Thanks korey! I already modified the se.py for that. But as you mentioned this, I thought of just trying this simple program on se.py and see. But still here is what I get:
command line: build/ALPHA/gem5.opt configs/example/se.py --cmd tests/test-progs/hello/bin/alpha/linux/hello;tests/test-progs/hello/bin/alpha/linux/hello --cpu-type detailed --caches --l2cache Global frequency set at 1000000000000 ticks per second 0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000 0: system.remote_gdb.listener: listening for remote gdb #1 on port 7001 **** REAL SIMULATION **** info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. info: Increasing stack size by one page. gem5.opt: build/ALPHA/cpu/o3/fetch_impl.hh:645: void DefaultFetch<Impl>::finishTranslation(Fault, Request*) [with Impl = O3CPUImpl, Fault = RefCountingPtr<FaultBase>, Request* = Request*]: Assertion `!finishTranslationEvent.scheduled()' failed. Program aborted at cycle 9606500 Aborted Is it a matter of configuration error? Thanks, Heba On Mon, Feb 20, 2012 at 7:56 AM, Korey Sewell <[email protected]> wrote: > If you look into se.py there should be a some python code that allows you > to specify multiple applications on one benchmark. I believe the semicolon > is parsed out of the string specifying the workloads and will allow you to > load multiple benchmarks per CPU. > > If that file hasn't been tweaked too much, you should be able to do > something like: > gem5.opt ... --cmd="hello;hello" --detailed ... > > and that would give you two hello world binaries on the O3CPU in SE mode. > > (But I would say the most important thing is to go through that se.py file > and make sure you on a high level understand what's going on. Part of the > "goodness" of gem5 is the ability to config through the Python front end..) > > On Mon, Feb 20, 2012 at 10:45 AM, Heba Saadeldeen <[email protected]>wrote: > >> Here is a quote I got from multiprogrammed workloads: >> " If you're using the O3 model, you can also assign a vector of workload >> objects to one CPU, in which case the CPU will run all of the workloads >> concurrently in SMT mode. Note that SE mode has no thread scheduling; if >> you need a scheduler, run in FS mode and use the fine scheduler built into >> the Linux kernel." >> >> I do not need a scheduler, I just need to be able to run them on the same >> cpu concurrently in SMT mode. Is there a flag to start SMT mode? >> >> Thanks, >> Heba >> >> >> On Mon, Feb 20, 2012 at 7:28 AM, Heba Saadeldeen <[email protected]>wrote: >> >>> I still do not get it. I see in the cpu code that there could exist >>> multiple threads and you can run multiple threads on the same cpu. Even in >>> se.py there is a part where you read multiple workloads separated by >>> semicoloumns to run on the same cpu. In O3CPU.py there is also a place were >>> you specify the number of instructions fetched by each thread. I just want >>> to run the multiple workloads as threads on the cpu, is that possible? >>> >>> Heba >>> >>> >>> On Sat, Feb 18, 2012 at 12:24 PM, Gabe Black <[email protected]>wrote: >>> >>>> ** >>>> I'm pretty sure you can't run multiple workloads on the same CPU. SE >>>> mode doesn't have a scheduler, so there would be no way to switch between >>>> them. You'll have to use FS mode. >>>> >>>> Gabe >>>> >>>> >>>> On 02/17/12 20:09, Heba Saadeldeen wrote: >>>> >>>> Hi, >>>> >>>> I am trying to run multiple workloads on the same cpu. But I got that >>>> error: >>>> >>>> 0: system.remote_gdb.listener: listening for remote gdb #0 on port 7000 >>>> 0: system.remote_gdb.listener: listening for remote gdb #1 on port 7001 >>>> panic: same statistic name used twice! >>>> name=system.cpu.workload1.num_syscalls >>>> @ cycle 0 >>>> >>>> I also found that I can't use fast forward for multiple workloads on >>>> the same cpu because to simulate the fast forwarded instructions gem5 uses >>>> simple cpu that does not support more than one workload. >>>> >>>> Any help is appreciated! >>>> Thanks, >>>> -- >>>> Heba >>>> >>>> >>>> _______________________________________________ >>>> gem5-users mailing >>>> [email protected]http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >>>> >>>> >>>> >>>> _______________________________________________ >>>> gem5-users mailing list >>>> [email protected] >>>> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >>>> >>> >>> >>> >>> -- >>> Heba >>> >> >> >> >> -- >> Heba >> >> _______________________________________________ >> gem5-users mailing list >> [email protected] >> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users >> > > > > -- > - Korey > > _______________________________________________ > gem5-users mailing list > [email protected] > http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users > -- Heba
_______________________________________________ gem5-users mailing list [email protected] http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
