ARSC HPC Users' Newsletter 225, August 3, 2001

Call for Papers: ARSC IBM SP Workshop

ARSC Workshop : CALL FOR PAPERS

Application Development and Tuning Workshop

September 4-7, 2001

Arctic Region Supercomputing Center Fairbanks Alaska

The Arctic Region Supercomputing Center (ARSC) will host a 4-day workshop on IBM SP system use, benchmarking methodologies, and related topics. In the mornings, users will describe their experiences developing and tuning scientific applications for various high performance computing systems and discuss the requirements of some emerging computational challenges. In the afternoons, staff from the IBM Advanced Computing Technology Center (ACTC) will provide IBM technology updates and training on selected topics to help users get the most out of SP systems.

This workshop is open to all members of the DoD HPCMP and University of Alaska communities. System access will be limited to users who have applied for, or hold, a National Agency Check.

A dedication event for ARSC's new IBM SP system will be held.

Call for Papers

To present a paper at the workshop, please submit a brief (no more that 150 words) abstract by August 15, 2001. Each presentation should be 30 minutes including 5 minutes for Q&A.

Presentations will be selected for their relevance to the HPC community. Notification will be August 17, 2001. Topics of interest include:

  • Benchmarking of Application Codes
  • Application Tuning & Optimization
  • Computational Requirements for Emerging Technologies

Submit abstracts as plain text or MS Word attachments to Guy Robinson via email: robinson@arsc.edu

ACTC Presentations

The workshop will be conducted in the afternoon session and will be specific to the IBM SP architecture. The sessions will focus around the following general topics:

  • Compilers and Programming Environments
  • MPI and OpenMP
  • Tools for Optimization
  • Q and A and additional hands-on

Additional information will be posted on the ARSC and HPCMP web pages as it becomes available:

/arsc/support/news/t3enews/t3enews127/index.xml

for more on streaming.) A T3E run with streaming turned off increased the time from 0.340 to 0.816 seconds.

ARSC Student Intern Presentations, Aug 9

Beginning at 2pm, Aug. 9, in Butrovich 109, ARSC's three summer interns will be presenting their projects over the AGN. These talks are open to interested members of the ARSC/UAF community, and, of course, to those with an Access Grid Node:

  • Annemarie Dahm (University of Montana) will present her work augmenting the GSLib kriging algorithms library to allow for interpolation of precipitation and other hydrologic data.

  • Orlando Solis (University of Texas El Paso) will present his system for automating and organizing regression testing across multiple platforms.

  • Doug Vicere (University of Alaska Anchorage) will present his work on a tsunami model, generalizing input and other aspects of the code, and producing a vizualization tool to help in code verification.

ARSC Faculty Camp: Lectures Open to Local Folks

Limited space is available for any interested users (or potential users) to attend the following lectures in ARSC's 2001 "Faculty Camp." Contact Guy Robinson, 474-6386, robinson@arsc.edu if you are interested, and he'll provide details.


  First Week.  August 6-10
  =================================
  Monday 
    10am: Introduction to ARSC
  
  Tuesday 
    10am: Users Introduction to ARSC Supercomputers
    2pm:  Introduction to Parallel Processing
  
  
  Second Week.  August 13-17
  =================================
  Tuesday 
    10am: Cray Presentation on Computing Technologies
  
  Thursday/Friday
    Workshop on Creating Computational Scientists in the 21st Century
  
  
  Third Week.  August 20-24
  =================================
  Tuesday 
    10am: Visualization Case Studies.
  
  Thursday 
    2pm:  Presentations and Faculty Camp achievements

If you can't attend, ARSC consultants and specialists are available for one-on-one discussions and will be putting together ARSC's fall 2001 schedule of courses soon. Let us know where your interests lie!

Quick-Tip Q & A


A:[[ I had some .lst and .lst.gz files, all of which I wanted to
  [[ hide in a separate subdirectory. I used "mv" (the cryptic Unix
  [[ alternative, it seems, to click and drag).  It seems to have worked,
  [[ but "mv" complains, and I don't know if I should worry about this.
  [[
  [[  termite$ ll
  [[    total 10
  [[    drwx------    2 morty    groop      4096 Jul 12 17:21 lst_files/
  [[    -rw-------    1 morty    groop     34129 Jul 12 17:20 ptsv.f
  [[    -rw-------    1 morty    groop     20011 Jul 12 17:20 ptsv_gen.f
  [[    -rw-------    1 morty    groop    791991 Jul 12 17:20 ptsv_gen.lst.gz
  [[    -rw-------    1 morty    groop     10233 Jul 12 17:20 ptsv.lst.gz
  [[    -rw-------    1 morty    groop       550 Jul 12 11:10 vgen.lst
  [[  termite$ 
  [[  termite$ mv *lst* lst_files
  [[    lst_files - Invalid argument
  [[  termite$ 
  [[  termite$ ll
  [[    total 8
  [[    drwx------    2 morty    groop      4096 Jul 12 17:21 lst_files/
  [[    -rw-------    1 morty    groop     34129 Jul 12 17:20 ptsv.f
  [[    -rw-------    1 morty    groop     20011 Jul 12 17:20 ptsv_gen.f
  [[  termite$ 
  [[  termite$ ll lst_files
  [[    total 2
  [[    -rw-------    1 morty    groop    791991 Jul 12 17:20 ptsv_gen.lst.gz
  [[    -rw-------    1 morty    groop     10233 Jul 12 17:20 ptsv.lst.gz
  [[    -rw-------    1 morty    groop       550 Jul 12 11:10 vgen.lst
  [[  termite$ 




#
# Three answers and a remark, sorted by verbosity:
#


#
# Nic Brummell
#

It is trying to move the directory lst_files into itself.  Fortunately,
Unix does not allow this Escher-like activity and therefore complains.


#
# Guy Robinson... (editorial remark)
#

Actually it is safe on most modern unix systems. However, back when I
was working on some of the first Unix ports, one user managed to issue a
similar command, and the system very happily kept moving a into a/a into
a/a/a into a/a/a/a until we were out of inodes.


#
# Richard Griswold
#

Since the regex *lst* matches the directory name lst_files, mv thinks you
want to move lst_files into lst_files.  The error, which varies from
system to system, is telling you that you cannot move a directory into
itself.  You can avoid this error message by using a more fine-tuned
regex, such as this:

  mv *.lst *.lst.gz lst_files

However, as long as the files are moved correctly you don't have to worry.


#
# Bradford Chamberlain 
#

In this command, what's happening is your use of wildcard characters is
not only matching the .lst.gz and .lst files you targeted, but also
lst_files (where the first * is evaluating to nothing and the second is
evaluating to "_files").  Thus, the UNIX command thinks that you want to
mv lst_files to lst_files, which is nonsensical, so it complains.

Thus, the short answer is that this isn't something to worry about.
It's just warning you that it's not doing the nonsensical thing you
requested.

If it seems like mv ought to be smart enough to know that this isn't
what you meant by the wildcards, keep in mind that your shell is the
culprit that's expanding the wildcard characters and sending the results
to mv.  mv is quite ignorant about the fact that you typed wildcard
characters at all, as it's just handed the following command by the
shell:

        mv lst_files ptsv_gen.lst.gz ptsv.lst.gz vgen.lst lst_files

(which specifies to move all the named files but the last into the
directory named by the last argument).

My best suggestion for making this work is to use a better wildcard
filter that doesn't match the directory name.  For example, in your case
you have the easy option of using:

        mv *.lst* lst_files

which will not match the lst_files directory.  If you really want to be
a geek, you can use:

        mv ?*lst* lst_files

which means "match anything that has at least one character followed by
"lst" followed by any other character."  Since your directory starts
with "lst" this will cause it not to match.




Q: I am rather upset, so please be nice.

   My Fortran program has variable called "sec", and I need to find
   wherever I subtract it.  The coding is not always consistent, so
   these statements can take various forms, like:

     dtime=tstart-sec 
     dtime = tstart - sec 

   I figured I'd be clever, so I tried egrep, but it didn't work.  So
   I tried grep, and got the same wierd output!  It's a total miss:


    morty$ egrep "-sec
- sec
-  sec" littleprog.F 
 tail    
        count(4) = 1
        write(*,*) 'parameters for ncvgtg call' 
        write(*,*) 'ncid   ',ncid
          write(*,*) 'sec:   ',sec
        write(*,*) 'Calling ncvgtg'
        call ncvgt(ncid,dataid,start,count,data,error)
        write(*,*) 'Finished calling ncvgtg'
        call ncclos(ncid,error)
           close(1)
          close(7)
    morty$ grep "-sec" littleprog.F 
 tail       
        count(4) = 1
        write(*,*) 'parameters for ncvgtg call' 
        write(*,*) 'ncid   ',ncid
          write(*,*) 'sec:   ',sec
        write(*,*) 'Calling ncvgtg'
        call ncvgt(ncid,dataid,start,count,data,error)
        write(*,*) 'Finished calling ncvgtg'
        call ncclos(ncid,error)
           close(1)
          close(7)

   So my question is:  WHAT HAVE YOU CHANGED ON YOUR SYSTEM!  (or...
   ahem, am I doing something wrong?)

[[ Answers, Questions, and Tips Graciously Accepted ]]


Current Editors:
Ed Kornkven ARSC HPC Specialist ph: 907-450-8669
Kate Hedstrom ARSC Oceanographic Specialist ph: 907-450-8678
Arctic Region Supercomputing Center
University of Alaska Fairbanks
PO Box 756020
Fairbanks AK 99775-6020
E-mail Subscriptions: Archives:
    Back issues of the ASCII e-mail edition of the ARSC T3D/T3E/HPC Users' Newsletter are available by request. Please contact the editors.
Back to Top