Thank you for your reply. I think a heuristic approach works. Will try to do that.
--Qiuyun On Thu, Oct 31, 2013 at 4:53 PM, Eduardo Cruz <[email protected]>wrote: > A simple, but not 100% accurate approach, would be to consider as stack > addr the highest virtual addressess, because usually stack addr are much > higher than heap addr. > Print the addreses of memory located in the heap and stack and you will > understand my point. > > -- > Eduardo Henrique Molina da Cruz > PhD student > Parallel and Distributed Processing Group > Federal University of Rio Grande do Sul (UFRGS) > Em 31/10/2013 18:38, "Curtis Dunham" <[email protected]> escreveu: > > Correct. Although you could build heuristics into MARSS. From each >> thread's perspective, its stack is most likely the memory range in >> /proc/*/maps that esp/rsp points into. >> >> On Thu, Oct 31, 2013 at 06:26:13PM -0200, Eduardo Cruz wrote: >> > I dont think MARSS has knowledge whether a memory access is in a heap or >> > stack addr, sice this is a abstraction provided by the language/os. >> > But you can instrument your application to provide MARSS that >> information. >> > Em 31/10/2013 18:12, "Qiuyun Wang" <[email protected]> escreveu: >> > >> > > Hello all, >> > > >> > > I am trying to separate stack and heap memory access from other memory >> > > access in Marss and DRAMSim for some benchmarks. >> > > >> > > Do anyone know is there a way to trace those information in ptlsim or >> kvm? >> > > I am not sure which part of the code should I look at. >> > > >> > > Thanks in advance for your reply. >> > > >> > > Best, >> > > --Qiuyun >> > > >> > > >> > > -- >> > > *********************** >> > > Qiuyun Wang >> > > Hudson 213, >> > > Electrical and Computer Engineering Department, >> > > Duke University >> > > M.S. University Paris-Sud XI >> > > >> > > _______________________________________________ >> > > http://www.marss86.org >> > > Marss86-Devel mailing list >> > > [email protected] >> > > https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel >> > > >> > > >> >> > _______________________________________________ >> > http://www.marss86.org >> > Marss86-Devel mailing list >> > [email protected] >> > https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel >> >> -- >> *********************** >> Qiuyun Wang >> Hudson 213, >> Electrical and Computer Engineering Department, >> Duke University >> M.S. University Paris-Sud XI >> >> >> >> >> >>
_______________________________________________ http://www.marss86.org Marss86-Devel mailing list [email protected] https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
