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>
This commit is contained in:
Moe Charm (CI)
@ -69,6 +69,7 @@
|
||||
#include "../box/free_tiny_fast_hotcold_stats_box.h" // Phase FREE-TINY-FAST-HOTCOLD-OPT-1: Stats
|
||||
#include "../box/tiny_metadata_cache_hot_box.h" // Phase 3 C2: Policy hot cache (metadata cache optimization)
|
||||
#include "../box/tiny_free_route_cache_env_box.h" // Phase 3 D1: Free path route cache
|
||||
#include "../box/hakmem_env_snapshot_box.h" // Phase 4 E1: ENV snapshot consolidation
|
||||
|
||||
// Helper: current thread id (low 32 bits) for owner check
|
||||
#ifndef TINY_SELF_U32_LOCAL_DEFINED
|
||||
@ -226,7 +227,16 @@ static inline void* malloc_tiny_fast_for_class(size_t size, int class_idx) {
|
||||
|
||||
// Phase v11a-5b: C7 ULTRA early-exit (skip policy snapshot for common case)
|
||||
// This is the most common hot path - avoids TLS policy overhead
|
||||
if (class_idx == 7 && tiny_c7_ultra_enabled_env()) {
|
||||
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
|
||||
bool c7_ultra_on;
|
||||
if (__builtin_expect(hakmem_env_snapshot_enabled(), 0)) {
|
||||
const HakmemEnvSnapshot* env = hakmem_env_snapshot();
|
||||
c7_ultra_on = env->tiny_c7_ultra_enabled;
|
||||
} else {
|
||||
c7_ultra_on = tiny_c7_ultra_enabled_env();
|
||||
}
|
||||
|
||||
if (class_idx == 7 && c7_ultra_on) {
|
||||
void* ultra_p = tiny_c7_ultra_alloc(size);
|
||||
if (TINY_HOT_LIKELY(ultra_p != NULL)) {
|
||||
return ultra_p;
|
||||
@ -384,8 +394,14 @@ static int free_tiny_fast_cold(void* ptr, void* base, int class_idx)
|
||||
route = tiny_route_for_class((uint8_t)class_idx);
|
||||
}
|
||||
const int use_tiny_heap = tiny_route_is_heap_kind(route);
|
||||
const TinyFrontV3Snapshot* front_snap =
|
||||
__builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL;
|
||||
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
|
||||
const TinyFrontV3Snapshot* front_snap;
|
||||
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;
|
||||
} else {
|
||||
front_snap = __builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL;
|
||||
}
|
||||
|
||||
// TWO-SPEED: SuperSlab registration check is DEBUG-ONLY to keep HOT PATH fast.
|
||||
// In Release builds, we trust header magic (0xA0) as sufficient validation.
|
||||
@ -576,7 +592,16 @@ static inline int free_tiny_fast_hot(void* ptr) {
|
||||
FREE_PATH_STAT_INC(total_calls);
|
||||
|
||||
// Phase v11b-1: C7 ULTRA early-exit (skip policy snapshot for most common case)
|
||||
if (class_idx == 7 && tiny_c7_ultra_enabled_env()) {
|
||||
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
|
||||
bool c7_ultra_free;
|
||||
if (__builtin_expect(hakmem_env_snapshot_enabled(), 0)) {
|
||||
const HakmemEnvSnapshot* env = hakmem_env_snapshot();
|
||||
c7_ultra_free = env->tiny_c7_ultra_enabled;
|
||||
} else {
|
||||
c7_ultra_free = tiny_c7_ultra_enabled_env();
|
||||
}
|
||||
|
||||
if (class_idx == 7 && c7_ultra_free) {
|
||||
FREE_TINY_FAST_HOTCOLD_STAT_INC(hot_c7_ultra);
|
||||
tiny_c7_ultra_free(ptr);
|
||||
FREE_TINY_FAST_HOTCOLD_STAT_INC(hot_hit);
|
||||
@ -719,7 +744,16 @@ static inline int free_tiny_fast(void* ptr) {
|
||||
FREE_PATH_STAT_INC(total_calls);
|
||||
|
||||
// Phase v11b-1: C7 ULTRA early-exit (skip policy snapshot for most common case)
|
||||
if (class_idx == 7 && tiny_c7_ultra_enabled_env()) {
|
||||
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
|
||||
bool c7_ultra_free;
|
||||
if (__builtin_expect(hakmem_env_snapshot_enabled(), 0)) {
|
||||
const HakmemEnvSnapshot* env = hakmem_env_snapshot();
|
||||
c7_ultra_free = env->tiny_c7_ultra_enabled;
|
||||
} else {
|
||||
c7_ultra_free = tiny_c7_ultra_enabled_env();
|
||||
}
|
||||
|
||||
if (class_idx == 7 && c7_ultra_free) {
|
||||
tiny_c7_ultra_free(ptr);
|
||||
return 1;
|
||||
}
|
||||
@ -790,8 +824,14 @@ legacy_fallback:
|
||||
route = tiny_route_for_class((uint8_t)class_idx);
|
||||
}
|
||||
const int use_tiny_heap = tiny_route_is_heap_kind(route);
|
||||
const TinyFrontV3Snapshot* front_snap =
|
||||
__builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL;
|
||||
// Phase 4 E1: Use ENV snapshot when enabled (consolidates 3 TLS reads → 1)
|
||||
const TinyFrontV3Snapshot* front_snap;
|
||||
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;
|
||||
} else {
|
||||
front_snap = __builtin_expect(tiny_front_v3_enabled(), 0) ? tiny_front_v3_snapshot_get() : NULL;
|
||||
}
|
||||
|
||||
// TWO-SPEED: SuperSlab registration check is DEBUG-ONLY to keep HOT PATH fast.
|
||||
// In Release builds, we trust header magic (0xA0) as sufficient validation.
|
||||
|
||||
Reference in New Issue
Block a user