Report rp_4baf688d11b52864 pass
This report disagrees with its peers.
default-spares load_time_max_s: -53.0% against peers' +23.0% default-spares load_time_s: -35.0% against peers' +16.0%
Machine
- Commit
- 3f72adcc48956b74dacfb826aa44597185ae16f3
- Baseline
- 544229a260c5f5008f241b9cf48ae6b01c1602b9
- App
- nightly-156-4ec688b0, attempt 1
- Game build
e0f3ccfa- os
- windows
- cpu
- AMD Ryzen 7 5800X3D 8-Core Processor
- gpu
- AMD Radeon RX 9070 XT
- tags
- windowsamdamd-proprietarydgpu
- driver
- 2.0.416
- ram_gb
- 32
- vram_mb
- 16,304
- gpu_vendor
- amd
- os_version
- Windows 10.0.26300
Builds
PR
165.6 s warm
Program cache: warm
Scenarios
default-spares
ok| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| load_time_s | 10.42 | 6.77 | −35% |
| load_time_max_s | 16.87 | 7.93 | −53% |
| field.hitch_count | 3 | 1 | −66.7% |
| log_forbidden_hits | 0 | 0 | ±0% |
| market.hitch_count | 2 | 2 | ±0% |
| field.stutter_count | 5 | 6 | +20% |
| log_expected_missing | 0 | 0 | ±0% |
| market.stutter_count | 4 | 4 | ±0% |
| field.frametime_max_ms | 267.13 | 53.69 | −79.9% |
| field.frametime_p50_ms | 16.61 | 16.64 | +0.2% |
| field.frametime_p99_ms | 28.11 | 25.94 | −7.7% |
| market.frametime_max_ms | 165.95 | 68.13 | −58.9% |
| market.frametime_p50_ms | 17.71 | 17.91 | +1.1% |
| market.frametime_p99_ms | 31.48 | 32.97 | +4.7% |
| field.frametime_1pct_low_ms | 61.44 | 35.96 | −41.5% |
| market.frametime_1pct_low_ms | 47.34 | 40.61 | −14.2% |
| screenshot_diff | — | 0 | — |
Pictures against main: field diff 0, market diff 0
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| load_time_s | 10.42 | 6.77 |
| load_time_max_s | 16.87 | 7.93 |
| field.hitch_count | 3 | 1 |
| log_forbidden_hits | 0 | 0 |
| market.hitch_count | 2 | 2 |
| field.stutter_count | 5 | 6 |
| log_expected_missing | 0 | 0 |
| market.stutter_count | 4 | 4 |
| field.frametime_max_ms | 267.13 | 53.69 |
| field.frametime_p50_ms | 16.61 | 16.64 |
| field.frametime_p99_ms | 28.11 | 25.94 |
| market.frametime_max_ms | 165.95 | 68.13 |
| market.frametime_p50_ms | 17.71 | 17.91 |
| market.frametime_p99_ms | 31.48 | 32.97 |
| field.frametime_1pct_low_ms | 61.44 | 35.96 |
| market.frametime_1pct_low_ms | 47.34 | 40.61 |
| screenshot_diff | — | 0 |
| loads | Market_Child 16.87 sHyruleField_Child 6.4 sMarket_Child 7.98 s | Market_Child 7.93 sHyruleField_Child 5.06 sMarket_Child 7.32 s |
zero-spares RX_VK_SPARSE_SPARE_MB=0 (PR only)
ok
| Metric (median) | main | PR | Δ |
|---|---|---|---|
| exit_code | 0 | 0 | ±0% |
| load_time_s | 7.12 | 7.03 | −1.3% |
| load_time_max_s | 8.12 | 8.07 | −0.6% |
| field.hitch_count | 4 | 3 | −25% |
| log_forbidden_hits | 0 | 0 | ±0% |
| market.hitch_count | 5 | 3 | −40% |
| field.stutter_count | 10 | 4 | −60% |
| log_expected_missing | 0 | 0 | ±0% |
| market.stutter_count | 10 | 6 | −40% |
| field.frametime_max_ms | 221.75 | 150.72 | −32% |
| field.frametime_p50_ms | 16.59 | 16.63 | +0.3% |
| field.frametime_p99_ms | 27.31 | 27.75 | +1.6% |
| market.frametime_max_ms | 177.72 | 121.69 | −31.5% |
| market.frametime_p50_ms | 18 | 17.76 | −1.3% |
| market.frametime_p99_ms | 34.88 | 31.55 | −9.6% |
| field.frametime_1pct_low_ms | 57.91 | 49.56 | −14.4% |
| market.frametime_1pct_low_ms | 58.73 | 48.84 | −16.8% |
| screenshot_diff | — | 0 | — |
Pictures against main: field diff 0, market diff 0
Runs (2)
| Metric | main 0 | pr 1 |
|---|---|---|
| hang | no | no |
| crashed | no | no |
| exit_code | 0 | 0 |
| load_time_s | 7.12 | 7.03 |
| load_time_max_s | 8.12 | 8.07 |
| field.hitch_count | 4 | 3 |
| log_forbidden_hits | 0 | 0 |
| market.hitch_count | 5 | 3 |
| field.stutter_count | 10 | 4 |
| log_expected_missing | 0 | 0 |
| market.stutter_count | 10 | 6 |
| field.frametime_max_ms | 221.75 | 150.72 |
| field.frametime_p50_ms | 16.59 | 16.63 |
| field.frametime_p99_ms | 27.31 | 27.75 |
| market.frametime_max_ms | 177.72 | 121.69 |
| market.frametime_p50_ms | 18 | 17.76 |
| market.frametime_p99_ms | 34.88 | 31.55 |
| field.frametime_1pct_low_ms | 57.91 | 49.56 |
| market.frametime_1pct_low_ms | 58.73 | 48.84 |
| screenshot_diff | — | 0 |
| loads | Market_Child 7.93 sHyruleField_Child 5.32 sMarket_Child 8.12 s | Market_Child 7.58 sHyruleField_Child 5.44 sMarket_Child 8.07 s |
Rules
| Scenario | Cell | Rule | Limit | main | PR | Δ % | Status |
|---|---|---|---|---|---|---|---|
| default-spares | crash | False | 0 | 0 | — | pass | |
| default-spares | screenshot.max_diff | 0.05 | — | 0 | — | pass | |
| default-spares | load_time_max_s.max_delta_pct | 15 | 16.87 | 7.93 | −53% | pass | |
| default-spares | log_forbidden_hits.max | 0 | 0 | 0 | — | pass | |
| default-spares | log_expected_missing.max | 0 | 0 | 0 | — | pass | |
| zero-spares | RX_VK_SPARSE_SPARE_MB=0 (PR only) | crash | False | 0 | 0 | — | pass |
| zero-spares | RX_VK_SPARSE_SPARE_MB=0 (PR only) | screenshot.max_diff | 0.05 | — | 0 | — | pass |
| zero-spares | RX_VK_SPARSE_SPARE_MB=0 (PR only) | load_time_max_s.max_delta_pct | 15 | 8.12 | 8.07 | −0.6% | pass |
| zero-spares | RX_VK_SPARSE_SPARE_MB=0 (PR only) | log_forbidden_hits.max | 0 | 0 | 0 | — | pass |
| zero-spares | RX_VK_SPARSE_SPARE_MB=0 (PR only) | log_expected_missing.max | 0 | 0 | 0 | — | pass |
Log (PR side, end)
[hos host] vk: program picks: 3800468 kept (1596168 by the last picks' textures, a uniform buffer bound since), 14784 new, 1184747 with other textures (of 5000000) [hos host] vk: replay reads of guest memory as submitted: 2240000 (1322852 pages from the captures) [hos host] vk: 8 textures retired (1290 left, 2407 MB): budget 8, drawn over 0, dead targets 0 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 81, 1116 MB with memory of 1736 MB (619 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 3072; 879 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 752 dirty pages from their submits' captures, 43847 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: write-back diff (600 submits): 2641 runs, 335.9 MB compared; 38 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 8142 in captures, 31 only in the collection, 11 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos sead::MainThread] nvn: GPU waits in 5 s: 125 sync waits (312 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: 14 textures retired (1276 left, 2399 MB): budget 14, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2260000 (1336190 pages from the captures) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.10, writes collected 0.06 [hos host] vk: 10 textures retired (1266 left, 2395 MB): budget 10, drawn over 0, dead targets 0 [hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1005a88004 mode 0 value 1 (lr 0x8348c78c) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 114894 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #75000: event 0x100c318014 mode 0 value 52133 (now 52114) (lr 0x80661124) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 713 dirty pages from their submits' captures, 42852 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: write-back diff (600 submits): 2636 runs, 335.9 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7714 in captures, 26 only in the collection, 12 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2280000 (1349542 pages from the captures) [hos host] vk: 13 textures retired (1257 left, 2392 MB): budget 13, drawn over 0, dead targets 0 [hos host] vk: 19 textures retired (1238 left, 2379 MB): budget 19, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2300000 (1362887 pages from the captures) [hos host] vk: sparse mirrors: 81, 1116 MB with memory of 1736 MB (619 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 3306; 879 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 420, 2060.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 742 dirty pages from their submits' captures, 43624 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: write-back diff (600 submits): 2762 runs, 353.0 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7618 in captures, 32 only in the collection, 12 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos Presentation Thread] vk: capture: a submit 0.24 ms (lock 0.01, scan 0.04 over 559 ranges, 4192 MB), 605 pages written, 605 copied (2.4 MB) [hos host] vk: a capture taken (ms): all 0.100; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.091, bytes copied 0.000; 17 kept (732 MB), 12 spare buffers, 20425 texture pages copied (79 MB) [hos host] vk: 6 textures retired (1241 left, 2380 MB): budget 6, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2320000 (1376214 pages from the captures) [hos host] vk: 1 textures retired (1250 left, 2383 MB): budget 1, drawn over 0, dead targets 0 [hos host] vk: a frame: 387 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 82 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.47, present 0.21, draw 7.99, descriptors 3.18, texture lookups 0.20, uploads 0.09, pipelines 0.37, programs 1.08, commands 2.76, dispatch 0.76, memory sync 1.00, queue submit 1.04, slot wait 0.30 [hos host] vk: a frame: mirrors 282 (1116 MB): 8.94 MB synced in 1221.6 copies, 17.79 MB written back [hos host] vk: 5040 presents, 55.5 fps; a frame: 2445 draws (0 skipped), 124 dispatches, 158 passes, 146 barriers, 6 submits, 0.9 uploads (0.3 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 43019 pipelines (22413 ms), 0 programs (10 failed), 1250 textures (2383 MB) [hos host] vk: host time in GPU resource waits: 1.92 ms a frame (fences 0.05, timelines 1.86, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 513.4 full barriers recorded, 217.6 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: 38.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 8.8 ms a frame (the longest submission 1.7 ms); 0.8 textures made a frame [hos host] vk: a frame: 0.22 MB unswizzled on the CPU in 0.02 ms [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 764 dirty pages from their submits' captures, 42465 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: write-back diff (600 submits): 2595 runs, 334.6 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7715 in captures, 23 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2340000 (1389585 pages from the captures) [hos host] vk: program picks: 3950726 kept (1648919 by the last picks' textures, a uniform buffer bound since), 14784 new, 1234489 with other textures (of 5200000) [hos host] vk: readback pages refreshed from guest memory: 1661808 pages so far (0 held: may be written ahead in their submission) [hos host] vk: sparse mirrors: 80, 1116 MB with memory of 1732 MB (615 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 3528; 879 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 378, 1854.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 758 dirty pages from their submits' captures, 40858 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: write-back diff (600 submits): 2476 runs, 317.4 MB compared; 89 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7126 in captures, 33 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: replay reads of guest memory as submitted: 2360000 (1402901 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1030 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 host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 761 dirty pages from their submits' captures, 42544 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: write-back diff (600 submits): 2601 runs, 333.8 MB compared; 34 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7464 in captures, 37 only in the collection, 14 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2380000 (1416320 pages from the captures) [hos host] vk: 6 textures retired (1340 left, 2463 MB): budget 6, drawn over 0, dead targets 0 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 86549 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.09, writes collected 0.07 [hos host] vk: replay reads of guest memory as submitted: 2400000 (1429663 pages from the captures) [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 3756; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 901 dirty pages from their submits' captures, 42667 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: write-back diff (600 submits): 2542 runs, 334.0 MB compared; 51 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7361 in captures, 29 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 8 textures retired (1345 left, 2496 MB): budget 8, drawn over 0, dead targets 0 [hos host] vk: 16 textures retired (1332 left, 2491 MB): budget 16, drawn over 0, dead targets 0 [hos Presentation Thread] vi: 5113 frames presented (56.0 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 24, 15.5-17.8 140, 17.8-22 103, 22-30 13, 30-40 0, over 40 0 [hos host] vk: replay reads of guest memory as submitted: 2420000 (1443022 pages from the captures) [hos sead::MainThread] vk: capture: a submit 0.25 ms (lock 0.02, scan 0.04 over 560 ranges, 4256 MB), 568 pages written, 568 copied (2.2 MB) [hos host] vk: a capture taken (ms): all 0.080; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.072, bytes copied 0.000; 25 kept (560 MB), 3 spare buffers, 18521 texture pages copied (72 MB) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 695 dirty pages from their submits' captures, 43062 from earlier ones', 3 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: write-back diff (600 submits): 2650 runs, 335.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7563 in captures, 29 only in the collection, 14 only by the replay itself [hos host] vk: read live, by pool: 0x7fa9000000 (12 MB, captured, state 2): 3; [hos host] vk: 15 textures retired (1328 left, 2490 MB): budget 15, drawn over 0, dead targets 0 [hos ModuleSystemWorker1] vcores: 298312 takes, 74372 waits (mean 55 us, longest 26.8 ms, 0 over HOS_VCORE_LOG_MS), 39244 kicks, 39174 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 2440000 (1456383 pages from the captures) [hos host] vk: 16 textures retired (1333 left, 2487 MB): budget 16, drawn over 0, dead targets 0 [hos host] vk: program picks: 4101201 kept (1701895 by the last picks' textures, a uniform buffer bound since), 14784 new, 1284014 with other textures (of 5400000) [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 3984; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 705 dirty pages from their submits' captures, 42815 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: write-back diff (600 submits): 2600 runs, 335.0 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 8007 in captures, 23 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 11 textures retired (1334 left, 2488 MB): budget 11, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2460000 (1469750 pages from the captures) [hos host] vk: 17 textures retired (1327 left, 2453 MB): budget 17, drawn over 0, dead targets 0 [hos host] vk: recorder: 8159580 packets run in 10.0 s (busy 1.94 s, spun idle 5.53 s, slept 3853 times, 2099 of them under 200 us), 0 calls made directly (no room); the replay waited for it 41241 times, 134.08 ms in all, the longest 0.32 ms; vkResetDescriptorPool 17215/63.33 ms (max 0.32), vkEndCommandBuffer 17215/51.91 ms (max 0.25), replay_mu unlock 6808/18.79 ms (max 0.10), vkQueueBindSparse 3/0.05 ms (max 0.03) [hos host] vk: readback pages refreshed from guest memory: 1734531 pages so far (0 held: may be written ahead in their submission) [hos sead::MainThread] nvn: CommandBufferSignalEvent #55000: event 0x100c31800c mode 0 value 55000 (lr 0x80660adc) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 764 dirty pages from their submits' captures, 43964 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: write-back diff (600 submits): 2604 runs, 334.4 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7641 in captures, 31 only in the collection, 12 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2480000 (1483061 pages from the captures) [hos host] vk: 34 textures retired (1301 left, 2399 MB): budget 34, drawn over 0, dead targets 0 [hos host] vk: a frame: 400 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 82 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.55, present 0.16, draw 8.24, descriptors 3.51, texture lookups 0.49, uploads 0.31, pipelines 0.36, programs 1.07, commands 2.74, dispatch 0.73, memory sync 0.87, queue submit 1.04, slot wait 0.28 [hos host] vk: a frame: mirrors 283 (1119 MB): 8.98 MB synced in 1223.6 copies, 17.72 MB written back [hos host] vk: 5160 presents, 55.4 fps; a frame: 2472 draws (0 skipped), 122 dispatches, 159 passes, 146 barriers, 6 submits, 2.7 uploads (0.8 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 43019 pipelines (22413 ms), 0 programs (10 failed), 1301 textures (2399 MB) [hos host] vk: host time in GPU resource waits: 1.94 ms a frame (fences 0.05, timelines 1.89, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 515.5 full barriers recorded, 217.9 left out (nothing recorded since the one before), 0.0 pass starts ordered in their fragment stages only (RX_VK_PASS_BARRIER=game) [hos host] vk: a frame: the game's barriers by their NVN flags: 0x1: 2.0; 0x8: 3.0; 0x9: 1.0; 0x11: 38.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 8.7 ms a frame (the longest submission 1.5 ms); 2.7 textures made a frame [hos host] vk: a frame: 0.72 MB unswizzled on the CPU in 0.06 ms [hos host] vk: texture slots registered again at another size: 200000 (of 283840 registrations; slot 25168 256x256 -> 360x202) [hos host] vk: 3 textures retired (1330 left, 2427 MB): budget 3, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2500000 (1496439 pages from the captures) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 4218; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 420, 2060.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 741 dirty pages from their submits' captures, 44092 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: write-back diff (600 submits): 2729 runs, 351.4 MB compared; 131 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7474 in captures, 29 only in the collection, 14 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 15 textures retired (1330 left, 2438 MB): budget 15, drawn over 0, dead targets 0 [hos ModuleSystemWorker5] nvn: 800000 recordings made, 83071 live copies (24.4 MB), 572 texture copies; 5 command buffers' segments (4.3 MB) [hos host] vk: replay reads of guest memory as submitted: 2520000 (1509845 pages from the captures) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 108358 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 21 textures retired (1316 left, 2438 MB): budget 21, drawn over 0, dead targets 0 [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 753 dirty pages from their submits' captures, 42768 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: write-back diff (600 submits): 2591 runs, 334.4 MB compared; 38 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7547 in captures, 28 only in the collection, 10 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.09, writes collected 0.06 [hos host] vk: 12 textures retired (1308 left, 2437 MB): budget 12, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2540000 (1523175 pages from the captures) [hos ModuleSystemWorker5] nvn: CommandBufferWaitEvent #80000: event 0x100c318014 mode 0 value 55933 (now 55914) (lr 0x80661124) [hos host] vk: render targets drawn over from another start, let go: 1165 so far (1829 MB), 1126 of them (1758 MB) between the passes [hos host] vk: 10 textures retired (1308 left, 2437 MB): budget 10, drawn over 0, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.25 ms (lock 0.02, scan 0.04 over 561 ranges, 4310 MB), 586 pages written, 586 copied (2.3 MB) [hos host] vk: a capture taken (ms): all 0.090; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.081, bytes copied 0.000; 25 kept (330 MB), 6 spare buffers, 20271 texture pages copied (79 MB) [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 4446; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 889 dirty pages from their submits' captures, 42562 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: write-back diff (600 submits): 2597 runs, 334.9 MB compared; 38 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7510 in captures, 33 only in the collection, 14 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: program picks: 4251200 kept (1754549 by the last picks' textures, a uniform buffer bound since), 14784 new, 1334015 with other textures (of 5600000) [hos host] vk: replay reads of guest memory as submitted: 2560000 (1536536 pages from the captures) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1050 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 host] vk: 10 textures retired (1307 left, 2435 MB): budget 10, drawn over 0, dead targets 0 [hos host] vk: 22 textures retired (1296 left, 2419 MB): budget 22, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2580000 (1549921 pages from the captures) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 769 dirty pages from their submits' captures, 42717 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: write-back diff (600 submits): 2597 runs, 334.4 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7912 in captures, 27 only in the collection, 11 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 26 textures retired (1273 left, 2390 MB): budget 26, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2600000 (1563266 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 1807040 pages so far (0 held: may be written ahead in their submission) [hos host] vk: 7 textures retired (1273 left, 2386 MB): budget 7, drawn over 0, dead targets 0 [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 4674; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 955 dirty pages from their submits' captures, 43678 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: write-back diff (600 submits): 2592 runs, 334.4 MB compared; 38 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7611 in captures, 38 only in the collection, 11 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 5 textures retired (1285 left, 2389 MB): budget 5, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2620000 (1576649 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 123 sync waits (317 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: 11 textures retired (1281 left, 2386 MB): budget 11, drawn over 0, dead targets 0 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 420, 2060.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 719 dirty pages from their submits' captures, 43582 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: write-back diff (600 submits): 2704 runs, 351.4 MB compared; 35 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7595 in captures, 26 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: 0x7fa9000000 (12 MB, captured, state 2): 1; [hos host] vk: texture #7553 0x10000a90800 480x270 NVN 0x3f: the GPU wrote its storage (submission 31424): uploaded again [hos host] vk: upload over a drawn image: #7553 0x10000a90800 480x270x1 x1 NVN 0x3f at present 5272 (texture frame 5273), finalized, 0 KB dirty in 0 ranges, a GPU buffer wrote it [hos host] vk: replay reads of guest memory as submitted: 2640000 (1590028 pages from the captures) [hos host] vk: 9 textures retired (1273 left, 2395 MB): budget 9, drawn over 0, dead targets 0 [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 82 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.03, present 0.17, draw 7.84, descriptors 3.27, texture lookups 0.38, uploads 0.20, pipelines 0.35, programs 1.05, commands 2.63, dispatch 0.72, memory sync 0.97, queue submit 0.98, slot wait 0.26 [hos host] vk: a frame: mirrors 283 (1116 MB): 8.94 MB synced in 1221.0 copies, 17.72 MB written back [hos host] vk: 5280 presents, 57.1 fps; a frame: 2440 draws (0 skipped), 122 dispatches, 158 passes, 146 barriers, 6 submits, 2.1 uploads (0.4 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 43019 pipelines (22413 ms), 0 programs (10 failed), 1273 textures (2395 MB) [hos host] vk: host time in GPU resource waits: 2.17 ms a frame (fences 0.05, timelines 2.12, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 512.3 full barriers recorded, 217.5 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: 38.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 8.8 ms a frame (the longest submission 1.6 ms); 2.1 textures made a frame [hos host] vk: a frame: 0.40 MB unswizzled on the CPU in 0.03 ms [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 91877 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 14 textures retired (1259 left, 2392 MB): budget 14, drawn over 0, dead targets 0 [hos host] vk: sparse mirrors: 80, 1116 MB with memory of 1736 MB (619 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 4908; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 751 dirty pages from their submits' captures, 42928 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: write-back diff (600 submits): 2594 runs, 334.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7588 in captures, 30 only in the collection, 8 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: replay reads of guest memory as submitted: 2660000 (1603320 pages from the captures) [hos host] vk: program picks: 4400792 kept (1806966 by the last picks' textures, a uniform buffer bound since), 14784 new, 1384423 with other textures (of 5800000) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.09, writes collected 0.06 [hos sead::MainThread] vk: capture: a submit 0.24 ms (lock 0.02, scan 0.04 over 556 ranges, 4328 MB), 563 pages written, 563 copied (2.2 MB) [hos host] vk: a capture taken (ms): all 0.081; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.072, bytes copied 0.000; 25 kept (302 MB), 4 spare buffers, 20294 texture pages copied (79 MB) [hos host] vk: replay reads of guest memory as submitted: 2680000 (1616740 pages from the captures) [hos host] vk: 15 textures retired (1245 left, 2389 MB): budget 15, drawn over 0, dead targets 0 [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 793 dirty pages from their submits' captures, 42580 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: write-back diff (600 submits): 2591 runs, 334.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7603 in captures, 24 only in the collection, 10 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29983 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 50.11 ms at most); waits met 82653, not met 0; captures at a CPU event's wait 2361, 0 of them at a wait met on arrival [hos host] vk: 5 textures retired (1241 left, 2388 MB): budget 5, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2700000 (1630132 pages from the captures) [hos host] vk: 6 textures retired (1235 left, 2386 MB): budget 6, drawn over 0, dead targets 0 [hos host] vk: sparse mirrors: 80, 1116 MB with memory of 1736 MB (619 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5136; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 660 dirty pages from their submits' captures, 42711 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: write-back diff (600 submits): 2592 runs, 334.9 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 8006 in captures, 30 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: replay reads of guest memory as submitted: 2720000 (1643493 pages from the captures) [hos host] vk: 1 textures retired (1243 left, 2382 MB): budget 1, drawn over 0, dead targets 0 [hos host] vk: readback pages refreshed from guest memory: 1879549 pages so far (0 held: may be written ahead in their submission) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 981 dirty pages from their submits' captures, 42661 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: write-back diff (600 submits): 2585 runs, 334.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7594 in captures, 33 only in the collection, 10 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: replay reads of guest memory as submitted: 2740000 (1656901 pages from the captures) [hos host] vk: 1 textures retired (1246 left, 2383 MB): budget 1, drawn over 0, dead targets 0 [hos ModuleSystemWorker1] vk: readbacks of GPU results: 984 of 3000 waited for their write-back, 0.14 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror) [hos host] vk: replay reads of guest memory as submitted: 2760000 (1670240 pages from the captures) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 80, 1116 MB with memory of 1736 MB (619 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5364; 880 binds (233.8 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 732 dirty pages from their submits' captures, 43525 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: write-back diff (600 submits): 2599 runs, 334.4 MB compared; 38 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7601 in captures, 24 only in the collection, 14 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 2 textures retired (1265 left, 2397 MB): budget 2, drawn over 0, dead targets 0 [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 58359 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: program picks: 4550850 kept (1859331 by the last picks' textures, a uniform buffer bound since), 14784 new, 1434365 with other textures (of 6000000) [hos host] vk: replay reads of guest memory as submitted: 2780000 (1683580 pages from the captures) [hos host] vk: write-backs left out (600 submits): 420, 2060.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 879 dirty pages from their submits' captures, 43445 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: write-back diff (600 submits): 2723 runs, 351.4 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7600 in captures, 32 only in the collection, 11 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: textures the GPU drew, written back into their memory before eviction: 1 so far [hos host] vk: 1 textures retired (1272 left, 2394 MB): budget 1, drawn over 0, dead targets 0 [hos Presentation Thread] vk: capture: a submit 0.21 ms (lock 0.02, scan 0.04 over 557 ranges, 4332 MB), 513 pages written, 513 copied (2.0 MB) [hos host] vk: a capture taken (ms): all 0.057; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.049, bytes copied 0.000; 25 kept (264 MB), 6 spare buffers, 5013 texture pages copied (19 MB) [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.06, writes collected 0.07 [hos host] vk: replay reads of guest memory as submitted: 2800000 (1696916 pages from the captures) [hos host] vk: memory: working set 17331 MB (peak 17719), private 24315 MB, staging 192 MB in 12 arenas, 35 made so far (104 ms) [hos host] vk: memory heaps: heap 0 (system): 14 blocks 848 MB, 37 allocations 774 MB; used 3688 of 15571 MB; heap 1 (device): 168 blocks 5151 MB, 19427 allocations 4190 MB; used 6354 of 15419 MB; [hos host] vk: image blocks: 1 blocks 32 MB, 6 images 24 MB; 1 free ranges, the largest 7 MB [hos host] vk: image blocks (render targets): 12 blocks 384 MB, 131 images 155 MB; 52 free ranges, the largest 32 MB [hos host] vk: image blocks (textures, compacted): 66 blocks 2112 MB, 1141 images 1692 MB; 392 free ranges, the largest 17 MB [hos host] vk: render target images: 549 reused from the pool, 818 made new, 684 destroyed from it; it holds 0 (0 MB) [hos host] vk: VRAM: 6354 MB used of 15419 MB allowed (961 MB of it free in the blocks); textures 2399 MB (budget 830 MB), 1278 textures [hos host] vk: textures: decoded ASTC 1231 MB, rendered 689 MB (63 drawn in one frame, kept: 27180 KB), other 267 MB; used in the last 8 presents 2125 MB [hos host] vk: decoded ASTC used again: 826 textures (1642 MB) copied from ones the game finalized, not decoded; 826 of those retired, 0 listed; 1825 MB of blocks hashed in 230 ms [hos host] vk: 288 MB: 0x114682a000 12288x12288x1 x1 levels 1 NVN 0x32 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: 64 MB: 0x113b7bd000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago [hos host] vk: 54 MB: 0x10001be6200 3072x3072x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 32 MB: 0x115882b000 4096x4096x1 x1 levels 1 NVN 0x32 rendered, last used 1 presents ago [hos host] vk: 31 MB: 0x111c019400 1775x1175x1 x8 levels 1 NVN 0x6, last used 1 presents ago [hos host] vk: 21 MB: 0x100056d2600 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago [hos host] vk: 13 MB: 0x110e554400 2288x6112x1 x1 levels 1 NVN 0x4b, last used 1 presents ago [hos host] vk: finalized textures the GPU drew once, kept for being made again: 56 (9545 KB): 140x42x1 NVN 0x25: 1 (22 KB); 204x106x1 NVN 0x1: 1 (21 KB); 260x260x1 NVN 0xd: 54 (9501 KB); [hos host] vk: 4 textures retired (1274 left, 2399 MB): budget 4, drawn over 0, dead targets 0 [hos Presentation Thread] vk: presents after the CPU's signal (600): 280 waited for it, 2.47 ms each, 0 let go after RX_VK_FRAME_GATE_MS [hos host] vk: status: 600 frames, the slowest 32.3 ms; VRAM 6.2 of 15.1 GB [hos host] vk: program census (play): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 35 program records loaded (33.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (play): 5802 queued, 5802 loaded (median 0.61 ms, 99th percentile 4.51 ms, worst 27.95 ms, 5676 ms and 1237.1 MB read in all); 7806 programs (1846 of them compute variants without their code, 0 graphics programs no note names), 10052 graphics pipelines (0 not in a cache), 740 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2084 pipelines made at create taken by draws; 3108 create calls with nothing kept for their stages, 0 before the index; units 8910 (5802 ready, 0 loading), 14602 programs alive [hos host] vk: module identifiers (play): 740 known, 0 learned in this run; 740 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before) [hos host] vk: a frame: 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 82 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 13.43, present 0.19, draw 7.42, descriptors 2.94, texture lookups 0.15, uploads 0.05, pipelines 0.34, programs 1.01, commands 2.59, dispatch 0.72, memory sync 0.77, queue submit 0.97, slot wait 0.26 [hos host] vk: a frame: mirrors 284 (1119 MB): 8.94 MB synced in 1218.3 copies, 17.72 MB written back [hos host] vk: 5400 presents, 59.0 fps; a frame: 2439 draws (0 skipped), 122 dispatches, 158 passes, 146 barriers, 6 submits, 0.6 uploads (0.1 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 43019 pipelines (22413 ms), 0 programs (10 failed), 1274 textures (2399 MB) [hos host] vk: host time in GPU resource waits: 2.22 ms a frame (fences 0.07, timelines 2.15, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 510.2 full barriers recorded, 217.5 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: 38.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 8.8 ms a frame (the longest submission 1.6 ms); 0.5 textures made a frame [hos host] vk: a frame: 0.06 MB unswizzled on the CPU in 0.01 ms [hos host] vk: the render thread's whole frames (600 presents): 0 jobs went on before their present after 1000 ms, 0 times a game's thread waited for the work handed over, 0 times for a fence of the frame in the making [hos host] vk: the render thread (600 presents, 17.56 ms a frame): its jobs 14.76 ms a frame (submits 8.16, presents 0.19, others 6.41), idle 2.80; the game waited for room at 1 presents, 1.18 ms each (0.00 a frame; 152.47 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); 298 captures at a CPU signal; the submits' waits read in 0.058 ms a frame; readbacks: 3000 next to a texture's storage (no catch-up), 0 in one, 0 read exactly (after the work handed over: among the catch-ups); a present made 14.79 ms after its hand-over (26.26 at most) [hos Presentation Thread] vi: 5402 frames presented (57.8 fps over the last 5.0 s, interval 1) [hos Presentation Thread] vi: present intervals: <15.5 ms 34, 15.5-17.8 158, 17.8-22 92, 22-30 5, 30-40 0, over 40 0 [hos sead::MainThread] nvn: CommandBufferWaitEvent #85000: event 0x100c318018 mode 0 value 59734 (now 59715) (lr 0x80661124) [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5598; 881 binds (233.9 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 760 dirty pages from their submits' captures, 42799 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: write-back diff (600 submits): 2601 runs, 334.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7612 in captures, 30 only in the collection, 10 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 3 textures retired (1282 left, 2408 MB): budget 3, drawn over 0, dead targets 0 [hos aglTextureDataMgr::Compaction] vcores: 308991 takes, 73246 waits (mean 55 us, longest 25.1 ms, 0 over HOS_VCORE_LOG_MS), 38601 kicks, 38550 yields, 0 starved grants, 0 escapes in 5 s [hos host] vk: replay reads of guest memory as submitted: 2820000 (1710323 pages from the captures) [hos ModuleSystemWorker4] nvn: CommandBufferSignalEvent #60000: event 0x100c318018 mode 0 value 60000 (lr 0x80660c94) [hos host] vk: 2 textures retired (1285 left, 2439 MB): budget 2, drawn over 0, dead targets 0 [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 661 dirty pages from their submits' captures, 42748 from earlier ones', 3 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: write-back diff (600 submits): 2597 runs, 335.0 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7592 in captures, 29 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: 0x7fa9000000 (12 MB, captured, state 2): 3; [hos host] vk: replay reads of guest memory as submitted: 2840000 (1723714 pages from the captures) [hos host] vk: readback pages refreshed from guest memory: 1952058 pages so far (0 held: may be written ahead in their submission) [hos host] vk: replay reads of guest memory as submitted: 2860000 (1737059 pages from the captures) [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 5826; 881 binds (233.9 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 664 dirty pages from their submits' captures, 42873 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: write-back diff (600 submits): 2595 runs, 334.4 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7939 in captures, 30 only in the collection, 12 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 7 textures retired (1284 left, 2440 MB): budget 7, drawn over 0, dead targets 0 [hos host] vk: program picks: 4700744 kept (1911991 by the last picks' textures, a uniform buffer bound since), 14784 new, 1484471 with other textures (of 6200000) [hos host] vk: replay reads of guest memory as submitted: 2880000 (1750442 pages from the captures) [hos host] vk: 15 textures retired (1270 left, 2427 MB): budget 15, drawn over 0, dead targets 0 [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: write-backs left out (600 submits): 420, 2060.2 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 507 dirty pages from their submits' captures, 44537 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: write-back diff (600 submits): 2719 runs, 351.4 MB compared; 36 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7640 in captures, 28 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 112504 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: 15 textures retired (1259 left, 2418 MB): budget 15, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2900000 (1763789 pages from the captures) [hos host] vk: 18 textures retired (1251 left, 2378 MB): budget 18, drawn over 0, dead targets 0 [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 6060; 881 binds (233.9 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 580 dirty pages from their submits' captures, 42989 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: write-back diff (600 submits): 2599 runs, 334.4 MB compared; 37 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7520 in captures, 29 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos ModuleSystemWorker3] nvn: DrawMeshTasksIndirect: 140000 so far (x1 0x117c658020 x2 0 x3 0x117c658000 x4 0x9b040) [hos host] vk: replay reads of guest memory as submitted: 2920000 (1777122 pages from the captures) [hos Presentation Thread] vk: capture: a submit 0.26 ms (lock 0.01, scan 0.04 over 557 ranges, 4336 MB), 657 pages written, 657 copied (2.6 MB) [hos host] vk: a capture taken (ms): all 0.115; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.106, bytes copied 0.000; 25 kept (272 MB), 8 spare buffers, 10951 texture pages copied (42 MB) [hos host] vk: 1 textures retired (1254 left, 2378 MB): budget 1, drawn over 0, dead targets 0 [hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.11, writes collected 0.06 [hos host] vk: 1 textures retired (1253 left, 2378 MB): budget 1, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2940000 (1790493 pages from the captures) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 789 dirty pages from their submits' captures, 42320 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: write-back diff (600 submits): 2464 runs, 317.3 MB compared; 34 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7597 in captures, 27 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: texture storage read as submitted (6001 times; 144345 pages from the copies, 0 of them rewritten in guest memory since their submit; 11697 pages kept, 546 spans, 1660 MB) [hos ModuleSystemWorker2] vk: readbacks of GPU results: 1079 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 host] vk: replay reads of guest memory as submitted: 2960000 (1803806 pages from the captures) [hos host] vk: 3 textures retired (1283 left, 2386 MB): budget 3, drawn over 0, dead targets 0 [hos host] vk: a frame: 393 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 82 ms in all, 0 jobs queued [hos host] vk: a frame's replay time (ms): submit 14.19, present 0.19, draw 7.84, descriptors 3.12, texture lookups 0.20, uploads 0.07, pipelines 0.38, programs 1.06, commands 2.73, dispatch 0.74, memory sync 0.98, queue submit 1.00, slot wait 0.28 [hos host] vk: a frame: mirrors 284 (1119 MB): 8.91 MB synced in 1216.1 copies, 17.72 MB written back [hos host] vk: 5520 presents, 56.1 fps; a frame: 2460 draws (0 skipped), 122 dispatches, 159 passes, 146 barriers, 6 submits, 1.1 uploads (0.2 MB), 82 ub updates (57 overlays), GPU-bound wait 0.1 ms (recording slots only); 43019 pipelines (22413 ms), 0 programs (10 failed), 1283 textures (2386 MB) [hos host] vk: host time in GPU resource waits: 1.70 ms a frame (fences 0.05, timelines 1.65, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking) [hos host] vk: a frame: 511.1 full barriers recorded, 217.8 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: 38.0; 0x12: 76.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0; [hos host] vk: GPU time 8.8 ms a frame (the longest submission 1.6 ms); 1.1 textures made a frame [hos host] vk: a frame: 0.10 MB unswizzled on the CPU in 0.01 ms [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 6282; 881 binds (233.9 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 378, 1854.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 849 dirty pages from their submits' captures, 40570 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: write-back diff (600 submits): 2599 runs, 334.4 MB compared; 32 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7543 in captures, 32 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos ModuleSystemWorker1] nvn: 850000 recordings made, 83160 live copies (25.1 MB), 572 texture copies; 6 command buffers' segments (4.3 MB) [hos host] vk: commit limit near: 1079 MB of commit left (reserve 2560 MB); the textures' budget down to 909 MB of their 2390 MB (RX_VK_COMMIT_RESERVE_MB) [hos host] vk: 6 textures retired (1282 left, 2387 MB): budget 6, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 2980000 (1817236 pages from the captures) [hos host] vk: program picks: 4851116 kept (1964888 by the last picks' textures, a uniform buffer bound since), 14784 new, 1534099 with other textures (of 6400000) [hos host] vk: readback pages refreshed from guest memory: 2024825 pages so far (0 held: may be written ahead in their submission) [hos host] vk: write-backs left out (600 submits): 399, 1957.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 705 dirty pages from their submits' captures, 43448 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: write-back diff (600 submits): 2593 runs, 333.8 MB compared; 32 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7265 in captures, 21 only in the collection, 15 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: 9 textures retired (1279 left, 2387 MB): budget 9, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 3000000 (1830543 pages from the captures) [hos sead::MainThread] nvn: GPU waits in 5 s: 126 sync waits (302 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms) [hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 78709 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged) [hos host] vk: the recording streams: 48 of 2 MB, the most one held 628 KB; 0 made on demand (0 MB kept now); c1 stages: at most 219 a recording; 8 descriptor pools made when a recording's own ran out [hos host] vk: sparse mirrors: 81, 1119 MB with memory of 1740 MB (620 MB spared); blocks given memory later 15579, given back 21592; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 6504; 881 binds (233.9 ms); 0 made whole for want of memory [hos host] vk: write-backs left out (600 submits): 378, 1854.1 MB; 26 bindings followed, 37 ranges the CPU read, 0 resets; CPU reads or writes of one left out: 1686 so far [hos host] vk: mirror syncs (600 submits): 870 dirty pages from their submits' captures, 41399 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: write-back diff (600 submits): 2476 runs, 317.4 MB compared; 31 pages read into the shadows; 292 MB of shadows; pages the shadows knew that the CPU wrote: 7552 in captures, 31 only in the collection, 13 only by the replay itself [hos host] vk: read live, by pool: [hos host] vk: imports: 153 live (2488 MB), 28 retired still imported (336 MB), 40 retired given back (812 MB) [hos host] vk: 3 textures retired (1280 left, 2414 MB): budget 3, drawn over 0, dead targets 0 [hos host] vk: replay reads of guest memory as submitted: 3020000 (1844045 pages from the captures) [hos host] control: quit asked by a client [hos host] vk: program census (close): created 0 (0 with stages; 0 with no present for 100 ms before, 0 in a frame of 100 ms or more; 0.0 ms of the game's threads), freed 0 (0 never used); first uses 0: program ready 0, loaded 0, translated 0, failed 0; pipeline ready 0, from a cache 0, compiled 0, made 0, left out 0, none 0; 0 with no create call seen, 0 whose stages are not the create call's; after the create call: under 16.7 ms 0, under 100 ms 0, under 1 s 0, longer 0; needing work 0 (0 of them 100 ms or more after the create call, 0 created in a load or a long frame); in play: 35 program records loaded (33.1 ms), 0 new graphics pipelines, pipelines from the driver's cache 0, from the start's cache 0, compiled 0; 0 draws and dispatches left out, 0 waits (0.0 ms) [hos host] vk: program loads at create (close): 5802 queued, 5802 loaded (median 0.61 ms, 99th percentile 4.51 ms, worst 27.95 ms, 5676 ms and 1237.1 MB read in all); 7806 programs (1846 of them compute variants without their code, 0 graphics programs no note names), 10052 graphics pipelines (0 not in a cache), 740 compute pipelines (0 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 2084 pipelines made at create taken by draws; 3108 create calls with nothing kept for their stages, 0 before the index; units 8910 (5802 ready, 0 loading), 14602 programs alive [hos host] vk: module identifiers (close): 740 known, 0 learned in this run; 740 compute pipelines made by them at a create call, 0 asked that way were in no cache (their code read, as before) [hos host] vk: page table census (close): no pool outside its windows, 64-72 GB and 508-512 GB (4263 pools in the table now) [hos host] control: exiting [hos host] stop: close work done (the game's saves are not waited for)