Information about the new S5 workunits

roadrunner_gs
roadrunner_gs
Joined: 7 Mar 06
Posts: 94
Credit: 3369656
RAC: 0

RE: Actually the debug info

Message 37877 in response to message 37876

Quote:
Actually the debug info can be most helpful in resolving any problems that might (or actually do) occur, so it would be counterproductive to remove them. Only a few bytes / second of debug info is produced, so it doesn't matter performance-wise.
(...)

I am working as an administrator for Webservers and Applicationservers.
This is what is called "operation" in our company.
The applications i do "operate" are in the so called "productive"-state.
No one would even consider to "operate" an application currently in "development"-state.
No one would consider inserting debug-statemens into operating applications or running those applications with debug-logging. ;)
But here the development seems to actually take place in "operation"-state stressing the voluntarily contributers instead of performing this state on development-boxes at einstein.
That - i am sorry to say so - has to be considered very "unprofessional".

Richard Haselgrove
Richard Haselgrove
Joined: 10 Dec 05
Posts: 2143
Credit: 2961002648
RAC: 694894

RE: RE: Actually the

Message 37878 in response to message 37877

Quote:
Quote:
Actually the debug info can be most helpful in resolving any problems that might (or actually do) occur, so it would be counterproductive to remove them. Only a few bytes / second of debug info is produced, so it doesn't matter performance-wise.
(...)

I am working as an administrator for Webservers and Applicationservers.
This is what is called "operation" in our company.
The applications i do "operate" are in the so called "productive"-state.
No one would even consider to "operate" an application currently in "development"-state.
No one would consider inserting debug-statemens into operating applications or running those applications with debug-logging. ;)
But here the development seems to actually take place in "operation"-state stressing the voluntarily contributers instead of performing this state on development-boxes at einstein.
That - i am sorry to say so - has to be considered very "unprofessional".


Is your company established to carry out cutting edge - potentially, Nobel prize winning - scientific research? If not ... different situation, different rules.

roadrunner_gs
roadrunner_gs
Joined: 7 Mar 06
Posts: 94
Credit: 3369656
RAC: 0

No the company i work for is

No the company i work for is the Deutsche Rentenversicherung Bund, the German national pension insurance fund.
Our Balance is an income of approximately 148 billion (Giga or Milliarde) Euro and an expense of approximately 141 billion (Giga or Milliarde) Euro, i suppose we don't play in the minor league.
But if "cutting edge - potentially, Nobel prize winning - scientific research" means banana-software and not thoroughly tested software - as one would presume with such a task set upon - we could assume i am wrong.
There could be a "beta"-branch on which voluntaries may attend and where those beta-apps are spread, but issuing them to all users is a bit far off.
But these all is only my opinion and i might be totally wrong.

Chris S
Chris S
Joined: 27 Aug 05
Posts: 2469
Credit: 19550265
RAC: 0

Bernt stated about S5R2 in

Bernt stated about S5R2 in April

Quote:

The application we'll use for this run is all new and has never been used before. The algorithm used in the old App is still a part of the new one, and other parts have also been used before, but they have never been used in the present combination, and in particular not in a distributed computing project of that scale. We expect some problems to arise from this.

One of the issues we are still working on is some "overhead", i.e. calculations that are performed for technical reasons, but don't actually contribute to the result, thus wasting computing power.

We therefore will set up S5R2 as a short, experimental run that limits the search to parts of the parameter space where the overhead is well under control. During this short run we will improve the Application in various aspects. The results will also help us tuning the parameters for the next, larger run (probably named S5R3).

We woz warned! Although later joiners to the project wouldn't have been aware of that. Yes they were a bit naughty experimenting like that, but hopefully it will pay off for S5R3

edit 74 days to go for end of S5R2

Waiting for Godot & salvation :-)

Why do doctors have to practice?
You'd think they'd have got it right by now

tullio
tullio
Joined: 22 Jan 05
Posts: 2118
Credit: 61407735
RAC: 0

RE: No the company i work

Message 37881 in response to message 37879

Quote:
No the company i work for is the Deutsche Rentenversicherung Bund, the German national pension insurance fund.
Our Balance is an income of approximately 148 billion (Giga or Milliarde) Euro and an expense of approximately 141 billion (Giga or Milliarde) Euro, i suppose we don't play in the minor league.
But if "cutting edge - potentially, Nobel prize winning - scientific research" means banana-software and not thoroughly tested software - as one would presume with such a task set upon - we could assume i am wrong.
There could be a "beta"-branch on which voluntaries may attend and where those beta-apps are spread, but issuing them to all users is a bit far off.
But these all is only my opinion and i might be totally wrong.


Years ago I was interviewed by an IBM engineer for a position with them. I asked him: do use use UNIX? Nah, he said, that is only for professors and students, we use MVS or something like that. Now they are running Linux on clusters of thousands of Power processors. Do you consider Linux a banana-software? IBM does not.
Tullio

roadrunner_gs
roadrunner_gs
Joined: 7 Mar 06
Posts: 94
Credit: 3369656
RAC: 0

So the einstein-app is Linux?

So the einstein-app is Linux? (which is in fact available tested to a fair amount, no banana involved unless you aren't using the latest beta release of a kernel voluntarily)
You see me completely amazed, i ever thought it is a self-programmed application.
How comes it runs as an application on Windows anyway if the einstein-app is a OS-kernel in the first place?
Or are you driving at a completely different point?

tullio
tullio
Joined: 22 Jan 05
Posts: 2118
Credit: 61407735
RAC: 0

RE: So the einstein-app is

Message 37883 in response to message 37882

Quote:
So the einstein-app is Linux? (which is in fact available tested to a fair amount, no banana involved unless you aren't using the latest beta release of a kernel voluntarily)
You see me completely amazed, i ever thought it is a self-programmed application.
How comes it runs as an application on Windows anyway if the einstein-app is a OS-kernel in the first place?
Or are you driving at a completely different point?


I am saying only that Linux arose from a teaching tool (by Andrew Tanenbaum) and was transformed into something useful by a student (Linus Torvalds) who exploited the work done by Richard Stallman and his Free Software Foundation. Nobody would have bet a penny on the future of such a contraption. And yet...
Tullio

roadrunner_gs
roadrunner_gs
Joined: 7 Mar 06
Posts: 94
Credit: 3369656
RAC: 0

...IBM ripped the kernel out

...IBM ripped the kernel out of Linus Torvalds hands when he finished the first beta and installed it onto their "clusters of thousands of Power processors" running productive right away without testing it?
I could hardly believe.
Either you are addressing a completely different topic or i am unable to see the connection of your posting to mine.

Enough said from me and now onto topic.

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3522
Credit: 734246658
RAC: 1292732

RE: So the einstein-app is

Message 37885 in response to message 37882

Quote:
So the einstein-app is Linux? (which is in fact available tested to a fair amount, no banana involved unless you aren't using the latest beta release of a kernel voluntarily)
You see me completely amazed, i ever thought it is a self-programmed application.
How comes it runs as an application on Windows anyway if the einstein-app is a OS-kernel in the first place?
Or are you driving at a completely different point?

I guess the point was that Linux and Unix began their respective lives as a fairly "academic" experiment before it entered the industrial mainstream. I think it's unfair to apply the same standards to a cutting-edge, academic and experimental (yes, this is what E@H is all about, a great science experiment) software to version 10.5.2 of some industrial application that was developed over the course of several years by hords of programmers and testers.

C'mon all, ... this is leading nowhere. Let's focus on what can be done now. Why lament over spilled milk?

BRM

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3522
Credit: 734246658
RAC: 1292732

BTW: Does anybody still

Message 37886 in response to message 37885

BTW:

Does anybody still have a copy of the S5R1 or S5RI science app for Windows??

Is the string "AuthenticAMD" also appearing in those apps? I wonder whether the math lib was perhaps changed in a recent update of the Microsoft compiler suite??

CU

BRM

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.