FPGA-Neural

Files

T

micheleandClaude Sonnet 5 481b5d223f perf: fix N=4@64MHz 7/8->8/8 by removing any_pending fan-out (user's idea)

Real critical-path trace after the flash #1 revert showed a NEW
bottleneck (neural_director.job_out_slot -> dependency_manager.
node_resolved/node_state, 76-84% routing) distinct from every prior
fix this session -- already a flat, parallel 64-way compare, not a
serial chain, so the established restructuring fix class doesn't
apply. Root cause: any_pending (added for FPGA_DATA_READY) reads
node_state[0:N_NODES-1] combinationally every cycle, adding real
fan-out onto the same congested signal.

User's own suggestion: replace the combinational scan with a
synchronous up/down counter. pending_count +1 on registration
acceptance, -1 on dispatch acceptance; any_pending = (pending_count
!= 0) -- mathematically identical (DEC-0008: nodes never reclaimed
mid-run) but reads one small register instead of scanning a 16-wide
array every cycle.

Verified: D-Stress N=4 bit-exact (49927 cycles, data_ready PASS).
Fresh 8-seed P&R: N_SLOTS=4 @ 64MHz now 8/8 PASS (was 7/8 after the
flash revert), worst seed1 64.55MHz, best seed0 72.37MHz.

See decisions.log DEC-0042.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013xXuuRUWZScuo1DeYJxs3v

2026-09-07 19:16:01 +02:00

activation_buffer.v

feat(v2): M3 activation/weight/result buffers, real BRAM mapping

2026-09-05 14:19:11 +02:00

activation_cache.v

perf(v2): shared activation cache - further 1.66-2.00x real speedup (DEC-0016)

2026-09-05 20:59:14 +02:00

dataflow_core.v

perf(v2): shared activation cache - further 1.66-2.00x real speedup (DEC-0016)

2026-09-05 20:59:14 +02:00

dependency_manager.v

perf: fix N=4@64MHz 7/8->8/8 by removing any_pending fan-out (user's idea)