顯示具有 atomic 標籤的文章。 顯示所有文章
顯示具有 atomic 標籤的文章。 顯示所有文章

2013年6月2日 星期日

A further look at the gcc __sync_bool_compare_and_swap.

Continuing the looks-pretty-good gcc atomic CAS functions, the point would be how to move these great results in application and make the pretty testing result helps. For the purpose to understand clearly its behavior, some more tests have been done.


2013年5月22日 星期三

A rough survey on gcc builtin atomic operations.

When my colleague suggested me the gcc __sync_* functions, not much interest to me for which was treated as a low-level lock rather than a lock-free pattern. But it does surprise me after some survey.