mirror of
https://github.com/duggasco/bc250-40cu-unlock.git
synced 2026-07-16 00:40:55 +00:00
- FP tolerance: iters/3 + 2 ULP (23 for default 64 iters) to account for CPU vs GPU FMA rounding accumulation in chained operations. Integer comparison remains exact. - Verified: 100M checks, zero errors on both boards at 40 CU. - Added cu_map.sh health overlay, CU health test, selective masking tool. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>