Log (PR side, end)
[hos host] vk: mirror syncs (600 submits): 1190 dirty pages from their submits' captures, 50745 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): 5390 runs, 2046.3 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16319 in captures, 4 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.19 ms (lock 0.01, scan 0.04 over 464 ranges, 3797 MB), 392 pages written, 392 copied (1.5 MB)
[hos host] vk: a capture taken (ms): all 0.070; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.052, bytes copied 0.000; 25 kept (126 MB), 11 spare buffers, 7641 texture pages copied (29 MB)
[hos AudioFrameworkThread] vcores: 312475 takes, 32002 waits (mean 26 us, longest 6.1 ms), 17273 kicks, 17296 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 537 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1244 dirty pages from their submits' captures, 50899 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): 5375 runs, 2044.9 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16321 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: replay reads of guest memory as submitted: 2920000 (1616435 pages from the captures)
[hos host] vk: readback pages refreshed from guest memory: 1890727 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: program picks: 4659826 kept (1965548 by the last picks' textures, a uniform buffer bound since), 2582 new, 1737591 with other textures (of 6400000)
[hos sead::MainThread] vk: readbacks of GPU results: 1548 of 3000 waited for their write-back, 0.15 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: mirror syncs (600 submits): 1174 dirty pages from their submits' captures, 51915 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): 5375 runs, 2044.8 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16869 in captures, 3 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #60000: event 0x100e640024 mode 0 value 60000 (lr 0x80665068)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 61734 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 2940000 (1623088 pages from the captures)
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 537 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1206 dirty pages from their submits' captures, 51511 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): 5542 runs, 2111.6 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16318 in captures, 4 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.11, writes collected 0.06
[hos host] vk: memory: working set 12538 MB (peak 12786), private 20223 MB, staging 256 MB in 4 arenas
[hos host] vk: memory heaps: heap 0 (device): 112 blocks 6081 MB, 17981 allocations 4824 MB; used 6328 of 7250 MB; heap 1 (system): 15 blocks 784 MB, 39 allocations 722 MB; used 3087 of 15319 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 5 images 16 MB; 1 free ranges, the largest 111 MB
[hos host] vk: image blocks (render targets): 8 blocks 1024 MB, 135 images 522 MB; 43 free ranges, the largest 69 MB
[hos host] vk: image blocks (textures, compacted): 17 blocks 2176 MB, 1993 images 1845 MB; 817 free ranges, the largest 72 MB
[hos host] vk: render target images: 306 reused from the pool, 714 made new, 579 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6328 MB used of 7250 MB allowed (1257 MB of it free in the blocks); textures 2893 MB (budget 2695 MB), 2130 textures
[hos host] vk: textures: decoded ASTC 1573 MB, rendered 570 MB (87 drawn in one frame, kept: 41774 KB), other 418 MB; used in the last 8 presents 1276 MB
[hos host] vk: 214 MB: 0x10a6aa2c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a322a600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x113db7d000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x11384dc000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 37 MB: 0x1111b8de00 1800x1380x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk: 27 MB: 0x100044b4400 2200x2200x1 x3 levels 1 NVN 0x32 rendered, last used 1341 presents ago
[hos host] vk: 27 MB: 0x1000408fc00 2200x2200x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 21 MB: 0x10006d34800 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 23 (4047 KB): 260x260x1 NVN 0xd: 23 (4047 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 571 waited for it, 1.44 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: status: 600 frames, the slowest 27.5 ms; VRAM 6.2 of 7.1 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: 55 program records loaded (150.7 ms), 2147 new graphics pipelines, pipelines from the driver's cache 633, from the start's cache 0, compiled 1658; 417743 draws and dispatches left out, 563 waits (106908.1 ms)
[hos host] vk: program loads at create (play): 5860 queued, 5860 loaded (median 0.95 ms, 99th percentile 12.50 ms, worst 29.47 ms, 12065 ms and 1280.2 MB read in all); 8098 programs (1360 of them compute variants without their code, 0 graphics programs no note names), 11 graphics pipelines (10277 not in a cache), 0 compute pipelines (707 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 3 pipelines made at create taken by draws; 3050 create calls with nothing kept for their stages, 0 before the index; units 8910 (5860 ready, 0 loading), 15494 programs alive
[hos host] vk: module identifiers (play): 752 known, 164 learned in this run; 0 compute pipelines made by them at a create call, 568 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.52, present 0.18, draw 3.31, descriptors 1.27, texture lookups 0.09, uploads 0.02, pipelines 0.17, programs 0.59, commands 1.00, dispatch 0.71, memory sync 0.97, queue submit 0.62, slot wait 0.06
[hos host] vk: a frame: mirrors 250 (977 MB): 6.78 MB synced in 1144.6 copies, 68.16 MB written back
[hos host] vk: 4800 presents, 60.1 fps; a frame: 1262 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2130 textures (2893 MB)
[hos host] vk: host time in GPU resource waits: 2.80 ms a frame (fences 0.04, timelines 2.77, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 499.4 full barriers recorded, 186.2 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.6 ms a frame (the longest submission 4.3 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.00 MB unswizzled on the CPU in 0.00 ms
[hos host] vk: 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, 16.75 ms a frame): its jobs 8.37 ms a frame (submits 2.08, presents 0.20, others 6.09), idle 8.38; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 124.28 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); 575 captures at a CPU signal; the submits' waits read in 0.026 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 8.39 ms after its hand-over (17.22 at most)
[hos ModuleSystemWorker5] nvn: DrawMeshTasksIndirect: 140000 so far (x1 0x117991e000 x2 0x1 x3 0x117991e000 x4 0x4040)
[hos sead::MainThread] vk: capture: a submit 0.20 ms (lock 0.01, scan 0.04 over 464 ranges, 3797 MB), 448 pages written, 448 copied (1.7 MB)
[hos host] vk: a capture taken (ms): all 0.101; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.083, bytes copied 0.000; 25 kept (126 MB), 11 spare buffers, 22791 texture pages copied (89 MB)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 1221 dirty pages from their submits' captures, 51454 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): 5378 runs, 2044.9 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16318 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker4] nvn: CommandBufferWaitEvent #85000: event 0x100e64001c mode 0 value 61138 (now 61119) (lr 0x80295158)
[hos host] vk: queues ordered by their events: 30000 submissions stopped at a wait, 29984 went on once it was reached, 14 waits gone past; made to go by presents 0, releases 0, waits for the replay 0, 50 ms 1 (stopped 50.87 ms at most); waits met 85170, not met 0; captures at a CPU event's wait 2949, 0 of them at a wait met on arrival
[hos host] vk: replay reads of guest memory as submitted: 2960000 (1630017 pages from the captures)
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 537 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1068 dirty pages from their submits' captures, 50903 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): 5385 runs, 2046.3 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16323 in captures, 7 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 154433 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: mirror syncs (600 submits): 1030 dirty pages from their submits' captures, 52825 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): 5475 runs, 2110.1 MB compared; 43 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16887 in captures, 16 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 2980000 (1636900 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.24 ms (lock 0.01, scan 0.04 over 465 ranges, 3789 MB), 586 pages written, 586 copied (2.3 MB)
[hos Presentation Thread] vi: 4896 frames presented (59.0 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 10, 15.5-17.8 230, 17.8-22 52, 22-30 3, 30-40 0, over 40 0
[hos host] vk: a capture taken (ms): all 0.164; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.144, bytes copied 0.000; 25 kept (150 MB), 10 spare buffers, 23483 texture pages copied (91 MB)
[hos sead::MainThread] nvn: GPU waits in 5 s: 256 sync waits (375 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.17, writes collected 0.06
[hos host] vk: program picks: 4810227 kept (2033580 by the last picks' textures, a uniform buffer bound since), 2582 new, 1787190 with other textures (of 6600000)
[hos host] vk: readback pages refreshed from guest memory: 1957736 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 2 textures retired (2131 left, 2875 MB): budget 0, drawn over 0, dead targets 2
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 978 dirty pages from their submits' captures, 49910 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): 5295 runs, 1979.7 MB compared; 48 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 15795 in captures, 7 only in the collection, 29 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.50, present 0.21, draw 3.62, descriptors 1.43, texture lookups 0.13, uploads 0.05, pipelines 0.18, programs 0.63, commands 1.08, dispatch 0.74, memory sync 1.49, queue submit 0.67, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.81 MB synced in 1148.0 copies, 68.16 MB written back
[hos host] vk: 4920 presents, 56.5 fps; a frame: 1277 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.1 uploads (0.2 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2131 textures (2875 MB)
[hos host] vk: host time in GPU resource waits: 2.58 ms a frame (fences 0.04, timelines 2.54, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 498.2 full barriers recorded, 186.6 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.7 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.15 MB unswizzled on the CPU in 0.03 ms
[hos sead::MainThread] vk: readbacks of GPU results: 1537 of 3000 waited for their write-back, 0.16 ms each; 0 looked at the stopped queues first, 1 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: mirror syncs (600 submits): 880 dirty pages from their submits' captures, 51213 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): 5401 runs, 2045.1 MB compared; 45 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16360 in captures, 10 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3000000 (1643845 pages from the captures)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 165729 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: recorder: 5081955 packets run in 10.0 s (busy 1.40 s, spun idle 3.11 s, slept 4062 times, 1188 of them under 200 us), 0 calls made directly (no room); the replay waited for it 30701 times, 99.16 ms in all, the longest 0.10 ms; vkEndCommandBuffer 11700/59.25 ms (max 0.10), replay_mu unlock 7303/24.04 ms (max 0.10), vkResetDescriptorPool 11697/15.86 ms (max 0.06), vkQueueBindSparse 1/0.01 ms (max 0.01)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1021 dirty pages from their submits' captures, 53113 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): 5411 runs, 2045.3 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16954 in captures, 13 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos sead::MainThread] vk: capture: a submit 0.25 ms (lock 0.01, scan 0.04 over 464 ranges, 3783 MB), 585 pages written, 585 copied (2.3 MB)
[hos host] vk: a capture taken (ms): all 0.167; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.147, bytes copied 0.000; 25 kept (268 MB), 11 spare buffers, 11170 texture pages copied (43 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.18, writes collected 0.06
[hos sead::MainThread] nvn: EventSignal (CPU) #10000: event 0x1007db0004 mode 0 value 1 (lr 0x8348c78c)
[hos host] vk: replay reads of guest memory as submitted: 3020000 (1650748 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 1028 dirty pages from their submits' captures, 51211 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): 5573 runs, 2112.2 MB compared; 43 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16453 in captures, 12 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos AudioFrameworkThread] vcores: 303610 takes, 32449 waits (mean 29 us, longest 7.0 ms), 17391 kicks, 17405 yields, 0 starved grants, 0 escapes in 5 s
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #90000: event 0x100e640018 mode 0 value 64937 (now 64918) (lr 0x80295158)
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #65000: event 0x100e64002c mode 0 value 64999 (lr 0x80667688)
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 870 dirty pages from their submits' captures, 51550 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): 5434 runs, 2045.7 MB compared; 45 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16469 in captures, 7 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.44, present 0.21, draw 3.66, descriptors 1.49, texture lookups 0.21, uploads 0.14, pipelines 0.18, programs 0.62, commands 1.08, dispatch 0.74, memory sync 1.41, queue submit 0.63, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.81 MB synced in 1147.7 copies, 68.18 MB written back
[hos host] vk: 5040 presents, 57.2 fps; a frame: 1265 draws (0 skipped), 156 dispatches, 150 passes, 130 barriers, 6 submits, 0.2 uploads (0.4 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2139 textures (2884 MB)
[hos host] vk: host time in GPU resource waits: 2.36 ms a frame (fences 0.04, timelines 2.32, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 499.2 full barriers recorded, 186.3 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.6 ms a frame (the longest submission 4.4 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.33 MB unswizzled on the CPU in 0.06 ms
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 145706 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 4960778 kept (2101858 by the last picks' textures, a uniform buffer bound since), 2582 new, 1836639 with other textures (of 6800000)
[hos host] vk: 95 textures retired (2044 left, 2797 MB): budget 95, drawn over 0, dead targets 0
[hos host] vk: readback pages refreshed from guest memory: 2024727 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3040000 (1657626 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 1043 dirty pages from their submits' captures, 51247 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): 5412 runs, 2046.7 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16425 in captures, 7 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos Presentation Thread] vk: capture: a submit 0.23 ms (lock 0.02, scan 0.04 over 461 ranges, 3717 MB), 535 pages written, 535 copied (2.1 MB)
[hos host] vk: a capture taken (ms): all 0.140; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.121, bytes copied 0.000; 25 kept (126 MB), 9 spare buffers, 10275 texture pages copied (40 MB)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.17, writes collected 0.06
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1035 dirty pages from their submits' captures, 51477 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): 5405 runs, 2045.3 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16399 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: 1 textures retired (2044 left, 2798 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 3060000 (1664698 pages from the captures)
[hos ModuleSystemWorker3] vk: readbacks of GPU results: 1536 of 3000 waited for their write-back, 0.15 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: 7 textures retired (2040 left, 2798 MB): budget 7, drawn over 0, dead targets 0
[hos host] vk: 5 textures retired (2039 left, 2798 MB): budget 5, drawn over 0, dead targets 0
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 1049 dirty pages from their submits' captures, 52567 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): 5439 runs, 2109.4 MB compared; 43 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16894 in captures, 1 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 152926 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: render targets drawn over from another start, let go: 869 so far (2668 MB)
[hos host] vk: 6 textures retired (2038 left, 2796 MB): budget 6, drawn over 0, dead targets 0
[hos sead::MainThread] nvn: 750000 recordings made, 67420 live copies (17.9 MB), 753 texture copies; 3 command buffers' segments (4.1 MB)
[hos host] vk: replay reads of guest memory as submitted: 3080000 (1671329 pages from the captures)
[hos Presentation Thread] vk: capture: a submit 0.24 ms (lock 0.01, scan 0.04 over 462 ranges, 3729 MB), 573 pages written, 573 copied (2.2 MB)
[hos host] vk: a capture taken (ms): all 0.161; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.141, bytes copied 0.000; 25 kept (126 MB), 10 spare buffers, 13376 texture pages copied (52 MB)
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 934 dirty pages from their submits' captures, 51052 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): 5481 runs, 2047.1 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16304 in captures, 9 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: 13 textures retired (2031 left, 2798 MB): budget 13, drawn over 0, dead targets 0
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.41, present 0.19, draw 3.59, descriptors 1.50, texture lookups 0.29, uploads 0.19, pipelines 0.18, programs 0.61, commands 1.02, dispatch 0.73, memory sync 1.45, queue submit 0.64, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.79 MB synced in 1145.3 copies, 68.17 MB written back
[hos host] vk: 5160 presents, 57.2 fps; a frame: 1261 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.3 uploads (0.5 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2031 textures (2798 MB)
[hos host] vk: host time in GPU resource waits: 2.54 ms a frame (fences 0.04, timelines 2.51, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 497.8 full barriers recorded, 186.2 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.6 ms a frame (the longest submission 4.3 ms); 0.2 textures made a frame
[hos host] vk: a frame: 0.54 MB unswizzled on the CPU in 0.10 ms
[hos Presentation Thread] vi: 5181 frames presented (56.8 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 11, 15.5-17.8 175, 17.8-22 93, 22-30 6, 30-40 0, over 40 0
[hos sead::MainThread] nvn: GPU waits in 5 s: 204 sync waits (306 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: mirror syncs (600 submits): 948 dirty pages from their submits' captures, 51185 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): 5382 runs, 2046.3 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16328 in captures, 12 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: program picks: 5110865 kept (2169756 by the last picks' textures, a uniform buffer bound since), 2582 new, 1886552 with other textures (of 7000000)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.19, writes collected 0.06
[hos sead::MainThread] nvn: DrawMeshTasksIndirect: 160000 so far (x1 0x117991e000 x2 0x1 x3 0x117991e000 x4 0x4040)
[hos host] vk: 2 textures retired (2031 left, 2798 MB): budget 2, drawn over 0, dead targets 0
[hos host] vk: readback pages refreshed from guest memory: 2091972 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3100000 (1678038 pages from the captures)
[hos host] vk: 6 textures retired (2027 left, 2797 MB): budget 6, drawn over 0, dead targets 0
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 182783 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: sparse mirrors: 77, 977 MB with memory of 1348 MB (370 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1100 dirty pages from their submits' captures, 52586 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): 5541 runs, 2111.6 MB compared; 43 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16893 in captures, 16 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: 5 textures retired (2024 left, 2797 MB): budget 5, drawn over 0, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #95000: event 0x100e64001c mode 0 value 68738 (now 68719) (lr 0x80295158)
[hos host] vk: mirror of pool 0x7faac00000 (4 MB) given back: idle, 6014 submissions since its sync
[hos Presentation Thread] vk: capture: a submit 0.25 ms (lock 0.01, scan 0.04 over 463 ranges, 3737 MB), 596 pages written, 596 copied (2.3 MB)
[hos host] vk: a capture taken (ms): all 0.168; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.149, bytes copied 0.000; 25 kept (238 MB), 8 spare buffers, 11151 texture pages copied (43 MB)
[hos host] vk: mirror syncs (600 submits): 999 dirty pages from their submits' captures, 50927 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): 5384 runs, 2044.9 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16325 in captures, 1 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: replay reads of guest memory as submitted: 3120000 (1684663 pages from the captures)
[hos host] vk: 3 textures retired (2022 left, 2797 MB): budget 3, drawn over 0, dead targets 0
[hos sead::MainThread] vk: readbacks of GPU results: 1536 of 3000 waited for their write-back, 0.16 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 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 909 dirty pages from their submits' captures, 51617 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): 5383 runs, 2046.3 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16342 in captures, 9 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.48, present 0.21, draw 3.53, descriptors 1.47, texture lookups 0.25, uploads 0.16, pipelines 0.17, programs 0.59, commands 1.01, dispatch 0.73, memory sync 1.56, queue submit 0.65, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.79 MB synced in 1144.4 copies, 68.16 MB written back
[hos host] vk: 5280 presents, 56.7 fps; a frame: 1261 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.3 uploads (0.4 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2024 textures (2797 MB)
[hos host] vk: host time in GPU resource waits: 2.52 ms a frame (fences 0.04, timelines 2.48, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 497.6 full barriers recorded, 186.1 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.6 ms a frame (the longest submission 4.3 ms); 0.1 textures made a frame
[hos host] vk: a frame: 0.44 MB unswizzled on the CPU in 0.08 ms
[hos ModuleSystemWorker1] nvn: CommandBufferSignalEvent #70000: event 0x100e640038 mode 0 value 69999 (lr 0x8066189c)
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.18, writes collected 0.07
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 152482 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos ModuleSystemWorker4] vcores: 295775 takes, 33713 waits (mean 27 us, longest 7.4 ms), 17911 kicks, 17873 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: replay reads of guest memory as submitted: 3140000 (1691352 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 1037 dirty pages from their submits' captures, 51707 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): 5377 runs, 2044.9 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16881 in captures, 4 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: capture: a submit 0.23 ms (lock 0.02, scan 0.03 over 404 ranges, 2678 MB), 539 pages written, 539 copied (2.1 MB)
[hos host] vk: a capture taken (ms): all 0.136; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.118, bytes copied 0.000; 25 kept (242 MB), 6 spare buffers, 10306 texture pages copied (40 MB)
[hos host] vk: program picks: 5261101 kept (2237656 by the last picks' textures, a uniform buffer bound since), 2582 new, 1936316 with other textures (of 7200000)
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1021 dirty pages from their submits' captures, 52108 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): 5541 runs, 2111.6 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16321 in captures, 10 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: readback pages refreshed from guest memory: 2158690 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: replay reads of guest memory as submitted: 3160000 (1698002 pages from the captures)
[hos host] vk: mirror syncs (600 submits): 890 dirty pages from their submits' captures, 51153 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): 5395 runs, 2046.3 MB compared; 46 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16328 in captures, 13 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 156659 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 0.17, writes collected 0.05
[hos host] vk: memory: working set 12500 MB (peak 12786), private 20058 MB, staging 128 MB in 2 arenas
[hos host] vk: memory heaps: heap 0 (device): 110 blocks 5953 MB, 17873 allocations 4600 MB; used 6200 of 7250 MB; heap 1 (system): 15 blocks 784 MB, 39 allocations 722 MB; used 3087 of 15319 MB;
[hos host] vk: image blocks: 1 blocks 128 MB, 5 images 16 MB; 1 free ranges, the largest 111 MB
[hos host] vk: image blocks (render targets): 8 blocks 1024 MB, 133 images 496 MB; 44 free ranges, the largest 69 MB
[hos host] vk: image blocks (textures, compacted): 17 blocks 2176 MB, 1889 images 1774 MB; 795 free ranges, the largest 72 MB
[hos host] vk: render target images: 306 reused from the pool, 714 made new, 581 destroyed from it; it holds 0 (0 MB)
[hos host] vk: VRAM: 6200 MB used of 7250 MB allowed (1353 MB of it free in the blocks); textures 2797 MB (budget 4677 MB), 2024 textures
[hos host] vk: textures: decoded ASTC 1470 MB, rendered 546 MB (86 drawn in one frame, kept: 39147 KB), other 452 MB; used in the last 8 presents 1252 MB
[hos host] vk: 214 MB: 0x10a322a600 1365x1365x1 x90 levels 11 NVN 0x8e ASTC, last used 1 presents ago
[hos host] vk: 214 MB: 0x10a6aa2c00 1365x1365x1 x90 levels 11 NVN 0x80 ASTC, last used 1 presents ago
[hos host] vk: 64 MB: 0x11384dc000 4096x4096x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: 64 MB: 0x113db7d000 512x512x64 x1 levels 1 NVN 0x3d rendered, last used 1 presents ago
[hos host] vk: 37 MB: 0x1111b8de00 1800x1380x1 x8 levels 1 NVN 0x6, last used 1 presents ago
[hos host] vk: 27 MB: 0x1000408fc00 2200x2200x1 x3 levels 1 NVN 0x32 rendered, last used 1 presents ago
[hos host] vk: 27 MB: 0x100044b4400 2200x2200x1 x3 levels 1 NVN 0x32 rendered, last used 1941 presents ago
[hos host] vk: 21 MB: 0x10006910000 2400x2400x1 x1 levels 1 NVN 0x34 rendered, last used 1 presents ago
[hos host] vk: finalized textures the GPU drew once, kept for being made again: 23 (4047 KB): 260x260x1 NVN 0xd: 23 (4047 KB);
[hos Presentation Thread] vk: presents after the CPU's signal (600): 543 waited for it, 1.27 ms each, 0 let go after RX_VK_FRAME_GATE_MS
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1035 dirty pages from their submits' captures, 51005 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): 5379 runs, 2044.8 MB compared; 44 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16314 in captures, 5 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: status: 600 frames, the slowest 28.1 ms; VRAM 6.1 of 7.1 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: 55 program records loaded (150.7 ms), 2147 new graphics pipelines, pipelines from the driver's cache 633, from the start's cache 0, compiled 1658; 417743 draws and dispatches left out, 563 waits (106908.1 ms)
[hos host] vk: program loads at create (play): 5860 queued, 5860 loaded (median 0.95 ms, 99th percentile 12.50 ms, worst 29.47 ms, 12065 ms and 1280.2 MB read in all); 8098 programs (1360 of them compute variants without their code, 0 graphics programs no note names), 11 graphics pipelines (10277 not in a cache), 0 compute pipelines (707 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 3 pipelines made at create taken by draws; 3050 create calls with nothing kept for their stages, 0 before the index; units 8910 (5860 ready, 0 loading), 15494 programs alive
[hos host] vk: module identifiers (play): 752 known, 164 learned in this run; 0 compute pipelines made by them at a create call, 568 asked that way were in no cache (their code read, as before)
[hos host] vk: a frame: 130 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 7.77, present 0.18, draw 3.27, descriptors 1.24, texture lookups 0.07, uploads 0.01, pipelines 0.17, programs 0.58, commands 1.00, dispatch 0.70, memory sync 1.30, queue submit 0.59, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.78 MB synced in 1144.7 copies, 68.16 MB written back
[hos host] vk: 5400 presents, 58.7 fps; a frame: 1265 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.1 uploads (0.0 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 2024 textures (2797 MB)
[hos host] vk: host time in GPU resource waits: 2.29 ms a frame (fences 0.04, timelines 2.26, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 497.8 full barriers recorded, 186.3 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.7 ms a frame (the longest submission 4.3 ms); 0.0 textures made a frame
[hos host] vk: a frame: 0.03 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, 17.47 ms a frame): its jobs 9.08 ms a frame (submits 2.79, presents 0.21, others 6.09), idle 8.38; the game waited for room at 0 presents, 0.00 ms each (0.00 a frame; 117.98 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); 552 captures at a CPU signal; the submits' waits read in 0.026 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 9.11 ms after its hand-over (14.90 at most)
[hos host] vk: replay reads of guest memory as submitted: 3180000 (1704886 pages from the captures)
[hos host] vk: 3 textures retired (2025 left, 2798 MB): budget 3, drawn over 0, dead targets 0
[hos Presentation Thread] vk: capture: a submit 0.24 ms (lock 0.01, scan 0.03 over 400 ranges, 2672 MB), 588 pages written, 588 copied (2.3 MB)
[hos host] vk: a capture taken (ms): all 0.166; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.147, bytes copied 0.000; 25 kept (218 MB), 10 spare buffers, 11553 texture pages copied (45 MB)
[hos host] vk: 9 textures retired (2018 left, 2797 MB): budget 9, drawn over 0, dead targets 0
[hos ModuleSystemWorker3] nvn: CommandBufferWaitEvent #100000: event 0x100e640018 mode 0 value 72537 (now 72518) (lr 0x80295158)
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: mirror syncs (600 submits): 922 dirty pages from their submits' captures, 52114 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): 5374 runs, 2044.8 MB compared; 44 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16298 in captures, 3 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos sead::MainThread] vk: readbacks of GPU results: 1539 of 3000 waited for their write-back, 0.13 ms each; 0 looked at the stopped queues first, 0 waited for their submission's last part (guest memory read in place after theirs), 0 waited for their whole submission (their pages written in place, no mirror)
[hos host] vk: replay reads of guest memory as submitted: 3200000 (1711801 pages from the captures)
[hos host] vk: 10 textures retired (2010 left, 2797 MB): budget 10, drawn over 0, dead targets 0
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 922 dirty pages from their submits' captures, 52082 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): 5545 runs, 2111.6 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16836 in captures, 8 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos rmbl::VibrationThread] hid: 45056 vibration values, strongest 0.00 since the last count
[hos Presentation Thread] vi: 5469 frames presented (57.6 fps over the last 5.0 s, interval 1)
[hos Presentation Thread] vi: present intervals: <15.5 ms 18, 15.5-17.8 167, 17.8-22 97, 22-30 6, 30-40 0, over 40 0
[hos host] vk: 14 textures retired (2000 left, 2793 MB): budget 14, drawn over 0, dead targets 0
[hos sead::MainThread] nvn: GPU waits in 5 s: 205 sync waits (334 ms), 0 polls timed out (0 ms), 0 queue finishes (0 ms)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 178733 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: program picks: 5410786 kept (2305498 by the last picks' textures, a uniform buffer bound since), 2582 new, 1986631 with other textures (of 7400000)
[hos host] vk: mirror syncs (600 submits): 981 dirty pages from their submits' captures, 51502 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): 5379 runs, 2044.9 MB compared; 42 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16302 in captures, 5 only in the collection, 30 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 0.22, writes collected 0.05
[hos sead::MainThread] vk: capture: a submit 0.26 ms (lock 0.01, scan 0.03 over 397 ranges, 2678 MB), 617 pages written, 617 copied (2.4 MB)
[hos host] vk: a capture taken (ms): all 0.185; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.164, bytes copied 0.000; 25 kept (246 MB), 6 spare buffers, 13161 texture pages copied (51 MB)
[hos host] vk: readback pages refreshed from guest memory: 2225768 pages so far (0 held: may be written ahead in their submission)
[hos host] vk: 3 textures retired (1999 left, 2797 MB): budget 3, drawn over 0, dead targets 0
[hos host] vk: replay reads of guest memory as submitted: 3220000 (1718701 pages from the captures)
[hos host] vk: texture 0x110a420200 600x1528x1 x3 levels 1 NVN 0x50 -> vk 143 (2000 textures, 2799 MB)
[hos host] vk: 6 textures retired (1994 left, 2796 MB): budget 6, drawn over 0, dead targets 0
[hos host] vk: a frame: 131 draws kept their neighbour's descriptors (0 of them through other slots' registrations)
[hos host] vk: a frame: 0.0 draws left out (not ready), 0.00 waits for shaders or pipelines (0.0 ms); translation 0 ms in all, 0 jobs queued
[hos host] vk: a frame's replay time (ms): submit 8.48, present 0.19, draw 3.72, descriptors 1.69, texture lookups 0.50, uploads 0.41, pipelines 0.17, programs 0.59, commands 1.00, dispatch 0.71, memory sync 1.59, queue submit 0.59, slot wait 0.06
[hos host] vk: a frame: mirrors 251 (977 MB): 6.79 MB synced in 1145.8 copies, 68.16 MB written back
[hos host] vk: 5520 presents, 56.5 fps; a frame: 1261 draws (0 skipped), 155 dispatches, 151 passes, 130 barriers, 6 submits, 0.3 uploads (1.1 MB), 80 ub updates (56 overlays), GPU-bound wait 0.1 ms (recording slots only); 2302 pipelines (672652 ms), 0 programs (0 failed), 1994 textures (2796 MB)
[hos host] vk: host time in GPU resource waits: 2.56 ms a frame (fences 0.04, timelines 2.52, idle 0.00, queries 0.00; sum across threads, not frame time; excludes pacing and driver submit/present blocking)
[hos host] vk: a frame: 497.4 full barriers recorded, 186.1 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: 29.0; 0x12: 68.5; 0x13: 2.0; 0x21: 4.0; 0x28: 16.0; 0x92: 3.0; 0x97: 1.0;
[hos host] vk: GPU time 11.6 ms a frame (the longest submission 4.3 ms); 0.1 textures made a frame
[hos host] vk: a frame: 1.06 MB unswizzled on the CPU in 0.20 ms
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1033 dirty pages from their submits' captures, 50766 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): 5388 runs, 2046.3 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16334 in captures, 8 only in the collection, 31 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos host] vk: recorder: 4920229 packets run in 10.0 s (busy 1.35 s, spun idle 2.96 s, slept 4322 times, 1243 of them under 200 us), 0 calls made directly (no room); the replay waited for it 29752 times, 95.61 ms in all, the longest 0.14 ms; vkEndCommandBuffer 11339/56.09 ms (max 0.08), replay_mu unlock 7075/23.43 ms (max 0.13), vkResetDescriptorPool 11338/16.10 ms (max 0.14)
[hos host] vk: 1 textures retired (1994 left, 2798 MB): budget 1, drawn over 0, dead targets 0
[hos host] vk: mirror syncs (600 submits): 965 dirty pages from their submits' captures, 52828 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): 5443 runs, 2109.5 MB compared; 43 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16875 in captures, 11 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos ModuleSystemWorker3] nvn: CommandBufferSignalEvent #75000: event 0x100e640044 mode 0 value 74999 (lr 0x802742f0)
[hos host] vk: shadow staging (600 takes): 0 shadow copies from staging, 184280 from the capture buffer; capture buffers: 600 host-cached, 0 not (write-combined: staged)
[hos host] vk: replay reads of guest memory as submitted: 3240000 (1725570 pages from the captures)
[hos host] vk: (its written part: 0 of 0 KB readable, 338 bytes not zero; levels L0)
[hos host] vk: texture 0x1111b8de00 1800x1380x1 x8 levels 1 NVN 0x6 (39444 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 0 KB of it
[hos host] vk: (its written part: 0 of 0 KB readable, 338 bytes not zero; levels L0)
[hos host] vk: texture 0x1111b8de00 1800x1380x1 x8 levels 1 NVN 0x6 (39444 KB of storage) re-uploaded (its memory was written; flags 0x4): what the CPU wrote, 0 KB of it
[hos host] vk: the recording streams: 48 of 2 MB, the most one held 620 KB; 0 made on demand (0 MB kept now); c1 stages: at most 97 a recording; 0 descriptor pools made when a recording's own ran out
[hos host] vk: sparse mirrors: 76, 977 MB with memory of 1344 MB (366 MB spared); blocks given memory later 7943, given back 12986; bindings served from guest memory meanwhile 0 (0 reaching blocks with memory too), from the mirror past every game pool 0; 538 binds (138.1 ms); 0 made whole for want of memory
[hos host] vk: mirror syncs (600 submits): 1292 dirty pages from their submits' captures, 50973 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): 5479 runs, 2047.1 MB compared; 41 pages read into the shadows; 380 MB of shadows; pages the shadows knew that the CPU wrote: 16298 in captures, 0 only in the collection, 30 only by the replay itself
[hos host] vk: read live, by pool:
[hos host] vk: imports: 170 live (2216 MB), 0 retired still imported (0 MB), 47 retired given back (1112 MB)
[hos Presentation Thread] vk: capture: a submit 0.23 ms (lock 0.01, scan 0.03 over 398 ranges, 2712 MB), 537 pages written, 537 copied (2.1 MB)
[hos host] vk: a capture taken (ms): all 0.145; GPU wait for late pages 0.000 (0 of 600 takes), pools lock 0.000, retires and stamps 0.126, bytes copied 0.000; 25 kept (176 MB), 9 spare buffers, 13649 texture pages copied (53 MB)
[hos ModuleSystemWorker4] nvn: DrawMeshTasksIndirect: 180000 so far (x1 0x117da3c000 x2 0 x3 0x117da3c000 x4 0x230040)
[hos host] vk: queues ordered by their events: 36000 submissions stopped at a wait, 35985 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 50.87 ms at most); waits met 104105, not met 0; captures at a CPU event's wait 3648, 0 of them at a wait met on arrival
[hos ModuleSystemWorker3] vcores: 286647 takes, 31635 waits (mean 30 us, longest 15.0 ms), 16906 kicks, 16864 yields, 0 starved grants, 0 escapes in 5 s
[hos host] vk: a submit's memory work (ms): maps 0.00, capture taken 0.16, writes collected 0.05
[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: 55 program records loaded (150.7 ms), 2147 new graphics pipelines, pipelines from the driver's cache 633, from the start's cache 0, compiled 1658; 417743 draws and dispatches left out, 563 waits (106908.1 ms)
[hos host] vk: program loads at create (close): 5860 queued, 5860 loaded (median 0.95 ms, 99th percentile 12.50 ms, worst 29.47 ms, 12065 ms and 1280.2 MB read in all); 8098 programs (1360 of them compute variants without their code, 0 graphics programs no note names), 11 graphics pipelines (10277 not in a cache), 0 compute pipelines (707 not in a cache); a first use ran 0 itself and waited for 0 (0.0 ms); 3 pipelines made at create taken by draws; 3050 create calls with nothing kept for their stages, 0 before the index; units 8910 (5860 ready, 0 loading), 15494 programs alive
[hos host] vk: module identifiers (close): 752 known, 164 learned in this run; 0 compute pipelines made by them at a create call, 568 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 (4304 pools in the table now)
[hos host] control: exiting
[hos host] stop: close work done (the game's saves are not waited for)