Hello,
I am creating the parsec benchmarks as follows. But when I run with the
checkpoints, rips are all ffffffff########
$qemu/qemu-system-x86_64 -m 4096 -drive file=parseROI.qcow2,cache=unsafe
-machine shared_l2_4core
then in the image terminal, I followed the create_checkpoints.py file but make
a simple change to create checkpoints after it runs for 5 minutes (marked in
bold red).
cd parsec-2.1
source env.sh
cd /root/parsec-2.1/pkgs/apps/blackscholes/run
export
LD_LIBRARY_PATH=/root/parsec-2.1/pkgs/libs/hooks/inst/amd64-linux.gcc-hooks/lib
export PARSEC_CPU_NUM=`grep processor /proc/cpuinfo | wc -l`; echo
$PARSEC_CPU_NUM
/root/parsec-2.1/pkgs/apps/blackscholes/inst/amd64-linux.gcc-hooks/bin/blackscholes
%d in_4K.txt prices.txt &
sleep 5m; ~/create_checkpoint blackscholes; ~/start_sim
Then I test the checkpoint blacksholes. The simulation runs at 30K insns/sec
and all the rips are ffffffff########.
Is there something wrong with my methods here? Could you please help me out?
Thank you very much,
kuniors
_______________________________________________
http://www.marss86.org
Marss86-Devel mailing list
[email protected]
https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
