Charm++ parallel programming system

[salam pradeep <salampradeep AT gmail.com>]

Respected Sir/madam,

I am a beginner in Molecular Dynamics simulation, When I m trying NAMD in VEGA ZZ and run the simulation its coming in command promt 

Charrm ++ Fatal Error 

Fatal Error Parameter not found in the configuration file.

Please help me in this regard.

With regards

Salam Pradeeep

Tezpur University, Assam, India

On Tue, Jun 7, 2011 at 9:53 AM, <charm-request AT cs.uiuc.edu> wrote:

Send charm mailing list submissions to
       charm AT cs.uiuc.edu

To subscribe or unsubscribe via the World Wide Web, visit
       http://lists.cs.uiuc.edu/mailman/listinfo/charm
or, via email, send a message with subject or body 'help' to
       charm-request AT cs.uiuc.edu

You can reach the person managing the list at
       charm-owner AT cs.uiuc.edu

When replying, please edit your Subject line so it is more specific
than "Re: Contents of charm digest..."


Today's Topics:

  1. Re: [ppl]  Question about IB (Eric Bohm)
  2. Re: [ppl]  Bluegene build (Abhinav S Bhatele)
  3. Re: [ppl] problem during charm build (Phil Miller)
  4. Re: [ppl]  problem during charm build (Abhinav S Bhatele)


----------------------------------------------------------------------

Message: 1
Date: Mon, 6 Jun 2011 12:35:03 -0500
From: Eric Bohm <ebohm AT illinois.edu>
Subject: Re: [charm] [ppl]  Question about IB
To: <ppl AT cs.uiuc.edu>, "charm AT cs.uiuc.edu" <charm AT cs.uiuc.edu>
Message-ID: <4DED0FC7.1040807 AT illinois.edu>
Content-Type: text/plain; charset="ISO-8859-1"; format=flowed

Yes it can.  If you modify the first line of the netconfig file to
disable the transceiver:

USE_TRANSCEIVER 0

Then it will expect you to load the communication from trace files.

Also, in case there was some confusion in the matter, the IB simulation
stands for Input Buffered (as opposed to Output Buffered) not as an
abbreviation for infiniband.

On 06/06/2011 01:13 AM, Xuehan Xu wrote:
> Dear sirs:
>          Can the IB simulation in BigNetSim use the bgTrace file to
> generate the network traffic? I tried, but I got this error
>
> Charmrun> charmrun started...
> Charmrun> using /root/.nodelist as nodesfile
> Charmrun> remote shell (localhost:0) started
> Charmrun> node programs all started
> Charmrun remote shell(localhost.0)> remote responding...
> Charmrun remote shell(localhost.0)> using xterm /usr/bin/xterm
> Charmrun remote shell(localhost.0)> using debugger /usr/local/bin/gdb
> Charmrun remote shell(localhost.0)> starting node-program...
> Charmrun remote shell(localhost.0)> rsh phase successful.
> Charmrun> node programs all connected
> Charmrun> started all node programs in 3.022 seconds.
> Charmrun> adding client 0: "localhost", IP:127.0.0.1
> Charmrun> Charmrun = localhost.localdomain, port = 40834
> start_nodes_rsh
> Charmrun> Sending "0 localhost.localdomain 40834 4413 0" to client 0.
> Charmrun> find the node program "/root/BigNetSim/trunk/IB/../tmp/pgm" at
> "/root/BigNetSim/trunk/IB" for 0.
> Charmrun> Starting ssh localhost -l root /bin/sh -f
> Charmrun> Waiting for 0-th client to connect.
> Charmrun> client 0 connected (IP=127.0.0.1 data_port=38504)
> Charmrun> All clients connected.
> Charmrun> IP tables sent.
> Warning> Randomization of stack pointer is turned on in kernel, thread
> migration may not work! Run 'echo 0 >
> /proc/sys/kernel/randomize_va_space' as root to disable it, or try run
> with '+isomalloc_sync'.
> Charm++> scheduler running in netpoll mode.
> Charm++> Running on 1 unique compute nodes.
> Charm++> cpu topology info is gathered in 0.003 seconds.
> ================= Simulation Configuration =================
> Number of physical PEs: 1
> POSE mode: Parallel
> Command line: /root/BigNetSim/trunk/tmp/pgm 1 0
> Timing factor: 1.000000e+08 (i.e., 1 GVT tick = 10 ns)
> cpufactor: 1.000000
> bgTrace summary: totalBGProcs=8 X=2 Y=2 Z=2 #CommThreads=1
> #WorkerThreads=1 #PEs=1 LogVersion=6
> Simulation mode: trace driven
> Simulation network mode: full contention
> Initializing POSE...
> POSE initialization complete.
> Using Inactivity Detection for termination.
> fanout 3 numP 6
> Network parameters:
>     Max packet size: 256
>     File window size: 0
>     Debug print level: 0
>     Window load threshold: 0
>     Intra node latency: 0.500000 us
>     Intra node bandwidth: 1.000000 GB/s
>     Number of buffers per port in each switch: 12
>     Switch buffer size: 1024
>     Channel bandwidth: 1.000000
>     Channel delay: 0
>     Link stats collection interval: 1000000 GVT ticks
>     Link stats on: no
>     Message stats on: no
>     Adaptive routing on: yes
>     Header size: 16 bytes
>     Processor send overhead: 0 GVT ticks
>     Processor receive overhead: 0 GVT ticks
>     Number of simulated nodes: 9
> ============================================================
> Info> invoking startup task from proc 0 ...
> Info> Starting at the beginning of the simulation
> Info> Running to the end of the simulation
> 176477 I am 0 But src 0 dst 0
> Packet misrouted to destination
> ------------- Processor 0 Exiting: Called CmiAbort ------------
> Reason: Commit ERROR
> [0] Stack Traceback:
>    [0:0] CmiAbort+0x75  [0x82ac98f]
>    [0:1] _ZN10eventQueue12CommitEventsEP3simx+0x1d3  [0x81be099]
>    [0:2] _ZN3sim6CommitEv+0x194  [0x81c00ce]
>    [0:3] _ZN10pvtObjects6CommitEv+0x52  [0x81cbb08]
>    [0:4] _ZN3PVT6setGVTEP6GVTMsg+0x11a  [0x81ba470]
>    [0:5] _ZN11CkIndex_PVT19_call_setGVT_GVTMsgEPvP3PVT+0x18  [0x81ba958]
>    [0:6] CkDeliverMessageFree+0x44  [0x821a972]
>    [0:7] /root/BigNetSim/trunk/tmp/pgm [0x821aa12]
>    [0:8] /root/BigNetSim/trunk/tmp/pgm [0x821aaa9]
>    [0:9] /root/BigNetSim/trunk/tmp/pgm [0x821b0dc]
>    [0:10] /root/BigNetSim/trunk/tmp/pgm [0x821b4e5]
>    [0:11] _Z15_processHandlerPvP11CkCoreState+0x10d  [0x821c377]
>    [0:12] CmiHandleMessage+0x63  [0x82b2dee]
>    [0:13] CsdScheduleForever+0x6a  [0x82b2ff1]
>    [0:14] CsdScheduler+0x11  [0x82b2f5c]
>    [0:15] /root/BigNetSim/trunk/tmp/pgm [0x82b138b]
>    [0:16] ConverseInit+0x344  [0x82b189c]
>    [0:17] main+0x49  [0x8222e8d]
>    [0:18] __libc_start_main+0xdc  [0x125e9c]
>    [0:19] __gxx_personality_v0+0x375  [0x813beb1]
> Charmrun: error on request socket--
> Socket closed before recv.
>
> Please help me, thank you:-)
>
>
>
> _______________________________________________
> charm mailing list
> charm AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/charm
>
>
>
> _______________________________________________
> ppl mailing list
> ppl AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/ppl



------------------------------

Message: 2
Date: Mon, 6 Jun 2011 18:45:13 -0500
From: Abhinav S Bhatele <bhatele AT illinois.edu>
Subject: Re: [charm] [ppl]  Bluegene build
To: Adamantini Peratikou <Adamantini.Peratikou AT port.ac.uk>
Cc: charm AT cs.uiuc.edu
Message-ID: <BANLkTi=CXaQ-0e6v-753FbYf_2pS-wk1Pw AT mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Hello Adamantini,

Can you give some details about which machine you are trying to build
BigNetSim on?

All you should have to do is build charm with the following options (
http://charm.cs.illinois.edu/manuals/html/bignetsim/1_2.html):
./build bgampi net-linux-x86_64
./build pose net-linux-x86_64

And then point BigNetSim to this charm and type make in the respective
network directory that you are trying to build.

- Abhinav


On Sun, Jun 5, 2011 at 11:34 AM, Adamantini Peratikou <
Adamantini.Peratikou AT port.ac.uk> wrote:

> hello i need your help,
>
> I have build bigsim, charms++net-linux-x86-64,pose,bgampi net-linux-x86_64
> bigemulator -O2, i have then used subversion to obtain the bignetsim
> package. i am now trying to install bluegene but each time i do make i get
> the following error, i ve tried to compile the rest of teh archs available
> such as HypCube but similar errors appear,
>
> Any help would be greatly appreciated.
>
> in BigNetSim/trunk directory when i use make the following error appears:
>
> Fatal Error by charmc in directory
> /home/psycho/charm/charm-6.2/BigNetSim/trunk/Main
>    Command g++ -fPIC -m64
> -I/home/psycho/charm/charm-6.2/net-linux-x86_64/bin/../include
> -D__CHARMC__=1 -I/home/psycho/charm/charm-6.2/net-linux-x86_64/include/pose
> -I/home/psycho/charm/charm-6.2/net-linux-x86_64/include -I../BlueGene -g -c
> TCsim_sim.C -o ../tmp/TCsim_sim.o returned error code 1
> charmc exiting...
> make[2]: *** [../tmp/TCsim_sim.o] Error 1
> make[2]: Leaving directory
> `/home/psycho/charm/charm-6.2/BigNetSim/trunk/Main'
> make[1]: *** [all] Error 1
> make[1]: Leaving directory
> `/home/psycho/charm/charm-6.2/BigNetSim/trunk/BlueGene'
> make: *** [bigsimulator] Error 2
>
>
>
> When i am using charms ./build with bluegene option i get this error my gcc
> compirler is there working fine with other apps:
>
> Performing 'make -j 16 basics OPTS= -O2 QUIET=' in mpi-bluegenep-xlc/tmp
> make charmxi
> make[1]: Entering directory
> `/home/psycho/charm/charm-6.2/mpi-bluegenep-xlc/tmp'
> ./configure
> ERROR: Invalid BGP_INSTALL or BGP_FLOOR, C/C++ compiler missing
> make[1]: *** [conv-autoconfig.h] Error 1
> make[1]: Leaving directory
> `/home/psycho/charm/charm-6.2/mpi-bluegenep-xlc/tmp'
> make: *** [headers] Error 2
> -------------------------------------------------
> Charm++ NOT BUILT. Either cd into mpi-bluegenep-xlc/tmp and try
> to resolve the problems yourself, visit
> http://charm.cs.uiuc.edu/
> for more information. Otherwise, email the developers at charm AT cs.uiuc.edu
>
> Thanking you in advance for your time and assistance.
>
> _______________________________________________
> charm mailing list
> charm AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/charm
>
> _______________________________________________
> ppl mailing list
> ppl AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/ppl
>
>


--
Abhinav S Bhatele, Ph. D.
Webpage: www.bhatele.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.cs.uiuc.edu/pipermail/charm/attachments/20110606/51938ce3/attachment-0001.html

------------------------------

Message: 3
Date: Mon, 6 Jun 2011 21:19:02 -0700
From: Phil Miller <mille121 AT illinois.edu>
Subject: Re: [charm] [ppl] problem during charm build
To: sabitha ramanathan <rk.sabitha AT gmail.com>
Cc: Charm Mailing List <charm AT cs.illinois.edu>
Message-ID: <BANLkTikQ-HpHSpfEUM6JBMPGiK5rvVZeKg AT mail.gmail.com>
Content-Type: text/plain; charset=UTF-8

Please get the latest released version of NAMD, 2.7, and not its beta
(2.7b1). If the Charm++ included with that has trouble, then come back
and include the output from that.

On Mon, Jun 6, 2011 at 21:09, sabitha ramanathan <rk.sabitha AT gmail.com> wrote:
> Dear Phil
>
> Thank you
> uname -a output
> Linux suse 2.6.16.21-0.8-bigsmp #1 SMP Mon Jul 3 18:25:39 UTC 2006 i686 i686
> i386 GNU/Linux
>
> I downloaded NAMD 2.7b1
> during make it is giving following? error
> please tell me hw to rectify
>
> mkdir inc
> mkdir obj
> pathCC -m64 -fPIC -DSOCKLEN_T=socklen_t -I/include
> -I.rootdir/charm-6.1/mpi-linux-gcc/include -DCMK_OPTIMIZE=1 - Isrc -Iinc
> -Iplugins/include -DSTATIC_PLUGIN -I/usr/include -I/root/tcl/include
> -I/usr/include/tcl8.3/ -DNAMD_T CL
> -I/Projects/namd2/fftw/linux-x86_64/include -DNAMD_FFTW
> -DNAMD_VERSION=\"2.7b1\" -DNAMD_PLATFORM=\"Linux-x8 6_64-MPI\"
> -DREMOVE_PROXYRESULTMSG_EXTRACOPY?? -lpathfortran -O3 -CG:local_fwd_sched=on
> -LNO:opt=0 -OPT:unroll_t imes_max=8:div_split=ON:roundoff=2 -OPT:alias=typed
> -o obj/common.o -c src/common.C
> make: pathCC: Command not found
> make: *** [obj/common.o] Error 127
>
> thanks in advance
>
> with regards
> Dr Sabitha
>
>
> On Mon, Jun 6, 2011 at 8:34 AM, Phil Miller <mille121 AT illinois.edu> wrote:
>>
>> Dr. Sabitha,
>>
>> That's a pretty old version of Charm++, distributed with an old
>> version of NAMD. I'd suggest getting the released NAMD 2.7 which
>> carries a newer version of Charm++.
>>
>> Also, you shouldn't need to specify gcc, since Charm++ will pick that
>> up by default.
>>
>> Is your machine 64 bit, or 32 bit? If you don't know directly, please
>> run 'uname -a' and send us the output. It should be just one line.
>>
>> Phil
>>
>> On Fri, Jun 3, 2011 at 23:57, sabitha ramanathan <rk.sabitha AT gmail.com>
>> wrote:
>> > Sir
>> > This is Dr Sabitha from Cancer Institute Chennai,India
>> > i tried my level best to build charm in my Suse Linux system
>> > but all in vain
>> > i updtaed reinstalled gcc g++ but i am not able to build i am here with
>> > enclosing output
>> > please tell me how to rectify?
>> >
>> > with regards
>> > Dr.Sabitha
>> > Asst Prof
>> > Cancer Institute(WIA)
>> > Adyar
>> > India
>> >
>> >
>> > _______________________________________________
>> > ppl mailing list
>> > ppl AT cs.uiuc.edu
>> > http://lists.cs.uiuc.edu/mailman/listinfo/ppl
>> >
>> >
>
>



------------------------------

Message: 4
Date: Mon, 6 Jun 2011 23:22:48 -0500
From: Abhinav S Bhatele <bhatele AT illinois.edu>
Subject: Re: [charm] [ppl]  problem during charm build
To: Phil Miller <mille121 AT illinois.edu>
Cc: Charm Mailing List <charm AT cs.illinois.edu>
Message-ID: <BANLkTimHJHtZLT=soxQOh9oBhyzcch8ScA AT mail.gmail.com>
Content-Type: text/plain; charset="iso-8859-1"

Actually the latest release is 2.8:
http://www.ks.uiuc.edu/Development/Download/download.cgi?PackageName=NAMD


On Mon, Jun 6, 2011 at 11:19 PM, Phil Miller <mille121 AT illinois.edu> wrote:

> Please get the latest released version of NAMD, 2.7, and not its beta
> (2.7b1). If the Charm++ included with that has trouble, then come back
> and include the output from that.
>
> On Mon, Jun 6, 2011 at 21:09, sabitha ramanathan <rk.sabitha AT gmail.com>
> wrote:
> > Dear Phil
> >
> > Thank you
> > uname -a output
> > Linux suse 2.6.16.21-0.8-bigsmp #1 SMP Mon Jul 3 18:25:39 UTC 2006 i686
> i686
> > i386 GNU/Linux
> >
> > I downloaded NAMD 2.7b1
> > during make it is giving following  error
> > please tell me hw to rectify
> >
> > mkdir inc
> > mkdir obj
> > pathCC -m64 -fPIC -DSOCKLEN_T=socklen_t -I/include
> > -I.rootdir/charm-6.1/mpi-linux-gcc/include -DCMK_OPTIMIZE=1 - Isrc -Iinc
> > -Iplugins/include -DSTATIC_PLUGIN -I/usr/include -I/root/tcl/include
> > -I/usr/include/tcl8.3/ -DNAMD_T CL
> > -I/Projects/namd2/fftw/linux-x86_64/include -DNAMD_FFTW
> > -DNAMD_VERSION=\"2.7b1\" -DNAMD_PLATFORM=\"Linux-x8 6_64-MPI\"
> > -DREMOVE_PROXYRESULTMSG_EXTRACOPY   -lpathfortran -O3
> -CG:local_fwd_sched=on
> > -LNO:opt=0 -OPT:unroll_t imes_max=8:div_split=ON:roundoff=2
> -OPT:alias=typed
> > -o obj/common.o -c src/common.C
> > make: pathCC: Command not found
> > make: *** [obj/common.o] Error 127
> >
> > thanks in advance
> >
> > with regards
> > Dr Sabitha
> >
> >
> > On Mon, Jun 6, 2011 at 8:34 AM, Phil Miller <mille121 AT illinois.edu>
> wrote:
> >>
> >> Dr. Sabitha,
> >>
> >> That's a pretty old version of Charm++, distributed with an old
> >> version of NAMD. I'd suggest getting the released NAMD 2.7 which
> >> carries a newer version of Charm++.
> >>
> >> Also, you shouldn't need to specify gcc, since Charm++ will pick that
> >> up by default.
> >>
> >> Is your machine 64 bit, or 32 bit? If you don't know directly, please
> >> run 'uname -a' and send us the output. It should be just one line.
> >>
> >> Phil
> >>
> >> On Fri, Jun 3, 2011 at 23:57, sabitha ramanathan <rk.sabitha AT gmail.com>
> >> wrote:
> >> > Sir
> >> > This is Dr Sabitha from Cancer Institute Chennai,India
> >> > i tried my level best to build charm in my Suse Linux system
> >> > but all in vain
> >> > i updtaed reinstalled gcc g++ but i am not able to build i am here
> with
> >> > enclosing output
> >> > please tell me how to rectify?
> >> >
> >> > with regards
> >> > Dr.Sabitha
> >> > Asst Prof
> >> > Cancer Institute(WIA)
> >> > Adyar
> >> > India
> >> >
> >> >
> >> > _______________________________________________
> >> > ppl mailing list
> >> > ppl AT cs.uiuc.edu
> >> > http://lists.cs.uiuc.edu/mailman/listinfo/ppl
> >> >
> >> >
> >
> >
>
> _______________________________________________
> charm mailing list
> charm AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/charm
>
> _______________________________________________
> ppl mailing list
> ppl AT cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/ppl
>



--
Abhinav S Bhatele, Ph. D.
Webpage: www.bhatele.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.cs.uiuc.edu/pipermail/charm/attachments/20110606/162ed55d/attachment.html

------------------------------

_______________________________________________
charm mailing list
charm AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/charm


End of charm Digest, Vol 44, Issue 5
************************************