84f5034e45
Changes: - scripts/box/pgo_fast_profile_config.sh: Expanded WS patterns (3→5) and seeds (1→3) for reduced overfitting and better production workload representativeness - PERFORMANCE_TARGETS_SCORECARD.md: Phase 68 baseline promoted (61.614M = 50.93%) - CURRENT_TASK.md: Phase 68 marked complete, Phase 67a (layout tax forensics) set Active Results: - 10-run verification: +1.19% vs Phase 66 baseline (GO, >+1.0% threshold) - M1 milestone: 50.93% of mimalloc (target 50%, exceeded by +0.93pp) - Stability: 10-run mean/median with <2.1% CV 🤖 Generated with Claude Code Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
96 lines
3.8 KiB
C
96 lines
3.8 KiB
C
// hakmem_env_snapshot_box.h - Phase 4 E1: ENV Snapshot Consolidation
|
|
//
|
|
// Purpose: Consolidate 3 hot ENV gate calls into 1 TLS snapshot read
|
|
// Target: tiny_c7_ultra_enabled_env (1.28%) + tiny_front_v3_enabled (1.01%) +
|
|
// tiny_metadata_cache_enabled (0.97%) = 3.26% combined ENV overhead
|
|
//
|
|
// Design:
|
|
// - ENV: HAKMEM_ENV_SNAPSHOT=0/1 (default 0, research box)
|
|
// - Single TLS snapshot struct containing all hot toggles
|
|
// - Lazy init with version-based refresh (follows tiny_front_v3_snapshot pattern)
|
|
// - Learner interlock: tiny_metadata_cache_eff = cache && !learner
|
|
//
|
|
// E3-4 Extension: Constructor init to eliminate lazy check overhead
|
|
// - ENV: HAKMEM_ENV_SNAPSHOT_CTOR=0/1 (default 0)
|
|
// - When =1: Gate init runs in constructor (before main)
|
|
// - Eliminates 3.22% lazy init check overhead
|
|
//
|
|
// Benefits:
|
|
// - 3 TLS reads → 1 TLS read (66% reduction)
|
|
// - 3 lazy init checks → 1 lazy init check
|
|
// - E3-4: Lazy init check → no check (constructor init)
|
|
// - Expected gain: +1-3% (E1) + +0.5-1.5% (E3-4)
|
|
|
|
#ifndef HAK_ENV_SNAPSHOT_BOX_H
|
|
#define HAK_ENV_SNAPSHOT_BOX_H
|
|
|
|
#include <stdbool.h>
|
|
#include <stdlib.h>
|
|
|
|
// ENV snapshot struct: consolidates all hot ENV gates
|
|
typedef struct HakmemEnvSnapshot {
|
|
bool tiny_c7_ultra_enabled; // ENV: HAKMEM_TINY_C7_ULTRA (default 1)
|
|
bool tiny_front_v3_enabled; // ENV: HAKMEM_TINY_FRONT_V3_ENABLED (default 1)
|
|
bool tiny_metadata_cache; // ENV: HAKMEM_TINY_METADATA_CACHE (default 0)
|
|
bool tiny_metadata_cache_eff; // Effective: cache && !learner (for hot path)
|
|
} HakmemEnvSnapshot;
|
|
|
|
// Global snapshot state (implemented in hakmem_env_snapshot_box.c)
|
|
extern HakmemEnvSnapshot g_hakmem_env_snapshot;
|
|
extern int g_hakmem_env_snapshot_ready;
|
|
|
|
// Snapshot initializer (implemented in hakmem_env_snapshot_box.c)
|
|
void hakmem_env_snapshot_init(void);
|
|
|
|
// Refresh from ENV (for bench_profile putenv sync)
|
|
void hakmem_env_snapshot_refresh_from_env(void);
|
|
|
|
// Fast snapshot getter: lazy init + 1 TLS read
|
|
static inline const HakmemEnvSnapshot* hakmem_env_snapshot(void) {
|
|
if (__builtin_expect(!g_hakmem_env_snapshot_ready, 0)) {
|
|
hakmem_env_snapshot_init();
|
|
}
|
|
return &g_hakmem_env_snapshot;
|
|
}
|
|
|
|
// E3-4: Global gate state (defined in hakmem_env_snapshot_box.c)
|
|
extern int g_hakmem_env_snapshot_gate;
|
|
extern int g_hakmem_env_snapshot_ctor_mode;
|
|
|
|
// ENV gate: default OFF (research box, set =1 to enable)
|
|
// E3-4: Dual-mode - constructor init (fast) or legacy lazy init (fallback)
|
|
// Phase 18 v2: BENCH_MINIMAL conditional (constant return when HAKMEM_BENCH_MINIMAL=1)
|
|
// Phase 63: FAST_PROFILE_FIXED conditional (constant return for FAST profile builds)
|
|
#if HAKMEM_BENCH_MINIMAL || HAKMEM_FAST_PROFILE_FIXED
|
|
// In bench mode, snapshot is always enabled (one-time cost, compile-away benefit)
|
|
static inline bool hakmem_env_snapshot_enabled(void) {
|
|
return 1;
|
|
}
|
|
#else
|
|
// Normal mode: runtime check
|
|
static inline bool hakmem_env_snapshot_enabled(void) {
|
|
// E3-4 Fast path: constructor mode (no lazy check, just global read).
|
|
// Important: do not put a static LIKELY/UNLIKELY hint here.
|
|
// - Default runs want ctor_mode==0 to be "fast"
|
|
// - CTOR runs want ctor_mode==1 to be "fast"
|
|
// Any fixed hint will be wrong for one of the modes and can induce steady-state mispredicts.
|
|
int ctor_mode = g_hakmem_env_snapshot_ctor_mode;
|
|
if (ctor_mode == 1) {
|
|
return g_hakmem_env_snapshot_gate != 0;
|
|
}
|
|
|
|
// Legacy path: lazy init (fallback when HAKMEM_ENV_SNAPSHOT_CTOR=0)
|
|
if (__builtin_expect(g_hakmem_env_snapshot_gate == -1, 0)) {
|
|
const char* e = getenv("HAKMEM_ENV_SNAPSHOT");
|
|
if (e && *e) {
|
|
g_hakmem_env_snapshot_gate = (*e == '1') ? 1 : 0;
|
|
} else {
|
|
g_hakmem_env_snapshot_gate = 0; // default: OFF (research box)
|
|
}
|
|
}
|
|
return g_hakmem_env_snapshot_gate != 0;
|
|
}
|
|
#endif
|
|
|
|
#endif // HAK_ENV_SNAPSHOT_BOX_H
|