Re: [m5-users] Fwd: alpha_fs disk image with the PARSEC benchmarks
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 1 2000 /parsec/install/inputs/canneal/10.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 completecomplete - bodytrack complete complete - cannealcomplete 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:
Re: [m5-users] Fwd: alpha_fs disk image with the PARSEC benchmarks
Hello Ali, you were right, I tried the workload in a non modified installation and it was working right, finally I traced the error to these lines that I added in the function recvTiming of bus.cc. I will post the lines that were causing the problem, because maybe it is helpful for someone in the future int foo = pkt-getDest(); if (foo == -1) foo = 8; My_counters[pkt-getSrc()][foo]++; I deleted them and now it is working fine. And another question, to debug the problem I was commenting and uncommenting the changes that I did, I would like to ask, if it is possible in this type of errors use gdb to see the lines that were causing the problem. Thanks. On Fri, Jan 2, 2009 at 3:36 PM, Ali Saidi sa...@umich.edu wrote: Have you modified the simulator, particularly the memory system, in any way? This error occurs when an object in the memory system receives a packet it was not expecting. If you have modified the simulator, the problem probably has to do with the modifications you've made, if you haven't modified it then you should enable some trace flags like Bus, Cache, etc to see what happens leading up to this error. With that data you should be able to better understand what is going wrong and begin to realize how to fix it. Ali On Jan 2, 2009, at 5:48 PM, Eduardo Olmedo Sanchez wrote: ck, 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. ___ 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
Re: [m5-users] Fwd: alpha_fs disk image with the PARSEC benchmarks
You can use GDB, that is the way most people debug issues with M5. Depending on the optimization level GDB may have some issues finding the exact line that you're executing but generally it works. Looking at those 3 lines I don't understand how they could be causing a problem. Perhaps your array is allocated incorrectly? Ali On Jan 2, 2009, at 8:16 PM, Eduardo Olmedo Sanchez wrote: Hello Ali, you were right, I tried the workload in a non modified installation and it was working right, finally I traced the error to these lines that I added in the function recvTiming of bus.cc. I will post the lines that were causing the problem, because maybe it is helpful for someone in the future int foo = pkt-getDest(); if (foo == -1) foo = 8; My_counters[pkt-getSrc()][foo]++; I deleted them and now it is working fine. And another question, to debug the problem I was commenting and uncommenting the changes that I did, I would like to ask, if it is possible in this type of errors use gdb to see the lines that were causing the problem. Thanks. On Fri, Jan 2, 2009 at 3:36 PM, Ali Saidi sa...@umich.edu wrote: Have you modified the simulator, particularly the memory system, in any way? This error occurs when an object in the memory system receives a packet it was not expecting. If you have modified the simulator, the problem probably has to do with the modifications you've made, if you haven't modified it then you should enable some trace flags like Bus, Cache, etc to see what happens leading up to this error. With that data you should be able to better understand what is going wrong and begin to realize how to fix it. Ali On Jan 2, 2009, at 5:48 PM, Eduardo Olmedo Sanchez wrote: ck, 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. ___ 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
Re: [m5-users] Fwd: alpha_fs disk image with the PARSEC benchmarks
Hello the problem was a very bad programming that I did, I defined this counters to count the number of the access depending on the src: static double My_counters[9][9]; I did that for SE mode and using the flags I verify that the maximum src number for SE it was 9, so I put that 9 in the definition after I forgot to change the size and I switch to FS. In FS mode the src numbers are bigger so in my code it was writing in other memory space, and you can imagine the problem. Sorry about this stupid problem and thanks for the help Ali. I would like to seize the opportunity of send this email, and ask Joel if he can give us the estimated simulation time for the benchmarks. Thanks. On Fri, Jan 2, 2009 at 7:28 PM, Ali Saidi sa...@umich.edu wrote: You can use GDB, that is the way most people debug issues with M5. Depending on the optimization level GDB may have some issues finding the exact line that you're executing but generally it works. Looking at those 3 lines I don't understand how they could be causing a problem. Perhaps your array is allocated incorrectly? Ali On Jan 2, 2009, at 8:16 PM, Eduardo Olmedo Sanchez wrote: Hello Ali, you were right, I tried the workload in a non modified installation and it was working right, finally I traced the error to these lines that I added in the function recvTiming of bus.cc. I will post the lines that were causing the problem, because maybe it is helpful for someone in the future int foo = pkt-getDest(); if (foo == -1) foo = 8; My_counters[pkt-getSrc()][foo]++; I deleted them and now it is working fine. And another question, to debug the problem I was commenting and uncommenting the changes that I did, I would like to ask, if it is possible in this type of errors use gdb to see the lines that were causing the problem. Thanks. On Fri, Jan 2, 2009 at 3:36 PM, Ali Saidi sa...@umich.edu wrote: Have you modified the simulator, particularly the memory system, in any way? This error occurs when an object in the memory system receives a packet it was not expecting. If you have modified the simulator, the problem probably has to do with the modifications you've made, if you haven't modified it then you should enable some trace flags like Bus, Cache, etc to see what happens leading up to this error. With that data you should be able to better understand what is going wrong and begin to realize how to fix it. Ali On Jan 2, 2009, at 5:48 PM, Eduardo Olmedo Sanchez wrote: ck, 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. ___ 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