Binary Radio Pulsar Search (Parkes PMPS XT) (BRP6) ending

cliff
cliff
Joined: 15 Feb 12
Posts: 176
Credit: 283452444
RAC: 0

Hi, I've got the same

Hi,

I've got the same problem, mega cpu error on BRP4G, changed my settings to not use those WU and now the machine that had the problem wont run 2x BRP6..

Anyway all my machine settings are now for NO BRP4G...

But if BRP6 is ending, whats left for GPU's?

 Cliff

 

Cliff,

Been there, Done that, Still no damm T Shirt.

Mumak
Joined: 26 Feb 13
Posts: 325
Credit: 3524304607
RAC: 1528521

I have just noticed that for

I have just noticed that for BRP6 there was never a Windows x64 version of CUDA55 application either. Did it have the same issue?
Since the x86 v1.57 BRP4G was OK, why not release it for both x86 and x64 systems - similar as BRP6 ?
I don't think there's any significant benefit in releasing a GPU app for x64.

-----

Keith Myers
Keith Myers
Joined: 11 Feb 11
Posts: 4964
Credit: 18745987571
RAC: 7029645

Mumak wrote:I have just

Mumak wrote:

I have just noticed that for BRP6 there was never a Windows x64 version of CUDA55 application either. Did it have the same issue?
Since the x86 v1.57 BRP4G was OK, why not release it for both x86 and x64 systems - similar as BRP6 ?
I don't think there's any significant benefit in releasing a GPU app for x64.

Based on developer comments for the apps over at SETI, you are likely correct there is no benefit to 64 bit apps for these science applications, in fact, actually causes more overhead and longer runtimes.  Probably can release the BRP6 CUDA55 beta app for BRP4G.  But really, after all these years, that app should already be the general release app and NOT Beta.  It's been well proven to work very well so far.

 

WhiteWulfe
Joined: 3 Mar 15
Posts: 31
Credit: 62249506
RAC: 0

For those of us who still

For those of us who still have the BRP4G-cuda55 jobs (I have 13 of the 1.56) should we cancel/abandon the work units, or see how they play out?

 

EDIT (21 Sept, 16:54 MDT): First one errored after just a few seconds, and contends of the error message that popped up were as follows:

----

Problem signature:

  Problem Event Name: APPCRASH

  Application Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe

  Application Version: 0.0.0.0

  Application Timestamp: 559beebb

  Fault Module Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe

  Fault Module Version: 0.0.0.0

  Fault Module Timestamp: 559beebb

  Exception Code: c0000005

  Exception Offset: 0000000000384548

  OS Version: 6.1.7601.2.1.0.768.3

  Locale ID: 1033

  Additional Information 1: 0c42

  Additional Information 2: 0c429a2f0f7486c392aa8ebcbaa01e47

  Additional Information 3: d4b0

  Additional Information 4: d4b0576d2029e957699ec1e4872682e2

 

Read our privacy statement online:

  http://go.microsoft.com/fwlink/?linkid=104288&clcid=0x0409

 

If the online privacy statement is not available, please read our privacy statement offline:

  C:\Windows\system32\en-US\erofflps.txt

----


Second one crashed and gave the following:

----

Problem signature:

  Problem Event Name: APPCRASH

  Application Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe

  Application Version: 0.0.0.0

  Application Timestamp: 559beebb

  Fault Module Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe

  Fault Module Version: 0.0.0.0

  Fault Module Timestamp: 559beebb

  Exception Code: c0000005

  Exception Offset: 0000000000384548

  OS Version: 6.1.7601.2.1.0.768.3

  Locale ID: 1033

  Additional Information 1: 0c42

  Additional Information 2: 0c429a2f0f7486c392aa8ebcbaa01e47

  Additional Information 3: d4b0

  Additional Information 4: d4b0576d2029e957699ec1e4872682e2

 

Read our privacy statement online:

  http://go.microsoft.com/fwlink/?linkid=104288&clcid=0x0409

 

If the online privacy statement is not available, please read our privacy statement offline:

  C:\Windows\system32\en-US\erofflps.txt

----
 
Third one crashed too:
----
Problem signature:
  Problem Event Name: BEX64
  Application Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe
  Application Version: 0.0.0.0
  Application Timestamp: 559beebb
  Fault Module Name: StackHash_1dc2
  Fault Module Version: 0.0.0.0
  Fault Module Timestamp: 00000000
  Exception Offset: 0000000000000000
  Exception Code: c0000005
  Exception Data: 0000000000000008
  OS Version: 6.1.7601.2.1.0.768.3
  Locale ID: 1033
  Additional Information 1: 1dc2
  Additional Information 2: 1dc22fb1de37d348f27e54dbb5278e7d
  Additional Information 3: eae3
  Additional Information 4: eae36a4b5ffb27c9d33117f4125a75c2
 
Read our privacy statement online:
 
If the online privacy statement is not available, please read our privacy statement offline:
  C:\Windows\system32\en-US\erofflps.txt
----
 
Fourth one same thing.
----
Problem signature:
  Problem Event Name: BEX64
  Application Name: einsteinbinary_BRP4G_1.56_windows_x86_64__BRP4G-cuda55.exe
  Application Version: 0.0.0.0
  Application Timestamp: 559beebb
  Fault Module Name: StackHash_1dc2
  Fault Module Version: 0.0.0.0
  Fault Module Timestamp: 00000000
  Exception Offset: 0000000000000000
  Exception Code: c0000005
  Exception Data: 0000000000000008
  OS Version: 6.1.7601.2.1.0.768.3
  Locale ID: 1033
  Additional Information 1: 1dc2
  Additional Information 2: 1dc22fb1de37d348f27e54dbb5278e7d
  Additional Information 3: eae3
  Additional Information 4: eae36a4b5ffb27c9d33117f4125a75c2
 
Read our privacy statement online:
 
If the online privacy statement is not available, please read our privacy statement offline:
  C:\Windows\system32\en-US\erofflps.txt
----
 
The remaining 9 also crashed, but I didn't get the error messages as I was trying to save supper from the oven.  I'm running four work units at a time on an MSI GTX 980 Ti Golden Edition that's at "stock" clocks (1341 core, 3505/7010 memory), nvidia driver 368.81, and Windows 7 Home Edition 64-Bit.
Jasper
Jasper
Joined: 14 Feb 12
Posts: 63
Credit: 4032891
RAC: 0

Bernd Machenschalk wrote:I am

Bernd Machenschalk wrote:

I am working on a GPU version of the Gamma-Ray pulsar search...

Does that mean that Einstein will be GPU only from then on? Or will there be a new Gravitational Wave search before? If not and without anything else left, it will also mean end of line for me.

Alexander Favorsky
Alexander Favorsky
Joined: 18 Jun 16
Posts: 36
Credit: 176475913
RAC: 76606

BRP4G-cuda55 is running okay

BRP4G-cuda55 is running okay on my home machine but recently I have got this:

22.09.2016 14:24:13 | Einstein@Home | Task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 exited with zero status but no 'finished' file
22.09.2016 14:24:13 | Einstein@Home | If this happens repeatedly you may need to reset the project.

So the app started from scratch.

Maybe this will help in analysis.

 

Bernd Machenschalk
Bernd Machenschalk
Moderator
Administrator
Joined: 15 Oct 04
Posts: 4312
Credit: 250561529
RAC: 34604

Jasper_7 wrote:Does that mean

Jasper_7 wrote:

Does that mean that Einstein will be GPU only from then on? Or will there be a new Gravitational Wave search before? If not and without anything else left, it will also mean end of line for me.

I replied in the Plans for near future of E@H thread, as this is probably of general interest.

BM

Alexander Favorsky
Alexander Favorsky
Joined: 18 Jun 16
Posts: 36
Credit: 176475913
RAC: 76606

Further details on

Further details on BRP4G-cuda55 v1.56:

Probably this app doesn't save checkpoints because every time it resumes computation from scratch.

Harri Liljeroos
Harri Liljeroos
Joined: 10 Dec 05
Posts: 4352
Credit: 3212883270
RAC: 2032432

Does anybody know what is the

Does anybody know what is the plan class for this BRP4G-cuda55 app? It is currently not showing in the applications page. I would like to get my app_config ready to handle it. I've got now 3 queued up waiting for execution.

[edit] Never mind I found it. It is BRP4G-cuda55. Obviously. Embarassed [/edit]

 

Alexander Favorsky
Alexander Favorsky
Joined: 18 Jun 16
Posts: 36
Credit: 176475913
RAC: 76606

Finally the BRP4G-cuda55

Finally the BRP4G-cuda55 v1.56 app finished with an error.

Here's copy of the log:

23.09.2016 8:04:21 | Einstein@Home | Computation for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 finished
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_0 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_1 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_2 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_3 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_4 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_5 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_6 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_7 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_8 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_9 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_10 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_11 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_12 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_13 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_14 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent
23.09.2016 8:04:21 | Einstein@Home | Output file p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0_15 for task p2030.20151216.G176.58-00.81.S.b6s0g0.00000_1872_0 absent

It took more than 12 hours to complete (with an error - what a waste of GPU time) while cuda 32 version usually takes 1h40m to complete.

Comment viewing options

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