X-Git-Url: https://git.sesse.net/?p=stockfish;a=blobdiff_plain;f=src%2Fbitcount.h;h=7a05970d2abcb45a96333a34a070504941ac3b20;hp=ef841f3a7984dc7eba803e19df2763ab302c9086;hb=c67b9916f1756b56895d66efffc88edcc0e15566;hpb=36437f14e8cbac4c6b883248cccc9e707e957c68

diff --git a/src/bitcount.h b/src/bitcount.h
index ef841f3a..7a05970d 100644
--- a/src/bitcount.h
+++ b/src/bitcount.h
@@ -22,21 +22,14 @@
 #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(_MSC_VER) && defined(IS_64BIT) && defined(USE_POPCNT) // Microsoft compiler
+#if defined(__INTEL_COMPILER) && defined(USE_POPCNT) // Intel compiler
 
-#include <intrin.h>
+#include <nmmintrin.h>
 
 inline bool cpu_has_popcnt() {
 
@@ -45,19 +38,11 @@ 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)
+#define POPCNT_INTRINSIC(x) _mm_popcnt_u64(x)
 
-#elif defined(__INTEL_COMPILER) && defined(IS_64BIT) && defined(USE_POPCNT) // Intel compiler
+#elif defined(_MSC_VER) && defined(USE_POPCNT) // Microsoft compiler
 
-#include <nmmintrin.h>
+#include <intrin.h>
 
 inline bool cpu_has_popcnt() {
 
@@ -66,10 +51,31 @@ 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
+
+inline void __cpuid(unsigned int op,
+                    unsigned int *eax, unsigned int *ebx,
+                    unsigned int *ecx, unsigned int *edx)
+{
+  *eax = op;
+  *ecx = 0;
+  __asm__("cpuid" : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx)
+                  : "0" (*eax), "2" (*ecx));
+}
+
+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