Boxify superslab registry, add bench profile, and document C7 hotpath experiments

core/box/remote_side_box.c

@@ -0,0 +1,88 @@
+#include "remote_side_box.h"
+
+#include <stdatomic.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifndef REM_SIDE_LOG2
+#define REM_SIDE_LOG2 20
+#endif
+
+static _Atomic uint32_t g_remote_log2 = REM_SIDE_LOG2;
+static _Atomic uint32_t g_remote_size = (1u << REM_SIDE_LOG2);
+static _Atomic uint32_t g_remote_mask = (1u << REM_SIDE_LOG2) - 1;
+static _Atomic int g_remote_profile_inited = 0;
+static rem_side_entry* g_remote_slots = NULL;
+static _Atomic int g_remote_allocated = 0;
+
+static void remote_side_apply_profile(const char* profile) {
+    if (g_remote_profile_inited) {
+        return;
+    }
+    const char* env_profile = profile ? profile : getenv("HAKMEM_PROFILE");
+    int is_bench = (env_profile && strcmp(env_profile, "bench") == 0);
+
+    uint32_t log2 = REM_SIDE_LOG2;
+    if (is_bench && REM_SIDE_LOG2 > 4) {
+        // bench 用: ハッシュ幅だけ 1/8〜1/16 程度に論理縮小
+        log2 = REM_SIDE_LOG2 - 3;  // 1/8
+        if (log2 < 12) {
+            log2 = 12;  // 4096 entries までは確保
+        }
+    }
+
+    uint32_t size = (1u << log2);
+    uint32_t mask = size - 1;
+
+    atomic_store_explicit(&g_remote_log2, log2, memory_order_relaxed);
+    atomic_store_explicit(&g_remote_size, size, memory_order_relaxed);
+    atomic_store_explicit(&g_remote_mask, mask, memory_order_relaxed);
+    atomic_store_explicit(&g_remote_profile_inited, 1, memory_order_release);
+}
+
+void remote_side_init(RemoteSideBox* box, const char* profile) {
+    (void)box;
+    remote_side_apply_profile(profile);
+
+    if (atomic_load_explicit(&g_remote_allocated, memory_order_acquire)) {
+        return;
+    }
+
+    uint32_t size = remote_side_effective_size();
+    g_remote_slots = (rem_side_entry*)calloc(size, sizeof(rem_side_entry));
+    if (!g_remote_slots) {
+        fprintf(stderr, "[REMOTE_SIDE] failed to allocate %zu bytes\n",
+                (size_t)size * sizeof(rem_side_entry));
+        abort();
+    }
+    atomic_store_explicit(&g_remote_allocated, 1, memory_order_release);
+}
+
+uint32_t remote_side_effective_log2(void) {
+    if (!atomic_load_explicit(&g_remote_profile_inited, memory_order_acquire)) {
+        remote_side_apply_profile(NULL);
+    }
+    return atomic_load_explicit(&g_remote_log2, memory_order_relaxed);
+}
+
+uint32_t remote_side_effective_size(void) {
+    if (!atomic_load_explicit(&g_remote_profile_inited, memory_order_acquire)) {
+        remote_side_apply_profile(NULL);
+    }
+    return atomic_load_explicit(&g_remote_size, memory_order_relaxed);
+}
+
+uint32_t remote_side_effective_mask(void) {
+    if (!atomic_load_explicit(&g_remote_profile_inited, memory_order_acquire)) {
+        remote_side_apply_profile(NULL);
+    }
+    return atomic_load_explicit(&g_remote_mask, memory_order_relaxed);
+}
+
+rem_side_entry* remote_side_table(void) {
+    if (!atomic_load_explicit(&g_remote_allocated, memory_order_acquire)) {
+        remote_side_init(NULL, NULL);
+    }
+    return g_remote_slots;
+}