Shallow probe verifying that auto-scan kicks the production pipeline
end-of-TX-side cleanly: chirp_scheduler emits new_chirp_frame, the
range pipeline (DDC + matched filter + range decimator) emits
multi-bin range profiles. Recovers G2.2 (new_chirp_frame pulse),
G4.1 (range_valid pulse), G4.2 (>=100 range bins) — three of T-2's
sixteen hidden failures.
Sim runs ~18 ms simulated (about 60-90 s wall on iverilog) — covers
one full 48-chirp frame TX time. Watchdog at 25 ms.
Deferred to PR-J:
G4.4 doppler_valid pulse, G5.1-5.4 USB egress, G9.x reset recovery.
Real finding: matched_filter_multi_segment hangs in ST_WAIT_FFT
under continuous auto-scan — the inner FFT chain (xfft_2048 +
frequency_matched_filter) does not assert fft_done in SIMULATION
mode after the first chirp's segment completes. tb_mf_cosim still
exercises the inner block in isolation (passes); the multi-segment
wrapper has no dedicated TB (T-9). The hang is a production-chain
integration bug, not a test infrastructure issue.
This TB is NOT yet wired into run_regression.sh — that lands in
PR-I.4 along with retiring tb_system_e2e.
f4fbee5dac