ARSC HPC Users' Newsletter 230, October 12, 2001



IMSL 4.01 on Chilkoot

As announced in "news imsl", IMSL 4.01 is now available to chilkoot users. This package is compatible with previous imsl libraries but adds Fortran 90 modules and MPI parallelized functions. As we gain experience, we'll provide details here.

For more information, see "news imsl" on chilkoot and the on-line documentation under "3rd Party Software" on ARSC's document server,


UK HPC User Meetings

[From a posting on comp-fortran-90.]

The UK Research Councils organize High Performance Computing User meetings and the last was held at Whitehall Place in Central London on Wednesday 26 September.

The home page for this is

Follow the links and you will eventually find details of the meetings they have held on HPC.


SC2001 Panel and Request from Co-Editor

[ Send your comments/opinions/questions to Guy, . ]

Guy Robinson has been asked to comment on the Best and Worst Ideas in Supercomputing in a panel session at SC2001. At least he thinks thats what the panel is for, not "as" examples of the best and worst ideas in supercomputing. Do any readers of the newsletter have any comments they'd like to share with him?

See for more on the panel session, but here's the outline:

SC2001 Panel Session FRIDAY, NOVEMBER 16

10:30am-noon Room A207/209

Topic: Supercomputing's Best and Worst Ideas

Panelists: James C. Browne, Professor Computer Science, University of Texas, Austin; Cherri M. Pancake, Professor, Oregon State University; Guy Robinson, Research Liaison/MPP Specialist, Arctic Region Supercomputing Center, University of Alaska; Charles Seitz, CEO & CTO, Myricom, Inc.; Burton Smith, Chief Scientist, Cray Inc.; Marc Snir, Professor, University of Illinois, Urbana-Champaign

The title of this panel is, to some extent, self-explanatory-but if that were all we said, the abstract would be too short. Thus, the questions below expand on the issues that the panelists may wish to consider. We are pleased to have a very distinguished group of panelists covering a wide range of aspects of supercomputing. We invite you to join in the discussion with your answers to the following questions, and with your own questions for the panelists and audience.

Some questions to be put forth at the panel are as follows:

What makes an idea a "supercomputing idea"? (You cannot use the word "supercomputer" in your answer)

What ideas have gone, over time, from best to worst, worst to best, or both?

From ideas that were bad, what good kernels have been extracted?

From ideas that were good, what bad impacts have occurred?

Are some ideas reminiscent of a "Tale of Two Cities"-it is the best of ideas and the worst of ideas?

Is one person's best idea choice another person's worst idea choice?

[... etc ...]

[... etc ...]


2001 Bear Encounters

[ This article has NOTHING to do with computing! Feel free to skip ahead to the (ever-relevant... for someone... we hope...) Quick-Tip. ]

In Issue #223 , I invited you to share your bear encounters of summer 2001. Now that the bears are starting to hibernate, I thought I'd share the stories. Fortunately, everyone, especially Guy, survived their terrifying encounters:

From Don Morton:

This happened in mid-June, I was running trails on Blue Mt. near Missoula, Montana. I had put in about 5 miles, making noise now and then to scare off any potential bears or mountain lions. This was to no avail, because I rounded a bend and saw, roughly 15 yards away, the derriere of a black bear, furiously digging away underneath a rotting log. The bear was so busy that it hadn't noticed me, so I stopped to ponder what to do. Well, it took about 3.72 seconds for me to realize that, at the very least, I should back off and get out of sight. I pondered turning around and heading back to the trailhead, but I have few opportunities for long runs in the mountains and was determined to climb the rest of the way up. So, I clapped and yelled, hoping to scare the bear off (from a distance) and, sure enough, I heard it crashing through the woods off the trail. Funny, my wife had just a few days earlier cursed all those tree stumps that look like bears and lions. Well, I'm here to tell you that after being close to a bear, those tree stumps look even MORE like bears! You're just a little on edge, and even a mouse scurrying around in the bushes can spook you for a bit!

From Tom Baring:

I've seen five bears since moving to Alaska, six years ago, and three were on the drive up. This summer's was the best encounter, as I felt no threat, and the bear was in its natural element, surrounded by incredible, primordial beauty: moss covered spruce, cloudy glacial peaks, silence, the occasional eagle or raven flying overhead, and moist undergrowth. It's likely this particular bear hadn't seen a road in its whole life. I was "camping" with my family and some friends in a forest service cabin on a bay in Prince William Sound. Two of us sea kayaked, at absolute high-tide, up the estuary of a nearby creek (but not too nearby), and just where the clear water of the creek began to dominate, pushing the siltier sea water back toward the bay, and where we first started to see the schools of pink salmon swimming under our boats, my companion whispered, "look up there." It was a black bear, probably 50 yards away, walking along the creek, undoubtedly well fed on salmon. Ten more steps, and he disappeared into the woods.

From Guy Robinson:

My bear encounter:

From Tom Bachert:

The ink of the night pressed in upon us as my dog "Scrub" and I huddled behind the shadowy hulk of my boat resting forlornly on its trailer in our driveway. Moments before, we had been part of a different world. A world of televisions blaring harsh reports of terror and disaster, of sinks of dirty dishes, and kids complaining of unfair homework assignments. A world where beepers remind us of the electronic complaints being issued by distant computers while electric lights shield us from the Alaskan night. Scrub, being of the canine persuasion, never really fit into such a world and thus had nuzzled me into taking our nightly walk in his world. Now we found ourselves in the darkness of the approaching winter listening with a mixture of fear and curiosity as teeth or claw shredded lumber and metal just outside our field of vision.

"Who goes there?" I demand, trying to sound like the confident king of my world. The night's sudden silence was my only answer.

"Is it a bear?" I whisper to Scrub but his only response is a wet lick of my hand reassuring me that I really am the king and thus all must be right in the world as far as he is concerned. "Geeezz! I live in town!" Certainly a bear wouldn't be stalking me here.

Then again this is ALASKA, and this certainly does seem to be the year of the bear.

It began in spring when I watched "bear" market eat any hopes of an early retirement. This was followed by that June night when my boat broke down miles from the nearest road and those giant grizzly tracks marked off the area where my son and I would be pitching our tent. August had brought that whole family of bruins which raided our backpacks and chased my son and me away from the best salmon fishing holes along the Talkeetna river. "Hmmm, maybe the bears are stalking me in my own neighborhood now!"

Gathering my courage I reach into my boat and retrieve a flashlight. I boldly step forward into the darkness and stab at the light's switch. To my relief, the batteries are still good and a bright yellow beam shoots into the darkness. My heart stops as I see two red eyes mirrored back at me along the edge of the cone of light, but it restarts a moment later when I realize the eyes belong to my neighbor's dog. His chain is tangled and his bowl of moose bones is stuck just out of reach under the corner of his wooden doghouse. Feeling much more like a king, I walk over to him, untangle his chain and retrieve his food bowl.

Scrub and I continue our walk under the darkness of the approaching winter, once again confident that all is well in the real world as long as one is not tangled in chains and is in possession of a warm bowl of bones.


Quick-Tip Q & A

A:[[ I have a wallop of text files.  It's easy to list those which
  [[ contain some word, for instance, "dungarees:"
  [[ grep -i -l "dungarees" *.txt
  [[ However, I need the files which do NOT contain the word.  This command:
  [[ grep -i -l -v "dungarees" *.txt
  [[ went berserk! It claimed that _every_ file does not contain dungarees,
  [[ which is false!  Does grep have some bug?  What should I do?

# From Chris Edsall

All hail the power of find!

The command:

  grep -i -l "dungarees" *.txt

could be rewritten, 

 find . -name \*.txt -exec grep -i "dungarees" {} \; -print

This is making use of the result code the grep normally returns to the
shell. From here it is easy to reverse the logic of the grep test:

  find . -name \*.txt ! -exec grep -i "dungarees" {} \; -print

# A couple of refinements are possible. 
# 1- grep can be silenced, so only the file names will be listed, by
#    giving grep the "-q" option (AIX or UNICOS) or "-s" option (IRIX).
# 2- find can be restricted to a search of the current working
#    directory using the -prune option.
# The following solution (AIX or UNICOS) was sent in by Dale Clark:

find * \( -type d -prune \) -o -name "*" ! -exec egrep -iq "valid until" {} \; -print

Q: I want to duplicate a file, _including_ its modification time, which
   is actually important to me.  But I'm stuck:

      -  "mv"  retains the mod time, but doesn't duplicate the file  
      -  "cp"  duplicates the file, but changes the time
   For example:

     sgi> ll my.old.file
       -rw-r-----    1 myname   mygrp    2112 Nov  8  1981 my.old.file
     sgi> cp my.old.file junk
     sgi> ll my.old.file junk
       -rw-------    1 myname   mygrp    2112 Oct 11 06:46 junk
       -rw-r-----    1 myname   mygrp    2112 Nov  8  1981 my.old.file
     sgi> mv my.old.file junk
     sgi> ll junk
       -rw-r-----    1 myname   mygrp    2112 Nov  8  1981 junk
   What's a guy supposed to do?

[[ 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