Model M under executor dx12: a fixed 2.5 GiB measuring arena at every context creation
維護者通常 1 天內回覆
還沒有人認領這個 Issue。
評估
- 難度
- 5/5
- 預估耗時
- 一週以上
- 新手友好度
- 35/100
- Issue 類型
- 功能
- 描述清晰度
- 需要釐清
- 活躍度
- 活躍
- 技術堆疊
- cpp
- 領域
- performance
研究方向
Start with clean/runtime/interop/executor_d3d12.cpp and clean/runtime/device_d3d12.cpp to trace the two-pass arena creation and the default size. First compare video memory before, during, and after Model M context creation on Windows and Proton. The issue asks for options to discuss, not a defined implementation; any eventual change must preserve bit-identical output.
由索引模型根據 Issue 內容生成。
描述
Discussion #10 reports that Model M allocated a 2,560 MiB buffer next to its 706 MiB arena. That buffer is the first of
two arenas the D3D12 executor creates on the game's device (clean/runtime/interop/executor_d3d12.cpp,
prepare_device): pass 1 makes a device with the default arena (WG_D3D12_ARENA_MB, default 2560 MiB,
clean/runtime/device_d3d12.cpp), runs the whole runtime creation to measure the highest arena offset the network
uses, and destroys it; pass 2 makes the arena that stays, sized to that measurement plus 1 MiB.
What could be better:
- The measuring arena is a fixed 2.5 GiB whatever the render and output size, so every context creation briefly
commits 2.5 GiB on the game's device on top of what the game holds, even when the context needs far less. On 8 GB
cards (RX 9060 XT / 9060, see #3) that is a large share; if the allocation keeps failing for 5 s, Model M falls back. - Pass 1's device has no log sink, so its teardown lines are dropped. If its teardown cannot confirm completion, the
device keeps its GPU objects, the 2.5 GiB arena included, until the game exits, and WrongGPU's log says nothing.
That would match the report of both buffers side by side. - The default and the two passes are documented only in code comments.
To do: first check on Windows and under Proton whether the 2.5 GiB buffer is still allocated after creation (video
memory before, during and after Model M's create). Then options to discuss: measure the need without a full-size arena
(a size from the context's render and output size, or a first pass that only counts allocations), give pass 1's device
the same log sink so its teardown is visible, and document the transient size. The output must stay bit-identical.
Related: Discussion #10, #3
- 主要語言
- C++
- 星號
- 12
- 分支
- 2
- 平均合併
- 3 小時 10 分鐘
- 30 天內合併 PR
- 171
環境準備
- 沒有 Dockerfile 或 Docker Compose 檔案
- 有 Pull Request 範本
- 閱讀貢獻指南
從這裡開始
- 先讀完整個 Issue,再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫,在一個分支上完成修改。
- 送出 Pull Request,並在描述裡引用這個 Issue 編號。
phantoslayer21/wronggpu 的其他 Issue
-
難度 2/5 1-3 小時 新手友好度 88/100
phantoslayer21/wronggpu#275 ·
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 82/100
phantoslayer21/wronggpu#274 ·
維護者通常 1 天內回覆
-
bug
難度 2/5 1-3 小時 新手友好度 88/100
phantoslayer21/wronggpu#241 ·
維護者通常 1 天內回覆
-
bug build
難度 2/5 1-3 小時 新手友好度 74/100
phantoslayer21/wronggpu#234 ·
維護者通常 1 天內回覆
-
bug build
難度 2/5 1-3 小時 新手友好度 80/100
phantoslayer21/wronggpu#233 ·
維護者通常 1 天內回覆
查看 phantoslayer21/wronggpu 的全部 Issue
相似的 Issue
-
ai_p2
難度 2/5 1-3 小時 新手友好度 80/100
ClickHouse/ClickHouse#132519 ·
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 76/100
juce-framework/JUCE#1810 ·
-
難度 1/5 1 小時以內 新手友好度 82/100
petercorke/robotics-toolbox-python#952 ·
維護者通常 1 天內回覆
-
NatronRenderer: a Python error in the script (-t / project script) doesn't change the exit status未關閉func:engine type:bug
難度 2/5 1-3 小時 新手友好度 72/100
NatronGitHub/Natron#1276 ·
維護者通常 1 天內回覆
-
難度 1/5 1-3 小時 新手友好度 77/100
維護者通常 1 天內回覆