d9991f39ff
Add comprehensive design docs and research boxes: - docs/analysis/ALLOC_TINY_FAST_DUALHOT_1_DESIGN.md: ALLOC DUALHOT investigation - docs/analysis/FREE_TINY_FAST_DUALHOT_1_DESIGN.md: FREE DUALHOT final specs - docs/analysis/FREE_TINY_FAST_HOTCOLD_OPT_1_DESIGN.md: Hot/Cold split research - docs/analysis/POOL_MID_INUSE_DEFERRED_DN_BATCH_DESIGN.md: Deferred batching design - docs/analysis/POOL_MID_INUSE_DEFERRED_REGRESSION_ANALYSIS.md: Stats overhead findings - docs/analysis/MID_DESC_CACHE_BENCHMARK_2025-12-12.md: Cache measurement results - docs/analysis/LAST_MATCH_CACHE_IMPLEMENTATION.md: TLS cache investigation Research boxes (SS page table): - core/box/ss_pt_env_box.h: HAKMEM_SS_LOOKUP_KIND gate - core/box/ss_pt_types_box.h: 2-level page table structures - core/box/ss_pt_lookup_box.h: ss_pt_lookup() implementation - core/box/ss_pt_register_box.h: Page table registration - core/box/ss_pt_impl.c: Global definitions Updates: - docs/specs/ENV_VARS_COMPLETE.md: HOTCOLD, DEFERRED, SS_LOOKUP env vars - core/box/hak_free_api.inc.h: FREE-DISPATCH-SSOT integration - core/box/pool_mid_inuse_deferred_box.h: Deferred API updates - core/box/pool_mid_inuse_deferred_stats_box.h: Stats collection - core/hakmem_super_registry: SS page table integration Current Status: - FREE-TINY-FAST-DUALHOT-1: +13% improvement, ready for adoption - ALLOC-TINY-FAST-DUALHOT-1: -2% regression, frozen as research box - Next: Optimization roadmap per ROI (mimalloc gap 2.5x) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
37 lines
1.0 KiB
C
37 lines
1.0 KiB
C
#ifndef SS_PT_LOOKUP_BOX_H
|
|
#define SS_PT_LOOKUP_BOX_H
|
|
|
|
#include "ss_pt_types_box.h"
|
|
#include "ss_pt_env_box.h"
|
|
|
|
// O(1) lookup (hot path, lock-free)
|
|
static inline struct SuperSlab* ss_pt_lookup(void* addr) {
|
|
uintptr_t p = (uintptr_t)addr;
|
|
|
|
// Out-of-range check (>> 48 for LA57 compatibility)
|
|
if (__builtin_expect(p >> 48, 0)) {
|
|
if (hak_ss_pt_stats_enabled()) t_ss_pt_stats.pt_out_of_range++;
|
|
return NULL; // Fallback to hash handled by caller
|
|
}
|
|
|
|
uint32_t l1_idx = SS_PT_L1_INDEX(addr);
|
|
uint32_t l2_idx = SS_PT_L2_INDEX(addr);
|
|
|
|
// L1 load (acquire)
|
|
SsPtL2* l2 = atomic_load_explicit(&g_ss_pt.l2[l1_idx], memory_order_acquire);
|
|
if (__builtin_expect(l2 == NULL, 0)) {
|
|
if (hak_ss_pt_stats_enabled()) t_ss_pt_stats.pt_miss++;
|
|
return NULL;
|
|
}
|
|
|
|
// L2 load (acquire)
|
|
struct SuperSlab* ss = atomic_load_explicit(&l2->entries[l2_idx], memory_order_acquire);
|
|
if (hak_ss_pt_stats_enabled()) {
|
|
if (ss) t_ss_pt_stats.pt_hit++;
|
|
else t_ss_pt_stats.pt_miss++;
|
|
}
|
|
return ss;
|
|
}
|
|
|
|
#endif
|