Report rp_783d4bc2799a36d3 fail
This report disagrees with its peers.
hyrule-field run_frametime_max_ms: -7.4% against peers' +28.0% hyrule-field run_hitch_count: +25.0% against peers' -5.0% hyrule-field#1 field.fps_mean: -7.8% against peers' -1.5% hyrule-field#1 field.frametime_max_ms: +5.2% against peers' +112.5% hyrule-field#1 field.stutter_count: -100.0% against peers' +550.0%
Machine
- Commit
- 2f24a499ca2a8fc708008cdb350c09fea17e9ea0
- Baseline
- 430eef4f2cc94e398b06d0daeb585a679d3ebcda
- App
- nightly-177-99542c21, attempt 1
- Game build
e0f3ccfa- os
- linux
- cpu
- AMD Ryzen 5 9600X 6-Core Processor
- gpu
- NVIDIA GeForce RTX 5070
- tags
- linuxnvidianvidia-proprietarydgpu
- driver
- 620.70.6
- ram_gb
- 32
- vram_mb
- 12,227
- gpu_vendor
- nvidia
- os_version
- CachyOS (kernel 7.3.5)
Builds
PR
52.1 s warm
Program cache: warm
Scenarios
hyrule-field RX_VK_ACQUIRE_AHEAD=0 (PR only)
timeout
a step ran out of time: timeout: not met in time
| Metric (median) | switch off | switch on | Δ |
|---|---|---|---|
| run_hitch_count | 4 | 5 | +25% |
| run_frametime_max_ms | 521.19 | 482.52 | −7.4% |
Runs (2)
| Metric | off 0 | on 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | — | — |
| run_hitch_count | 4 | 5 |
| run_frametime_max_ms | 521.19 | 482.52 |
hyrule-field RX_VK_ACQUIRE_AHEAD=1 (PR only)
crashed
| Metric (median) | switch off | switch on | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| field.fps_mean | 89.84 | 82.87 | −7.8% |
| run_hitch_count | 6 | 7 | +16.7% |
| field.draws_mean | 1,199.1 | 1,207.4 | +0.7% |
| field.hitch_count | 0 | 0 | ±0% |
| field.stutter_count | 0.5 | 0 | −100% |
| run_frametime_max_ms | 224.75 | 199.81 | −11.1% |
| field.frametime_max_ms | 20.72 | 21.8 | +5.2% |
| field.frametime_p50_ms | 10.61 | 11.07 | +4.3% |
| field.frametime_p99_ms | 15.64 | 17.98 | +15% |
| field.frametime_1pct_low_ms | 16.36 | 18.45 | +12.8% |
| screenshot_diff | — | 0.02 | — |
Pictures against the switch off: field diff 0.0204 (switch off against itself 0.0368)
Runs (4)
| Metric | off 0 | on 1 | on 2 | off 3 |
|---|---|---|---|---|
| hang | no | yes | no | no |
| crashed | no | yes | no | no |
| exit_code | 0 | — | 0 | 0 |
| field.fps_mean | 82.92 | — | 82.87 | 96.76 |
| run_hitch_count | 7 | — | 7 | 5 |
| field.draws_mean | 1,203.2 | — | 1,207.4 | 1,195 |
| field.hitch_count | 0 | — | 0 | 0 |
| field.stutter_count | 0 | — | 0 | 1 |
| run_frametime_max_ms | 262.28 | — | 199.81 | 187.22 |
| field.frametime_max_ms | 20.79 | — | 21.8 | 20.64 |
| field.frametime_p50_ms | 11.01 | — | 11.07 | 10.2 |
| field.frametime_p99_ms | 18.16 | — | 17.98 | 13.12 |
| field.frametime_1pct_low_ms | 18.78 | — | 18.45 | 13.95 |
| screenshot_diff | — | — | 0.02 | — |
Rules
| Scenario | Cell | Rule | Limit | switch off | switch on | Δ % | Status |
|---|---|---|---|---|---|---|---|
| hyrule-field | RX_VK_ACQUIRE_AHEAD=0 (PR only) | crash | False | 0 | 0 | — | pass |
| hyrule-field | RX_VK_ACQUIRE_AHEAD=0 (PR only) | screenshot.max_diff | 0.05 | — | — | — | skippedthe plan has no screenshot probe |
| hyrule-field | RX_VK_ACQUIRE_AHEAD=1 (PR only) | crash | False | 0 | 1 | — | fail |
| hyrule-field | RX_VK_ACQUIRE_AHEAD=1 (PR only) | screenshot.max_diff | 0.05 | 0.04 | 0.02 | — | pass |
| hyrule-field | RX_VK_ACQUIRE_AHEAD=1 (PR only) | field.fps_mean: RX_VK_ACQUIRE_AHEAD=1 vs RX_VK_ACQUIRE_AHEAD=0 (PR) | 5 | — | 82.87 | — | skippedthe metric was not measured in both cells |
| hyrule-field | RX_VK_ACQUIRE_AHEAD=1 (PR only) | field.frametime_p99_ms: RX_VK_ACQUIRE_AHEAD=1 vs RX_VK_ACQUIRE_AHEAD=0 (PR) | 15 | — | 17.98 | — | skippedthe metric was not measured in both cells |
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: write-back diff (600 submits): 7932 runs, 846.4 MB compared; 76 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25166 in captures, 1 only in the collection, 46 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.12, present 0.12, draw 3.07, descriptors 0.91, texture lookups 0.05, uploads 0.00, pipelines 0.11, programs 0.44, commands 1.32, dispatch 0.77, memory sync 0.21, queue submit 0.13, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.15 MB synced in 1181.6 copies, 18.40 MB written back [hos Presentation Thread] vk: 7320 presents, 84.8 fps; a frame: 1199 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.06 ms a frame (fences 0.01, timelines 2.06, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.2 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.2 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vi: 7323 frames presented (84.3 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 361, 15.5-17.8 56, 17.8-22 5, 22-30 0, 30-40 0, over 40 0 [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 313 pages written, 313 copied (1.2 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.013; 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 (276 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 1868 dirty pages from their submits' captures, 82706 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1437 dispatches, 54948 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 8092 runs, 864.8 MB compared; 82 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24564 in captures, 2 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1020000 (388099 pages from the captures) [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 2772 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: late pages' fix (600 recordings with one): of 767 captures with late pages 767 fixed (102.9 pages, 103.6 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; 314 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 95 blocks (6080 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 248, of an earlier recording 66, not recorded yet 0, of this part 0; pages fixed from stamps 77692, from snapshots 1200; the shadows: 508678 pages synced from captures, 493623 made known by it, 15055 left unknown because the replay or the collection wrote them since [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2086 dirty pages from their submits' captures, 83581 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1457 dispatches, 55884 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7999 runs, 861.7 MB compared; 77 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25069 in captures, 0 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 2154 of 3000 waited for their write-back, 0.10 ms each; 52 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 1481 kept their virtual core (nothing there to wait for), 3127 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1040000 (395326 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 309 pages written, 309 copied (1.2 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.012; 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 (276 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.11, present 0.14, draw 3.05, descriptors 0.86, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.45, commands 1.35, dispatch 0.78, memory sync 0.20, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.17 MB synced in 1180.8 copies, 18.40 MB written back [hos Presentation Thread] vk: 7440 presents, 86.5 fps; a frame: 1203 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.03 ms a frame (fences 0.01, timelines 2.03, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.2 full barriers recorded, 173.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.2 ms a frame (the longest submission 7.4 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: program picks: 2549075 kept (1104721 by the last picks' textures, a uniform buffer bound since), 2494 new, 848430 with other textures (of 3400000) [hos sead::MainThread] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 96 a recording; 0 descriptor pools made when a recording's own ran out [hos sead::MainThread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos sead::MainThread] vk: mirror syncs (600 submits): 2051 dirty pages from their submits' captures, 82804 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos sead::MainThread] vk: mirror syncs' pass (600 submits): 1438 dispatches, 54918 chunks; 0 syncs as copies (no table room) [hos sead::MainThread] vk: write-back diff (600 submits): 8027 runs, 849.5 MB compared; 79 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24733 in captures, 3 only in the collection, 47 only by the replay itself [hos sead::MainThread] vk: read live, by pool: [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1060000 (402768 pages from the captures) [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 3826 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos sead::MainThread] nvn: EventSignal (CPU) #15000: event 0x1006e38004 mode 0 value 1 (lr 0x8348c78c) [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2459 dirty pages from their submits' captures, 81809 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 Presentation Thread] vk: mirror syncs' pass (600 submits): 1432 dispatches, 54861 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7917 runs, 846.4 MB compared; 76 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24634 in captures, 1 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: 0x1066000000 (4 MB, captured, state 2): 1; [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #85000: event 0x100d6c8048 mode 0 value 54632 (now 54613) (lr 0x806661f8) [hos host] vk: replay reads of guest memory as submitted: 1080000 (410367 pages from the captures) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #55000: event 0x100d6c8018 mode 0 value 55000 (lr 0x802915c8) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 313 pages written, 313 copied (1.2 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.013; 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 (276 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos Presentation Thread] vk: readback pages refreshed from guest memory: 782380 pages so far (0 held: may be written ahead in their submission) [hos Presentation Thread] vk: queues ordered by their events: 36000 submissions stopped at a wait, 35996 went on once it was reached, 1 waits gone past; made to go by presents 1259, releases 0, waits for the replay 0, 50 ms 0 (stopped 15.63 ms at most); waits met 85650, not met 0; captures at a CPU event's wait 2818, 152 of them at a wait met on arrival [hos host] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 2073 dirty pages from their submits' captures, 83429 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): 1458 dispatches, 55916 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 8082 runs, 863.7 MB compared; 78 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25114 in captures, 2 only in the collection, 46 only by the replay itself [hos host] vk: read live, by pool: [hos ModuleSystemWorker5] nvn: 500000 recordings made, 37194 live copies (12.6 MB), 492 texture copies; 5 command buffers' segments (4.2 MB) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.10, present 0.14, draw 3.16, descriptors 0.95, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.46, commands 1.35, dispatch 0.75, memory sync 0.21, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.14 MB synced in 1180.9 copies, 18.40 MB written back [hos Presentation Thread] vk: 7560 presents, 85.8 fps; a frame: 1200 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 1.96 ms a frame (fences 0.01, timelines 1.95, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.1 full barriers recorded, 173.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.3 ms a frame (the longest submission 7.1 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 2130 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos ModuleSystemWorker2] tex: the game's texture heap: 48 compaction rounds asked for in 7200 frames without one running [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1100000 (417959 pages from the captures) [hos sead::MainThread] vk: readbacks of GPU results: 2242 of 3000 waited for their write-back, 0.10 ms each; 55 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: 1362 kept their virtual core (nothing there to wait for), 2990 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: render targets drawn over from another start, let go: 365 so far (1025 MB), 309 of them (881 MB) between the passes [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2148 dirty pages from their submits' captures, 82042 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1436 dispatches, 54878 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7926 runs, 847.4 MB compared; 81 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24656 in captures, 3 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos Presentation Thread] vk: program picks: 2701842 kept (1171851 by the last picks' textures, a uniform buffer bound since), 2494 new, 895663 with other textures (of 3600000) [hos ModuleSystemWorker2] nvn: DrawMeshTasksIndirect: 140000 so far (x1 0x117b427040 x2 0x6001d40 x3 0x117b427000 x4 0xf33080) [hos nn.npln.Callback] vcores: 219385 takes, 20969 waits (mean 28 us, longest 2.4 ms, 0 over HOS_VCORE_LOG_MS), 8860 kicks, 8661 yields, 0 starved grants, 0 escapes in 5 s [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 313 pages written, 313 copied (1.2 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.012; 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 (276 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1120000 (425552 pages from the captures) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2378 dirty pages from their submits' captures, 81643 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1432 dispatches, 54881 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7927 runs, 846.4 MB compared; 78 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24691 in captures, 0 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 2048 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.08, present 0.13, draw 3.06, descriptors 0.91, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.44, commands 1.31, dispatch 0.75, memory sync 0.20, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.15 MB synced in 1181.3 copies, 18.40 MB written back [hos Presentation Thread] vk: 7680 presents, 85.7 fps; a frame: 1202 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.00 ms a frame (fences 0.01, timelines 1.99, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.3 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.2 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 96 a recording; 0 descriptor pools made when a recording's own ran out [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1140000 (433145 pages from the captures) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2510 dirty pages from their submits' captures, 82570 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1450 dispatches, 55350 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7924 runs, 846.4 MB compared; 77 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24637 in captures, 1 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos sead::MainThread] nvn: CommandBufferWaitEvent #90000: event 0x100d6c8048 mode 0 value 58432 (now 58413) (lr 0x806661f8) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 306 pages written, 306 copied (1.2 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.012; 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 (290 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos host] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 1995 dirty pages from their submits' captures, 82905 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): 1447 dispatches, 55619 chunks; 0 syncs as copies (no table room) [hos host] vk: write-back diff (600 submits): 8089 runs, 863.8 MB compared; 78 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25097 in captures, 0 only in the collection, 46 only by the replay itself [hos host] vk: read live, by pool: [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1160000 (440751 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 210 sync waits (423 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 2798 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vi: 7753 frames presented (85.9 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 372, 15.5-17.8 54, 17.8-22 4, 22-30 0, 30-40 0, over 40 0 [hos sead::MainThread] vk: readbacks of GPU results: 2222 of 3000 waited for their write-back, 0.10 ms each; 60 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: 1364 kept their virtual core (nothing there to wait for), 2988 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: readback pages refreshed from guest memory: 850197 pages so far (0 held: may be written ahead in their submission) [hos Presentation Thread] vk: program picks: 2854419 kept (1238980 by the last picks' textures, a uniform buffer bound since), 2494 new, 943086 with other textures (of 3800000) [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2273 dirty pages from their submits' captures, 81559 from earlier ones', 24 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1432 dispatches, 54923 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7941 runs, 847.4 MB compared; 78 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24670 in captures, 4 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: 0x1065800000 (8 MB, captured, state 2): 24; [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #60000: event 0x100d6c8024 mode 0 value 60000 (lr 0x80665068) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1180000 (448318 pages from the captures) [hos Presentation Thread] vk: memory: working set 18869 MB (peak 18996), private 10403 MB, staging 32 MB in 2 arenas, 27 made so far (6 ms) [hos Presentation Thread] vk: memory heaps: heap 0 (device): 194 blocks 6425 MB, 17202 allocations 5632 MB; used 7456 of 10155 MB; heap 1 (system): 32 blocks 1104 MB, 39 allocations 1019 MB; used 2744 of 23390 MB; [hos Presentation Thread] vk: image blocks: 1 blocks 32 MB, 4 images 12 MB; 1 free ranges, the largest 19 MB [hos Presentation Thread] vk: image blocks (render targets): 17 blocks 544 MB, 108 images 228 MB; 53 free ranges, the largest 32 MB [hos Presentation Thread] vk: image blocks (textures, compacted): 83 blocks 2656 MB, 1572 images 2593 MB; 788 free ranges, the largest 19 MB [hos Presentation Thread] vk: render target images: 171 reused from the pool, 408 made new, 294 destroyed from it; it holds 0 (0 MB) [hos Presentation Thread] vk: VRAM: 7456 MB used of 10155 MB allowed (792 MB of it free in the blocks); textures 4105 MB (budget 7132 MB), 1688 textures [hos Presentation Thread] vk: textures: decoded ASTC 2456 MB, rendered 948 MB (81 drawn in one frame, kept: 41551 KB), other 437 MB; used in the last 8 presents 1329 MB [hos Presentation Thread] vk: decoded ASTC used again: 50 textures (173 MB) copied from ones the game finalized, not decoded; 50 of those retired, 187 listed; 718 MB of blocks hashed in 39 ms [hos Presentation Thread] vk: 288 MB: 0x1147c16000 12288x12288x1 x1 levels 1 NVN 0x32 rendered, last used 3075 presents ago [hos Presentation Thread] vk: 214 MB: 0x10a5b22c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago [hos Presentation Thread] vk: 214 MB: 0x10a22aa600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago [hos Presentation Thread] vk: 64 MB: 0x113755c000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos Presentation Thread] vk: 64 MB: 0x113cba9000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos Presentation Thread] vk: 54 MB: 0x100032c0400 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2742 presents ago [hos Presentation Thread] vk: 54 MB: 0x100030a4200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 3075 presents ago [hos Presentation Thread] vk: 54 MB: 0x10002ff0200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 2748 presents ago [hos Presentation Thread] vk: finalized textures the GPU drew once, kept for being made again: 31 (9405 KB): 8x8x1 NVN 0x3f: 1 (2 KB); 62x41x1 NVN 0x25: 1 (9 KB); 74x32x1 NVN 0x25: 1 (9 KB); 90x34x1 NVN 0x25: 1 (11 KB); 126x105x1 NVN 0x1: 1 (12 KB); 138x96x1 NVN 0x1: 1 (12 KB); 154x98x1 NVN 0x1: 1 (14 KB); 198x40x1 NVN 0x25: 2 (61 KB); 242x40x1 NVN 0x25: 3 (113 KB); 260x260x1 NVN 0xd: 2 (351 KB); 262x104x1 NVN 0x1: 3 (79 KB); 306x104x1 NVN 0x1: 3 (93 KB); 592x49x1 NVN 0x25: 3 (339 KB); 656x113x1 NVN 0x1: 3 (217 KB); 1466x282x1 NVN 0x25: 5 (8074 KB); [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02 [hos Presentation Thread] vk: status: 600 frames, the slowest 18.7 ms; VRAM 7.3 of 9.9 GB [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.12, present 0.14, draw 3.10, descriptors 0.90, texture lookups 0.07, uploads 0.00, pipelines 0.11, programs 0.45, commands 1.35, dispatch 0.76, memory sync 0.22, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.13 MB synced in 1183.3 copies, 18.40 MB written back [hos Presentation Thread] vk: 7800 presents, 85.7 fps; a frame: 1201 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.04 ms a frame (fences 0.01, timelines 2.03, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.4 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.3 ms); 0.1 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 641 ranges, 1999 MB), 310 pages written, 310 copied (1.2 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.013; 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 (284 MB), 12 spare buffers, 3172 texture pages copied (12 MB) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2355 dirty pages from their submits' captures, 82113 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1435 dispatches, 54988 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7928 runs, 846.4 MB compared; 77 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24554 in captures, 0 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 3230 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 1200000 (455522 pages from the captures) [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2343 dirty pages from their submits' captures, 83548 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1457 dispatches, 56102 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 8044 runs, 862.6 MB compared; 77 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25121 in captures, 1 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1220000 (462714 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 315 pages written, 315 copied (1.2 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.014; 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 (276 MB), 12 spare buffers, 3513 texture pages copied (13 MB) [hos sead::MainThread] nvn: CommandBufferWaitEvent #95000: event 0x100d6c8048 mode 0 value 62232 (now 62213) (lr 0x806661f8) [hos host] vk: program picks: 3007137 kept (1306139 by the last picks' textures, a uniform buffer bound since), 2494 new, 990368 with other textures (of 4000000) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.07, present 0.13, draw 3.00, descriptors 0.86, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.44, commands 1.31, dispatch 0.75, memory sync 0.21, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.16 MB synced in 1184.5 copies, 18.40 MB written back [hos Presentation Thread] vk: 7920 presents, 85.6 fps; a frame: 1202 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.06 ms a frame (fences 0.01, timelines 2.05, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.1 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.3 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos sead::MainThread] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 96 a recording; 0 descriptor pools made when a recording's own ran out [hos sead::MainThread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos sead::MainThread] vk: mirror syncs (600 submits): 2222 dirty pages from their submits' captures, 82261 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos sead::MainThread] vk: mirror syncs' pass (600 submits): 1438 dispatches, 55080 chunks; 0 syncs as copies (no table room) [hos sead::MainThread] vk: write-back diff (600 submits): 7983 runs, 848.6 MB compared; 79 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24579 in captures, 1 only in the collection, 47 only by the replay itself [hos sead::MainThread] vk: read live, by pool: [hos ModuleSystemWorker5] vk: readbacks of GPU results: 2247 of 3000 waited for their write-back, 0.09 ms each; 58 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: 1228 kept their virtual core (nothing there to wait for), 2868 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 5886 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: replay reads of guest memory as submitted: 1240000 (469943 pages from the captures) [hos sead::MainThread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos sead::MainThread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos sead::MainThread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos sead::MainThread] vk: mirror syncs (600 submits): 2464 dirty pages from their submits' captures, 82116 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos sead::MainThread] vk: mirror syncs' pass (600 submits): 1432 dispatches, 54922 chunks; 0 syncs as copies (no table room) [hos sead::MainThread] vk: write-back diff (600 submits): 7926 runs, 846.4 MB compared; 78 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24706 in captures, 0 only in the collection, 46 only by the replay itself [hos sead::MainThread] vk: read live, by pool: [hos sead::MainThread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos Presentation Thread] vk: readback pages refreshed from guest memory: 917842 pages so far (0 held: may be written ahead in their submission) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 311 pages written, 311 copied (1.2 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.013; 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 (298 MB), 12 spare buffers, 3513 texture pages copied (13 MB) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos host] vk: replay reads of guest memory as submitted: 1260000 (477154 pages from the captures) [hos ModuleSystemWorker1] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x117899e000 x2 0x1 x3 0x117899e000 x4 0x4040) [hos Presentation Thread] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2242 dirty pages from their submits' captures, 83486 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1457 dispatches, 56025 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7932 runs, 846.4 MB compared; 80 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25341 in captures, 0 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos sead::MainThread] vk: shadow staging (600 takes): 0 shadow copies from staging, 3968 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos ModuleSystemWorker1] nvn: 550000 recordings made, 37216 live copies (14.3 MB), 492 texture copies; 3 command buffers' segments (4.1 MB) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.11, present 0.12, draw 3.11, descriptors 0.92, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.45, commands 1.33, dispatch 0.75, memory sync 0.20, queue submit 0.12, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.17 MB synced in 1183.4 copies, 18.40 MB written back [hos Presentation Thread] vk: 8040 presents, 85.1 fps; a frame: 1202 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.08 ms a frame (fences 0.01, timelines 2.07, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.3 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.0 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos rmbl::VibrationThread] vcores: 218310 takes, 20020 waits (mean 30 us, longest 2.2 ms, 0 over HOS_VCORE_LOG_MS), 8706 kicks, 8508 yields, 0 starved grants, 0 escapes in 5 s [hos sead::MainThread] nvn: CommandBufferSignalEvent #65000: event 0x100d6c802c mode 0 value 64999 (lr 0x80667688) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1280000 (484435 pages from the captures) [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2296 dirty pages from their submits' captures, 82353 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1435 dispatches, 55082 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 8088 runs, 863.7 MB compared; 76 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24574 in captures, 0 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos host] vk: program picks: 3159927 kept (1373082 by the last picks' textures, a uniform buffer bound since), 2494 new, 1037578 with other textures (of 4200000) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 640 ranges, 1995 MB), 315 pages written, 315 copied (1.2 MB) [hos Presentation Thread] 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 (290 MB), 12 spare buffers, 3413 texture pages copied (13 MB) [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.02, writes collected 0.02 [hos ModuleSystemWorker2] vk: readbacks of GPU results: 2199 of 3000 waited for their write-back, 0.10 ms each; 60 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: 1403 kept their virtual core (nothing there to wait for), 2949 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 1971 dirty pages from their submits' captures, 82152 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1436 dispatches, 55007 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7932 runs, 847.4 MB compared; 76 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24638 in captures, 1 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos sead::MainThread] nvn: CommandBufferWaitEvent #100000: event 0x100d6c8048 mode 0 value 66032 (now 66013) (lr 0x806661f8) [hos host] vk: replay reads of guest memory as submitted: 1300000 (492282 pages from the captures) [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 6284 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos sead::MainThread] vk: late pages' fix (600 recordings with one): of 713 captures with late pages 713 fixed (110.7 pages, 111.5 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; 275 read on the CPU first, 0 with no table, 0 pages whose shadow changed first; stamps 95 blocks (6080 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 215, of an earlier recording 60, not recorded yet 0, of this part 0; pages fixed from stamps 77716, from snapshots 1200; the shadows: 405783 pages synced from captures, 395271 made known by it, 10512 left unknown because the replay or the collection wrote them since [hos Presentation Thread] vk: the recording streams: 48 of 2 MB, the most one held 382 KB; 0 made on demand (0 MB kept now); c1 stages: at most 96 a recording; 0 descriptor pools made when a recording's own ran out [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2032 dirty pages from their submits' captures, 83485 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1467 dispatches, 56059 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 8092 runs, 863.7 MB compared; 80 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25097 in captures, 3 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.15, present 0.12, draw 3.14, descriptors 0.93, texture lookups 0.06, uploads 0.00, pipelines 0.11, programs 0.46, commands 1.35, dispatch 0.75, memory sync 0.23, queue submit 0.13, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.12 MB synced in 1183.4 copies, 18.40 MB written back [hos Presentation Thread] vk: 8160 presents, 86.2 fps; a frame: 1202 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 1.93 ms a frame (fences 0.01, timelines 1.92, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.0 full barriers recorded, 173.8 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.3 ms a frame (the longest submission 7.1 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1320000 (499876 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 212 sync waits (432 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos sead::MainThread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 638 ranges, 1965 MB), 315 pages written, 315 copied (1.2 MB) [hos sead::MainThread] vk: a capture taken (ms): all 0.014; 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 (290 MB), 12 spare buffers, 1365 texture pages copied (5 MB) [hos Presentation Thread] vi: 8182 frames presented (85.6 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 369, 15.5-17.8 58, 17.8-22 2, 22-30 0, 30-40 0, over 40 0 [hos Presentation Thread] vk: render targets drawn over from another start, let go: 365 so far (1025 MB), 309 of them (881 MB) between the passes [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2432 dirty pages from their submits' captures, 81666 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1436 dispatches, 54897 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7928 runs, 846.4 MB compared; 74 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24745 in captures, 4 only in the collection, 46 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 6144 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1340000 (507432 pages from the captures) [hos Presentation Thread] vk: readback pages refreshed from guest memory: 985433 pages so far (0 held: may be written ahead in their submission) [hos Presentation Thread] vk: program picks: 3312473 kept (1440297 by the last picks' textures, a uniform buffer bound since), 2494 new, 1085032 with other textures (of 4400000) [hos Presentation Thread] vk: sparse mirrors: 62, 952 MB with memory of 1232 MB (279 MB spared); blocks given memory later 2910, given back 4613; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 250 binds (21.7 ms); 0 made whole for want of memory [hos Presentation Thread] vk: sparse mirrors' buffers: 13 taken from the spares, 104 made new; 55 kept as spares, 0 destroyed; 42 spares now, 928 MB of address space (RX_VK_SPARSE_SPARE_MB=4096) [hos Presentation Thread] vk: write-backs left out (600 submits): 1104, 5025.7 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 2090 dirty pages from their submits' captures, 81256 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1433 dispatches, 54813 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 7925 runs, 847.4 MB compared; 77 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 24566 in captures, 2 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos Presentation Thread] vk: imports: 101 live (1620 MB), 0 retired still imported (0 MB), 18 retired given back (720 MB) [hos Presentation Thread] vk: capture: a submit 0.09 ms (lock 0.00, scan 0.02 over 637 ranges, 1961 MB), 308 pages written, 308 copied (1.2 MB) [hos Presentation Thread] vk: a capture taken (ms): all 0.012; 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 (276 MB), 12 spare buffers, 1365 texture pages copied (5 MB) [hos ModuleSystemWorker1] vk: readbacks of GPU results: 2208 of 3000 waited for their write-back, 0.09 ms each; 56 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos ModuleSystemWorker1] vk: invalidates since the last readbacks line: 1374 kept their virtual core (nothing there to wait for), 2978 gave it up (counted by 256 a thread; RX_VK_INVALIDATE_QUICK=0: none kept) [hos Presentation Thread] vk: replay reads of guest memory as submitted: 1360000 (515029 pages from the captures) [hos Presentation Thread] vk: a frame: 125 draws kept their neighbour's descriptors (0 of them through other slots' registrations) [hos Presentation Thread] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued [hos Presentation Thread] vk: a frame's replay time (ms): submit 5.08, present 0.12, draw 3.05, descriptors 0.89, texture lookups 0.05, uploads 0.00, pipelines 0.11, programs 0.44, commands 1.32, dispatch 0.75, memory sync 0.21, queue submit 0.14, slot wait 0.01 [hos Presentation Thread] vk: a frame: mirrors 117 (952 MB): 7.12 MB synced in 1182.3 copies, 18.40 MB written back [hos Presentation Thread] vk: 8280 presents, 85.8 fps; a frame: 1200 draws (0 skipped), 145 dispatches, 146 passes, 130 barriers, 6 submits, 0.0 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.0 ms (recording slots only); 32425 pipelines (3480150 ms), 0 programs (0 failed), 1688 textures (4105 MB) [hos Presentation Thread] vk: host time in GPU resource waits: 2.09 ms a frame (fences 0.01, timelines 2.08, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos Presentation Thread] vk: a frame: 408.1 full barriers recorded, 173.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos Presentation Thread] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos Presentation Thread] vk: GPU time 8.4 ms a frame (the longest submission 7.2 ms); 0.0 textures made a frame [hos Presentation Thread] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms [hos Presentation Thread] vk: write-backs left out (600 submits): 1128, 5134.9 MB; 31 bindings followed, 43 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos Presentation Thread] vk: mirror syncs (600 submits): 1797 dirty pages from their submits' captures, 84053 from earlier ones', 0 from guest memory as it was at the replay; 25 captures kept; 0 pages the GPU wrote copied over (0 live); 0 kept for the GPU (RX_VK_PROTECT_BARE) [hos Presentation Thread] vk: mirror syncs' pass (600 submits): 1463 dispatches, 56179 chunks; 0 syncs as copies (no table room) [hos Presentation Thread] vk: write-back diff (600 submits): 8099 runs, 864.8 MB compared; 82 pages read into the shadows; 348 MB of shadows; pages the shadows knew that the CPU wrote: 25048 in captures, 2 only in the collection, 47 only by the replay itself [hos Presentation Thread] vk: read live, by pool: [hos sead::MainThread] vk: a submit's memory work (ms): maps 0.00, capture taken 0.01, writes collected 0.02 [hos sead::MainThread] nvn: CommandBufferWaitEvent #105000: event 0x100d6c8048 mode 0 value 69832 (now 69813) (lr 0x806661f8) [hos host] vk: present 8307 written to /<user>/<user>/Beanstalk/jobs/jb_f0947403740e4c7a/runs/hyrule-field-g1-02-pr/shots/hyrule-field-c1-pr-02-field.png (the control bridge) [hos Presentation Thread] vk: shadow staging (600 takes): 0 shadow copies from staging, 4096 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] control: quit asked by a client [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4302 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)