[PATCH] D11259: Fix OMPT support for task frames for parallel regions and parallel regions + loops

Andrey Churbanov andrey.churbanov at intel.com
Thu Jul 16 07:14:33 PDT 2015


AndreyChurbanov added a subscriber: AndreyChurbanov.

================
Comment at: runtime/src/kmp_runtime.c:2094
@@ -2089,2 +2093,3 @@
         KMP_DEBUG_ASSERT(master_th->th.th_task_team == parent_team->t.t_task_team[master_th->th.th_task_state]);
+#endif
         KA_TRACE( 20, ( "__kmp_fork_call: Master T#%d pushing task_team %p / team %p, new task_team %p / team %p\n",
----------------
jmellorcrummey wrote:
> Hahnfeld wrote:
> > This probably shouldn't be here, it's part of another issue...
> I don't quite know how to handle this. The runtime works though I have test codes that cause the assert to trip. In my development version, I patched out the assert pending patches from Intel. Is leaving in the broken assert preferable? Should I delete the assert entirely and let Intel restore a variant of it later after they have altered the runtime to ensure that the condition is true?
John,  I think that either #if0 or temporarily removing the assertion should work fine.  But please do this as a separate patch, because it is indeed not related to the OMPT changes.  We will then restore the assertion with the patch that fixes the reason of it.


http://reviews.llvm.org/D11259







More information about the llvm-commits mailing list