gistfile1.txt

#if __SSE2__
#include <emmintrin.h>
// There's no equivalent in libc, you'd think so ... std::mismatch exists, but it's not optimized at all. :(
static unsigned find_mismatch(const uint32_t *a, const uint32_t *b, unsigned samples)
{
   unsigned i;
   unsigned sse_samples = samples & ~3;
   for (i = 0; i < sse_samples; i += 4)
   {
      __m128i v0 = _mm_loadu_si128((const __m128i*)(a + i));
      __m128i v1 = _mm_loadu_si128((const __m128i*)(b + i));
      __m128i c = _mm_cmpeq_epi32(v0, v1);
      uint32_t mask = _mm_movemask_epi8(c);
      if (mask != 0xffff) // Something has changed, figure out where.
         return i + (__builtin_ctz(~mask) >> 2);
   }

   for (; i < samples; i++)
      if (a[i] != b[i])
         return i;

   return samples;
}
#else
static unsigned find_mismatch(const uint32_t *a, const uint32_t *b, unsigned samples)
{
   unsigned i;
   for (i = 0; i < samples; i++)
      if (a[i] != b[i])
         return i;
   return samples;
}
#endif