我正在编写一个帮助程序类,我打算用它来从数据块中反向读取位。
我尝试进行优化,其中我使用“rol”指令来屏蔽数据。但是,令我惊讶的是,这实际上比在每次访问期间创建新的位掩码要慢。
class reverse_bit_reader
{
public:
static const size_t bits_per_block = sizeof(unsigned long)*8;
static const size_t high_bit = 1 << (bits_per_block-1);
reverse_bit_reader(const void* data, size_t size)
: data_(reinterpret_cast<const unsigned long*>(data))
, index_(size-1)
{
// Bits are stored in left to right order, potentially ignore the last bits
size_t last_bit_index = index_ % bits_per_block;
bit_mask_ = high_bit >> (last_bit_index+1);
if(bit_mask_ == 0)
bit_mask_ = high_bit;
}
bool next_bit1()
{
return get_bit(index_--);
}
bool next_bit2() // Why is next_bit1 faster?
{
__asm // Rotate bit_mask.
{
mov eax, [ecx+0];
rol eax, 1;
mov [ecx+0], eax;
}
return data_[index_-- / bits_per_block] & bit_mask_;
}
bool eof() const{return index_ < 0;}
private:
bool get_bit(size_t index) const
{
const size_t block_index = index / bits_per_block;
const size_t bit_index = index % bits_per_block;
const size_t bit_mask = high_bit >> bit_index;
return data_[block_index] & bit_mask;
}
unsigned long bit_mask_;
int index_;
const unsigned long* data_;
};
任何人都可以解释为什么next_bit1比next_bit2快?
答案 0 :(得分:1)
如果您将从最长位开始按顺序读取位,并且您希望它尽可能快,那么您可以沿着这些线做某些事情吗?
#define GETBIT ((theBit = (theLong < 0)), (theLong <<= 1), theBit)