From: Morad Alawneh (alawneh_at_chem.byu.edu)
Date: Mon Jan 15 2007 - 14:54:38 CST
*Hi Brian,
The results shown before were for GE connection. I compiled the program
according the instruction mentioned before.
It seems to me I did a wrong choice by compiling GE using those
instructions, did not I?
If that is true, what options should I use for charm++ and namd?
Could you help me with that? I have down my guess for the possible choices?
For charm++:
**build charm++ net-linux-amd64 **tcp icc **--basedir=
/opt/intel/cce/9.1--no-build-shared -O -verbose -DCMK_OPTIMIZE=1 > build.log
**build charm++ net-linux-amd64 **icc **--basedir=
/opt/intel/cce/9.1--no-build-shared -O -verbose -DCMK_OPTIMIZE=1 >
build.log*
*build charm++ net-linux-amd64 ** **--no-build-shared -O
-verbose -DCMK_OPTIMIZE=1 > build.log*
*For namd: modify
**Linux-amd64-TCP-icc.arch ** (if tcp and icc will be used)*
*Linux-amd64-icc.arch (if icc will be used)**
**Linux-amd64-g++.arch *
*Linux-amd64.fftw
Linux-amd64.tcl
Thanks again.
*
Brian Bennion wrote:
> Hi Morad,
>
> I completely missed the point here. If you are going to use a gigabit
> connection then you need to compile the TCP/UDP net-linux versions of
> charm and namd2.6
> If you are going to stick with the infiniband then continue using the
> mpi based version of charm and namd2.6 that you detailed below.
>
> What are the times that you get with the infiniband switches using the
> mpi code that you compiled below?
>
> Brian
>
>
>
> At 08:18 AM 1/13/2007, you wrote:
>
>> Thank you for answering my inquiry.
>> My system size is 12,458 atoms, and the scalability is fine when I
>> use the infiniband of this linux cluster.
>>
>> After a lot of debugging, I think you are right, it is a hardware
>> problem.
>>
>> Here is the time information for each number of cpus:
>>
>> Info: Benchmark time: 4 CPUs 0.206016 s/step 1.19222 days/ns 32100 kB
>> memory
>> TIMING: 600 CPU: 129.219, 0.206016/step Wall: 129.219,
>> 0.206016/step, 572.231 hours remaining, 32100 kB of memory in use.
>>
>> Info: Benchmark time: 8 CPUs 0.149766 s/step 0.866699 days/ns 23608
>> kB memory
>> TIMING: 600 CPU: 96.7031, 0.149766/step Wall: 96.7031,
>> 0.149766/step, 415.991 hours remaining, 23608 kB of memory in use.
>>
>> Info: Benchmark time: 16 CPUs 0.114141 s/step 0.660536 days/ns 16032
>> kB memory
>> TIMING: 600 CPU: 79.2344, 0.11418/step Wall: 79.2344, 0.11418/step,
>> 317.147 hours remaining, 16032 kB of memory in use.
>>
>>
>> Thanks.
>>
>> Morad Alawneh
>>
>>
>> Brian Bennion wrote:
>>> Hello Morad,
>>>
>>> How big is the system your are studying? Perhaps it does not have
>>> enough atoms to justify more that 4 cpus.
>>> The switch/cables may be defective.
>>> I am not sure that adding debugging symbols and dependency tracking
>>> to the fftw libraries is a good idea for production simulations.
>>> The compile wiki at
>>> http://www.ks.uiuc.edu/Research/namd/wiki/index.cgi?NamdCompile
>>> Doesn't have these flags for ffttw compilation.
>>>
>>> Can you post some timing information to so how bad it really is?
>>> Regards
>>> Brian Bennion
>>>
>>> At 08:56 AM 1/12/2007, you wrote:
>>>> To NAMD Developers and Users,
>>>>
>>>> I have a problem getting NAMD2.6 working in parallel. The
>>>> efficiency is getting worse when I use more than 4 cpus per node.
>>>>
>>>> Can any one check the way I installed the NAMD on my system?
>>>> And if it is OK, I appreciate any suggestions to solve this problem.
>>>>
>>>>
>>>> My System:
>>>> *Dell 1955 Linux cluster. Each node is equipped with two Quad-core
>>>> Intel Xeon EM64T processors (2.6GHz) and 8 GB of memory. All nodes
>>>> are connected with Gigabit Ethernet. The cluster's EM64T processors
>>>> run a 64-bit Linux kernel.*
>>>>
>>>>
>>>> Installation Instructions:
>>>>
>>>> *fftw-2.1.5 Installation:**
>>>> -------------------------
>>>>
>>>> ./configure --prefix=/ibrix/home/mfm42/opt/fftw --enable-mpi
>>>> --enable-float --enable-type-prefix --enable-debug
>>>> --enable-dependency-tracking --enable-static
>>>>
>>>> make
>>>>
>>>> make install
>>>>
>>>> ###################################################################################
>>>>
>>>> tcl-8.4.13 Installation:
>>>> ------------------------
>>>>
>>>> ./configure --prefix=/ibrix/home/mfm42/opt/tcl --enable-64bit
>>>> --disable-shared
>>>>
>>>> make
>>>>
>>>> make install
>>>>
>>>> ###################################################################################
>>>>
>>>> charm++ Installation:
>>>> ---------------------
>>>>
>>>> Edit the file charm/src/arch/mpi-linux-amd64/conv-mach.sh:
>>>> 1)change mpiCC to mpicxx
>>>> 2)use /opt/mpich/gnu/bin as the path to mpicc and mpicxx.
>>>>
>>>> ./build charm++ mpi-linux-amd64 --basedir=/opt/mpich/gnu
>>>> --no-build-shared -O -verbose -DCMK_OPTIMIZE=1 > build.log
>>>>
>>>> ###################################################################################
>>>>
>>>> namd Installation:
>>>> ------------------
>>>>
>>>> Edit namd/Make.charm
>>>> (set CHARMBASE to the full path to charm-??)
>>>>
>>>> Edit various configuration files:
>>>> 1) namd/arch/Linux-amd64.fftw (fix path to files,
>>>> delete -I$(HOME)/fftw/include and
>>>> -L$(HOME)/fftw/lib)
>>>> 2) namd/arch/Linux-amd64.tcl (fix path to files
>>>> delete -I$(HOME)/tcl/include and
>>>> -L$(HOME)/tcl/lib
>>>> use -ltcl8.4 instead of -ltcl8.3
>>>> add -DUSE_NON_CONST to TCLFLAGS)
>>>> 3) namd/arch/Linux-amd64-MPI.arch use /opt/mpich/gnu/bin as a path to
>>>> mpicxx and mpicc instead of g++/gcc
>>>>
>>>> Set up build directory and compile:
>>>> ./config tcl fftw Linux-amd64-MPI
>>>> cd Linux-amd64-MPI
>>>> make > make.log*
>>>>
>>>>
>>>>
>>>> *Submission command: *
>>>> */opt/mpiexec/bin/mpiexec
>>>> /ibrix/home/mfm42/opt/namd-GE/Linux-amd64-MPI/namd2
>>>> gamma_150_sys.namd "+strategy USE_GRID" > gamma_150_sys.log*
>>>>
>>>>
>>>> Thanks
>>>>
>>>> Morad Alawneh
>>>> Department of Chemistry and Biochemistry, BYU
>>>> Provo, UT
This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:44:18 CST