CRC64 and MMX

I've done experimental implementation of CRC64 routines using MMX 64 bit registers.
It makes COMP_CRC64() 10~30% faster than the marco written in C on my PentiumIII laptop.
But my Pentium4 box shows the MMX code is slower 2~3 times than plain C code.

What's happened in the processor?

#define COMP_CRC64_MMX(crc, data, len) do {   uint64                __crc0 = (crc).crc0;   unsigned char *__data = (unsigned char *) (data);   uint32                __len = (len);    while (__len-- > 0)   {   __asm__ __volatile__ (   "movq (%1),%%mm0;"    /* __crc0  -> %%mm0 */   "movq %%mm0,%%mm4;"   /* __crc0  -> %%mm4 */   "movq (%2),%%mm1;"    /* *__data -> %%mm1 */    "movl %3,%%eax;"        /* __crc64_const_vals      */   "movq   (%%eax),%%mm5;" /* load '56'               */   "movq  8(%%eax),%%mm6;" /* load '0xff'             */   "movq 16(%%eax),%%mm7;" /* load '8'                */    "psrlq %%mm5,%%mm0;"  /* __crc0(%%mm0) >> 56   */   "pxor  %%mm1,%%mm0;"  /* __crc0(%%mm0) ^ *data */   "pand  %%mm6,%%mm0;"  /* __crc0(%%mm0) & 0xff  */    "mov %4,%%ebx;"       /* crc_table */    "movd %%mm0,%%eax;"   /* move __tab_index to the register */   "imul $8,%%eax;"      /* 8 bytes per table entry */   "addl %%eax,%%ebx;"    "movq (%%ebx),%%mm0;" /* crc_table[__tab_index] -> %%mm0 */    "psllq %%mm7,%%mm4;"  /* %%mm4 << 8 */    "pxor %%mm4,%%mm0;"   /* crc_table[__tab_index] ^ (__crc0 << 8) */    "movq %%mm0,%0;"    "emms;"   : "+g"(__crc0)   : "r"(&__crc0), "r"(__data), "r"(__crc64_const_vals), "r"(crc_table)   : "%eax", "%ebx"   );    __data++;   }; /* while() */    (crc).crc0 = __crc0; } while (0);