编辑：这里的代码仍有一些错误，它可以在性能部门做得更好，但不是试图解决这个问题，为了记录，我把问题解决了英特尔的讨论小组得到了很多很好的反馈，如果一切顺利的话，英特尔线程构建模块的近期版本中将包含一个优质的原子浮点数
好的，这是一个艰难的，我想要一个原子浮点，不是为了超快的图形性能，而是常规地用作类的数据成员。而且我不想为在这些类上使用锁定付出代价，因为它不能为我的需求提供额外的好处。
现在有了intel的tbb和我见过的其他原子库，支持整数类型，但不支持浮点数。所以我继续实施了一个，它可以工作......但是我不确定它是否真的有用，或者我很幸运，它的工作原理。
这里的任何人都知道这不是某种形式的异端邪说吗？
typedef unsigned int uint_32;
struct AtomicFloat
{
private:
tbb::atomic<uint_32> atomic_value_;
public:
template<memory_semantics M>
float fetch_and_store( float value )
{
const uint_32 value_ = atomic_value_.tbb::atomic<uint_32>::fetch_and_store<M>((uint_32&)value);
return reinterpret_cast<const float&>(value_);
}
float fetch_and_store( float value )
{
const uint_32 value_ = atomic_value_.tbb::atomic<uint_32>::fetch_and_store((uint_32&)value);
return reinterpret_cast<const float&>(value_);
}
template<memory_semantics M>
float compare_and_swap( float value, float comparand )
{
const uint_32 value_ = atomic_value_.tbb::atomic<uint_32>::compare_and_swap<M>((uint_32&)value,(uint_32&)compare);
return reinterpret_cast<const float&>(value_);
}
float compare_and_swap(float value, float compare)
{
const uint_32 value_ = atomic_value_.tbb::atomic<uint_32>::compare_and_swap((uint_32&)value,(uint_32&)compare);
return reinterpret_cast<const float&>(value_);
}
operator float() const volatile // volatile qualifier here for backwards compatibility
{
const uint_32 value_ = atomic_value_;
return reinterpret_cast<const float&>(value_);
}
float operator=(float value)
{
const uint_32 value_ = atomic_value_.tbb::atomic<uint_32>::operator =((uint_32&)value);
return reinterpret_cast<const float&>(value_);
}
float operator+=(float value)
{
volatile float old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<float&>(atomic_value_);
new_value_ = old_value_ + value;
} while(compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_);
}
float operator*=(float value)
{
volatile float old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<float&>(atomic_value_);
new_value_ = old_value_ * value;
} while(compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_);
}
float operator/=(float value)
{
volatile float old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<float&>(atomic_value_);
new_value_ = old_value_ / value;
} while(compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_);
}
float operator-=(float value)
{
return this->operator+=(-value);
}
float operator++()
{
return this->operator+=(1);
}
float operator--()
{
return this->operator+=(-1);
}
float fetch_and_add( float addend )
{
return this->operator+=(-addend);
}
float fetch_and_increment()
{
return this->operator+=(1);
}
float fetch_and_decrement()
{
return this->operator+=(-1);
}
};
谢谢！
编辑：将size_t更改为uint32_t，正如格雷格罗杰斯建议的那样，它更便于携带
修改：添加了整个内容的列表，并修复了一些内容。
更多编辑：使用锁定的浮点数为5.000.000 +的性能明智+ =我的机器上有100个线程的操作需要3.6秒，而我的原子浮点数即使其愚蠢的操作需要0.2秒做同样的工作。因此，如果正确的话，> 30倍的性能提升意味着它的价值，（这就是问题）。
更多编辑：由于Awgn指出我的fetch_and_xxxx部分都错了。修复了我不确定的API和移除的部分（模板化内存模型）。并根据operator + =实现其他操作以避免代码重复
已添加：添加了运算符* =和运算符/ =，因为没有它们，浮点数不会浮动。感谢Peterchen的评论，注意到这一点
编辑：最新版本的代码如下（我将保留旧版本以供参考）
#include <tbb/atomic.h>
typedef unsigned int uint_32;
typedef __TBB_LONG_LONG uint_64;
template<typename FLOATING_POINT,typename MEMORY_BLOCK>
struct atomic_float_
{
/* CRC Card -----------------------------------------------------
| Class: atmomic float template class
|
| Responsability: handle integral atomic memory as it were a float,
| but partially bypassing FPU, SSE/MMX, so it is
| slower than a true float, but faster and smaller
| than a locked float.
| *Warning* If your float usage is thwarted by
| the A-B-A problem this class isn't for you
| *Warning* Atomic specification says we return,
| values not l-values. So (i = j) = k doesn't work.
|
| Collaborators: intel's tbb::atomic handles memory atomicity
----------------------------------------------------------------*/
typedef typename atomic_float_<FLOATING_POINT,MEMORY_BLOCK> self_t;
tbb::atomic<MEMORY_BLOCK> atomic_value_;
template<memory_semantics M>
FLOATING_POINT fetch_and_store( FLOATING_POINT value )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::fetch_and_store<M>((MEMORY_BLOCK&)value);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
FLOATING_POINT fetch_and_store( FLOATING_POINT value )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::fetch_and_store((MEMORY_BLOCK&)value);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
template<memory_semantics M>
FLOATING_POINT compare_and_swap( FLOATING_POINT value, FLOATING_POINT comparand )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::compare_and_swap<M>((MEMORY_BLOCK&)value,(MEMORY_BLOCK&)compare);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
FLOATING_POINT compare_and_swap(FLOATING_POINT value, FLOATING_POINT compare)
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::compare_and_swap((MEMORY_BLOCK&)value,(MEMORY_BLOCK&)compare);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
operator FLOATING_POINT() const volatile // volatile qualifier here for backwards compatibility
{
const MEMORY_BLOCK value_ = atomic_value_;
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
//Note: atomic specification says we return the a copy of the base value not an l-value
FLOATING_POINT operator=(FLOATING_POINT rhs)
{
const MEMORY_BLOCK value_ = atomic_value_.tbb::atomic<MEMORY_BLOCK>::operator =((MEMORY_BLOCK&)rhs);
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
//Note: atomic specification says we return an l-value when operating among atomics
self_t& operator=(self_t& rhs)
{
const MEMORY_BLOCK value_ = atomic_value_.tbb::atomic<MEMORY_BLOCK>::operator =((MEMORY_BLOCK&)rhs);
return *this;
}
FLOATING_POINT& _internal_reference() const
{
return reinterpret_cast<FLOATING_POINT&>(atomic_value_.tbb::atomic<MEMORY_BLOCK>::_internal_reference());
}
FLOATING_POINT operator+=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ + value;
//floating point binary representation is not an issue because
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator*=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ * value;
//floating point binary representation is not an issue becaus
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator/=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ / value;
//floating point binary representation is not an issue because
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator-=(FLOATING_POINT value)
{
return this->operator+=(-value); //return resulting value
}
//Prefix operator
FLOATING_POINT operator++()
{
return this->operator+=(1); //return resulting value
}
//Prefix operator
FLOATING_POINT operator--()
{
return this->operator+=(-1); //return resulting value
}
//Postfix operator
FLOATING_POINT operator++(int)
{
const FLOATING_POINT temp = this;
this->operator+=(1);
return temp//return resulting value
}
//Postfix operator
FLOATING_POINT operator--(int)
{
const FLOATING_POINT temp = this;
this->operator+=(1);
return temp//return resulting value
}
FLOATING_POINT fetch_and_add( FLOATING_POINT addend )
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(addend);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
FLOATING_POINT fetch_and_increment()
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(+1);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
FLOATING_POINT fetch_and_decrement()
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(-1);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
};
typedef atomic_float_<float,uint_32> AtomicFloat;
typedef atomic_float_<double,uint_64> AtomicDouble;
答案 0 :(得分：5)
我会认真反对公共继承。我不知道原子实现是什么样的，但我假设它已经重载了使用它作为整数类型的运算符，这意味着在许多（可能是大多数？）情况下，这些促销将被用来代替你的浮点数。
我认为没有任何理由不起作用，但是像我一样，我必须证明这一点...
一个注意事项：你的operator float()例程没有load-acquire语义，不应该将它标记为const volatile（或者至少是const）？
编辑：如果您打算提供运营商 - （），您应提供前缀/后缀形式。
答案 1 :(得分：3)
看起来您的实现假定为sizeof(size_t) == sizeof(float)。这对您的目标平台总是如此吗？
我不会说线程异端，就像施放异端邪说一样。 ：）
答案 2 :(得分：1)
这是在知识产权委员会谈判后现在的代码状态，但仍未经过彻底验证，无法在所有情况下正常工作。
#include <tbb/atomic.h>
typedef unsigned int uint_32;
typedef __TBB_LONG_LONG uint_64;
template<typename FLOATING_POINT,typename MEMORY_BLOCK>
struct atomic_float_
{
/* CRC Card -----------------------------------------------------
| Class: atmomic float template class
|
| Responsability: handle integral atomic memory as it were a float,
| but partially bypassing FPU, SSE/MMX, so it is
| slower than a true float, but faster and smaller
| than a locked float.
| *Warning* If your float usage is thwarted by
| the A-B-A problem this class isn't for you
| *Warning* Atomic specification says we return,
| values not l-values. So (i = j) = k doesn't work.
|
| Collaborators: intel's tbb::atomic handles memory atomicity
----------------------------------------------------------------*/
typedef typename atomic_float_<FLOATING_POINT,MEMORY_BLOCK> self_t;
tbb::atomic<MEMORY_BLOCK> atomic_value_;
template<memory_semantics M>
FLOATING_POINT fetch_and_store( FLOATING_POINT value )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::fetch_and_store<M>((MEMORY_BLOCK&)value);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
FLOATING_POINT fetch_and_store( FLOATING_POINT value )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::fetch_and_store((MEMORY_BLOCK&)value);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
template<memory_semantics M>
FLOATING_POINT compare_and_swap( FLOATING_POINT value, FLOATING_POINT comparand )
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::compare_and_swap<M>((MEMORY_BLOCK&)value,(MEMORY_BLOCK&)compare);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
FLOATING_POINT compare_and_swap(FLOATING_POINT value, FLOATING_POINT compare)
{
const MEMORY_BLOCK value_ =
atomic_value_.tbb::atomic<MEMORY_BLOCK>::compare_and_swap((MEMORY_BLOCK&)value,(MEMORY_BLOCK&)compare);
//atomic specification requires returning old value, not new one
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
operator FLOATING_POINT() const volatile // volatile qualifier here for backwards compatibility
{
const MEMORY_BLOCK value_ = atomic_value_;
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
//Note: atomic specification says we return the a copy of the base value not an l-value
FLOATING_POINT operator=(FLOATING_POINT rhs)
{
const MEMORY_BLOCK value_ = atomic_value_.tbb::atomic<MEMORY_BLOCK>::operator =((MEMORY_BLOCK&)rhs);
return reinterpret_cast<const FLOATING_POINT&>(value_);
}
//Note: atomic specification says we return an l-value when operating among atomics
self_t& operator=(self_t& rhs)
{
const MEMORY_BLOCK value_ = atomic_value_.tbb::atomic<MEMORY_BLOCK>::operator =((MEMORY_BLOCK&)rhs);
return *this;
}
FLOATING_POINT& _internal_reference() const
{
return reinterpret_cast<FLOATING_POINT&>(atomic_value_.tbb::atomic<MEMORY_BLOCK>::_internal_reference());
}
FLOATING_POINT operator+=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ + value;
//floating point binary representation is not an issue because
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator*=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ * value;
//floating point binary representation is not an issue becaus
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator/=(FLOATING_POINT value)
{
FLOATING_POINT old_value_, new_value_;
do
{
old_value_ = reinterpret_cast<FLOATING_POINT&>(atomic_value_);
new_value_ = old_value_ / value;
//floating point binary representation is not an issue because
//we are using our self's compare and swap, thus comparing floats and floats
} while(self_t::compare_and_swap(new_value_,old_value_) != old_value_);
return (new_value_); //return resulting value
}
FLOATING_POINT operator-=(FLOATING_POINT value)
{
return this->operator+=(-value); //return resulting value
}
//Prefix operator
FLOATING_POINT operator++()
{
return this->operator+=(1); //return resulting value
}
//Prefix operator
FLOATING_POINT operator--()
{
return this->operator+=(-1); //return resulting value
}
//Postfix operator
FLOATING_POINT operator++(int)
{
const FLOATING_POINT temp = this;
this->operator+=(1);
return temp//return resulting value
}
//Postfix operator
FLOATING_POINT operator--(int)
{
const FLOATING_POINT temp = this;
this->operator+=(1);
return temp//return resulting value
}
FLOATING_POINT fetch_and_add( FLOATING_POINT addend )
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(addend);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
FLOATING_POINT fetch_and_increment()
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(+1);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
FLOATING_POINT fetch_and_decrement()
{
const FLOATING_POINT old_value_ = atomic_value_;
this->operator+=(-1);
//atomic specification requires returning old value, not new one as in operator x=
return old_value_;
}
};
typedef atomic_float_<float,uint_32> AtomicFloat;
typedef atomic_float_<double,uint_64> AtomicDouble;
答案 3 :(得分：1)
虽然 uint32_t 的大小可能与给定arch上的 float 的大小相等，但是通过将一个转换从一个转换为另一个，你隐式假设原子增量，减量和所有其他位操作在两种类型上在语义上是等价的，这是实际上不存在的。我怀疑它是否按预期工作。
答案 4 :(得分：1)
我强烈怀疑你在fetch_and_add等中得到了正确的值，因为float add与int addition不同。
以下是我从这些算术中得到的结果：
1 + 1 = 1.70141e+038
100 + 1 = -1.46937e-037
100 + 0.01 = 1.56743e+038
23 + 42 = -1.31655e-036
所以是的，线程安全但不是你期望的。
无锁算法（运算符+等）应该与原子性有关（没有检查算法本身..）
其他解决方案： 因为它是所有的加法和减法，你可能能够为每个线程提供自己的实例，然后从多个线程中添加结果。
答案 5 :(得分：1)
关于这个的一点说明（我想发表评论，但显然不允许新用户发表评论）：在引用上使用reinterpret_cast会产生gcc 4.1 -O3的错误代码。这似乎在4.4中得到修复，因为它有效。将reinterpret_casts更改为指针虽然稍微丑陋，但在两种情况下都适用。
答案 6 :(得分：0)
从我对该代码的阅读中，我会非常生气地对这样的编译器感到生气，因为它为这个非原子的组件进行了组装。
答案 7 :(得分：0)
让您的编译器生成汇编代码并查看它。如果操作不只是一个汇编语言指令，那么不是一个原子操作，并且需要锁才能在多处理器系统中正常运行。
不幸的是，我不确定反之亦然 - 单指令操作 保证是原子的。我不知道多级处理器编程的细节到那个级别。我可以为任何一个结果提出理由。 （如果其他人有关于此的确切信息，请随时加入。）