GNU/Linux S5R3 App 4.38 available for Beta test

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4,305
Credit: 248,668,503
RAC: 30,844
Topic 193541

A new Linux App is available from our Beta Test page.

Actually it's not a new App at all. The package includes renamed versions of the Apps formaly known as 4.31 and 4.35 and a little wrapper program that switches between them based on the CPU fetures it detects.

If something goes wrong with the automatic switching (i.e. you get "signal 4" "illegal instruction" errors), placing a file named "CPU_TYPE_0" in the BOINC directory should run the generic (non-SSE) App even if the wrapper would detect SSE.

This is a beta test for the wrapper more than anything else. If successful it should enable us to deliver optimized Apps to the larger public that doesn't run "power"- or "beta"-Apps.

The app_info.xml has entries for

420
421
424
427
431
435
438

If your current App version is not listed here, you'll have to add it manually.

BM

BM

Jos van Wolput
Jos van Wolput
Joined: 11 Feb 05
Posts: 47
Credit: 800,840
RAC: 0

GNU/Linux S5R3 App 4.38 available for Beta test

Just successfully started app 4.38 with boinc client 5.10.43!

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3,522
Credit: 693,510,687
RAC: 101,526

Hi! Under Knoppix 5.2 I

Hi!

Under Knoppix 5.2 I get the following error and the app refuses to run:

einstein_S5R3_4.38_i686-pc-linux-gnu: /lib/tls/i686/cmov/libc.so.6: version `GLIBC_2.4' not found (required by einstein_S5R3_4.38_i686-pc-linux-gnu)
Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4,305
Credit: 248,668,503
RAC: 30,844

RE: Hi! Under Knoppix 5.2

Message 79862 in response to message 79861

Quote:

Hi!

Under Knoppix 5.2 I get the following error and the app refuses to run:

einstein_S5R3_4.38_i686-pc-linux-gnu: /lib/tls/i686/cmov/libc.so.6: version `GLIBC_2.4' not found (required by einstein_S5R3_4.38_i686-pc-linux-gnu)


Oh yeah - the switcher should be linked statically. Will fix this.

BM

BM

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3,522
Credit: 693,510,687
RAC: 101,526

On a system with a more

On a system with a more recent libc, all is working fine, tho.

Unfortunately the only non-SSE capable host I've got won't run this one (see above), so I can't really test the CPU detection.
Bikeman

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4,305
Credit: 248,668,503
RAC: 30,844

RE: Oh yeah - the switcher

Message 79864 in response to message 79862

Quote:
Oh yeah - the switcher should be linked statically. Will fix this.


Done.

Have another go!

BM

BM

ML1
ML1
Joined: 20 Feb 05
Posts: 347
Credit: 86,460,850
RAC: 2,610

Is there also a Linux 64-bit

Is there also a Linux 64-bit version that can tried out?

And has Akos been in on the act for the hot loops?

Looking interesting...

Regards,
Martin

See new freedom: Mageia Linux
Take a look for yourself: Linux Format
The Future is what We all make IT (GPLv3)

Bikeman (Heinz-Bernd Eggenstein)
Bikeman (Heinz-...
Moderator
Joined: 28 Aug 06
Posts: 3,522
Credit: 693,510,687
RAC: 101,526

RE: RE: Oh yeah - the

Message 79866 in response to message 79864

Quote:
Quote:
Oh yeah - the switcher should be linked statically. Will fix this.

Done.

Have another go!

BM

That particular host has run out of quota, but another one (SEE-capable, tho) with an older libc now runs this app without problem.

CU
Bikeman

Brian Silvers
Brian Silvers
Joined: 26 Aug 05
Posts: 772
Credit: 282,700
RAC: 0

Since we're talking about

Since we're talking about feature detection now, are there any plans to go up to SSE2, or would the costs of doing so outweigh the benefits?

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4,305
Credit: 248,668,503
RAC: 30,844

RE: Since we're talking

Message 79868 in response to message 79867

Quote:
Since we're talking about feature detection now, are there any plans to go up to SSE2, or would the costs of doing so outweigh the benefits?


There's still some room for improvements of the SSE code, I'll try that first. My rough guess is that SSE2 would gain less than 10% over the best possible SSE App.

However with the new way of feature-based App switching the "costs" (for the project) are lowered too, compared to the cumbersome mixed-linked Apps we had before.

BM

BM

Brian Silvers
Brian Silvers
Joined: 26 Aug 05
Posts: 772
Credit: 282,700
RAC: 0

RE: RE: Since we're

Message 79869 in response to message 79868

Quote:
Quote:
Since we're talking about feature detection now, are there any plans to go up to SSE2, or would the costs of doing so outweigh the benefits?

There's still some room for improvements of the SSE code, I'll try that first. My rough guess is that SSE2 would gain less than 10% over the best possible SSE App.

However with the new way of feature-based App switching the "costs" (for the project) are lowered too, compared to the cumbersome mixed-linked Apps we had before.

Fair enough. There will definitely be diminishing returns on the efforts. If you provide SSE2, then I'm sure people will want SSE3, SSSE3, SSE4, etc... My guess, based on what is being seen with SETI, is that SSE3 is where meaningful improvements would stop. For AMD processors, it became apparent that SSE3 had negligible differences (perhaps due to missing HyperThreading?)...

Comment viewing options

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