Hello, I am having problems with the PARSEC benchmarks, I am getting this error running x264, bodytrack, canneal, swaptions in a 4 core system, in Full System mode, with 4 threads and with the small workload.
warn: allocating bonus target for snoop m5.opt: build/ALPHA_FS/mem/tport.cc:97: virtual bool SimpleTimingPort::recvTiming(Packet*): Assertion `pkt->isResponse()' failed. Program aborted at cycle 1878100939500 Aborted This is my script: #!/bin/sh /sbin/m5 checkpoint /sbin/m5 switchcpu /sbin/m5 dumpstats /sbin/m5 resetstats cd /parsec/install/bin ./x264 --quiet --qp 20 --partitions b8x8,i4x4 --bframes 3 --ref 5 --direct auto --b-pyramid --b-rdo --weightb --bime --mixed-refs --no-fast-pskip --me umh --subme 7 --analyse b8x8,i4x4 --threads 4 -o /parsec/install/inputs/x264/eledream.264 /parsec/install/inputs/x264/eledream_640x360_8.y4m ./bodytrack /parsec/install/inputs/bodytrack/sequenceB_1 4 1 1000 5 0 4 ./canneal 4 10000 2000 /parsec/install/inputs/canneal/100000.nets ./swaptions -ns 16 -sm 5000 -nt 4 echo "Done :D" /sbin/m5 exit /sbin/m5 exit Have anyone experienced the same problem?. Is this a problem of the benchmarks or is a problem of the simulator?, when I am running my own simple test in the simulator normally I do not have any problems. And finally is thre anyone there that have tried to run several of the benchmarks together in the same workload?. Thanks in advance. On Thu, Nov 20, 2008 at 8:54 PM, Joel Hestness <hestn...@cs.utexas.edu> wrote: > Ah yes, how could I forget... > I have also placed a script that generates these scripts on my site. Note > that it requires the command line parameters file also located there: > http://www.cs.utexas.edu/~hestness/links/writescripts.pl > http://www.cs.utexas.edu/~hestness/links/inputsets.txt > You will probably have to do some hacking on the script for your > particular arrangement, but hopefully the out-of-box results will be close > (no guarantees are written or implied concerning the correctness of these > scripts :P). More information about PARSEC input sets and PARSEC command > lines can be found in the benchmark suite itself. > Good luck. Enjoy, > Joel > > Joel Hestness > Computer Architecture > Dept. of Computer Science, University of Texas - Austin > > > On Thu, Nov 20, 2008 at 10:31 PM, Rick Strong <rstr...@cs.ucsd.edu> wrote: >> >> Hi Joel, >> >> I would love to try the parsec benchmarks on a full system model. Do you >> have any sehll scripts that run the benchmarks. >> >> Best, >> -Rick >> >> Joel Hestness wrote: >> > Hi, >> > Another member of my research group, Mark Gebhart, and I have been >> > working on putting together a disk image for use with M5 that contains >> > the PARSEC benchmark binaries. >> > To date, we have compiled all of the benchmarks for ALPHA and placed >> > them on a disk image. We are still ironing out bugs with some of >> > them, but the image contains 9+ working benchmarks. I have placed a >> > link to the image on my website: >> > >> > http://www.cs.utexas.edu/~hestness/links/linux-parsec-golden.img.bz2 >> > <http://www.cs.utexas.edu/%7Ehestness/links/linux-parsec-golden.img.bz2> >> > Also, I have placed a README next to it that contains the current >> > status of the PARSEC benchmarks on the image: >> > >> > http://www.cs.utexas.edu/~hestness/links/linux-parsec-golden-status.txt >> > >> > <http://www.cs.utexas.edu/%7Ehestness/links/linux-parsec-golden-status.txt> >> > Here is the current status: >> > >> > -------------------------- >> > The binaries on this disk image are located at /parsec/install/bin >> > The input sets on this disk image are located at /parsec/install/inputs >> > linux-parsec-golden.img (as of 11/17/08): >> > This matrix indicates if the benchmarks complete with many threads >> > running on the specified input sets: >> > simsmall: simmedium: simlarge: >> > - blackscholes complete complete complete >> > - bodytrack complete complete >> > - canneal complete complete >> > - dedup complete >> > - facesim >> > - ferret complete complete >> > - fluidanimate complete complete >> > - freqmine complete complete >> > - streamcluster fail-kernel bug >> > - swaptions fail-unaligned trap >> > - vips complete complete >> > - x264 complete >> > -------------------------- >> > >> > If you have fully working binaries for any of the benchmarks that we >> > don't currently have working, I will definitely welcome links to them >> > and can update the image. When we get all of the PARSEC benchmarks >> > working, we will make this image available through the M5 site. >> > Thanks, >> > Joel >> > >> > Joel Hestness >> > Computer Architecture >> > Dept. of Computer Science, University of Texas - Austin >> > >> > >> > >> > ---------- Forwarded message ---------- >> > From: <eduardo.olmedo.sanc...@alumnos.upm.es >> > <mailto:eduardo.olmedo.sanc...@alumnos.upm.es>> >> > Date: Thu, Nov 20, 2008 at 3:13 PM >> > Subject: alpha_fs disk image with the PARSEC benchmarks >> > To: hestn...@cs.utexas.edu <mailto:hestn...@cs.utexas.edu> >> > Hello I am doing research with the M5 simulator, and we are planning >> > to use >> > your benchmarks at our lab here in the Technical University of Madrid, I >> > have seen in this message >> > >> > https://lists.cs.princeton.edu/pipermail/parsec-users/2008-July/000160.html >> > that you have a disk image with the binares of some benchmarks on it, it >> > will be really appreciable if you can send me the image because in >> > that way >> > you will save me many time, thank you. >> > Best, >> > Ed >> > ------------------------------------------------------------------------ >> > >> > _______________________________________________ >> > m5-users mailing list >> > m5-users@m5sim.org >> > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users >> >> _______________________________________________ >> m5-users mailing list >> m5-users@m5sim.org >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > > > _______________________________________________ > m5-users mailing list > m5-users@m5sim.org > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > _______________________________________________ m5-users mailing list m5-users@m5sim.org http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
