diff options
Diffstat (limited to 'wiki/OpenGL.md')
| -rw-r--r-- | wiki/OpenGL.md | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/wiki/OpenGL.md b/wiki/OpenGL.md index cc35fe6..08f26fa 100644 --- a/wiki/OpenGL.md +++ b/wiki/OpenGL.md @@ -12,7 +12,7 @@ > [`../docs/03-architecture/02-guest-stack-and-cudasw.md`](../docs/03-architecture/02-guest-stack-and-cudasw.md) > (the guest stack). The docs tree wins on disagreement. -Status: 2026-11-09, tree `master @ 4acc81e8`. Tags: `[live]` observed with the +Status: 2026-11-09, tree `master @ e342bd0f`. Tags: `[live]` observed with the stock guest driver; `[wip]` partial; `[wall]` current blocker; `[target]` defined success state. @@ -76,12 +76,16 @@ Rated honestly, against the milestone ladder in the plan: | `glxinfo -B` reports the NVIDIA renderer (OpenGL 4.6.0, driver 570.144, direct rendering) | `[live]` | | The X driver's RC-watchdog channel registers and its notifier is authored | `[live]` | | GZDoom obtains a real GL context; windowed GZDoom reaches renderer startup | `[live]` (menu/frames black) | +| GZDoom reaches `MAP01` on Mesa llvmpipe (not the emulated vGPU path) | `[wip]` | +| X server survives the GZDoom run on a 12 GB guest (the DDX's 4 GB sysmem allocation forces the size) | `[live]` | | X server's `0xC597` graphics section captured and decoded | `[live]` | | Engine executes a launch built from the captured section (real `sm_75` SASS retired) | `[live]` | | Verbatim 3D method-stream replay retired by the engine, no MMU fault | `[live]` | | Direct GL client: device-init gate handled; client channels allocate; readback path returns with no GL error | `[live]` | | Direct GL client submits and retires its per-frame draws (GR `0xbeef0100`, CE `0xbeef0101`/`0xbeef0102`); DDX kick channel decoded | `[live]` | -| X GLX context-creation completion and the client kick-slot word | `[wall]` | +| NVIDIA Vulkan ICD creates a device, or forced GLX (`SDL_VIDEO_X11_FORCE_EGL=0`) reaches glcore | `[wall]` | +| DDX push-buffer get-word publish and notifier recycle | `[wall]` | +| Physical dispatch of the direct-GL draws (`forwarded=0`) | `[wall]` | | Non-black rendered frames through the emulated vGPU | `[wall]` | | 60 fps sustained, no forcing (M-GL4) | `[target]` | @@ -104,14 +108,15 @@ non-black through the mdev), M-GL4 (60 fps, no forcing), M-GL5 (two VMs, two mdevs), M-GL6 (split-screen video). The project sits **between M-GL1 and M-GL2**: the interface and execution work is done — the display/KMS stack registers, X settles, the client submits and retires its GR/CE channels, and -the engine authors stores — and the remaining gate is the X GLX -context-creation completion plus the client kick-slot word before the first -rendered frame. +the engine authors stores — and the remaining gates are the NVIDIA renderer +path (Vulkan ICD or forced GLX), the X DDX get-word/notifier completion, and +physical dispatch of the client's draws before the first rendered frame. ## 6. What is not claimed * No OpenGL frame from the emulated vGPU has produced real rendered pixels - yet; every capture so far is black. + yet; every capture so far is black. GZDoom reaching `MAP01` on Mesa + llvmpipe is not a rendered frame from the emulated vGPU. * No frame-rate or latency numbers. * The published two-VM GZDoom demo videos used the labelled `virtio-gpu`/ `virgl` path, not the emulated vGPU. |