Use 128 bit multiply for TT index

[stockfish] / src / tt.cpp

diff --git a/src/tt.cpp b/src/tt.cpp
index 92aaee001824276e49f1090c72ec451070900dd0..d0a5d4e0aa96ab948129a0706f4262de34886e5c 100644 (file)
--- a/src/tt.cpp
+++ b/src/tt.cpp
@@ -36,17 +36,17 @@ TranspositionTable TT; // Our global transposition table
 void TTEntry::save(Key k, Value v, bool pv, Bound b, Depth d, Move m, Value ev) {
 
   // Preserve any existing move for the same position
-  if (m || (k >> 48) != key16)
+  if (m || (uint16_t)k != key16)
       move16 = (uint16_t)m;
 
   // Overwrite less valuable entries
-  if (  (k >> 48) != key16
+  if ((uint16_t)k != key16
       || d - DEPTH_OFFSET > depth8 - 4
       || b == BOUND_EXACT)
   {
       assert(d >= DEPTH_OFFSET);
 
-      key16     = (uint16_t)(k >> 48);
+      key16     = (uint16_t)k;
       value16   = (int16_t)v;
       eval16    = (int16_t)ev;
       genBound8 = (uint8_t)(TT.generation8 | uint8_t(pv) << 2 | b);
@@ -65,10 +65,8 @@ void TranspositionTable::resize(size_t mbSize) {
 
   aligned_ttmem_free(mem);
 
-  superClusterCount = mbSize * 1024 * 1024 / (sizeof(Cluster) * ClustersPerSuperCluster);
-
-  table = static_cast<Cluster*>(
-      aligned_ttmem_alloc(superClusterCount * ClustersPerSuperCluster * sizeof(Cluster), mem));
+  clusterCount = mbSize * 1024 * 1024 / sizeof(Cluster);
+  table = static_cast<Cluster*>(aligned_ttmem_alloc(clusterCount * sizeof(Cluster), mem));
   if (!mem)
   {
       std::cerr << "Failed to allocate " << mbSize
@@ -91,8 +89,6 @@ void TranspositionTable::clear() {
   {
       threads.emplace_back([this, idx]() {
 
-          const size_t clusterCount = superClusterCount * ClustersPerSuperCluster;
-
           // Thread binding gives faster search on systems with a first-touch policy
           if (Options["Threads"] > 8)
               WinProcGroup::bindThisThread(idx);
@@ -121,7 +117,7 @@ void TranspositionTable::clear() {
 TTEntry* TranspositionTable::probe(const Key key, bool& found) const {
 
   TTEntry* const tte = first_entry(key);
-  const uint16_t key16 = key >> 48;  // Use the high 16 bits as key inside the cluster
+  const uint16_t key16 = (uint16_t)key;  // Use the low 16 bits as key inside the cluster
 
   for (int i = 0; i < ClusterSize; ++i)
       if (!tte[i].key16 || tte[i].key16 == key16)