N=8 with the same pipelined neural_processor_packed.v: 16/16 functional
PASS, real P&R WNS=+0.108ns (up from the original exact-zero 0.000ns),
0 failing endpoints, no regression -- the fix is a pure improvement for
N=8 too.
N=16 margin-hunt: worst path moved again (now inside
neural_director_grouped.v's own queue update logic, still route-
dominated) -- confirms the MAC fix resolved its own real bottleneck.
A second real P&R attempt with alternate directives gave WNS=+0.168ns,
worse than the first attempt's +0.269ns -- confirms real P&R variance,
not further systematic gain available without touching Director RTL
(not attempted, current margin already comfortable).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MUG92aM9m68TRc4rG55BcC
micheleandClaude Sonnet 5
2ab2ff7769