Files
NawfalMotii79-PLFM_RADAR/9_Firmware/9_2_FPGA
Jason ad37f88cd3 test(fft): PR-L — fix tb_fft_engine N=32→16 dropdown bugs (T-4)
The TB hard-coded /32.0 in cosine/sine angle math and read out_re[28] /
out_re[30] which don't exist for N=16, so 3/12 checks failed (Test 3
single-tone, Test 7 imag-tone). Pure TB math error — fft_engine.v is
correct (proven by every production MF/Doppler cosim passing bit-exact).

Test 3: /32.0 → /N, peak expected = N/2*1000 = 8000 (not 16000),
        conjugate read at bin N-4=12 (not 28).
Test 7: /32.0 → /N, conjugate peak at bin N-2=14 (not 30).

Result: 12/12 PASS at N=16 with bin 4 = 7997 ≈ 8000.

Closes T-4. Final regression: 42 passed / 0 failed of 42 — first
all-green since PR-Tests-1 exposed hidden failures.
2026-05-01 15:32:35 +05:45
..