Files
hakmem/core/box/tiny_legacy_fallback_box.h

68 lines
2.8 KiB
C
Raw Normal View History

#ifndef HAKMEM_TINY_LEGACY_FALLBACK_BOX_H
#define HAKMEM_TINY_LEGACY_FALLBACK_BOX_H
#include <stdbool.h>
#include <stdint.h>
#include "../front/tiny_unified_cache.h"
2025-12-13 19:19:42 +09:00
#include "../front/tiny_first_page_cache.h" // Phase 3 C2: First page inline cache
#include "../hakmem.h"
#include "tiny_front_v3_env_box.h"
#include "free_path_stats_box.h"
#include "tiny_front_hot_box.h"
2025-12-13 19:19:42 +09:00
#include "tiny_metadata_cache_env_box.h" // Phase 3 C2: Metadata cache ENV gate
Phase 4 E1: ENV Snapshot Consolidation - GO (+3.92% avg, +4.01% median) Target: Consolidate 3 ENV gate TLS reads → 1 TLS read - tiny_c7_ultra_enabled_env(): 1.28% self - tiny_front_v3_enabled(): 1.01% self - tiny_metadata_cache_enabled(): 0.97% self - Total overhead: 3.26% self (perf profile analysis) Implementation: - core/box/hakmem_env_snapshot_box.h (new): ENV snapshot struct & API - core/box/hakmem_env_snapshot_box.c (new): TLS snapshot implementation - core/front/malloc_tiny_fast.h: Migrated 5 call sites to snapshot - core/box/tiny_legacy_fallback_box.h: Migrated 2 call sites - core/box/tiny_metadata_cache_hot_box.h: Migrated 1 call site - core/bench_profile.h: Added hakmem_env_snapshot_refresh_from_env() - Makefile: Added hakmem_env_snapshot_box.o to build - ENV gate: HAKMEM_ENV_SNAPSHOT=0/1 (default: 0, research box) A/B Test Results (Mixed, 10-run, 20M iters): - Baseline (E1=0): 43,617,549 ops/s (avg), 43,562,895 ops/s (median) - Optimized (E1=1): 45,327,239 ops/s (avg), 45,309,218 ops/s (median) - Improvement: avg +3.92%, median +4.01% Decision: GO (+3.92% >= +2.5% threshold) - Action: Keep as research box (default OFF) for Phase 4 - Next: Consider promotion to default in MIXED_TINYV3_C7_SAFE preset Design Rationale: - Shape optimizations (B3, D3) reached saturation (+0.56% NEUTRAL) - Shift to memory/TLS overhead optimization (new optimization frontier) - Pattern: Similar to existing tiny_front_v3_snapshot (proven approach) - Expected: +1-3% from 3.26% ENV overhead → Achieved: +3.92% Technical Details: - Consolidation: 3 TLS reads → 1 TLS read (66% reduction) - Learner interlock: tiny_metadata_cache_eff pre-computed in snapshot - Version sync: Refreshes on small_policy_v7_version_changed() - Fallback safety: Existing ENV gates still available when E1=0 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-14 00:59:12 +09:00
#include "hakmem_env_snapshot_box.h" // Phase 4 E1: ENV snapshot consolidation
// Purpose: Encapsulate legacy free logic (shared by multiple paths)
// Called by: malloc_tiny_fast.h (free path) + tiny_c6_ultra_free_box.c (C6 fallback)
//
// Contract:
// - base: BASE pointer (already extracted via ptr - 1)
// - class_idx: size class (0-7)
// - Returns: void (always succeeds or falls back to tiny_hot_free_fast)
//
__attribute__((always_inline))
static inline void tiny_legacy_fallback_free_base(void* base, uint32_t class_idx) {
Phase 4 E1: ENV Snapshot Consolidation - GO (+3.92% avg, +4.01% median) Target: Consolidate 3 ENV gate TLS reads → 1 TLS read - tiny_c7_ultra_enabled_env(): 1.28% self - tiny_front_v3_enabled(): 1.01% self - tiny_metadata_cache_enabled(): 0.97% self - Total overhead: 3.26% self (perf profile analysis) Implementation: - core/box/hakmem_env_snapshot_box.h (new): ENV snapshot struct & API - core/box/hakmem_env_snapshot_box.c (new): TLS snapshot implementation - core/front/malloc_tiny_fast.h: Migrated 5 call sites to snapshot - core/box/tiny_legacy_fallback_box.h: Migrated 2 call sites - core/box/tiny_metadata_cache_hot_box.h: Migrated 1 call site - core/bench_profile.h: Added hakmem_env_snapshot_refresh_from_env() - Makefile: Added hakmem_env_snapshot_box.o to build - ENV gate: HAKMEM_ENV_SNAPSHOT=0/1 (default: 0, research box) A/B Test Results (Mixed, 10-run, 20M iters): - Baseline (E1=0): 43,617,549 ops/s (avg), 43,562,895 ops/s (median) - Optimized (E1=1): 45,327,239 ops/s (avg), 45,309,218 ops/s (median) - Improvement: avg +3.92%, median +4.01% Decision: GO (+3.92% >= +2.5% threshold) - Action: Keep as research box (default OFF) for Phase 4 - Next: Consider promotion to default in MIXED_TINYV3_C7_SAFE preset Design Rationale: - Shape optimizations (B3, D3) reached saturation (+0.56% NEUTRAL) - Shift to memory/TLS overhead optimization (new optimization frontier) - Pattern: Similar to existing tiny_front_v3_snapshot (proven approach) - Expected: +1-3% from 3.26% ENV overhead → Achieved: +3.92% Technical Details: - Consolidation: 3 TLS reads → 1 TLS read (66% reduction) - Learner interlock: tiny_metadata_cache_eff pre-computed in snapshot - Version sync: Refreshes on small_policy_v7_version_changed() - Fallback safety: Existing ENV gates still available when E1=0 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-14 00:59:12 +09:00
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
const TinyFrontV3Snapshot* front_snap;
bool metadata_cache_on;
if (__builtin_expect(hakmem_env_snapshot_enabled(), 0)) {
const HakmemEnvSnapshot* env = hakmem_env_snapshot();
front_snap = env->tiny_front_v3_enabled ? tiny_front_v3_snapshot_get() : NULL;
metadata_cache_on = env->tiny_metadata_cache_eff; // Uses effective (cache && !learner)
} else {
front_snap = __builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL;
metadata_cache_on = tiny_metadata_cache_enabled();
}
2025-12-13 19:19:42 +09:00
// Phase 3 C2 Patch 2: First page cache hint (optional fast-path)
// Check if pointer is in cached page (avoids metadata lookup in future optimizations)
Phase 4 E1: ENV Snapshot Consolidation - GO (+3.92% avg, +4.01% median) Target: Consolidate 3 ENV gate TLS reads → 1 TLS read - tiny_c7_ultra_enabled_env(): 1.28% self - tiny_front_v3_enabled(): 1.01% self - tiny_metadata_cache_enabled(): 0.97% self - Total overhead: 3.26% self (perf profile analysis) Implementation: - core/box/hakmem_env_snapshot_box.h (new): ENV snapshot struct & API - core/box/hakmem_env_snapshot_box.c (new): TLS snapshot implementation - core/front/malloc_tiny_fast.h: Migrated 5 call sites to snapshot - core/box/tiny_legacy_fallback_box.h: Migrated 2 call sites - core/box/tiny_metadata_cache_hot_box.h: Migrated 1 call site - core/bench_profile.h: Added hakmem_env_snapshot_refresh_from_env() - Makefile: Added hakmem_env_snapshot_box.o to build - ENV gate: HAKMEM_ENV_SNAPSHOT=0/1 (default: 0, research box) A/B Test Results (Mixed, 10-run, 20M iters): - Baseline (E1=0): 43,617,549 ops/s (avg), 43,562,895 ops/s (median) - Optimized (E1=1): 45,327,239 ops/s (avg), 45,309,218 ops/s (median) - Improvement: avg +3.92%, median +4.01% Decision: GO (+3.92% >= +2.5% threshold) - Action: Keep as research box (default OFF) for Phase 4 - Next: Consider promotion to default in MIXED_TINYV3_C7_SAFE preset Design Rationale: - Shape optimizations (B3, D3) reached saturation (+0.56% NEUTRAL) - Shift to memory/TLS overhead optimization (new optimization frontier) - Pattern: Similar to existing tiny_front_v3_snapshot (proven approach) - Expected: +1-3% from 3.26% ENV overhead → Achieved: +3.92% Technical Details: - Consolidation: 3 TLS reads → 1 TLS read (66% reduction) - Learner interlock: tiny_metadata_cache_eff pre-computed in snapshot - Version sync: Refreshes on small_policy_v7_version_changed() - Fallback safety: Existing ENV gates still available when E1=0 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2025-12-14 00:59:12 +09:00
if (__builtin_expect(metadata_cache_on, 0)) {
2025-12-13 19:19:42 +09:00
// Note: This is a hint-only check. Even if it hits, we still use the standard path.
// The cache will be populated during refill operations for future use.
// Currently this just validates the cache state; actual optimization TBD.
if (tiny_first_page_cache_hit(class_idx, base, 4096)) {
// Future: could optimize metadata access here
}
}
// Legacy fallback - Unified Cache push
if (!front_snap || front_snap->unified_cache_on) {
if (unified_cache_push(class_idx, HAK_BASE_FROM_RAW(base))) {
FREE_PATH_STAT_INC(legacy_fallback);
// Per-class breakdown (Phase 4-1)
if (__builtin_expect(free_path_stats_enabled(), 0)) {
if (class_idx < 8) {
g_free_path_stats.legacy_by_class[class_idx]++;
}
}
return;
}
}
// Final fallback
tiny_hot_free_fast(class_idx, base);
}
#endif // HAKMEM_TINY_LEGACY_FALLBACK_BOX_H