Files
hakmem/docs/analysis/PHASE5_POST_E1_NEXT_INSTRUCTIONS.md
Moe Charm (CI) 6cdbd815ab Phase 5 E4 Combined: E4-1 + E4-2 (+6.43% GO, baseline consolidated)
Combined A/B Test Results (10-run Mixed):
- Baseline (both OFF): 44.48M ops/s (mean), 44.39M ops/s (median)
- Optimized (both ON): 47.34M ops/s (mean), 47.38M ops/s (median)
- Improvement: +6.43% mean, +6.74% median

Interaction Analysis:
- E4-1 alone: +3.51% (measured in separate session)
- E4-2 alone: +21.83% (measured in separate session)
- Combined: +6.43% (measured in same binary)
- Pattern: SUBADDITIVE (overlapping bottlenecks)

Key Finding: Single-binary incremental gain is the accurate metric
- E4-1 and E4-2 target overlapping TLS/branch resources
- Individual measurements were from different baselines/sessions
- Combined measurement (same binary, both flags) shows true progress

Phase 5 Total Progress:
- Original baseline (session start): 35.74M ops/s
- Combined optimized: 47.34M ops/s
- Total gain: +32.4% (cross-session, reference only)
- Same-binary gain: +6.43% (E4-1+E4-2 both ON vs both OFF)

New Baseline Perf Profile (47.0M ops/s):
- free: 37.56% self% (still top hotspot)
- tiny_alloc_gate_fast: 13.73% (reduced from 19.50%)
- malloc: 12.95% (reduced from 16.13%)
- tiny_region_id_write_header: 6.97% (header write tax)
- hakmem_env_snapshot_enabled: 4.29% (ENV overhead visible)

Health Check: PASS
- MIXED_TINYV3_C7_SAFE: 42.3M ops/s
- C6_HEAVY_LEGACY_POOLV1: 20.9M ops/s

Phase 5 E5 Candidates (from perf profile):
- E5-1: free() path internals (37.56% self%)
- E5-2: Header write reduction (6.97% self%)
- E5-3: ENV snapshot overhead (4.29% self%)

Deliverables:
- docs/analysis/PHASE5_E4_COMBINED_AB_TEST_RESULTS.md
- docs/analysis/PHASE5_E5_NEXT_INSTRUCTIONS.md
- CURRENT_TASK.md (E4 combined complete, E5 candidates)
- docs/analysis/PHASE5_POST_E1_NEXT_INSTRUCTIONS.md (E5 pointer)
- perf.data.e4combined (perf profile data)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-14 05:36:57 +09:00

2.0 KiB
Raw Blame History

Phase 5: Post-E1 Baseline & Next Target次の指示書

Status2025-12-14

  • Phase 4 の勝ち箱は E1ENV SnapshotMIXED_TINYV3_C7_SAFE で default 化)
  • E3-4ENV CTORNO-GO / freeze
  • Phase 5 の勝ち箱: E4-1free wrapper snapshotMIXED_TINYV3_C7_SAFE で default 化)
  • Phase 5 の勝ち箱: E4-2malloc wrapper snapshotMIXED_TINYV3_C7_SAFE で default 化)
  • 次は “形” ではなく 新 baseline で perf を取り直し、self% ≥ 5% の芯を殴る

Step 0: Baseline 固定Mixed

HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE ./bench_random_mixed_hakmem 20000000 400 1

注意:

  • 以後の A/B はこのプロファイル(=E1 ONを基準にする

Step 1: perf で “芯” を選ぶself% ≥ 5%

HAKMEM_PROFILE=MIXED_TINYV3_C7_SAFE perf record -F 99 -- \
  ./bench_random_mixed_hakmem 20000000 400 1
perf report --stdio --no-children

GO/NO-GO:

  • self% が 5% 未満の最適化は原則 NO-GOまず他を削る

Step 2: 研究箱の候補を 1 つに絞るBox Theory

要件:

  • L0 ENV gatedefault OFFを必ず用意戻せる
  • 境界は 1 箇所(変換点を増やさない)
  • 可視化はカウンタ 1 本まで(常時ログ禁止)

Step 3: A/B で GO 判定Mixed

Mixed 10-run:

  • GO: mean +1.0% 以上
  • ±1%: NEUTRALfreeze
  • -1% 以下: NO-GOfreeze

Step 4: 健康診断

scripts/verify_health_profiles.sh

Step 5: 昇格

  • 勝ち箱だけを core/bench_profile.h のプリセットへ
  • docs/analysis/ENV_PROFILE_PRESETS.md に結果rollback を追記
  • CURRENT_TASK.md を更新

Next

  • E4-1 昇格: docs/analysis/PHASE5_E4_1_FREE_WRAPPER_ENV_SNAPSHOT_NEXT_INSTRUCTIONS.md
  • E4-2 設計/実装: docs/analysis/PHASE5_E4_2_MALLOC_WRAPPER_ENV_SNAPSHOT_NEXT_INSTRUCTIONS.md
  • E4 合算 A/B: docs/analysis/PHASE5_E4_COMBINED_AB_TEST_NEXT_INSTRUCTIONS.md
  • E5 次の芯: docs/analysis/PHASE5_E5_NEXT_INSTRUCTIONS.md