Welcome to MilkyWay@home

Posts by VictordeHollander

1) Questions and Answers : Unix/Linux : "Failed to calculate integral 0 Failed to calculate likelihood" errors (Message 67335)
Posted 15 Apr 2018 by VictordeHollander
Post:
or 4. the Milkyway OpenCL Linux executable
2) Questions and Answers : Unix/Linux : "Failed to calculate integral 0 Failed to calculate likelihood" errors (Message 67334)
Posted 15 Apr 2018 by VictordeHollander
Post:
I installed Windows 10 Pro (1709) on the hardware and it now runs without errors (700+ valid tasks). Previously it would produce the error (above) in about 1 every 20 tasks (so 1 "Failed to calculate likelihood" in about 100 WUs/streams).

Now that I know the hardware is fine, I suspect it is one of these:
1. the AMD graphic cards drivers for Linux (I used the .deb package for Ubuntu 14.04.2)
2. BOINC client (7.9.3 on Ubuntu vs. 7.8.3 on Win10)
3. Priority (Ubuntu runs BOINC and subprocesses at "nice 10", so lower than standard/normal, while Windows at Normal/standard priority (equivalent to nice 0). The lower priority could mean it takes too long before the task gets CPU time and errors out. I can change the nicelevel of the boinc-client to 0 on Ubuntu with superuser commands, but every OpenCL process/WU start with nice 10 again.
3) Questions and Answers : Unix/Linux : "Failed to calculate integral 0 Failed to calculate likelihood" errors (Message 67324)
Posted 11 Apr 2018 by VictordeHollander
Post:
Hi,

Does anybody know what is causing the
"Failed to calculate integral 0
Failed to calculate likelihood"
errors?


Likelihood time = 2.088974 s
<background_integral3> 0.000135044562893 </background_integral3>
<stream_integral3>  73.177979946439066  191.871483289292200  122.601402164019433 </stream_integral3>
<background_likelihood3> -3.327750849128395 </background_likelihood3>
<stream_only_likelihood3>  -3.332280687700035  -4.324665411311142  -8.682139791419360 </stream_only_likelihood3>
<search_likelihood3> -2.929028725467456 </search_likelihood3>
Using SSE3 path
Found 1 platform
Platform 0 information:
  Name:       AMD Accelerated Parallel Processing
  Version:    OpenCL 2.0 AMD-APP (1912.5)
  Vendor:     Advanced Micro Devices, Inc.
  Extensions: cl_khr_icd cl_amd_event_callback cl_amd_offline_devices 
  Profile:    FULL_PROFILE
Using device 0 on platform 0
Found 1 CL device
Device 'Tahiti' (Advanced Micro Devices, Inc.:0x1002) (CL_DEVICE_TYPE_GPU)
Board: AMD Radeon HD 7900 Series 
Driver version:      1912.5 (VM)
Version:             OpenCL 1.2 AMD-APP (1912.5)
Compute capability:  0.0
Max compute units:   28
Clock frequency:     800 Mhz
Global mem size:     2896491072
Local mem size:      32768
Max const buf size:  65536
Double extension:    cl_khr_fp64
Estimated AMD GPU GFLOP/s: 2867 SP GFLOP/s, 717 DP FLOP/s
Using a target frequency of 60.0
Using a block size of 7168 with 78 blocks/chunk
Using clWaitForEvents() for polling (mode -1)
Range:          { nu_steps = 320, mu_steps = 800, r_steps = 700 }
Iteration area: 560000
Chunk estimate: 1
Num chunks:     2
Chunk size:     559104
Added area:     558208
Effective area: 1118208
Initial wait:   20 ms
Integration time: 11.634570 s. Average time per iteration = 36.358030 ms
Integral 0 time = 11.993249 s
Failed to calculate integral 0
Failed to calculate likelihood


For instance in this WU:
http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=2308241462

It calculates a lot of streams successfully (and randomly fails at that point)

The system has 600+ valid tasks and some (32 at the moment) invalid and a few with error status (7).

The ones that failed have different de_modfit_XX and it seems to happen at random?

Is this a hardware or driver or BOINC issue?

OS: Ubuntu 14.04
GPU: AMD HD7950
BOINC: 7.9.3
4) Message boards : News : Scheduled Server Maintenance 3/27 (Message 67287)
Posted 1 Apr 2018 by VictordeHollander
Post:
Are the database errors in the last couple of days related to the maintenance?
Is de server dying?
Or is it just regular cleanup of workunits?
5) Message boards : MilkyWay@home Science : Planck Data - new Hubble constant and cosmic recipe (Message 57603)
Posted 22 Mar 2013 by VictordeHollander
Post:
http://www.esa.int/Our_Activities/Space_Science/Planck/Planck_reveals_an_almost_perfect_Universe

'New' Planck Constant: 67.15 kilometres per second per megaparsec
'New' age of univers: 13.82 billion years

New estimation of the cosmic recipe of the universe:
Before Planck:
Ordinary matter 4,5%
Dark Matter 22,7%
Dark Energy 72,8%

After Planck:
Ordinary matter 4,9% (up 0,4%)
Dark Matter 26,8% (up 4,1%)
Dark Energy 68,3% (down 4,5%)
6) Message boards : Number crunching : ps_separation_82 (Message 50106)
Posted 15 Jul 2011 by VictordeHollander
Post:
Got some ps_separation_82 workunits (mix0, mix1, mix2, mix3, mix4), any news on these (new) WUs? And could somebody explain the differences between these (mix0 etc) and fix/free the other searches use?
7) Message boards : News : started some new searches (Message 49753)
Posted 29 Jun 2011 by VictordeHollander
Post:
the ps_separation_17_3s_fix tasks seem to be working just fine for me...

Windows XP Pro SP3 32-bit
AMD Phenom II X6 1090T
4GB (2x2GB) PC12800 (DDR1600)
AMD/ATI HD 5870 2GB GPU
BOINC v 6.12.33

...i also noticed that i'm getting ~320 credits for them, unlike the typical ~167, ~213, and ~267 credits we're used to earning for validated tasks...not that i'm complaining ;-)...i just thought i'd mention it.

But the 17_3s tasks also take longer to complete then the 10_3s or 13_3s, so the credit/sec seems to be roughly the same.
8) Message boards : Number crunching : No work 4 GPU (Message 49651)
Posted 27 Jun 2011 by VictordeHollander
Post:
Maybe they are reconfiguring the separation_assimilator for the (new) ps_separation tasks?
9) Message boards : Number crunching : ps_separation (Message 49645)
Posted 27 Jun 2011 by VictordeHollander
Post:
Seems like the ps_test WUs are out of the testing fase and now named ps_separation?
Is there anything interesting to report about these new workunits?
10) Message boards : News : Any remaining major credit or application problems? (Message 49610)
Posted 26 Jun 2011 by VictordeHollander
Post:
So will the double credit days start today/night @00:00:01 ?
11) Message boards : News : Any remaining major credit or application problems? (Message 49526)
Posted 24 Jun 2011 by VictordeHollander
Post:
Hi Travis,

What I see is that WU's with a longer runtime, but a shorter CPU time get less credit. I have made a post of it mounths ago, but none of the admins reacted.

So it seems to me that credit is granted for the CPU time and not the run time. Is this correct or am I missing something important. In that case I apologize.

Maybe I can clear this up a bit for you.
For example, a MW@home workunit that runs for 60 min (3600 sec) on a CPU and using 90% of that CPU. The actual amount of time the CPU spent on calculating that workunit is in that case : 3600x0.9=3240 sec.
12) Message boards : Number crunching : GPU Requirements (Message 49522)
Posted 24 Jun 2011 by VictordeHollander
Post:

No wonder that the top 20 computers all use AMD/ATI GPUs.

I was referring to the top 20 computers on Milkyway@home =).
13) Message boards : Number crunching : GPU Requirements (Message 49518)
Posted 23 Jun 2011 by VictordeHollander
Post:
You might want to mention that most of the NVidia GeForce cards are poor for double precision tasks, especially the Fermi cards.

Tesla's:
Tesla C2050 (515 gigaflops of double precision performance) 3GB


The Tesla C2050 costs something like EUR 2.000+ (not sure how much that in US Doller is) and in comparison to the latest ATI/AMD cards has relatively poor DP performance.

For example:
AMD 6950 costs something like EUR 200 and delivers 563 Gflops in DP!

source: http://www.legitreviews.com/article/1488/1/

No wonder that the top 20 computers all use AMD/ATI GPUs.
14) Message boards : News : Any remaining major credit or application problems? (Message 49517)
Posted 23 Jun 2011 by VictordeHollander
Post:
Maybe a silly question, but is the double credit days for CPU only or also GPU?


Both.

Nice!

Only 'issue' is that one CPU core needs to be at idle to let MW@home use 99% of my GPU (6950). See also the tread in number-crunching:
http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=2461
15) Message boards : News : Any remaining major credit or application problems? (Message 49515)
Posted 23 Jun 2011 by VictordeHollander
Post:
Maybe a silly question, but is the double credit days for CPU only or also GPU?
16) Message boards : Number crunching : MW@home 0.82 (ati14) performance (Message 49349)
Posted 15 Jun 2011 by VictordeHollander
Post:
I found that if I leave one logical core free on an i7 I get 99% utilization again and nice run times. However, at full cpu load I get ~80+/-5%. The higher values were obtained with frequency 30 and priority "higher than normal", while the lower numbers where at frequency 60.

The higher frequency didn't improve anything - the screen is quite smooth even at 30 Hz.

MrS

Thanks for the quick reactions!

Leaving one logic core free has solved the utilization problem for me. Still it is a pity to leave one core doing nothing. Running times are now also back to normal, maybe even 1-2 sec faster.
17) Message boards : Number crunching : MW@home 0.82 (ati14) performance (Message 49340)
Posted 15 Jun 2011 by VictordeHollander
Post:
I was talking about 0.62 -> 0.82. Two weeks ago i still had 99% utilisation, now with no changes in hardware or software only 70%.
18) Message boards : Number crunching : MW@home 0.82 (ati14) performance (Message 49311)
Posted 14 Jun 2011 by VictordeHollander
Post:
The performance of the new ati separation seems to have gone down from the last build. The ati13 utilised 99% of my AMD 6950, ati14 now only about 70%. This leads to longer running times of the WUs (+30 sec). Can anybody explain these changes?
19) Message boards : Number crunching : GPU Requirements [OLD] (Message 49240)
Posted 13 Jun 2011 by VictordeHollander
Post:
I think the list in the OP needs a little update, since most nvidia Fermi based cards can run MW and also the latest high end amd/ati cards (6950, 6970, 6990)




©2019 Astroinformatics Group