feat(vk): FPS counter Breakdown in the graph: the frame's parts, the render thread's lane, the game's waits by cause #928

Merged
HumanBean merged 1 commit from ballotstomper/Longshot:feat/fps-breakdown-lanes into main 2026-11-15 21:10:24 +00:00
Contributor

Type: feat · Risk: low · Tested on: Linux, RX 6750 XT · Needs: Windows, any GPU

Why

The FPS counter's Breakdown level showed a single bar of Game / Renderer / GPU wait / Pacing beside the graph. It didn't say what the game was waiting on, it didn't show that the GPU and the render thread run in parallel with the frame, and with Threaded rendering on, the render thread (often the real limit) didn't show at all. When you're chasing a stutter or a low frame rate, you couldn't tell from the counter whether the game, the render thread or the GPU was holding the frame. The 1% low was also shown as a frame rate next to a frame time, so the two numbers didn't compare.

No issue asks for this. Related: #562 adds a System level after Dev to the same counter. It's a separate level, not an overlap, but both change draw_fps, fps_stats.h and the language counts in gpu/vk/menu_i18n.h, so whichever lands second redoes those lines.

What changed

The Breakdown now draws each frame's parts stacked in the graph's own columns, so you can see over the last 4 seconds where each frame's time went. The waits are split by what the game was waiting on. With Threaded rendering on, a lane under the graph shows the render thread's own frame on the same scale. Dev also shows the CPU, GPU and driver, so screenshots and recordings say what they ran on.

  • Measuring: gpu/vk/vk_fps.cpp/.h, gpu/vk/fps_stats.h
    • A frame's parts are Game, Renderer, and the waits under "Waiting on": Render thread, GPU fence and GPU present. Then Pacing. They add up to the frame time.
    • FpsFenceWait in wait() (gpu/vk/vk_replay.cpp) sorts a game fence wait by whether its work was already recorded. Recorded work is a wait on the GPU; unrecorded work is a wait on the render thread. A fence wait on another thread is carved out of Game.
    • FpsRtWait times the render thread: recording, waiting for the parallel replay's workers, waiting for a GPU slot, and idle. It only runs on the render thread, and only at the Breakdown level.
    • columns() uses fixed time slots and returns a sub-slot scroll, so the graph moves smoothly instead of jumping a column at a time.
    • The 1% low is now a frame time: "1% low 20.1 ms".
  • Drawing: draw_fps in gpu/vk/vk_menu.cpp
    • Stacked parts with the green frame-time line on top. The scale goes up at once and comes down slowly.
    • The render-thread lane has its own ms scale and labels. It's hidden when there is no render thread (Threaded rendering off).
    • The legend groups what adds up to the frame time, then "Render thread / in parallel", then "GPU / in parallel" (GPU time and its share of the frame).
    • Colours stay in families: blue for the game's work, red for the GPU, purple for the render thread, grey for pacing and idle.
    • Dev adds three lines under the frame time: the CPU (bug_report::cpu_name(), the cpuid code the bug report already used, now its own function), the GPU (device_name_text()) and the driver (driver_text()). The CPU and GPU names drop their (R)/(TM) marks, clock speed, core count and a trailing driver note in brackets. A line too long for the column is cut with "...".
  • Text:
    • The FPS counter row's help is updated for the Breakdown, Dev and the 1% low, translated in all 13 languages (gpu/vk/menu_i18n.h).
    • The new legend labels are English only for now.
    • The README's FPS counter section is updated.
  • Checks: tests/test_fps_stats.cpp expects the new 1% low text.

Measurements

Verdict: no cost with the counter off. At Breakdown, the PR is within run-to-run noise of main's Breakdown (≤ 1 fps a segment). A profiled run puts the whole counter, drawing included, at 0.01% of samples.

Hardware: Arch Linux (kernel 7.3.4), RX 6750 XT 12 GB, Mesa 26.2.7 (RADV), Ryzen 5 5600X, 16 GB
Scene: Castle Town Market at noon as a child (the crowd), 2560x1440 output, fixed render resolution, no upscaler or frame generation, Uncapped, V-Sync off
Method: a scripted run in game frames (each run goes through the same game states frame for frame): stand 6 s, camera turned right and back 8 s, walk 8 s of game time. The FPS counter was Off (fps_counter=0) or at Breakdown (fps_counter=4). Main and the PR were interleaved after a warm-up run: main, PR, main, PR, with the game rebuilt before each build's runs. Each segment's fps, 2 runs each (the mean of the two).
How to reproduce: a scripted runner on the game's control bridge (HOS_CONTROL): teleport to the market at noon, then the steps above, with the counter level set in longshot_options.ini before each run.

The PR column was measured at 8136d7f7. After it, the PR changed only text (help, labels, README), the Dev level's three lines, and a rebase onto the new main. None of that runs below the Dev level.

fps Before: main @ f637b42d, counter Off After: this PR @ 8136d7f7, counter Off Before: main @ f637b42d, Breakdown After: this PR @ 8136d7f7, Breakdown
stand 33.2 (32.4, 34.0) 34.0 (one run) 34.2 (34.0, 34.4) 33.4 (32.9, 33.9)
camera 35.3 (35.6, 35.0) 35.5 (one run) 34.8 (33.9, 35.6) 34.7 (34.1, 35.2)
walk 31.0 (30.3, 31.6) 31.2 (one run) 31.7 (31.4, 32.0) 31.1 (30.7, 31.4)
walk p99 ms 44.6 (45.9, 43.3) 46.0 (one run) 46.8 (46.3, 47.3) 47.4 (47.6, 47.2)

The PR's second counter-off run doesn't count: it sat on a loading screen at an uncapped ~230 fps and never reached the market ("FAILED teleport" below).

segment             secs  CPU%  GPU%    fps  p99ms
main off 1   stand: Market 11.1 38.8 70.7 32.4 42.5 | camera: Market 13.5 33.1 69.3 35.6 40.9 | walk: Market 17.0 39.3 69.5 30.3 45.9
main off 2   stand: Market 10.6 35.6 71.4 34.0 41.7 | camera: Market 13.7 30.8 69.3 35.0 43.4 | walk: Market 16.2 34.8 69.4 31.6 43.3
PR off 1     stand: Market 10.6 36.1 70.6 34.0 42.4 | camera: Market 13.5 33.0 67.8 35.5 42.5 | walk: Market 16.4 35.1 69.7 31.2 46.0
PR off 2     FAILED teleport: Market 15.0 47.4 29.4 223.5 12.7 (a loading screen, not counted)
main on 1    stand: Market 10.6 37.7 70.9 34.0 42.6 | camera: Market 14.2 38.1 67.7 33.9 45.6 | walk: Market 16.3 36.2 69.1 31.4 46.3
main on 2    stand: Market 10.5 36.0 71.2 34.4 40.6 | camera: Market 13.5 35.6 68.2 35.6 42.7 | walk: Market 15.9 36.1 71.0 32.0 47.3
PR on 1      stand: Market 11.0 35.6 70.1 32.9 42.6 | camera: Market 14.1 36.5 69.3 34.1 44.0 | walk: Market 16.6 35.0 69.3 30.7 47.6
PR on 2      stand: Market 10.6 38.2 70.5 33.9 43.2 | camera: Market 13.7 36.3 68.3 35.2 44.9 | walk: Market 16.4 35.2 69.9 31.4 47.2

Flags and settings

No switch, ini key or build flag is added. One menu row changes what its levels show; its values, default and key stay the same.

Flag What it is Before this PR After this PR Effect Helps / doesn't help / untested Recommendation
FPS counter (fps_counter=) the FPS counter's level: Off, FPS, Frame time, Graph, Breakdown, Dev Off; Breakdown a bar of four parts beside the graph; 1% low as fps Off; Breakdown the parts stacked in the graph, the render thread's lane, the waits by cause; Dev adds the CPU, GPU and driver; 1% low in ms only the counter's drawing, and its measuring at Breakdown and up helps: shows what holds a frame default stays Off

Testing

Tested:

  • In the game, on Linux (RX 6750 XT, Mesa 26.2.7): every FPS counter level with Threaded rendering on and off.
    • The graph's stacked parts and the legend's values add up to the frame time.
    • The render-thread lane shows only with Threaded rendering on.
    • The CPU, GPU and driver lines show at Dev only.
  • python -I -B tests/run_all.py: 536 passed, 18 failed, 75 skipped. The failures are test_appimage_player_build, test_bake_portability, test_crash_dialog, test_crash_record, test_crt_options, test_env_on, test_lift_cleanup_error, test_linux_preflight, test_linux_update, test_make_game_cache, test_missing_nup, test_mods_size_table, test_options_budget_once, test_pipeline_tour, test_readback_late, test_vk_occlusion_queries, test_vk_pgo and test_walk_key.
    • All of them fail without this PR on this PC.
    • test_readback_late and test_vk_occlusion_queries read files this PR changes, so I ran them on main's tree too: same failures.
    • test_crash_record passes when run alone; its forced-kill timing cases fail only in the parallel full run.

Not tested:

  • Windows. I'm on Linux; the change is the same code on both, apart from the CPU name, which uses the bug report's existing Windows cpuid path.
  • NVIDIA and Intel GPUs: the GPU-name shortening was only checked with sample names in a small test program.

Must be tested:

  • Windows, any GPU (by hand): set the FPS counter to Breakdown, then Dev, with Threaded rendering on and off.
    • Expect the stacked graph, the render-thread lane only with Threaded rendering on, and the legend inside the column.
    • At Dev, expect three lines under the frame time: the CPU, the GPU and the driver, each in one line.

Risks

What could break: the FPS counter's drawing at Breakdown and Dev: a legend running past the column, or a lane on the wrong scale. The measuring adds a clock read around fence waits and the render thread's waits, only at the Breakdown level and above. The new legend labels are untranslated in the other 12 languages.

Turning it off: set the FPS counter below Breakdown, or revert the commit.

Compatibility: Nothing changes: no new options-file key, no cache or ABI change.

Checklist

Everyone

  • One topic.
  • The title is a Conventional Commit (type(scope): description) of the status line's type.
  • Why gives the reason plainly and links the issues that fit (the tracker searched).
  • Measurements has a verdict, or one line saying why there is nothing to measure.
  • Testing names what was tested, what wasn't, and what must still be tested, where and how.
  • Rebased on current main.
  • python -I -B tests/run_all.py passes (any failure that also fails on main is named).
  • No game files, dumps, build output or generated files.
  • third_party/ untouched (a new folder with a PROVENANCE.md instead).
  • The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled.

When it applies

  • Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported. (Not yet: the PR's counter-off case has one valid run, and with 2 runs a side the table gives their mean.)
  • Screenshots of the same spot, captioned like the Measurements columns, for a change that shows on screen. (Not yet: the final build at Dev is in the comments, but the Breakdown before/after shots were taken before "Renderer" was restored; a matching pair of the final build at the same spot is to follow.)
  • A check under tests/ that reads changed source updated in this PR, not weakened.
  • Host code builds on both Windows (llvm-mingw) and Linux, with UTF-8 paths. (Linux builds and runs; the Windows build is the Must be tested item above.)
  • Docs updated.
**Type:** feat · **Risk:** low · **Tested on:** Linux, RX 6750 XT · **Needs:** Windows, any GPU ## Why The FPS counter's Breakdown level showed a single bar of Game / Renderer / GPU wait / Pacing beside the graph. It didn't say what the game was waiting on, it didn't show that the GPU and the render thread run in parallel with the frame, and with Threaded rendering on, the render thread (often the real limit) didn't show at all. When you're chasing a stutter or a low frame rate, you couldn't tell from the counter whether the game, the render thread or the GPU was holding the frame. The 1% low was also shown as a frame rate next to a frame time, so the two numbers didn't compare. No issue asks for this. Related: #562 adds a System level after Dev to the same counter. It's a separate level, not an overlap, but both change `draw_fps`, `fps_stats.h` and the language counts in `gpu/vk/menu_i18n.h`, so whichever lands second redoes those lines. ## What changed The Breakdown now draws each frame's parts stacked in the graph's own columns, so you can see over the last 4 seconds where each frame's time went. The waits are split by what the game was waiting on. With Threaded rendering on, a lane under the graph shows the render thread's own frame on the same scale. Dev also shows the CPU, GPU and driver, so screenshots and recordings say what they ran on. - **Measuring:** `gpu/vk/vk_fps.cpp/.h`, `gpu/vk/fps_stats.h` - A frame's parts are Game, Renderer, and the waits under "Waiting on": Render thread, GPU fence and GPU present. Then Pacing. They add up to the frame time. - `FpsFenceWait` in `wait()` (`gpu/vk/vk_replay.cpp`) sorts a game fence wait by whether its work was already recorded. Recorded work is a wait on the GPU; unrecorded work is a wait on the render thread. A fence wait on another thread is carved out of Game. - `FpsRtWait` times the render thread: recording, waiting for the parallel replay's workers, waiting for a GPU slot, and idle. It only runs on the render thread, and only at the Breakdown level. - `columns()` uses fixed time slots and returns a sub-slot scroll, so the graph moves smoothly instead of jumping a column at a time. - The 1% low is now a frame time: "1% low 20.1 ms". - **Drawing:** `draw_fps` in `gpu/vk/vk_menu.cpp` - Stacked parts with the green frame-time line on top. The scale goes up at once and comes down slowly. - The render-thread lane has its own ms scale and labels. It's hidden when there is no render thread (Threaded rendering off). - The legend groups what adds up to the frame time, then "Render thread / in parallel", then "GPU / in parallel" (GPU time and its share of the frame). - Colours stay in families: blue for the game's work, red for the GPU, purple for the render thread, grey for pacing and idle. - Dev adds three lines under the frame time: the CPU (`bug_report::cpu_name()`, the cpuid code the bug report already used, now its own function), the GPU (`device_name_text()`) and the driver (`driver_text()`). The CPU and GPU names drop their (R)/(TM) marks, clock speed, core count and a trailing driver note in brackets. A line too long for the column is cut with "...". - **Text:** - The FPS counter row's help is updated for the Breakdown, Dev and the 1% low, translated in all 13 languages (`gpu/vk/menu_i18n.h`). - The new legend labels are English only for now. - The README's FPS counter section is updated. - **Checks:** `tests/test_fps_stats.cpp` expects the new 1% low text. ## Measurements **Verdict:** no cost with the counter off. At Breakdown, the PR is within run-to-run noise of main's Breakdown (≤ 1 fps a segment). A profiled run puts the whole counter, drawing included, at 0.01% of samples. Hardware: Arch Linux (kernel 7.3.4), RX 6750 XT 12 GB, Mesa 26.2.7 (RADV), Ryzen 5 5600X, 16 GB Scene: Castle Town Market at noon as a child (the crowd), 2560x1440 output, fixed render resolution, no upscaler or frame generation, Uncapped, V-Sync off Method: a scripted run in game frames (each run goes through the same game states frame for frame): stand 6 s, camera turned right and back 8 s, walk 8 s of game time. The FPS counter was Off (`fps_counter=0`) or at Breakdown (`fps_counter=4`). Main and the PR were interleaved after a warm-up run: main, PR, main, PR, with the game rebuilt before each build's runs. Each segment's fps, 2 runs each (the mean of the two). How to reproduce: a scripted runner on the game's control bridge (`HOS_CONTROL`): teleport to the market at noon, then the steps above, with the counter level set in `longshot_options.ini` before each run. The PR column was measured at 8136d7f7. After it, the PR changed only text (help, labels, README), the Dev level's three lines, and a rebase onto the new main. None of that runs below the Dev level. | fps | Before: main @ f637b42d, counter Off | After: this PR @ 8136d7f7, counter Off | Before: main @ f637b42d, Breakdown | After: this PR @ 8136d7f7, Breakdown | |---|---|---|---|---| | stand | 33.2 (32.4, 34.0) | 34.0 (one run) | 34.2 (34.0, 34.4) | 33.4 (32.9, 33.9) | | camera | 35.3 (35.6, 35.0) | 35.5 (one run) | 34.8 (33.9, 35.6) | 34.7 (34.1, 35.2) | | walk | 31.0 (30.3, 31.6) | 31.2 (one run) | 31.7 (31.4, 32.0) | 31.1 (30.7, 31.4) | | walk p99 ms | 44.6 (45.9, 43.3) | 46.0 (one run) | 46.8 (46.3, 47.3) | 47.4 (47.6, 47.2) | The PR's second counter-off run doesn't count: it sat on a loading screen at an uncapped ~230 fps and never reached the market ("FAILED teleport" below). ``` segment secs CPU% GPU% fps p99ms main off 1 stand: Market 11.1 38.8 70.7 32.4 42.5 | camera: Market 13.5 33.1 69.3 35.6 40.9 | walk: Market 17.0 39.3 69.5 30.3 45.9 main off 2 stand: Market 10.6 35.6 71.4 34.0 41.7 | camera: Market 13.7 30.8 69.3 35.0 43.4 | walk: Market 16.2 34.8 69.4 31.6 43.3 PR off 1 stand: Market 10.6 36.1 70.6 34.0 42.4 | camera: Market 13.5 33.0 67.8 35.5 42.5 | walk: Market 16.4 35.1 69.7 31.2 46.0 PR off 2 FAILED teleport: Market 15.0 47.4 29.4 223.5 12.7 (a loading screen, not counted) main on 1 stand: Market 10.6 37.7 70.9 34.0 42.6 | camera: Market 14.2 38.1 67.7 33.9 45.6 | walk: Market 16.3 36.2 69.1 31.4 46.3 main on 2 stand: Market 10.5 36.0 71.2 34.4 40.6 | camera: Market 13.5 35.6 68.2 35.6 42.7 | walk: Market 15.9 36.1 71.0 32.0 47.3 PR on 1 stand: Market 11.0 35.6 70.1 32.9 42.6 | camera: Market 14.1 36.5 69.3 34.1 44.0 | walk: Market 16.6 35.0 69.3 30.7 47.6 PR on 2 stand: Market 10.6 38.2 70.5 33.9 43.2 | camera: Market 13.7 36.3 68.3 35.2 44.9 | walk: Market 16.4 35.2 69.9 31.4 47.2 ``` ### Flags and settings No switch, ini key or build flag is added. One menu row changes what its levels show; its values, default and key stay the same. | Flag | What it is | Before this PR | After this PR | Effect | Helps / doesn't help / untested | Recommendation | |---|---|---|---|---|---|---| | FPS counter (`fps_counter=`) | the FPS counter's level: Off, FPS, Frame time, Graph, Breakdown, Dev | Off; Breakdown a bar of four parts beside the graph; 1% low as fps | Off; Breakdown the parts stacked in the graph, the render thread's lane, the waits by cause; Dev adds the CPU, GPU and driver; 1% low in ms | only the counter's drawing, and its measuring at Breakdown and up | helps: shows what holds a frame | default stays Off | ## Testing **Tested:** - In the game, on Linux (RX 6750 XT, Mesa 26.2.7): every FPS counter level with Threaded rendering on and off. - The graph's stacked parts and the legend's values add up to the frame time. - The render-thread lane shows only with Threaded rendering on. - The CPU, GPU and driver lines show at Dev only. - `python -I -B tests/run_all.py`: 536 passed, 18 failed, 75 skipped. The failures are `test_appimage_player_build`, `test_bake_portability`, `test_crash_dialog`, `test_crash_record`, `test_crt_options`, `test_env_on`, `test_lift_cleanup_error`, `test_linux_preflight`, `test_linux_update`, `test_make_game_cache`, `test_missing_nup`, `test_mods_size_table`, `test_options_budget_once`, `test_pipeline_tour`, `test_readback_late`, `test_vk_occlusion_queries`, `test_vk_pgo` and `test_walk_key`. - All of them fail without this PR on this PC. - `test_readback_late` and `test_vk_occlusion_queries` read files this PR changes, so I ran them on main's tree too: same failures. - `test_crash_record` passes when run alone; its forced-kill timing cases fail only in the parallel full run. **Not tested:** - Windows. I'm on Linux; the change is the same code on both, apart from the CPU name, which uses the bug report's existing Windows cpuid path. - NVIDIA and Intel GPUs: the GPU-name shortening was only checked with sample names in a small test program. **Must be tested:** - Windows, any GPU (by hand): set the FPS counter to Breakdown, then Dev, with Threaded rendering on and off. - Expect the stacked graph, the render-thread lane only with Threaded rendering on, and the legend inside the column. - At Dev, expect three lines under the frame time: the CPU, the GPU and the driver, each in one line. ## Risks **What could break:** the FPS counter's drawing at Breakdown and Dev: a legend running past the column, or a lane on the wrong scale. The measuring adds a clock read around fence waits and the render thread's waits, only at the Breakdown level and above. The new legend labels are untranslated in the other 12 languages. **Turning it off:** set the FPS counter below Breakdown, or revert the commit. **Compatibility:** Nothing changes: no new options-file key, no cache or ABI change. ## Checklist ### Everyone - [x] One topic. - [x] The title is a Conventional Commit (`type(scope): description`) of the status line's type. - [x] Why gives the reason plainly and links the issues that fit (the tracker searched). - [x] Measurements has a verdict, or one line saying why there is nothing to measure. - [x] Testing names what was tested, what wasn't, and what must still be tested, where and how. - [x] Rebased on current `main`. - [x] `python -I -B tests/run_all.py` passes (any failure that also fails on `main` is named). - [x] No game files, dumps, build output or generated files. - [x] `third_party/` untouched (a new folder with a `PROVENANCE.md` instead). - [x] The license is OK: GPL-3.0-or-later, nothing incompatible and nothing decompiled. ### When it applies - [ ] Numbers from the same PC, scene and settings, at least 2 interleaved runs each, the median reported. (Not yet: the PR's counter-off case has one valid run, and with 2 runs a side the table gives their mean.) - [ ] Screenshots of the same spot, captioned like the Measurements columns, for a change that shows on screen. (Not yet: the final build at Dev is in the comments, but the Breakdown before/after shots were taken before "Renderer" was restored; a matching pair of the final build at the same spot is to follow.) - [x] A check under `tests/` that reads changed source updated in this PR, not weakened. - [ ] Host code builds on both Windows (llvm-mingw) and Linux, with UTF-8 paths. (Linux builds and runs; the Windows build is the Must be tested item above.) - [x] Docs updated.
feat(vk): FPS counter Breakdown in the graph: the frame's parts, the render thread's lane, the game's waits by cause
Some checks failed
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
Website / Website on Cloudflare (pull_request_target) Has been skipped
PR description / Description follows the template (pull_request_target) Failing after 4s
2db129e093
Author
Contributor

Tested in game: RX 6750 XT, Mesa 26.2.7, Arch Linux: every FPS counter level with Threaded rendering on and off. The stacked graph, the legend and the render-thread lane (only with threading on) looked correct, and the CPU/GPU/driver lines showed only at Dev.

Tested in game: RX 6750 XT, Mesa 26.2.7, Arch Linux: every FPS counter level with Threaded rendering on and off. The stacked graph, the legend and the render-thread lane (only with threading on) looked correct, and the CPU/GPU/driver lines showed only at Dev.
Author
Contributor

Screenshots, Linux, RX 6750 XT, Breakdown level. These are from before the last changes: the after shots still read "Submit", now "Renderer" again, and don't show the Dev lines. New ones of the final build will follow.

Before: main, Breakdown
main, Breakdown

After: this PR, Breakdown, Threaded rendering off (no render-thread lane)
this PR, Breakdown, threading off

After: this PR, Breakdown, Threaded rendering on (the render-thread lane under the graph)
this PR, Breakdown, threading on

Screenshots, Linux, RX 6750 XT, Breakdown level. These are from before the last changes: the after shots still read "Submit", now "Renderer" again, and don't show the Dev lines. New ones of the final build will follow. Before: main, Breakdown ![main, Breakdown](https://git.magicbean.dev/attachments/0aacdf9a-fe90-4f0b-87a6-fe9a61bbe581) After: this PR, Breakdown, Threaded rendering off (no render-thread lane) ![this PR, Breakdown, threading off](https://git.magicbean.dev/attachments/de6f6159-9b4b-4fef-bf93-932621807f9f) After: this PR, Breakdown, Threaded rendering on (the render-thread lane under the graph) ![this PR, Breakdown, threading on](https://git.magicbean.dev/attachments/1ccdf244-0954-4d8a-ba68-0973ec5850d5)
Author
Contributor

The final build (2db129e0) at the Dev level, Linux, RX 6750 XT, Threaded rendering on: the CPU, GPU and driver lines under the frame time, "Renderer" back in the legend, the render-thread lane under the graph.

this PR @ 2db129e0, Dev, threading on

The final build (2db129e0) at the Dev level, Linux, RX 6750 XT, Threaded rendering on: the CPU, GPU and driver lines under the frame time, "Renderer" back in the legend, the render-thread lane under the graph. ![this PR @ 2db129e0, Dev, threading on](https://git.magicbean.dev/attachments/0e321a21-787a-4c54-b3f8-5d2f89422cae)
new.webp
27 KiB
Author
Contributor

Description: the screenshot box now notes the Dev screenshot of the final build; a matching Breakdown pair at the same spot is still to come.

Description: the screenshot box now notes the Dev screenshot of the final build; a matching Breakdown pair at the same spot is still to come.
HumanBean changed title from WIP: feat(vk): FPS counter Breakdown in the graph: the frame's parts, the render thread's lane, the game's waits by cause to feat(vk): FPS counter Breakdown in the graph: the frame's parts, the render thread's lane, the game's waits by cause 2026-11-15 21:10:17 +00:00
HumanBean deleted branch feat/fps-breakdown-lanes 2026-11-15 21:10:24 +00:00
Some checks failed
CI / Conventional Commit title (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 1/2) (pull_request) Blocked by required conditions
CI / Python source checks (ubuntu-24.04, part 2/2) (pull_request) Blocked by required conditions
CI / SPIR-V fixtures (global narrow load/store, direct surface atomics, F2I immediate) (pull_request) Blocked by required conditions
CI / Workflow lint (actionlint) (pull_request) Blocked by required conditions
Guide screenshots / Guide images and local UI source review (pull_request) Blocked by required conditions
Third-party parts / As their notes say (pull_request) Blocked by required conditions
Third-party parts / The same as upstream (pull_request) Blocked by required conditions
Website / Website on Cloudflare (pull_request_target) Has been skipped
PR description / Description follows the template (pull_request_target) Failing after 4s
Some workflows are waiting to be reviewed.
Sign in to join this conversation.
No reviewers
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
MagicBeanDev/Longshot!928
No description provided.