[Wien] help pl.

[M. Koshino]

Dr. R.K.thapa

If the installer of intel compilers does not work properly, the OS of your PC might not recognize your hardware.

You should have got some message from the installer.

Check your system monitor and confirm that the name and number of your processors are correct.

You should look at the FAQ or forum of intel compilers.

I attached the mail that I installed the system.

p.s. I have my PC installed on CentOS 6.0 which figured out my hardware successfully.

Masanori Koshino

Nanotube Research Center
National Institute of Advanced Industrial Science and Technology
AIST Central 5, 1-1-1 Higashi, Tsukuba 305-8565, JAPAN
m-koshino at aist.go.jp
Tel: +81-29-861-4479


>  From:    "M. Koshino" <m-koshino at aist.go.jp>
>  To:      A Mailing list for WIEN2k users <wien at zeus.theochem.tuwien.ac.at>
>  Date:    Fri, 17 Jun 2011 12:01:55 +0900
>  Subject: Re: [Wien] Help with Operation System
> ----
> 
> Dear all,
> 
> In my opinion, xeon is not a new cpu so that it does not matter what OS you choose as long as your system and compilers properly recognize your hardware.
> 
> I recently set up a very cheap, new PC by myself and here is a note to encourage researchers of less funded.
> 
> When I first installed CentOS 5.6 on my core i7 2600 machine, the cpu was not properly recognized (there could be some ways but I easily gave up).
> The intel compilers and other software were therefore not properly installed on the system with core i7 2600.
> 
> I could set up the latest intel compilers properly on fedora core 15, and could compile wien2k ver.11 (properly I hope).
> 
> System:
> CPU: Core i7 2600 BOX
> (recognized as processor 0-7: core i7-2600 cpu @ 3.40 GHz)
> Motherboard: ASUS, P8P67 DELUXE REV 3.0
> Video Card: ASUS, EAH5850 DIRECTCU/2DIS/1GD5 (PCIExp 1GB)
> OS: Linux 2.6.38.6-27.fc15.x86_64
> GNOME 3.0.1
> memory: 16 GB
> Corsair CMZ8GX3M2A1600C8 (4GBx4)
> compiler
> /opt/intel/composerxe-2011.4.191/bin/intel64/ifort
> applying update 4.0 for C++ compiler XE 12.0, Fortran Compiler XE 12.0, Debugger 12.0, MKL 10.3, IPP 7.0, TBB 3.0.
> (I could save $20K by comparing to my previous purchase from a high performance computer vendor.)
> 
> After running the test_case
> command "x lapw1 -c"
> test_case.output1:       TIME HAMILT (CPU)  =     6.5, HNS =     4.4, HORB =     0.0, DIAG =    25.4
> test_case.output1:       TIME HAMILT (WALL) =     6.9, HNS =     4.4, HORB =     0.0, DIAG =    25.8
> 
> command "x lapw1 -p"
> test_case.output1:       TIME HAMILT (CPU)  =     6.5, HNS =     4.4, HORB =     0.0, DIAG =    25.4
> test_case.output1:       TIME HAMILT (WALL) =     6.7, HNS =     4.4, HORB =     0.0, DIAG =    25.6
> 
> after running the mpi-benchmark
> command "x lapw1 -p"
> Intel_core2_2.4_single_ifort-10_mkl-9.1.output1:       TIME HAMILT (CPU)  =   200.5, HNS =   154.5, HORB =     0.0, DIAG =   923.7
> mpi-benchmark.output1:       TIME HAMILT (CPU)  =    91.0, HNS =    50.6, HORB =     0.0, DIAG =   300.0
> mpi-benchmark.output1:       TIME HAMILT (WALL) =    91.8, HNS =    51.0, HORB =     0.0, DIAG =   303.4
> 
> I am not familiar with the values here so I hope someone will make a comment on this.
> 
> Kind regards,
> 
> Masanori Koshino
> 
> Nanotube Research Center
> AIST, JAPAN
> m-koshino at aist.go.jp