BTW, the test case in PAPI-CVS is called, krentel-pthreads, in honor of Mark's hard work.
Phil On Apr 18, 2008, at 5:19 PM, Philip Mucci wrote: > Rob, > > These issues are all solved in the latest copy of PAPI by using a RT > signal. If you have a test case on any platform where this isn't true, > please send it along. Marks note only reflects changes made in the > PAPI library, not any code that cray has, nor the Perfmon2 code. > > However, I can assure you that the issues here are related to PAPI's > inability to properly handle a running context across fork/exec. > > Phil > > > On Apr 18, 2008, at 5:09 PM, Rob Fowler wrote: > >> Typically, two SIGIOs are delivered: one occurs with the >> first event; all visible events are handled with SIGIO blocked; when >> the handler returns, a second SIGIO is delivered to indicate the >> occurrence of the 2nd through Nth events. Since all of the events >> may have already been handled before the 2nd SIGIO is delivered, the >> signal handler also needs to be able to deal with the "no events >> pending" case. >> An aside: >> >> Mark K sent a note to me that >> said "On CNL 2.1 and perfmon 2.3, I was able to complete 1-hour runs >> with multiple threads, at 2,000 interrupts/second, 10,000/second and >> even 100,000/second without dropping interrupts." >> >> It would begood if Cray pushed their fixes back to the world. > > _______________________________________________ > Perfapi-devel mailing list > [EMAIL PROTECTED] > http://lists.cs.utk.edu/listinfo/perfapi-devel ------------------------------------------------------------------------- This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone _______________________________________________ perfmon2-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/perfmon2-devel
