1a8652a91a
Implement C6 ULTRA intrusive LIFO freelist with ENV gating: - Single-linked LIFO using next pointer at USER+1 offset - tiny_next_store/tiny_next_load for pointer access (single source of truth) - Segment learning via ss_fast_lookup (per-class seg_base/seg_end) - ENV gate: HAKMEM_TINY_C6_ULTRA_INTRUSIVE_FL (default OFF) - Counters: c6_ifl_push/pop/fallback in FREE_PATH_STATS Files: - core/box/tiny_ultra_tls_box.h: Added c6_head field for intrusive LIFO - core/box/tiny_ultra_tls_box.c: Pop/push with intrusive branching (case 6) - core/box/tiny_c6_ultra_intrusive_env_box.h: ENV gate (new) - core/box/tiny_c6_intrusive_freelist_box.h: L1 pure LIFO (new) - core/tiny_debug_ring.h: C6_IFL events - core/box/free_path_stats_box.h/c: c6_ifl_* counters A/B Test Results (1M iterations, ws=200, 257-512B): - ENV_OFF (array): 56.6 Mop/s avg - ENV_ON (intrusive): 57.6 Mop/s avg (+1.8%, within noise) - Counters verified: c6_ifl_push=265890, c6_ifl_pop=265815, fallback=0 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
79 lines
2.7 KiB
C
79 lines
2.7 KiB
C
// tiny_ultra_tls_box.h - Phase TLS-UNIFY-1: Unified ULTRA TLS API
|
|
//
|
|
// Goal: Single API for C4-C7 ULTRA TLS operations
|
|
// Phase 1: Thin wrapper delegating to existing TinyC*UltraFreeTLS
|
|
// Phase 2: Replace with unified struct (1 cache line hot path)
|
|
//
|
|
#ifndef HAKMEM_TINY_ULTRA_TLS_BOX_H
|
|
#define HAKMEM_TINY_ULTRA_TLS_BOX_H
|
|
|
|
#include <stdint.h>
|
|
#include <stdbool.h>
|
|
|
|
// ============================================================================
|
|
// TinyUltraTlsCtx - Unified TLS context (Phase TLS-UNIFY-2a + TLS-UNIFY-3)
|
|
// ============================================================================
|
|
//
|
|
// Phase 1: Thin wrapper delegating to per-class TLS (completed)
|
|
// Phase 2a: Unified struct with array magazines for C4-C6 (completed)
|
|
// C7 remains in separate TinyC7Ultra box.
|
|
// Phase 3: C6 intrusive LIFO (current) - ENV gated
|
|
//
|
|
// Capacity constants
|
|
#define TINY_ULTRA_C4_CAP 64
|
|
#define TINY_ULTRA_C5_CAP 64
|
|
#define TINY_ULTRA_C6_CAP 128
|
|
|
|
typedef struct TinyUltraTlsCtx {
|
|
// Hot line: counts (8B aligned)
|
|
uint16_t c4_count;
|
|
uint16_t c5_count;
|
|
uint16_t c6_count;
|
|
uint16_t _pad_count;
|
|
|
|
// C6 intrusive LIFO head (Phase TLS-UNIFY-3)
|
|
// Used when HAKMEM_TINY_C6_ULTRA_INTRUSIVE_FL=1
|
|
void* c6_head;
|
|
|
|
// Per-class segment ranges (learned on first free)
|
|
uintptr_t c4_seg_base;
|
|
uintptr_t c4_seg_end;
|
|
uintptr_t c5_seg_base;
|
|
uintptr_t c5_seg_end;
|
|
uintptr_t c6_seg_base;
|
|
uintptr_t c6_seg_end;
|
|
|
|
// Per-class array magazines (C4/C5 always, C6 when intrusive OFF)
|
|
void* c4_freelist[TINY_ULTRA_C4_CAP]; // 512B
|
|
void* c5_freelist[TINY_ULTRA_C5_CAP]; // 512B
|
|
void* c6_freelist[TINY_ULTRA_C6_CAP]; // 1024B (kept for ENV_OFF fallback)
|
|
// Total: ~2KB per thread (acceptable for array magazine design)
|
|
|
|
// Note: C7 is NOT included here - uses separate TinyC7Ultra box
|
|
} TinyUltraTlsCtx;
|
|
|
|
// ============================================================================
|
|
// Unified API
|
|
// ============================================================================
|
|
|
|
// Get TLS context (Phase 1: returns dummy, Phase 2: returns actual unified ctx)
|
|
TinyUltraTlsCtx* tiny_ultra_tls_ctx(void);
|
|
|
|
// Pop BASE pointer from TLS freelist (C4-C7)
|
|
// Returns: BASE pointer on hit, NULL on miss (caller should fallback)
|
|
// class_idx: 4, 5, 6, or 7
|
|
void* tiny_ultra_tls_pop(uint8_t class_idx);
|
|
|
|
// Push BASE pointer to TLS freelist (C4-C7)
|
|
// class_idx: 4, 5, 6, or 7
|
|
// base: BASE pointer (not user pointer)
|
|
void tiny_ultra_tls_push(uint8_t class_idx, void* base);
|
|
|
|
// Check if unified TLS is enabled (ENV gate)
|
|
static inline int tiny_ultra_tls_unified_enabled(void) {
|
|
// Phase 1: Always enabled (thin wrapper mode)
|
|
return 1;
|
|
}
|
|
|
|
#endif // HAKMEM_TINY_ULTRA_TLS_BOX_H
|