问如何使用movntdqa避免缓存污染？

EN

void memcpy(char *dst,char*src,unsigned size){
    char *dst_end=dst+size;
    while(dst!=dst_end){
        __m128i res = _mm_stream_load_si128((__m128i *)src);
        *((__m128i *)dst)=res;
        src+=16;
        dst+=16;
    }
}

void memcpy(char *dst,char*src,unsigned size){

        char *dst_end = dst+size;

        __asm{
        mov edi, dst 
        mov edx, dst_end 
        mov esi,src
        inner_start: 
        LFENCE 
      MOVNTDQA xmm0,    [esi ]
      MOVNTDQA xmm1, [esi+16] 
      MOVNTDQA xmm2, [esi+32] 
      MOVNTDQA xmm3, [esi+48] 
      //19. ; Copy data to buffer 
      MOVDQA [edi], xmm0 
      MOVDQA  [edi+16], xmm1 
      MOVDQA  [edi+32], xmm2 
      MOVDQA  [edi+48], xmm3 
    //  25. ; Increment pointers by cache line size and test for end of loop 
      add esi, 040h 
      add edi, 040h 
      cmp edi, edx 
      jne inner_start 


}
}

        void test(int table_size,int num_iter,int item_size){
            char *src_table=alloc_aligned(table_size*item_size);//return value is aligned on 64 bytes
            char *dst=alloc_aligned(item_size); //destination is always the same buffer
            for (int i=0;i<num_iter;i++){
                int location=my_rand()%table_size;
                char *src=src_table+location*item_size;//selecting a different src every time
                memcpy(dst,src,item_size);
            }

        }
main(){
       test(1024*32,1024*1024,1024*32)
}