X-Git-Url: https://git.sesse.net/?p=stockfish;a=blobdiff_plain;f=src%2Fbitcount.h;h=6b5f5b5789bb5f8b0b895fafa650566ceba107c2;hp=4747afc6aa73861e7a34785833352fc905c030e4;hb=72ab2cd3e98e694ef22316153a42462e2484b466;hpb=5d79af9e0d466572217dc47f5c307f6fd382a646

diff --git a/src/bitcount.h b/src/bitcount.h
index 4747afc6..6b5f5b57 100644
--- a/src/bitcount.h
+++ b/src/bitcount.h
@@ -22,19 +22,21 @@
 #if !defined(BITCOUNT_H_INCLUDED)
 #define BITCOUNT_H_INCLUDED
 
-// To disable POPCNT support uncomment following line. You should do it only
-// in PGO compiling to exercise the default fallback path. Don't forget to
-// re-comment the line for the final optimized compile though ;-)
-//#define DISABLE_POPCNT_SUPPORT
+// To enable POPCNT support uncomment USE_POPCNT define. For PGO compile on a Core i7
+// you may want to collect profile data first with USE_POPCNT disabled and then, in a
+// second profiling session, with USE_POPCNT enabled so to exercise both paths. Don't
+// forget to leave USE_POPCNT enabled for the final optimized compile though ;-)
+
+//#define USE_POPCNT
 
 
 #include "types.h"
 
 // Select type of intrinsic bit count instruction to use
 
-#if defined(_MSC_VER) && defined(_WIN64) // Microsoft compiler
+#if defined(__INTEL_COMPILER) && defined(IS_64BIT) && defined(USE_POPCNT) // Intel compiler
 
-#include <intrin.h>
+#include <nmmintrin.h>
 
 inline bool cpu_has_popcnt() {
 
@@ -43,11 +45,19 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-#define POPCNT_INTRINSIC(x) __popcnt64(x)
+// Define a dummy template to workaround a compile error if _mm_popcnt_u64() is not defined.
+//
+// If _mm_popcnt_u64() is defined in <nmmintrin.h> it will be choosen first due to
+// C++ overload rules that always prefer a function to a template with the same name.
+// If not, we avoid a compile error and because cpu_has_popcnt() should return false,
+// our templetized _mm_popcnt_u64() is never called anyway.
+template<typename T> inline unsigned _mm_popcnt_u64(T) { return 0; } // Is never called
 
-#elif defined(__INTEL_COMPILER) && (defined(__x86_64) || defined(_M_X64)) // Intel compiler
+#define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
 
-#include <nmmintrin.h>
+#elif defined(_MSC_VER) && defined(IS_64BIT) && defined(USE_POPCNT) // Microsoft compiler
+
+#include <intrin.h>
 
 inline bool cpu_has_popcnt() {
 
@@ -56,15 +66,18 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-#define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
+// See comment of _mm_popcnt_u64<>() few lines above for an explanation.
+template<typename T> inline unsigned __popcnt64(T) { return 0; } // Is never called
+
+#define POPCNT_INTRINSIC(x) __popcnt64(x)
 
-#else // Safe fallback for unsupported compilers
+#else // Safe fallback for unsupported compilers or when USE_POPCNT is disabled
 
 inline bool cpu_has_popcnt() { return false; }
 
-#define POPCNT_INTRINSIC(x) count_1s(x)
+#define POPCNT_INTRINSIC(x) 0
 
-#endif // cpu_has_popcnt() selection
+#endif // cpu_has_popcnt() and POPCNT_INTRINSIC() definitions
 
 
 /// Software implementation of bit count functions
@@ -131,18 +144,14 @@ inline int count_1s_max_15(Bitboard b) {
 }
 
 
-// Global variable initialized at startup that is set to true if
+// Global constant initialized at startup that is set to true if
 // CPU on which application runs supports POPCNT intrinsic. Unless
-// DISABLE_POPCNT_SUPPORT is defined.
-#if defined(DISABLE_POPCNT_SUPPORT)
-const bool CpuHasPOPCNT = false;
-#else
+// USE_POPCNT is not defined.
 const bool CpuHasPOPCNT = cpu_has_popcnt();
-#endif
 
 
-// Global variable used to print info about the use of 64 optimized
-// functions to verify that a 64bit compile has been correctly built.
+// Global constant used to print info about the use of 64 optimized
+// functions to verify that a 64 bit compile has been correctly built.
 #if defined(IS_64BIT)
 const bool CpuHas64BitPath = true;
 #else