#include "movegen.h"
#include "tt.h"
-
-/// This is the number of TTEntry slots for each position
-static const int ClusterSize = 5;
-
+// The main transposition table
+TranspositionTable TT;
////
//// Functions
// We store a cluster of ClusterSize number of TTEntry for each position
// and newSize is the maximum number of storable positions.
- while ((2 * newSize) * ClusterSize * (sizeof(TTEntry)) <= (mbSize << 20))
+ while ((2 * newSize) * sizeof(TTCluster) <= (mbSize << 20))
newSize *= 2;
if (newSize != size)
{
size = newSize;
delete [] entries;
- entries = new TTEntry[size * ClusterSize];
+ entries = new TTCluster[size];
if (!entries)
{
std::cerr << "Failed to allocate " << mbSize
void TranspositionTable::clear() {
- memset(entries, 0, size * ClusterSize * sizeof(TTEntry));
+ memset(entries, 0, size * sizeof(TTCluster));
}
inline TTEntry* TranspositionTable::first_entry(const Key posKey) const {
- return entries + ((uint32_t(posKey) & (size - 1)) * ClusterSize);
+ return entries[uint32_t(posKey) & (size - 1)].data;
}
/// blocking function and do not stalls the CPU waiting for data
/// to be loaded from RAM, that can be very slow. When we will
/// subsequently call retrieve() the TT data will be already
-/// quickly accessible in L1/l2 CPU cache.
+/// quickly accessible in L1/L2 CPU cache.
void TranspositionTable::prefetch(const Key posKey) const {
- _mm_prefetch((char*)first_entry(posKey), _MM_HINT_T0);
+#if defined(__INTEL_COMPILER) || defined(__ICL)
+ // This hack prevents prefetches to be optimized away by the
+ // Intel compiler. Both MSVC and gcc seems not affected.
+ __asm__ ("");
+#endif
+
+ char const* addr = (char*)first_entry(posKey);
+ _mm_prefetch(addr, _MM_HINT_T2);
+ _mm_prefetch(addr+64, _MM_HINT_T2); // 64 bytes ahead
}