Michael Chus
bf6ecab4f0
Add per-precision benchmark phases, weighted TOPS scoring, and ECC tracking
- Split steady window into 6 equal slots: fp8/fp16/fp32/fp64/fp4 + combined
- Each precision phase runs bee-gpu-burn with --precision filter so PowerCVPct reflects single-kernel stability (not round-robin artifact)
- Add fp4 support in bee-gpu-stress.c for Blackwell (cc>=100) via existing CUDA_R_4F_E2M1 guard
- Weighted TOPS: fp64×2.0, fp32×1.0, fp16×0.5, fp8×0.25, fp4×0.125
- SyntheticScore = sum of weighted TOPS from per-precision phases
- MixedScore = sum from combined phase; MixedEfficiency = Mixed/Synthetic
- ComputeScore = SyntheticScore × (1 + MixedEfficiency × 0.3)
- ECC volatile counters sampled before/after each phase and overall
- DegradationReasons: ecc_uncorrected_errors, ecc_corrected_errors
- Report: per-precision stability table with ECC columns, methodology section
- Ramp-up history table redesign: GPU indices as columns, runs as rows
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-13 10:49:49 +03:00
..
2026-04-05 19:21:10 +03:00
2026-04-09 15:21:14 +03:00
2026-04-01 09:42:59 +03:00
2026-04-13 10:49:49 +03:00
2026-04-12 13:07:32 +03:00
2026-03-31 22:17:36 +03:00
2026-04-09 15:21:14 +03:00
2026-03-31 11:37:21 +03:00
2026-04-06 12:22:04 +03:00
2026-03-13 16:52:16 +03:00
2026-04-01 09:10:55 +03:00
2026-04-09 15:14:48 +03:00
2026-04-05 19:30:41 +03:00
2026-04-09 15:14:48 +03:00
2026-03-13 16:52:16 +03:00
2026-04-01 21:25:23 +03:00