summaryrefslogtreecommitdiffstats
path: root/wiki/Execution-Frontier.md
diff options
context:
space:
mode:
Diffstat (limited to 'wiki/Execution-Frontier.md')
-rw-r--r--wiki/Execution-Frontier.md28
1 files changed, 17 insertions, 11 deletions
diff --git a/wiki/Execution-Frontier.md b/wiki/Execution-Frontier.md
index e8efcc3..57ede35 100644
--- a/wiki/Execution-Frontier.md
+++ b/wiki/Execution-Frontier.md
@@ -14,7 +14,7 @@
> [`../docs/04-implementation/03-execution-frontier.md`](../docs/04-implementation/03-execution-frontier.md);
> the docs tree wins on disagreement.
-Status: 2026-11-09, tree `master @ 4acc81e8`.
+Status: 2026-11-09, tree `master @ e342bd0f`.
Tags: `[live]` observed; `[wip]` partial; `[wall]` current blocker; theories
are labelled as such.
@@ -98,13 +98,16 @@ Graphics execution shares this page's submission and completion machinery but
runs a different engine workload. The display and GL stacks now run end to
end in the guest: the emulated display engine serves the modeset push buffers,
nvidia-modeset/NvKms registers (`/dev/dri`), X settles, `glxinfo` reports
-OpenGL 4.6.0 with direct rendering, and GZDoom obtains a real GL context; the
-direct GL client's GR and CE channels submit and retire, and the X server's
-DDX kick channel is decoded. What is missing is **rendered pixels**: the
-remaining wall is the X GLX context-creation completion (with the client's
-kick-slot word), and every frame is still black. The guest Vulkan pipeline
-runs end to end but its inline-to-memory upload arm remains the named gap.
-The full picture lives on [`Graphics-Execution.md`](Graphics-Execution.md).
+OpenGL 4.6.0 with direct rendering, and the X DDX waits are fixed
+(class-aware display arm, `0x8000 -> 0` notification completion, decoded GL
+release applied); the direct GL client's GR and CE channels submit and retire,
+and the X DDX kick channel is decoded. GZDoom reached `MAP01` once the DDX
+push-buffer loop was unblocked, but on Mesa llvmpipe — not the emulated vGPU.
+What is missing is **rendered pixels through the NVIDIA path**: the renderer
+backend (Vulkan ICD device creation or forced GLX), the DDX get-word/notifier
+completion and physical dispatch of the GL draws are the named walls, and the
+guest Vulkan pipeline's inline-to-memory upload arm remains its gap. The full
+picture lives on [`Graphics-Execution.md`](Graphics-Execution.md).
No breadth beyond these is claimed: Windows guests, migration and performance
numbers remain planned.
@@ -162,9 +165,12 @@ CUDA guests is in progress.
**Issue D — the graphics pixel frontier.** The display/KMS stack and the GL
client now run end to end (NvKms registers, X settles, GL 4.6, direct-GL
-channels submit and retire), but no rendered (non-black) frame has been
-produced yet; the X GLX context-creation completion and the client kick-slot
-word are the named blockers ([`Graphics-Execution.md`](Graphics-Execution.md)).
+channels submit and retire, the X DDX waits are fixed), but no rendered
+(non-black) frame has been produced yet through the NVIDIA path; GZDoom's
+`MAP01` is a Mesa llvmpipe datapoint. The renderer backend (Vulkan ICD or
+forced GLX), the DDX get-word/notifier completion and physical dispatch of
+the GL draws (`forwarded=0`) are the named blockers
+([`Graphics-Execution.md`](Graphics-Execution.md)).
## 6. Lines of investigation (live)