在x86上将float转换成int的最快方法是什么

http://www.stereopsis.com/FPU.html

ffmpeg

static const float Snapper=3<<22;

union UFloatInt {
 int i;
 float f;
};

/** by Vlad Kaipetsky
portable assuming FP24 set to nearest rounding mode
efficient on x86 platform
*/
inline int toInt( float fval )
{
  Assert( fabs(fval)<=0x003fffff ); // only 23 bit values handled
  UFloatInt &fi = *(UFloatInt *)&fval;
  fi.f += Snapper;
  return ( (fi.i)&0x007fffff ) - 0x00400000;
}

http://software.intel.com/en-us/articles/how-to-implement-the-fisttp-streaming-simd-extensions-3-instruction/

Processors with SSE3 support

lua_Number

/*
@@ lua_number2int is a macro to convert lua_Number to int.
@@ lua_number2integer is a macro to convert lua_Number to lua_Integer.
** CHANGE them if you know a faster way to convert a lua_Number to
** int (with any rounding method and without throwing errors) in your
** system. In Pentium machines, a naive typecast from double to int
** in C is extremely slow, so any alternative is worth trying.
*/

/* On a Pentium, resort to a trick */
#if defined(LUA_NUMBER_DOUBLE) && !defined(LUA_ANSI) && !defined(__SSE2__) && \
    (defined(__i386) || defined (_M_IX86) || defined(__i386__))

/* On a Microsoft compiler, use assembler */
#if defined(_MSC_VER)

#define lua_number2int(i,d)   __asm fld d   __asm fistp i
#define lua_number2integer(i,n)     lua_number2int(i, n)

/* the next trick should work on any Pentium, but sometimes clashes
   with a DirectX idiosyncrasy */
#else

union luai_Cast { double l_d; long l_l; };
#define lua_number2int(i,d) \
  { volatile union luai_Cast u; u.l_d = (d) + 6755399441055744.0; (i) = u.l_l; }
#define lua_number2integer(i,n)     lua_number2int(i, n)

#endif

/* this option always works, but may be slow */
#else
#define lua_number2int(i,d) ((i)=(int)(d))
#define lua_number2integer(i,d) ((i)=(lua_Integer)(d))

#endif

see this MSDN overview

http://softwarecommunity.intel.com/articles/eng/2076.htm

MSDN doc _mm_cvtsd_si64x

 #include <intrin.h>
 #pragma intrinsic(_mm_cvtsd_si64x)
 long long _inline double2int(const double &d)
 {
     return _mm_cvtsd_si64x(*(__m128d*)&d);
 }

        i=double2int(d);
000000013F651085  cvtsd2si    rax,mmword ptr [rsp+38h]  
000000013F65108C  mov         qword ptr [rsp+28h],rax  

    _control87(_RC_NEAR,_MCW_RC);

float.h _control87()

_asm fld d
_asm fistp i

i = (int)f

int convert(float x)
{
    int n;
    __asm {
        fld x
        fisttp n // the extra 't' means truncate
    }
    return n;
}

#include <xmmintrin.h>
int convert(float x)
{
    return _mm_cvtt_ss2si(_mm_load_ss(&x)); // extra 't' means truncate
}

fistp

void Set_Trunc()
{
    // cw is a 16-bit register [_ _ _ ic rc1 rc0 pc1 pc0 iem _ pm um om zm dm im]
    __asm {
        push ax // use stack to store the control word
        fnstcw word ptr [esp]
        fwait // needed to make sure the control word is there
        mov ax, word ptr [esp] // or pop ax ...
        or ax, 0xc00 // set both rc bits (alternately "or ah, 0xc")
        mov word ptr [esp], ax // ... and push ax
        fldcw word ptr [esp]
        pop ax
    }
}

void convertArray(int *dest, const float *src, int n)
{
    Set_Trunc();
    __asm {
        mov eax, src
        mov edx, dest
        mov ecx, n // load loop variables

        cmp ecx, 0
        je bottom // handle zero-length arrays

    top:
        fld dword ptr [eax]
        fistp dword ptr [edx]
        loop top // decrement ecx, jump to top
    bottom:
    }
}