Move __cpuid() definition for gcc in types.h

[stockfish] / src / bitcount.h

diff --git a/src/bitcount.h b/src/bitcount.h
index 6b5f5b5789bb5f8b0b895fafa650566ceba107c2..43895180c1e9ae7566e16e3f35f29b93e00e18eb 100644 (file)
--- a/src/bitcount.h
+++ b/src/bitcount.h
@@ -22,21 +22,12 @@
 #if !defined(BITCOUNT_H_INCLUDED)
 #define BITCOUNT_H_INCLUDED
 
-// 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
+// Select type of intrinsic bit count instruction to use, see
+// README.txt on how to pgo compile with POPCNT support.
 
-#if defined(__INTEL_COMPILER) && defined(IS_64BIT) && defined(USE_POPCNT) // Intel compiler
-
-#include <nmmintrin.h>
+#if defined(__INTEL_COMPILER) && defined(USE_POPCNT) // Intel compiler
 
 inline bool cpu_has_popcnt() {
 
@@ -45,19 +36,9 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-// 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
-
 #define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
 
-#elif defined(_MSC_VER) && defined(IS_64BIT) && defined(USE_POPCNT) // Microsoft compiler
-
-#include <intrin.h>
+#elif defined(_MSC_VER) && defined(USE_POPCNT) // Microsoft compiler
 
 inline bool cpu_has_popcnt() {
 
@@ -66,10 +47,21 @@ inline bool cpu_has_popcnt() {
   return (CPUInfo[2] >> 23) & 1;
 }
 
-// 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) (int)__popcnt64(x)
+
+#elif defined(__GNUC__) && defined(USE_POPCNT) // Gcc compiler
+
+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) __popcnt64(x)
+#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