Hi, This happens to me whenever I compile with google's tcmalloc. If you have that, try disabling it. I tend to just remove the tcmalloc package and do a fresh rebuild whenever I need to use valgrind to debug memory issues. This is just because by default valgrind doesn't recognize/trap the alloc/free calls with that library (though I'm sure there is a way to make it do so).
Note: when using valgrind you will want to enable the suppressions present in util/valgrind-suppressions to disable false/superfluous warnings. Hope this helps. On Thu, Sep 19, 2013 at 5:50 PM, Naranjo Carmona, Alberto Javier < ajn...@neo.tamu.edu> wrote: > Hi everyone! > > I am running some test with PARSEC with X86 architecture in detailed mode > and I noted that I might have a memory leak because after some time the > gem5 process consumes a great part of the memory in the server (more than > 66GB). > I ran Valgrind to find any potential but the result was "total heap usage: > 0 allocs, 0 frees, 0 bytes allocated", which is not convincent because it > obviously allocated memory. > So, in order to prove this, I deliberately added a leak in the code > (called malloc several times in /src/sim/simulate.cc and didn't free it) > hoping for Valgrind to detect it but the result was the same. > > Do you know why Valgrind apparently does not see through GEM5? > Do you know of any other method or tool I can use to find the memory leaks? > > The command I'm using is > valgrind --tool=memcheck --leak-check=yes ./build/X86/gem5.debug -d > simout/ff_Blackscholes/ ./configs/example/ruby_fs.py > --kernel=x86_64-vmlinux-2.6.28.4-smp --script=runscript/blackscholes.rcS > -F 437696510 --cpu-type=detailed --num-cpus=16 --num-dirs=16 > --topology=Mesh --num-l2caches=16 --mesh-rows=4 --garnet-network=fixed > > Thanks for your help!!! > -- > Alberto Javier Naranjo-Carmona > M.S. Student Electrical Engineering > Computer Engineering & Systems Group > Texas A&M University, College Station, TX > _______________________________________________ > gem5-users mailing list > gem5-users@gem5.org > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
