c++ - `std::memory_order_acquire` 的语义是否需要 x86/x86_64 上的处理器指令？

Question

众所周知，在 x86 上，操作 load() 和 store() 内存屏障 memory_order_consume, memory_order_acquire, memory_order_release , memory_order_acq_rel 不需要缓存和流水线的处理器指令，汇编代码始终对应于 std::memory_order_relaxed，这些限制仅对编译器的优化是必要的:http://www.stdthread.co.uk/forum/index.php?topic=72.0

这段反汇编代码为 store() (MSVS2012 x86_64) 确认了这一点:

std::atomic<int> a;
    a.store(0, std::memory_order_relaxed);
000000013F931A0D  mov         dword ptr [a],0  
    a.store(1, std::memory_order_release);
000000013F931A15  mov         dword ptr [a],1  

但是这段代码没有为 load() (MSVS2012 x86_64) 确认这一点，使用 lock cmpxchg:

    int val = a.load(std::memory_order_acquire);
000000013F931A1D  prefetchw   [a]  
000000013F931A22  mov         eax,dword ptr [a]  
000000013F931A26  mov         edx,eax  
000000013F931A28  lock cmpxchg dword ptr [a],edx  
000000013F931A2E  jne         main+36h (013F931A26h)  

    std::cout << val << "\n";

但是 Anthony Williams said :

some_atomic.load(std::memory_order_acquire) does just drop through to a simple load instruction, and some_atomic.store(std::memory_order_release) drops through to a simple store instruction.

我哪里错了，std::memory_order_acquire 的语义需要 x86/x86_64 上的处理器指令 lock cmpxchg 还是只需要一个简单的加载指令 mov 正如 Anthony Williams 所说？

答案:与此错误报告相同:http://connect.microsoft.com/VisualStudio/feedback/details/770885

Answer 1

没有。 std::memory_order_acquire 的语义不需要 x86/x86_64 上的处理器指令。

除了 atomic.store(val, std::memory_order_seq_cst); 需要 外，x86_64 上的任何 load()/store() 操作都不需要处理器指令(锁/栅栏) (LOCK) XCHG 或替代方法:MOV(进入内存)，MFENCE。

x86(CAS 除外)以及 ARM 和 PowerPC 的处理器内存屏障指令:http://www.cl.cam.ac.uk/~pes20/cpp/cpp0xmappings.html

反汇编程序 GCC 4.8.1 x86_64 - GDB - load():

    20      temp = a.load(std::memory_order_relaxed);
    21      temp = a.load(std::memory_order_acquire);
    22      temp = a.load(std::memory_order_seq_cst);
0x46140b  <+0x007b>         mov    0x38(%rsp),%ebx
0x46140f  <+0x007f>         mov    0x34(%rsp),%esi
0x461413  <+0x0083>         mov    0x30(%rsp),%edx

反汇编程序 GCC 4.8.1 x86_64 - GDB - store():

a.store(temp, std::memory_order_relaxed);
a.store(temp, std::memory_order_release);
a.store(temp, std::memory_order_seq_cst);
0x4613dc  <+0x004c>         mov    %eax,0x20(%rsp)
0x4613e0  <+0x0050>         mov    0x38(%rsp),%eax
0x4613e4  <+0x0054>         mov    %eax,0x20(%rsp)
0x4613e8  <+0x0058>         mov    0x38(%rsp),%eax
0x4613ec  <+0x005c>         mov    %eax,0x20(%rsp)
0x4613f0  <+0x0060>         mfence
0x4613f3  <+0x0063>         mov    %ebx,0x20(%rsp)

反汇编程序 MSVS 2012 x86_64 - load() - 它与此错误报告相同:http://connect.microsoft.com/VisualStudio/feedback/details/770885 :

    temp = a.load(std::memory_order_relaxed);
000000013FE51A1F  prefetchw   [a]  
000000013FE51A24  mov         eax,dword ptr [a]  
000000013FE51A28  nop         dword ptr [rax+rax]  
000000013FE51A30  mov         ecx,eax  
000000013FE51A32  lock cmpxchg dword ptr [a],ecx  
000000013FE51A38  jne         main+40h (013FE51A30h)  
000000013FE51A3A  mov         dword ptr [temp],eax  
    temp = a.load(std::memory_order_acquire);
000000013FE51A3E  prefetchw   [a]  
000000013FE51A43  mov         eax,dword ptr [a]  
000000013FE51A47  nop         word ptr [rax+rax]  
000000013FE51A50  mov         ecx,eax  
000000013FE51A52  lock cmpxchg dword ptr [a],ecx  
000000013FE51A58  jne         main+60h (013FE51A50h)  
000000013FE51A5A  mov         dword ptr [temp],eax  
    temp = a.load(std::memory_order_seq_cst);
000000013FE51A5E  prefetchw   [a]  
    temp = a.load(std::memory_order_seq_cst);
000000013FE51A63  mov         eax,dword ptr [a]  
000000013FE51A67  nop         word ptr [rax+rax]  
000000013FE51A70  mov         ecx,eax  
000000013FE51A72  lock cmpxchg dword ptr [a],ecx  
000000013FE51A78  jne         main+80h (013FE51A70h)  
000000013FE51A7A  mov         dword ptr [temp],eax  

反汇编程序 MSVS 2012 x86_64 - store():

    a.store(temp, std::memory_order_relaxed);
000000013F8C1A58  mov         eax,dword ptr [temp]  
000000013F8C1A5C  mov         dword ptr [a],eax  

    a.store(temp, std::memory_order_release);
000000013F8C1A60  mov         eax,dword ptr [temp]  
000000013F8C1A64  mov         dword ptr [a],eax  

    a.store(temp, std::memory_order_seq_cst);
000000013F8C1A68  mov         eax,dword ptr [temp]  
000000013F8C1A6C  xchg        eax,dword ptr [a]