Silicon closeout evidence for the Ch443f scanout CDC hardening (commits 064484c +
4110846). Text/hashes/verdict/samples only — RBFs and framebuffer .mem dumps left
uncommitted (preserved local / on board).
Ch443f board verdict: RBF 59c6372e, fit setup +0.068 / all classes clean, fpga0
operating, CORE_ID 0x50533200 ABI 0x100. 311-epoch f52 replay DONE rc=0 zero
drops, FB byte-identical golden d0047677. Scanout diagnostic 120 samples (60 @
50ms + 60 @ non-harmonic 7ms) all identical: 0x02C=0xD1 (scan-error clear),
0x120=0x18 (qualified valid=0 / underflow=0 / read-error=0 / live pmax=0). The
two phase-sweep logs are byte-identical -> no phase-dependent CDC artifact. The
former residual "underflow" was purely the raw-readiness CDC/sync transient; the
Ch443e 4-buffer/lead-2 already fixed the real lookahead starvation. No fifth
buffer justified.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
thejayman77
7d68577c75