Increase the maximum hash size by a factor of 256

[stockfish] / src / tt.cpp

diff --git a/src/tt.cpp b/src/tt.cpp
index b8fe7567c569a6a3d633c2d9b086fcd39fafd96d..92aaee001824276e49f1090c72ec451070900dd0 100644 (file)
--- a/src/tt.cpp
+++ b/src/tt.cpp
@@ -2,7 +2,7 @@
   Stockfish, a UCI chess playing engine derived from Glaurung 2.1
   Copyright (C) 2004-2008 Tord Romstad (Glaurung author)
   Copyright (C) 2008-2015 Marco Costalba, Joona Kiiski, Tord Romstad
-  Copyright (C) 2015-2019 Marco Costalba, Joona Kiiski, Gary Linscott, Tord Romstad
+  Copyright (C) 2015-2020 Marco Costalba, Joona Kiiski, Gary Linscott, Tord Romstad
 
   Stockfish is free software: you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
@@ -35,23 +35,22 @@ TranspositionTable TT; // Our global transposition table
 
 void TTEntry::save(Key k, Value v, bool pv, Bound b, Depth d, Move m, Value ev) {
 
-  assert(d / ONE_PLY * ONE_PLY == d);
-
   // Preserve any existing move for the same position
   if (m || (k >> 48) != key16)
       move16 = (uint16_t)m;
 
   // Overwrite less valuable entries
   if (  (k >> 48) != key16
-      || d / ONE_PLY + 10 > depth8
+      || d - DEPTH_OFFSET > depth8 - 4
       || b == BOUND_EXACT)
   {
+      assert(d >= DEPTH_OFFSET);
+
       key16     = (uint16_t)(k >> 48);
       value16   = (int16_t)v;
       eval16    = (int16_t)ev;
       genBound8 = (uint8_t)(TT.generation8 | uint8_t(pv) << 2 | b);
-      assert((d - DEPTH_NONE) / ONE_PLY >= 0);
-      depth8    = (uint8_t)((d - DEPTH_NONE) / ONE_PLY);
+      depth8    = (uint8_t)(d - DEPTH_OFFSET);
   }
 }
 
@@ -64,11 +63,12 @@ void TranspositionTable::resize(size_t mbSize) {
 
   Threads.main()->wait_for_search_finished();
 
-  clusterCount = mbSize * 1024 * 1024 / sizeof(Cluster);
+  aligned_ttmem_free(mem);
 
-  free(mem);
-  mem = malloc(clusterCount * sizeof(Cluster) + CacheLineSize - 1);
+  superClusterCount = mbSize * 1024 * 1024 / (sizeof(Cluster) * ClustersPerSuperCluster);
 
+  table = static_cast<Cluster*>(
+      aligned_ttmem_alloc(superClusterCount * ClustersPerSuperCluster * sizeof(Cluster), mem));
   if (!mem)
   {
       std::cerr << "Failed to allocate " << mbSize
@@ -76,7 +76,6 @@ void TranspositionTable::resize(size_t mbSize) {
       exit(EXIT_FAILURE);
   }
 
-  table = (Cluster*)((uintptr_t(mem) + CacheLineSize - 1) & ~(CacheLineSize - 1));
   clear();
 }
 
@@ -92,13 +91,15 @@ 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);
 
           // Each thread will zero its part of the hash table
-          const size_t stride = clusterCount / Options["Threads"],
-                       start  = stride * idx,
+          const size_t stride = size_t(clusterCount / Options["Threads"]),
+                       start  = size_t(stride * idx),
                        len    = idx != Options["Threads"] - 1 ?
                                 stride : clusterCount - start;
 
@@ -106,7 +107,7 @@ void TranspositionTable::clear() {
       });
   }
 
-  for (std::thread& th: threads)
+  for (std::thread& th : threads)
       th.join();
 }
 
@@ -151,9 +152,9 @@ TTEntry* TranspositionTable::probe(const Key key, bool& found) const {
 int TranspositionTable::hashfull() const {
 
   int cnt = 0;
-  for (int i = 0; i < 1000 / ClusterSize; ++i)
+  for (int i = 0; i < 1000; ++i)
       for (int j = 0; j < ClusterSize; ++j)
           cnt += (table[i].entry[j].genBound8 & 0xF8) == generation8;
 
-  return cnt * 1000 / (ClusterSize * (1000 / ClusterSize));
+  return cnt / ClusterSize;
 }