0009ce13b3
Modular implementation of hot-class inline slots optimization: - Created 5 new boxes: env_box, tls_box, fast_path_api, integration_box, test_script - Single decision point at TLS init (ENV gate: HAKMEM_TINY_C6_INLINE_SLOTS=0/1) - Integration: 2 minimal boundary points (alloc/free paths for C6 class) - Default OFF: zero overhead when disabled (full backward compatibility) Results (10-run Mixed SSOT, WS=400): - Baseline (C6 inline OFF): 44.24 M ops/s - Treatment (C6 inline ON): 45.51 M ops/s - Delta: +1.27 M ops/s (+2.87%) Status: ✅ GO - Strong improvement via C6 ring buffer fast-path Mechanism: Branch elimination on unified_cache_push/pop for C6 allocations Next: Phase 75-2 (add C5 inline slots, target 85% C4-C7 coverage) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
105 lines
4.5 KiB
C
105 lines
4.5 KiB
C
#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"
|
|
#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"
|
|
#include "tiny_metadata_cache_env_box.h" // Phase 3 C2: Metadata cache ENV gate
|
|
#include "hakmem_env_snapshot_box.h" // Phase 4 E1: ENV snapshot consolidation
|
|
#include "tiny_unified_cache_fastapi_env_box.h" // Phase 74-3: FASTAPI ENV gate
|
|
#include "tiny_c6_inline_slots_env_box.h" // Phase 75-1: C6 inline slots ENV gate
|
|
#include "../front/tiny_c6_inline_slots.h" // Phase 75-1: C6 inline slots API
|
|
|
|
// 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_with_env(void* base, uint32_t class_idx, const HakmemEnvSnapshot* env) {
|
|
// Phase 75-1: C6 Inline Slots early-exit (ENV gated)
|
|
// Try C6 inline slots FIRST (before unified cache) for class 6
|
|
if (class_idx == 6 && tiny_c6_inline_slots_enabled()) {
|
|
if (c6_inline_push(c6_inline_tls(), base)) {
|
|
// Success: pushed to C6 inline slots
|
|
FREE_PATH_STAT_INC(legacy_fallback);
|
|
if (__builtin_expect(free_path_stats_enabled(), 0)) {
|
|
g_free_path_stats.legacy_by_class[class_idx]++;
|
|
}
|
|
return;
|
|
}
|
|
// FULL → fall through to unified cache
|
|
}
|
|
|
|
const TinyFrontV3Snapshot* front_snap =
|
|
env ? (env->tiny_front_v3_enabled ? tiny_front_v3_snapshot_get() : NULL)
|
|
: (__builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL);
|
|
const bool metadata_cache_on = env ? env->tiny_metadata_cache_eff : tiny_metadata_cache_enabled();
|
|
|
|
// 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)
|
|
if (__builtin_expect(metadata_cache_on, 0)) {
|
|
// 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) {
|
|
// Phase 74-3 (P0): FASTAPI path (ENV-gated)
|
|
if (tiny_uc_fastapi_enabled()) {
|
|
// Preconditions guaranteed:
|
|
// - unified_cache_on == true (checked above)
|
|
// - TLS init guaranteed by front_gate_unified_enabled() in malloc_tiny_fast.h
|
|
// - Stats compiled-out in FAST builds
|
|
if (unified_cache_push_fast(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;
|
|
}
|
|
// FULL → fallback to slow path (rare)
|
|
}
|
|
|
|
// Original path (FASTAPI=0 or fallback)
|
|
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);
|
|
}
|
|
|
|
__attribute__((always_inline))
|
|
static inline void tiny_legacy_fallback_free_base(void* base, uint32_t class_idx) {
|
|
const HakmemEnvSnapshot* env = hakmem_env_snapshot_enabled() ? hakmem_env_snapshot() : NULL;
|
|
tiny_legacy_fallback_free_base_with_env(base, class_idx, env);
|
|
}
|
|
|
|
#endif // HAKMEM_TINY_LEGACY_FALLBACK_BOX_H
|