Hello,
Has anyone gotten to run simpoint execution with multiple workloads
in SE mode. I have looked at the asplos tutorial and some threads which
discussed this problem before. Single workloads simpoints are running
fine but with say 2 workloads, it segfaults: (i am running the spec2k6
workloads in SE mode, assigning a different workload to each processor)
gcc.simpoint = 1e6
astar.simpoint = 2e6
M5 compiled Nov 7 2009 17:32:43
M5 revision 15e5581286b6 6285 default tip
M5 started Nov 8 2009 20:14:23
M5 executing on lowpower
command line: ./build/ALPHA_SE/m5.fast configs/spec2k6/runmix.py -d -n 2
--caches --simpoint -s -w 100000 --max-inst=100
Global frequency set at 1000000000000 ticks per second
0: system.remote_gdb.listener: listening for remote gdb on port 7000
0: system.remote_gdb.listener: listening for remote gdb on port 7001
Switch at instruction count:1000000
info: Entering event queue @ 0. Starting simulation...
info: Increasing stack size by one page.
info: Increasing stack size by one page.
warn: ignoring syscall rt_sigaction(8, 4831386176, ...)
hack: be nice to actually delete the event here
Switched CPUS @ cycle = 659180000
switching cpus
Switch at instruction count:0
info: Entering event queue @ 659180000. Starting simulation...
Segmentation fault
If I use m5.opt, i get the following error:
For more information see: http://www.m5sim.org/warn/f7ecd6d6
hack: be nice to actually delete the event here
Switched CPUS @ cycle = 659180000
switching cpus
m5.opt: build/ALPHA_SE/cpu/o3/mem_dep_unit_impl.hh:116: void
MemDepUnit<MemDepPred, Impl>::switchOut() [with MemDepPred = StoreSet,
Impl = O3CPUImpl]: Assertion `instList[0].empty()' failed.
Program aborted at cycle 659180000
Aborted
Could anyone help with this?
Thanks,
Sujay
_______________________________________________
m5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
