I actually got all my SPEC 2K binaries from the pool file system and they are working for SE MODE ALPHA. I think there are full SPEC binaries in one folder, MinneSpec in another folder, and then they have the actual code on the last folder.
I think they are in the directory "spec2000_binaries" or something like that... Dig around in there and you should fine them. Also, if you dont mind, please update the Benchmark WIKI when you find what you need so someone else can benefit from the hard work you are putting in currently: http://wiki.eecs.umich.edu/TrevsGroup/index.php?title=Benchmarks_workloads On Tue, Mar 25, 2008 at 12:14 PM, nathan binkert <[EMAIL PROTECTED]> wrote: > I don't believe so. I think you'll have to build them yourself. If > you do, please share them with us so we can use them as well. > > Nate > > > > > Yes I got this. Thanks for the tip Ali! Also, do we have all the binaries > > for alpha/linux? The directory on /m5/dist/cpu2000 has only a few > > benchmarks. > > > > - Sujay > > > > > > > > ----- Original Message ----- > > From: "nathan binkert" <[EMAIL PROTECTED]> > > To: "M5 users mailing list" <[email protected]> > > Sent: Tuesday, March 25, 2008 12:06 AM > > Subject: Re: [m5-users] Troubel running Spec2K > > > > > > > Did you get this figured out? I understand the bug in M5 that allowed > > > you to silently ignore this, but this is an error in your script as > > > Ali pointed out. > > > > > > Nate > > > > > > On Mon, Mar 24, 2008 at 12:22 PM, Sujay Phadke <[EMAIL PROTECTED]> > > > wrote: > > >> > > >> > > >> > > >> Hello, > > >> I am trying to get Spec2K to run. (beta 4 or 5) I have attached > my > > >> example config script here, which tries to run only the gzip_log > > >> benchmark. > > >> I get the following error: > > >> > > >> > ./build/ALPHA_SE/m5.opt configs/spec2000/test2.py -b gzip > > >> > > >> M5 compiled Feb 18 2008 17:51:36 > > >> M5 started Mon Mar 24 15:16:41 2008 > > >> M5 executing on vm1 > > >> command line: ./build/ALPHA_SE/m5.opt configs/spec2000/test2.py -b gzip > > >> Global frequency set at 1000000000000 ticks per second > > >> warn: This DRAM module has not been tested with the new memory system > at > > >> all! > > >> panic: only one workload allowed > > >> @ cycle 0 > > >> [create:build/ALPHA_SE/cpu/simple/atomic.cc, line 817] > > >> Program aborted at cycle 0 > > >> > > > >> > > >> It seems the workload is not being assigned correctly, but I am not > able > > >> to > > >> figure out why. The line in atomic.cc which issues the panic is: > > >> > > >> #if FULL_SYSTEM > > >> params->profile = profile; > > >> params->do_quiesce = do_quiesce; > > >> params->do_checkpoint_insts = do_checkpoint_insts; > > >> params->do_statistics_insts = do_statistics_insts; > > >> #else > > >> if (workload.size() != 1) > > >> panic("only one workload allowed"); > > >> params->process = workload[0]; > > >> #endif > > >> > > >> So maybe the workload.size() is not evaluating correctly. > > >> > > >> Can someone help me out? > > >> > > >> Thanks, > > >> Sujay > > >> > > >> _______________________________________________ > > >> m5-users mailing list > > >> [email protected] > > >> http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > > >> > > > _______________________________________________ > > > m5-users mailing list > > > [email protected] > > > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > > > > > > > _______________________________________________ > > m5-users mailing list > > [email protected] > > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > > > > > _______________________________________________ > m5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/m5-users > -- ---------- Korey L Sewell Graduate Student - PhD Candidate Computer Science & Engineering University of Michigan _______________________________________________ m5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/m5-users
