From 2198cd0524574f0d9df8c0ec9aaf14ad8c94402b Mon Sep 17 00:00:00 2001 From: Joost VandeVondele Date: Mon, 18 Dec 2017 16:32:21 +0100 Subject: [PATCH] Allow for general transposition table sizes. (#1341) For efficiency reasons current master only allows for transposition table sizes that are N = 2^k in size, the index computation can be done efficiently as (hash % N) can be written instead as (hash & 2^k - 1). On a typical computer (with 4, 8... etc Gb of RAM), this implies roughly half the RAM is left unused in analysis. This issue was mentioned on fishcooking by Mindbreaker: http://tests.stockfishchess.org/tests/view/5a3587de0ebc590ccbb8be04 Recently a neat trick was proposed to map a hash into the range [0,N[ more efficiently than (hash % N) for general N, nearly as efficiently as (hash % 2^k): https://lemire.me/blog/2016/06/27/a-fast-alternative-to-the-modulo-reduction/ namely computing (hash * N / 2^32) for 32 bit hashes. This patch implements this trick and now allows for general hash sizes. Note that for N = 2^k this just amounts to using a different subset of bits from the hash. Master will use the lower k bits, this trick will use the upper k bits (of the 32 bit hash). There is no slowdown as measured with [-3, 1] test: http://tests.stockfishchess.org/tests/view/5a3587de0ebc590ccbb8be04 LLR: 2.96 (-2.94,2.94) [-3.00,1.00] Total: 128498 W: 23332 L: 23395 D: 81771 There are two (smaller) caveats: 1) the patch is implemented for a 32 bit hash (so that a 64 bit multiply can be used), this effectively limits the number of clusters that can be used to 2^32 or to 128Gb of transpostion table. That's a change in the maximum allowed TT size, which could bother those using 256Gb or more regularly. 2) Already in master, an excluded move is hashed into the position key in rather simple way, essentially only affecting the lower 16 bits of the key. This is OK in master, since bits 0-15 end up in the index, but not in the new scheme, which picks the higher bits. This is 'fixed' by shifting the excluded move a few bits up. Eventually a better hashing scheme seems wise. Despite these two caveats, I think this is a nice improvement in usability. Bench: 5346341 --- src/search.cpp | 2 +- src/tt.cpp | 2 +- src/tt.h | 4 ++-- src/ucioption.cpp | 3 ++- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/src/search.cpp b/src/search.cpp index 8b3b8fb4..1aa3e92e 100644 --- a/src/search.cpp +++ b/src/search.cpp @@ -557,7 +557,7 @@ namespace { // search to overwrite a previous full search TT value, so we use a different // position key in case of an excluded move. excludedMove = ss->excludedMove; - posKey = pos.key() ^ Key(excludedMove); + posKey = pos.key() ^ Key(excludedMove << 16); // isn't a very good hash tte = TT.probe(posKey, ttHit); ttValue = ttHit ? value_from_tt(tte->value(), ss->ply) : VALUE_NONE; ttMove = rootNode ? thisThread->rootMoves[thisThread->PVIdx].pv[0] diff --git a/src/tt.cpp b/src/tt.cpp index f283d0c6..a1ef4442 100644 --- a/src/tt.cpp +++ b/src/tt.cpp @@ -33,7 +33,7 @@ TranspositionTable TT; // Our global transposition table void TranspositionTable::resize(size_t mbSize) { - size_t newClusterCount = size_t(1) << msb((mbSize * 1024 * 1024) / sizeof(Cluster)); + size_t newClusterCount = mbSize * 1024 * 1024 / sizeof(Cluster); if (newClusterCount == clusterCount) return; diff --git a/src/tt.h b/src/tt.h index 24045ed0..e1bef323 100644 --- a/src/tt.h +++ b/src/tt.h @@ -104,9 +104,9 @@ public: void resize(size_t mbSize); void clear(); - // The lowest order bits of the key are used to get the index of the cluster + // The 32 lowest order bits of the key are used to get the index of the cluster TTEntry* first_entry(const Key key) const { - return &table[(size_t)key & (clusterCount - 1)].entry[0]; + return &table[(uint32_t(key) * uint64_t(clusterCount)) >> 32].entry[0]; } private: diff --git a/src/ucioption.cpp b/src/ucioption.cpp index b902677f..f85ede18 100644 --- a/src/ucioption.cpp +++ b/src/ucioption.cpp @@ -55,7 +55,8 @@ bool CaseInsensitiveLess::operator() (const string& s1, const string& s2) const void init(OptionsMap& o) { - const int MaxHashMB = Is64Bit ? 1024 * 1024 : 2048; + // at most 2^32 clusters. + const int MaxHashMB = Is64Bit ? 131072 : 2048; o["Debug Log File"] << Option("", on_logger); o["Contempt"] << Option(0, -100, 100); -- 2.30.2