确保使用双比较和交换指令，用于无锁堆栈？ [英] Ensuring usage of double-compare-and-swap instruction, for lock-free stack?

问题描述

（假设64位x86-64架构和英特尔第3代/第4代CPU）

(Assume 64-bit x86-64 architecture and Intel 3rd/4th generation CPU)

这是一个无锁的实现，第202页：

Here is a lock-free implementation for a stack from Concurrency in Action book, page 202:

template<typename T>
class lock_free_stack
{
private:
    struct node;

    struct counted_node_ptr
    {
        int external_count;
        node* ptr;
    };

    struct node
    {
        std::shared_ptr<T> data;
        std::atomic<int> internal_count;
        counted_node_ptr next;

        node(T const& data_):data(std::make_shared<T>(data_)),internal_count(0){}
    };

    std::atomic<counted_node_ptr> head;

public:
    ~lock_free_stack()
    {
        while(pop());
    }

    void push(T const& data)
    {
        counted_node_ptr new_node;
        new_node.ptr=new node(data);
        new_node.external_count=1;
        new_node.ptr->next=head.load();
        while(!head.compare_exchange_weak(new_node.ptr->next,new_node));
    }
};

它在代码下面说：

在那些支持double-word-compare-and-swap
操作的平台上，这个结构将足够小，
std :: atomic是无锁的。 / p>

On those platforms that support a double-word-compare-and-swap operation, this structure will be small enough for std::atomic to be lock-free.

我相信x86-64确实支持double CAS（我不记得我头顶的指令名称） 。

I believe x86-64 does have support for the double CAS (I cannot remember the name of the instruction off the top of my head).

如果我要检查程序集（我看不到双CAS指令），我需要写入什么内联汇编函数，使用CAS？

更新 - 我想我已经找到了我在这里寻找的东西：

UPDATE - I think I have found what I was looking for here:

http：// blog.lse.epita.fr/articles/42-implementing-generic-double-word-compare-and-swap-.html

template<typename T>
struct DPointer <T,sizeof (uint64_t)> {
public:
  union {
    uint64_t ui[2];
    struct {
      T* ptr;
      size_t count;
    } __attribute__ (( __aligned__( 16 ) ));
  };

  DPointer() : ptr(NULL), count(0) {}
  DPointer(T* p) : ptr(p), count(0) {}
  DPointer(T* p, size_t c) : ptr(p), count(c) {}

  bool cas(DPointer<T,8> const& nval, DPointer<T,8> const& cmp)
  {
    bool result;
    __asm__ __volatile__ (
        "lock cmpxchg16b %1\n\t"
        "setz %0\n"
        : "=q" ( result )
         ,"+m" ( ui )
        : "a" ( cmp.ptr ), "d" ( cmp.count )
         ,"b" ( nval.ptr ), "c" ( nval.count )
        : "cc"
    );
    return result;
  }

  // We need == to work properly
  bool operator==(DPointer<T,8> const&x)
  {
    return x.ptr == ptr && x.count == count;
  }
};

推荐答案

x86_64的最旧版本不支持此指令（CMPXCHG16B），这是Windows 8.1 / 64位及更高版本所必需的。 Afaik这是大部分的Athlon64系列（插座751,939和一些X2的，也许是第一代（8xx）Pentium D）

The oldest versions of the x86_64 do not support this instruction (CMPXCHG16B), which is required for Windows 8.1/64-bit and newer. Afaik this is most of the Athlon64 range (socket 751, 939 and some of the X2's, maybe the first generation (8xx) of Pentium D too)

如何强制编译器使用一定的指令变化，通常必须使用不完全移植的内在。

How to force a compiler to use a certain instruction varies, usually one must use a not wholly portable intrinsic.

这篇关于确保使用双比较和交换指令，用于无锁堆栈？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！