Preserve the Ch441 timing/renderer board-validation evidence and the
Codex-directed follow-up:
- FB reconciliation: the Ch437 A/B dump's 8-word first-beat delta was a
non-reproducible one-time transient; 3x render+dump and 8x pure-probe
re-reads all return golden d0047677 (words 0-7 correct). Memory integrity
confirmed deterministic. (fb_reconciliation.md)
- Structural audit + A-D diagnostic proposal for LPDDR_STATUS[5]: bit5 ORs
sticky CDC-synced underflow with AXI read-errors; dump path (arid=1) is
separate from scanout/HDMI (arid=3). Instrumentation proposal only, not
implemented. (scanout_status_bit5_proposal.md)
- Raw board logs, status samples, RBF hashes, A/B FB dump, board PNG.
No RTL edits, no compile, no builds.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Per-vertex GS fog end-to-end (gs_stub emit incl. persp_emit5, gs_prim_list_feeder
XYZ2->XYZF2 on PRIM.FGE, gs_make_sh3_scheduler_fixture.py F/FGE packing), new fog
TBs, fidelity attribution tooling. Functional baseline before removing the dead
bilinear lerp8 clamps (Codex: 161-node comb loop -> -0.042ns setup fail).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
RTL (GS rasterizer, EE core stub, platform bridge, LPDDR4B path), sim regression
(272 TBs), docs, and tooling. Copyrighted PS2 content (BIOS, game code, GS dumps,
and all dump-derived textures/traces) is excluded via .gitignore and stays local.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
thejayman77