Hi all,
Is the prefetching module written within ruby is stable with
the present ruby setup? I found a seg fault when i tried running ruby with
enable_prefetch = True for MESI_CMP_directory.py.
*command:*
./build/ALPHA/gem5.opt configs/example/ruby_fs.py -n 4 --l1i_size=32kB
--l1d_size=32kB --l2_size=512MB --num-l2caches=4 --topology=Mesh
--num-dirs=4 --mesh-rows=2 --mem-size=1024MB --cpu-type=detailed
--script=../../PAR_PRE/
request/m5parsec/bodytrack_4c_simlarge.rcS
*output from gdb:*
Program received signal SIGSEGV, Segmentation fault.
MessageBuffer::enqueue (this=0x3391340, message=..., delay=...) at
build/ALPHA/mem/ruby/buffers/MessageBuffer.cc:159
159 if (m_time_last_time_enqueue < m_receiver_ptr->curCycle()) {
(gdb) bt
#0 MessageBuffer::enqueue (this=0x3391340, message=..., delay=...) at
build/ALPHA/mem/ruby/buffers/MessageBuffer.cc:159
#1 0x0000000000b4195f in L1Cache_Controller::enqueuePrefetch
(this=0x322da10, param_address=..., param_type=@0x322be8c) at
build/ALPHA/mem/protocol/L1Cache_Controller.cc:1394
#2 0x0000000000c6e016 in Prefetcher::initializeStream (this=0x322acb0,
address=<optimized out>, stride=1, index=<optimized out>, type=<optimized
out>)
at build/ALPHA/mem/ruby/structures/Prefetcher.cc:318
#3 0x0000000000c7095a in Prefetcher::observeMiss (this=0x322acb0,
address=..., type=@0x2734a88) at
build/ALPHA/mem/ruby/structures/Prefetcher.cc:171
#4 0x0000000000b3ef41 in L1Cache_Controller::po_observeMiss
(this=0x322da10, m_tbe_ptr=<optimized out>, m_cache_entry_ptr=<optimized
out>, addr=<optimized out>)
at build/ALPHA/mem/protocol/L1Cache_Controller.cc:1187
#5 0x0000000000b5df63 in L1Cache_Controller::doTransitionWorker
(this=0x322da10, event=L1Cache_Event_Ifetch, state=L1Cache_State_FIRST,
next_state=<optimized out>,
m_tbe_ptr=@0x7fffffffbf58, m_cache_entry_ptr=@0x7fffffffbf60, addr=...)
at build/ALPHA/mem/protocol/L1Cache_Transitions.cc:194
#6 0x0000000000b5f2f1 in L1Cache_Controller::doTransition (this=0x322da10,
event=L1Cache_Event_Ifetch, m_cache_entry_ptr=0x27e34a0,
m_tbe_ptr=0x27d7ae8, addr=...)
at build/ALPHA/mem/protocol/L1Cache_Transitions.cc:36
#7 0x0000000000b64cfc in L1Cache_Controller::wakeup (this=0x322da10) at
build/ALPHA/mem/protocol/L1Cache_Wakeup.cc:633
#8 0x0000000000bb4c52 in Consumer::ConsumerEvent::process (this=0x27954a0)
at build/ALPHA/mem/ruby/common/Consumer.hh:108
#9 0x00000000008e73b6 in EventQueue::serviceOne (this=<optimized out>) at
build/ALPHA/sim/eventq.cc:207
#10 0x0000000000927330 in simulate (num_cycles=<optimized out>) at
build/ALPHA/sim/simulate.cc:72
#11 0x000000000088fb2c in _wrap_simulate__SWIG_0 (args=<optimized out>) at
build/ALPHA/python/swig/event_wrap.cc:4559
#12 _wrap_simulate (self=<optimized out>, args=<optimized out>) at
build/ALPHA/python/swig/event_wrap.cc:4609
#13 0x00007ffff77bc0ee in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#14 0x00007ffff77bdf05 in PyEval_EvalCodeEx () from
/usr/lib/libpython2.7.so.1.0
#15 0x00007ffff77bc075 in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#16 0x00007ffff77bd064 in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#17 0x00007ffff77bd064 in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#18 0x00007ffff77bdf05 in PyEval_EvalCodeEx () from
/usr/lib/libpython2.7.so.1.0
#19 0x00007ffff77be042 in PyEval_EvalCode () from
/usr/lib/libpython2.7.so.1.0
#20 0x00007ffff77bc5e9 in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#21 0x00007ffff77bdf05 in PyEval_EvalCodeEx () from
/usr/lib/libpython2.7.so.1.0
#22 0x00007ffff77bc075 in PyEval_EvalFrameEx () from
/usr/lib/libpython2.7.so.1.0
#23 0x00007ffff77bdf05 in PyEval_EvalCodeEx () from
/usr/lib/libpython2.7.so.1.0
#24 0x00007ffff77be042 in PyEval_EvalCode () from
/usr/lib/libpython2.7.so.1.0
#25 0x00007ffff77e04bc in PyRun_StringFlags () from
/usr/lib/libpython2.7.so.1.0
#26 0x00000000008edbcf in m5Main (argc=<optimized out>, argv=<optimized
out>) at build/ALPHA/sim/init.cc:280
#27 0x0000000000414452 in main (argc=14, argv=0x7fffffffe038) at
build/ALPHA/sim/main.cc:57
Any pointers on this issue?
--
*thanks®ards
*
*BISWABANDAN*
http://www.cse.iitm.ac.in/~biswa/
*Any intelligent fool can make things bigger, more complex, and more
violent.
It takes a touch of genius - and a lot of courage - to move in the opposite
direction.*
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
