diff options
Diffstat (limited to 'wiki/Execution-Frontier.md')
| -rw-r--r-- | wiki/Execution-Frontier.md | 61 |
1 files changed, 34 insertions, 27 deletions
diff --git a/wiki/Execution-Frontier.md b/wiki/Execution-Frontier.md index 15396c6..4549f08 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: 2026-11-15, tree `master @ 6aeb20c7`. +Status: 2026-11-15, tree `master @ 88d5005a`. Tags: `[live]` observed; `[wip]` partial; `[wall]` current blocker; theories are labelled as such. @@ -131,17 +131,21 @@ fire -> synthetic `GR LAUNCH 0x6d6d6500` -> `MME-PACK-REARM` -> DS `0x84000420`), and the held-CALL census plus the SA[34] golden fill prove the `DRAW_IAB` call and its target are present (`MME-CALL-TARGET slot=34 method=0x3910 client=0x265 golden=0x265 used=0x265`). What is missing is -**window/screen pixels through the NVIDIA path**: the blocker is **call -order** — the saved 728-B state window places the slot-34 run after the -`0x33/0x39` setup, so the last `0x39` latches DS `0x84000420` and the MFE -never reaches CALL(34) (c780), while the 324-B DRAW window places it first -and ran `mac=0x22` (c716). A release-window reorder (`a03a68ea`) is landed -but unexercised, and pack completion is still a per-boot lottery (poisoned -pack-part; no pump pass after the carry arm; carry-armed-never-fired); -`6aeb20c7` (eng64) chains the release behind a successful pack carrier and -names a stalled carrier's gate, validation pending. The -DS still carries the stage type/context bits (SPH5/SPH10/SPH18), so the draw -does not store (`wrote=0`, `px0=0`); the window/screen +**window/screen pixels through the NVIDIA path**: **the draw macro now +executes end to end** — c788 ran `DRAW_IAB` (`mac=0x22`) on a released held +window after the `MME-DRAW-MOVE` reorder, TCS-off (`45dbcdcd`) clears the DS +latch (the `0x84000420` was the synthesized TCS bind), a synthetic full-RT +viewport (`dab4a02c`) and a release chained after any GR launch +(`3481e62d`) complete the replay, and the DRAW_IAB body decodes with the +public Mesa MME toolchain (`mme_tu104_sim`: slot 34, 8 draws of 3 vertices) +— but the **vertex buffer** is not identified (no captured client push binds +the stream directly; the eng71 scan's CB-page candidate is a heuristic, and +a stale nonzero `VS0` also stores nothing) and **render-target store +visibility** is unproven (the release writes only CB/GR-context/report +pages; the big-surface alias pages do not yet populate `GUEST-WIT`); eng74 +(`88d5005a`) dumps the scanned vertex candidate (`VS-BLOB`) and records the +alias RT pages in the WIT, so both blockers are measurable next boot. The +draw does not store (`wrote=0`, `0/1025`, `px0=0`); the window/screen present path is unproven, glxgears' window is black, and a synchronous window draw wedges X on some boots. The per-boot binding and X first-generation start lottery are now the dominant throughput limiter. The guest Vulkan @@ -221,14 +225,16 @@ populated. The **DS stage-0/1 image is now authored and live** (a VTG SPH at host-deterministic when the pack completes: the saved-window release carrier re-submits the held window with the calls released (c772), and the held-CALL census plus SA[34] golden fill prove the slot-34 `DRAW_IAB` address -(`client=golden=used=0x265`). The remaining blocker is call order: the 728-B -state window places the slot-34 run after the `0x33/0x39` setup, so the `0x39` -DS latch pre-empts it (c780), while the 324-B DRAW window places it first and -ran `mac=0x22` (c716); the reorder `a03a68ea` is landed but unexercised, and -pack completion is still a per-boot lottery (`6aeb20c7`, eng64, chains the -release behind a successful pack carrier; validation pending). The DS stage -type/context bits (SPH5/SPH10/SPH18) remain after the call, so the draws -still do not store. +(`client=golden=used=0x265`). The draw macro now executes end to end (c788 ran +`DRAW_IAB` `mac=0x22` on the released held window after the `MME-DRAW-MOVE` +reorder; TCS-off clears the DS latch; the synthetic viewport and the chained +release complete the replay; the body decodes with the public Mesa MME +toolchain as 8 draws of 3 vertices). The remaining blockers are the vertex +buffer (no captured client push binds the stream directly; the eng71 scan +candidate is a heuristic) and render-target store/alias visibility (the +big-surface alias pages do not yet enter `GUEST-WIT`; eng74 `88d5005a` +records them and dumps the candidate blob), so the draws still do +not store. glxgears' window is black, a window draw wedges X on some boots, and the per-boot binding plus X first-generation start lottery is the dominant throughput limiter @@ -246,13 +252,14 @@ dominant throughput limiter 4. **Hold the acceptance battery** — vector-add, matrix-multiply and the transformer kernel; each entry is accepted only on its own verification output (`bad=0` + `STATUS OK`). -5. **The graphics pixel frontier** — the DS stage image is authored and live - for both vertex slots, and the saved-window release carrier now replays the - held window deterministically when the pack completes; next exercise the - release-window reorder so the slot-34 `DRAW_IAB` call runs before the setup - calls and stores (`wrote>0`) at the bound render target, then clear the DS - stage type/context bits, make the window/screen present land, and reduce - the per-boot binding/X start lottery so the proven off-screen frames become +5. **The graphics pixel frontier** — the released replay now executes the + draw macro (`DRAW_IAB`, `mac=0x22`, TCS-off DS clean, synthetic viewport, + chained release); next identify the draw's true vertex buffer (no captured + client push binds it; the eng71 scan candidate is a heuristic), make the + render-target store/alias visible (`GUEST-WIT` coverage of the big-surface + alias pages) so the draw stores (`wrote>0`) at the bound render target, + then make the window/screen present land, and reduce the per-boot + binding/X start lottery so the proven off-screen frames become window pixels; the lanes, the walls and the milestone ladder are on [`Graphics-Execution.md`](Graphics-Execution.md). |
