I wrote a CLOMP program beneath Redhat endeavor. The entire OpenMP programs runs effortlessly. A cluster openmp program runs well, if the lock api is not called. On the other hand, when the program reached to kmp_lock_cond_wait, a runtime error determines to be output, and the procedure determine to be terminated. I actually necessitate adding the lock characteristic to my cluster OpenMP program. It seems that kmp_lock_cond_wait is the merely choice for me.
Bookmarks