Move __cpuid() definition for gcc in types.h

[stockfish] / src / bitcount.h

diff --git a/src/bitcount.h b/src/bitcount.h
index 9a3b481169b667943dedbb28cf538f977e02ca5e..43895180c1e9ae7566e16e3f35f29b93e00e18eb 100644 (file)
--- a/src/bitcount.h
+++ b/src/bitcount.h
@@ -22,20 +22,12 @@
 #if !defined(BITCOUNT_H_INCLUDED)
 #define BITCOUNT_H_INCLUDED
 
-// To disable POPCNT support uncomment NO_POPCNT define. 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 NO_POPCNT
-
-
 #include "types.h"
 
-// Select type of intrinsic bit count instruction to use
-
-#if defined(_MSC_VER) && defined(IS_64BIT) && !defined(NO_POPCNT) // Microsoft compiler
+// Select type of intrinsic bit count instruction to use, see
+// README.txt on how to pgo compile with POPCNT support.
 
-#include <intrin.h>
+#if defined(__INTEL_COMPILER) && defined(USE_POPCNT) // Intel compiler
 
 inline bool cpu_has_popcnt() {
 
@@ -44,19 +36,9 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-// Define a dummy template to workaround a compile error if __popcnt64() is not defined.
-//
-// If __popcnt64() is defined in <intrin.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 __popcnt64() is never called anyway.
-template<typename T> unsigned __popcnt64(T) { return 0; } // Is never called
-
-#define POPCNT_INTRINSIC(x) __popcnt64(x)
-
-#elif defined(__INTEL_COMPILER) && defined(IS_64BIT) && !defined(NO_POPCNT) // Intel compiler
+#define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
 
-#include <nmmintrin.h>
+#elif defined(_MSC_VER) && defined(USE_POPCNT) // Microsoft compiler
 
 inline bool cpu_has_popcnt() {
 
@@ -65,12 +47,23 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-// See comment of __popcnt64<>() few lines above for an explanation.
-template<typename T> unsigned _mm_popcnt_u64(T) { return 0; } // Is never called
+#define POPCNT_INTRINSIC(x) (int)__popcnt64(x)
 
-#define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
+#elif defined(__GNUC__) && defined(USE_POPCNT) // Gcc compiler
 
-#else // Safe fallback for unsupported compilers or when NO_POPCNT is defined
+inline bool cpu_has_popcnt() {
+
+  unsigned int eax, ebx, ecx, edx;
+  __cpuid(1, &eax, &ebx, &ecx, &edx);
+  return (ecx >> 23) & 1;
+}
+
+#define POPCNT_INTRINSIC(x) ({ \
+   unsigned long __ret; \
+   __asm__("popcnt %1, %0" : "=r" (__ret) : "r" (x)); \
+   __ret; })
+
+#else // Safe fallback for unsupported compilers or when USE_POPCNT is disabled
 
 inline bool cpu_has_popcnt() { return false; }
 
@@ -145,12 +138,8 @@ inline int count_1s_max_15(Bitboard b) {
 
 // Global constant initialized at startup that is set to true if
 // CPU on which application runs supports POPCNT intrinsic. Unless
-// NO_POPCNT is defined.
-#if defined(NO_POPCNT)
-const bool CpuHasPOPCNT = false;
-#else
+// USE_POPCNT is not defined.
 const bool CpuHasPOPCNT = cpu_has_popcnt();
-#endif
 
 
 // Global constant used to print info about the use of 64 optimized