thejayman77
2123e646c8
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>
8 lines
679 B
Plaintext
8 lines
679 B
Plaintext
Ch441 board A/B scanout comparison (2026-07-21)
|
|
|
|
Candidate Ch441 = 9463602d... : replay DONE rc=0, 311 drains, zero drops, FB SHA d0047677 (byte-identical golden). LPDDR_STATUS[5] SET ~15/16 (0xF1).
|
|
Accepted Ch437 = 3dd624cd... : replay DONE rc=0, 311 drains. LPDDR_STATUS[5] SET 16/16 (0xF1) — SAME underflow.
|
|
Canonical retroDE_ps2.core.rbf = 56e45346... = Ch439b (previously REJECTED for this exact 0xF1).
|
|
|
|
VERDICT: both Ch441 and the ACCEPTED Ch437 underflow identically -> reproduced BASELINE scanout defect (LPDDR_STATUS[5]), NOT a Ch441 regression. Ch441 remains the timing-clean / renderer-correct candidate; scanout defect stays OPEN. Ch441 NOT promoted to canonical.
|