#ifndef _SSE_MATH_FUN_
#define  _SSE_MATH_FUN_

#include <xmmintrin.h>



/* yes I know, the top of this file is quite ugly */

#ifdef _MSC_VER /* visual c++ */
# define ALIGN16_BEG __declspec(align(16))
# define ALIGN16_END 
#else /* gcc or icc */
# define ALIGN16_BEG
# define ALIGN16_END __attribute__((aligned(16)))
#endif

/* __m128 is ugly to write */
typedef __m128 v4sf;  // vector of 4 float (sse1)

#ifdef USE_SSE2
# include <emmintrin.h>
typedef __m128i v4si; // vector of 4 int (sse2)
#else
typedef __m64 v2si;   // vector of 2 int (mmx)
#endif

/* natural logarithm computed for 4 simultaneous float 
   return NaN for x <= 0
*/
v4sf log_ps(v4sf x);

#ifndef USE_SSE2
typedef union xmm_mm_union {
  __m128 xmm;
  __m64 mm[2];
} xmm_mm_union;

#define COPY_XMM_TO_MM(xmm_, mm0_, mm1_) {          \
    xmm_mm_union u; u.xmm = xmm_;                   \
    mm0_ = u.mm[0];                                 \
    mm1_ = u.mm[1];                                 \
}

#define COPY_MM_TO_XMM(mm0_, mm1_, xmm_) {                         \
    xmm_mm_union u; u.mm[0]=mm0_; u.mm[1]=mm1_; xmm_ = u.xmm;      \
  }

#endif // USE_SSE2


v4sf exp_ps(v4sf x);

v4sf sin_ps(v4sf x);

/* almost the same as sin_ps */
v4sf cos_ps(v4sf x);

/* since sin_ps and cos_ps are almost identical, sincos_ps could replace both of them..
   it is almost as fast, and gives you a free cosine with your sine */
void sincos_ps(v4sf x, v4sf *s, v4sf *c);

#endif