ms, 99th percentile 21.99 ms, worst 47.07 ms, 29850 ms and 1170.1 MB read in all); 7464 programs (1631 of them compute variants without their code, 0 graphics programs no note names), 9555 graphics pipelines (0 not in a cache), 363 compute pipelines (305 not in a cache); a first use ran 20 itself and waited for 1 (112.6 ms); 1344 pipelines made at create taken by draws; 2893 create calls with nothing kept for their stages, 0 before the index; units 8233 (5340 ready, 0 loading), 14313 programs alive; 18 noted graphics pipeline probes deferred to first use [hos host] vk: module identifiers (close): 669 known, 0 learned in this run; 363 compute pipelines made by them at a create call, 305 asked that way were in no cache (their code read, as before) [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4254 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)