https://llvm.org/bugs/show_bug.cgi?id=26649
Bug ID: 26649
Summary: buggy adaptive locking case
Product: OpenMP
Version: unspecified
Hardware: Other
OS: All
Status: NEW
Severity: normal
Priority: P
Component: Runtime Library
Assignee: unassignedb...@nondot.org
Reporter: pawel.osmialow...@foss.arm.com
CC: llvm-bugs@lists.llvm.org
Classification: Unclassified
Hello,
In __kmp_get_user_lock_owner() function in kmp_lock.cpp I've found
following switch:
switch (seq) {
case lockseq_tas:
case lockseq_nested_tas:
return __kmp_get_tas_lock_owner((kmp_tas_lock_t *)lck);
#if KMP_HAS_FUTEX
case lockseq_futex:
case lockseq_nested_futex:
return __kmp_get_futex_lock_owner((kmp_futex_lock_t *)lck);
#endif
case lockseq_ticket:
case lockseq_nested_ticket:
return __kmp_get_ticket_lock_owner((kmp_ticket_lock_t *)lck);
case lockseq_queuing:
case lockseq_nested_queuing:
#if KMP_USE_ADAPTIVE_LOCKS
case lockseq_adaptive:
return __kmp_get_queuing_lock_owner((kmp_queuing_lock_t *)lck);
#endif
case lockseq_drdpa:
case lockseq_nested_drdpa:
return __kmp_get_drdpa_lock_owner((kmp_drdpa_lock_t *)lck);
default:
return 0;
}
Seems like '#endif' correspondig to '#if KMP_USE_ADAPTIVE_LOCKS' was
placed one line too low causing queuing and nested queuing lock cases
are currently handled by drdpa lock case function when
KMP_USE_ADAPTIVE_LOCKS is not 1.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
