快速内存拷贝

void MemCopy(void *pDst, void *pSrc, DWORD dwSize)//顺序拷贝
{
	_asm
	{
		    mov esi, pSrc;  //传递源指针
		    mov edi, pDst;  //传递目标指针
		    mov ebx, dwSize;//ebx 字节计数
		    shr ebx, 7;     //除 128 (8 * 128bit registers)
	  L1:
		    movdqu xmm0, 0[ESI]; //从内存移动数据到寄存器
		    movdqu xmm1, 16[ESI];
		    movdqu xmm2, 32[ESI];
		    movdqu xmm3, 48[ESI];
		    movdqu xmm4, 64[ESI];
		    movdqu xmm5, 80[ESI];
		    movdqu xmm6, 96[ESI];
		    movdqu xmm7, 112[ESI];

		    movntdq 0[EDI], xmm0; //从寄存器移动数据到内存
		    movntdq 16[EDI], xmm1;
		    movntdq 32[EDI], xmm2;
		    movntdq 48[EDI], xmm3;
		    movntdq 64[EDI], xmm4;
		    movntdq 80[EDI], xmm5;
		    movntdq 96[EDI], xmm6;
		    movntdq 112[EDI], xmm7;

		    add esi, 128;
		    add edi, 128;
		    dec ebx; //减1
		    jnz L1;  //不为0循环

	  	    mov ecx, dwSize;
		    and ecx, 127;
		    rep movsb; //余数循环
	}
}