Optimized bitScanReverse32()

[stockfish] / src / bitboard.cpp

diff --git a/src/bitboard.cpp b/src/bitboard.cpp
index 6f1569250a7fe6681c080733c86370fc32b46f0c..380c5985c1603ac50afc4a616673998f1e9ac83c 100644 (file)
--- a/src/bitboard.cpp
+++ b/src/bitboard.cpp
@@ -348,24 +348,60 @@ union b_union {
 
 Square pop_1st_bit(Bitboard* bb) {
 
-   b_union* u;
+   b_union u;
    Square ret;
 
-   u = (b_union*)bb;
+   u.b = *bb;
 
-   if (u->dw.l)
+   if (u.dw.l)
    {
-       ret = Square(BitTable[((u->dw.l ^ (u->dw.l - 1)) * 0x783a9b23) >> 26]);
-       u->dw.l &= (u->dw.l - 1);
+       ret = Square(BitTable[((u.dw.l ^ (u.dw.l - 1)) * 0x783a9b23) >> 26]);
+       u.dw.l &= (u.dw.l - 1);
+       *bb = u.b;
        return ret;
    }
-   ret = Square(BitTable[((~(u->dw.h ^ (u->dw.h - 1))) * 0x783a9b23) >> 26]);
-   u->dw.h &= (u->dw.h - 1);
+   ret = Square(BitTable[((~(u.dw.h ^ (u.dw.h - 1))) * 0x783a9b23) >> 26]);
+   u.dw.h &= (u.dw.h - 1);
+   *bb = u.b;
    return ret;
 }
 
 #endif
 
+// Optimized bitScanReverse32() implementation by Pascal Georges. Note
+// that first bit is 1, this allow to differentiate between 0 and 1.
+static CACHE_LINE_ALIGNMENT
+const char MsbTable[256] = {
+  0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5,
+  5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+  6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7,
+  7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+  7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+  7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+  8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+  8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+  8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+  8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+  8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8
+};
+
+int bitScanReverse32(uint32_t b)
+{
+   int result = 0;
+
+   if (b > 0xFFFF)
+   {
+      b >>= 16;
+      result += 16;
+   }
+   if (b > 0xFF)
+   {
+      b >>= 8;
+      result += 8;
+   }
+   return result + MsbTable[b];
+}
+
 namespace {
 
   // All functions below are used to precompute various bitboards during