Hi Khadidja,

Did you tried the suggested changes? Did it work? Please, check my last
propose if you didn't fix the problem yet.

http://www.mail-archive.com/[email protected]/msg13935.html

Cano.

2017-03-06 20:25 GMT+01:00 Lebeane, Michael <[email protected]>:

> Hi Raziye,
>
>
>
> Correct.  The problem appears to be with the DMA controller’s state
> machine, not with the benchmark itself.
>
>
>
> -Michael
>
>
>
> *From:* gem5-users [mailto:[email protected]] *On Behalf Of *raziye
> deylamsalehi
> *Sent:* Monday, March 6, 2017 1:08 PM
>
> *To:* gem5 users mailing list <[email protected]>
> *Subject:* Re: [gem5-users] Invalid transition error while running PARSEC
> benchmark in ALPHA CPU
>
>
>
> I must do that, if I use other benchmark?
>
> Thanks,
> Raziye
>
>
>
> On Mar 6, 2017 10:35 PM, "Lebeane, Michael" <[email protected]>
> wrote:
>
> Hi Raziye,
>
>
>
> You add them to the protocol file, recompile gem5, and re-run the
> benchmark that is throwing invalid transitions.
>
>
>
> Thanks,
>
> Michael
>
>
>
> *From:* gem5-users [mailto:[email protected]] *On Behalf Of *raziye
> deylamsalehi
> *Sent:* Monday, March 6, 2017 12:57 PM
> *To:* gem5 users mailing list <[email protected]>
> *Subject:* Re: [gem5-users] Invalid transition error while running PARSEC
> benchmark in ALPHA CPU
>
>
>
> Hi Michael
>
>
>
> Must we add those lines to MOESI_CMP_directory-dma.sm for using moesi
> protocol or parsec bench?
>
>
>
> Thanks,
>
> Raziye
>
>
>
> On Mon, Mar 6, 2017 at 7:40 PM, Lebeane, Michael <[email protected]>
> wrote:
>
> Hi Khadidja,
>
>
>
> Looks like the same issue reported here:
>
> http://www.mail-archive.com/[email protected]/msg13935.html
>
>
>
> Can you please try the fix suggested in the link above and let me know how
> it goes?
>
>
>
> Thanks,
>
> Michael LeBeane
>
>
>
> *From:* gem5-users [mailto:[email protected]] *On Behalf Of *Gaffour
> Khadidja
> *Sent:* Sunday, March 5, 2017 7:36 AM
> *To:* [email protected]
> *Subject:* [gem5-users] Invalid transition error while running PARSEC
> benchmark in ALPHA CPU
>
>
>
> Hi
>
> I am running the gem5 version with moesi-cmp_directory protocol with ruby 
> option.
>
> While running the PARSEc benchmark i am getting the below error.
>
>
> warn: ClockedObject: More than one power state change request encountered 
> within the same simulation tick
> warn: ClockedObject: More than one power state change request encountered 
> within the same simulation tick
> warn: ClockedObject: More than one power state change request encountered 
> within the same simulation tick
> warn: ClockedObject: More than one power state change request encountered 
> within the same simulation tick
> **** REAL SIMULATION ****
> info: Entering event queue @ 0.  Starting simulation...
> warn: Replacement policy updates recently became the responsibility of SLICC 
> state machines. Make sure to setMRU() near callbacks in .sm files!
> info: Launching CPU 1 @ 801922000
> info: Launching CPU 2 @ 812364000
> info: Launching CPU 3 @ 822734000
> warn: Prefetch instructions in Alpha do not do anything
> warn: Prefetch instructions in Alpha do not do anything
> panic: Invalid transition
> system.ruby.dma_cntrl0 time: 3542177833 addr: 22782016 event: WriteRequest 
> state: BUSY_WR
> Memory Usage: 959420 KBytes
> Program aborted at tick 1771088916500
> --- BEGIN LIBC BACKTRACE ---
> build/ALPHA/gem5.opt(_Z15print_backtracev+0x15)[0xa29c75]
> build/ALPHA/gem5.opt(_Z12abortHandleri+0x36)[0xa38c96]
> /lib/x86_64-linux-gnu/libpthread.so.0(+0x10330)[0x7f940fd14330]
> /lib/x86_64-linux-gnu/libc.so.6(gsignal+0x37)[0x7f940e263c37]
> /lib/x86_64-linux-gnu/libc.so.6(abort+0x148)[0x7f940e267028]
> build/ALPHA/gem5.opt(_ZN14DMA_Controller18doTransitionWorkerE9DMA_Event9DMA_StateRS1_RP7DMA_TBEm+0x2a0)[0x9dd2f0]
> build/ALPHA/gem5.opt(_ZN14DMA_Controller12doTransitionE9DMA_EventP7DMA_TBEm+0x1c3)[0x9dd503]
> build/ALPHA/gem5.opt(_ZN14DMA_Controller6wakeupEv+0x33d)[0x9e00ad]
> build/ALPHA/gem5.opt(_ZN10EventQueue10serviceOneEv+0xb1)[0xa31a61]
> build/ALPHA/gem5.opt(_Z9doSimLoopP10EventQueue+0x38)[0xa52ce8]
> build/ALPHA/gem5.opt(_Z8simulatem+0x35b)[0xa533cb]
> build/ALPHA/gem5.opt[0x791c8c]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x45f7)[0x7f940f8df5b7]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x80d)[0x7f940f8e1c3d]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x48d8)[0x7f940f8df898]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x4b59)[0x7f940f8dfb19]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x4b59)[0x7f940f8dfb19]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x80d)[0x7f940f8e1c3d]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCode+0x32)[0x7f940f8e1f22]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x563e)[0x7f940f8e05fe]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x80d)[0x7f940f8e1c3d]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x48d8)[0x7f940f8df898]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x80d)[0x7f940f8e1c3d]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyEval_EvalCode+0x32)[0x7f940f8e1f22]
> /usr/lib/x86_64-linux-gnu/libpython2.7.so.1.0(PyRun_StringFlags+0x79)[0x7f940f7f4529]
> build/ALPHA/gem5.opt(_Z6m5MainiPPc+0x7f)[0xa3822f]
> build/ALPHA/gem5.opt(main+0x33)[0x5f0883]
> /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf5)[0x7f940e24ef45]
> build/ALPHA/gem5.opt[0x615c8f]
> --- END LIBC BACKTRACE ---
> Abandon (core dumped)
>
> Thanks,
>
> K.GAFFOUR
>
>
>
>
> _______________________________________________
> gem5-users mailing list
> [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
>
>
>
> _______________________________________________
> gem5-users mailing list
> [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

Reply via email to