47797a3ba0
Changes - core/hakmem_tiny_config.c: set g_fast_cap_defaults[7]=64 (was 0) to reduce SuperSlab path frequency for 1024B. - core/tiny_remote.c: add env HAKMEM_TINY_ASSUME_1T=1 to disable Remote Side table in single‑thread runs (A/B friendly). A/B (1T, cpu2 pinned, 500k iters) - 256B: cycles ↓ ~119.7M → ~60.0M, time 95.4ms → 83.2ms (~12% faster), IPC ~0.92→0.88, branch‑miss ~11%. - 1024B: cycles ↓ ~74.4M → ~27.3M, time 83.3ms → 73.5ms (~12% faster), IPC ~0.82→0.75, branch‑miss ~11%. Notes - Branch‑miss率は依然高め。今後: adopt境界の分岐整理、超シンプルrefill（class7特例）/fast path優先度の再調整で詰める。 - A/B: export HAKMEM_TINY_ASSUME_1T=1 で1T時にRemote SideをOFF。HAKMEM_TINY_REMOTE_SIDEで明示的制御も可。
71 lines
2.1 KiB
C
71 lines
2.1 KiB
C
/**
|
||
* hakmem_tiny_config.c
|
||
*
|
||
* Implementation of centralized Tiny configuration constants
|
||
*/
|
||
|
||
#include "hakmem_tiny_config.h"
|
||
|
||
// ============================================================================
|
||
// Fast Cache Configuration
|
||
// ============================================================================
|
||
|
||
// Factory defaults (“balanced”) – mutable at runtime
|
||
static const uint16_t k_fast_cap_defaults_factory[TINY_NUM_CLASSES] = {
|
||
128, // Class 0: 8B
|
||
128, // Class 1: 16B
|
||
128, // Class 2: 32B
|
||
128, // Class 3: 64B (reduced from 512 to limit RSS)
|
||
128, // Class 4: 128B (trimmed via ACE/TLS caps)
|
||
128, // Class 5: 256B
|
||
128, // Class 6: 512B
|
||
64 // Class 7: 1KB (enable small fast cache to reduce Superslab path)
|
||
};
|
||
|
||
uint16_t g_fast_cap_defaults[TINY_NUM_CLASSES] = {
|
||
128, 128, 128, 128, 128, 128, 128, 64
|
||
};
|
||
|
||
void tiny_config_reset_defaults(void) {
|
||
for (int i = 0; i < TINY_NUM_CLASSES; i++) {
|
||
g_fast_cap_defaults[i] = k_fast_cap_defaults_factory[i];
|
||
}
|
||
}
|
||
|
||
// ============================================================================
|
||
// TLS Magazine Configuration
|
||
// ============================================================================
|
||
|
||
// Default TLS magazine capacities per class
|
||
int tiny_default_cap(int class_idx) {
|
||
switch (class_idx) {
|
||
case 0: return 128; // 8B
|
||
case 1: return 128; // 16B
|
||
case 2: return 128; // 32B
|
||
case 3: return 128; // 64B (reduced from 512 to limit RSS)
|
||
case 4: return 96; // 128B (aggressively trimmed to limit RSS)
|
||
case 5: return 128; // 256B
|
||
case 6: return 128; // 512B
|
||
default: return 64; // 1KB
|
||
}
|
||
}
|
||
|
||
// Alias for tiny_default_cap
|
||
int tiny_mag_default_cap(int class_idx) {
|
||
return tiny_default_cap(class_idx);
|
||
}
|
||
|
||
// Maximum allowed TLS magazine capacities per class
|
||
int tiny_cap_max_for_class(int class_idx) {
|
||
switch (class_idx) {
|
||
case 0: return 2048;
|
||
case 1: return 1024;
|
||
case 2: return 768;
|
||
case 3: return 512;
|
||
case 4: return 160;
|
||
case 5: return 256;
|
||
case 6: return 128;
|
||
default: return 64;
|
||
}
|
||
}
|