Gamma-ray pulsar search #3 v1.11 (FGRPopencl-ati) failing on Linux?

Gordon Lack
Gordon Lack
Joined: 19 Jun 13
Posts: 6
Credit: 1120909
RAC: 1631
Topic 197587

Every time I get sent one of these (FGRPopencl-ati) it quickly fails - looks like this is because it's trying to allocate 256MB when the maximum possible is 128MB.
Is this fixable, or should I just disable this executable as an option?

Quote:

7.2.42

process exited with code 65 (0x41, -191)

13:21:47 (6248): [normal]: This Einstein@home App was built at: Feb 18 2014 15:42:42

13:21:47 (6248): [normal]: Start of BOINC application '../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-ati'.
command line: ../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-ati --inputfile ../../projects/einstein.phys.uwm.edu/LATeah0092C.dat --outputfile results.cand.out --alpha 1.85606135223 --delta -0.187105282293 --pcutfu 0.06251659 --skyRadius 1.402826e-02 --f0start 0.0 --f0Band 32 --firstSkyPoint 13464 --numSkyPoints 99 --f1dot -9.12e-10 --f1dotBand 1e-12 --df1dot 8.207629151e-15 --ephemdir ../../projects/einstein.phys.uwm.edu/JPLEPH --Tcoh 524288.0 --toplist 5 --cohFollow 1 --numCells 1 --useWeights 1 --Srefinement 1 --CohSkyRef 1 --cohfullskybox 1 --interbinning 2 --useDiriWin 10 --mmfu 0.15 --reftime 55471 --debug 1 --device 0
output files: 'results.cand.out' '../../projects/einstein.phys.uwm.edu/LATeah0092C_32.0_13464_-9.11e-10_1_0' 'results.cand.out.cohfu' '../../projects/einstein.phys.uwm.edu/LATeah0092C_32.0_13464_-9.11e-10_1_1'
13:21:47 (6248): [debug]: Flags: X64 SSE SSE2 GNUC X86 GNUX86
13:21:47 (6248): [debug]: glibc version/release: 2.17/stable
13:21:47 (6248): [debug]: Set up communication with graphics process.
boinc_get_opencl_ids returned [0x28f7500 , 0x7fd4b897cfc0]
Using OpenCL platform provided by: Advanced Micro Devices, Inc.
Using OpenCL device "Turks" by: Advanced Micro Devices, Inc.
Max allocation limit: 134217728
% Opening inputfile: ../../projects/einstein.phys.uwm.edu/LATeah0092C.dat
% Total amount of photon times: 10000
% Preparing toplist of length: 5
read_checkpoint(): Couldn't open file 'results.cand.out.cpt': No such file or directory (2)
% fft_size: 33554432 (0x2000000)
% Sky point 1/99
% Creating FFT plan.
Error allocating device memory: 268435456 bytes (error: -61)
13:21:47 (6248): [CRITICAL]: ERROR: MAIN() returned with error '1'
FPU status flags:
mv: cannot stat âresults.cand.outâ: No such file or directory
mv: cannot stat âresults.cand.outâ: No such file or directory
mv: cannot stat âresults.cand.outâ: No such file or directory
mv: cannot stat âresults.cand.outâ: No such file or directory
mv: cannot stat âresults.cand.outâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
mv: cannot stat âresults.cand.out.cohfuâ: No such file or directory
13:21:59 (6248): [normal]: done. calling boinc_finish(65).
13:21:59 (6248): called boinc_finish

]]>

Technojunkie
Technojunkie
Joined: 14 Nov 12
Posts: 3
Credit: 8397831
RAC: 0

Gamma-ray pulsar search #3 v1.11 (FGRPopencl-ati) failing on Lin

Perhaps along the same line here but also having problems with memory allocation failures but with Nvidia card.
History shows about 18 tasks that have failed of LATeah0092C_..... projects and 1 success past month all with same error message

PB0013_.... and PB0012_.... seems to be ticking along nicely.

Stderr output

7.0.27

process exited with code 69 (0x45, -187)

../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-nvidia: /usr/lib/nvidia-331/libOpenCL.so.1: no version information available (required by ../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-nvidia)
11:01:44 (8743): [normal]: This Einstein@home App was built at: Feb 18 2014 15:42:42

11:01:44 (8743): [normal]: Start of BOINC application '../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-nvidia'.
command line: ../../projects/einstein.phys.uwm.edu/hsgamma_FGRP3_1.11_x86_64-pc-linux-gnu__FGRPopencl-nvidia --inputfile ../../projects/einstein.phys.uwm.edu/LATeah0092C.dat --outputfile results.cand.out --alpha 1.85606135223 --delta -0.187105282293 --pcutfu 0.06251659 --skyRadius 1.402826e-02 --f0start 32 --f0Band 64 --firstSkyPoint 20295 --numSkyPoints 99 --f1dot -9.9e-11 --f1dotBand 1e-12 --df1dot 8.207629151e-15 --ephemdir ../../projects/einstein.phys.uwm.edu/JPLEPH --Tcoh 524288.0 --toplist 5 --cohFollow 1 --numCells 1 --useWeights 1 --Srefinement 1 --CohSkyRef 1 --cohfullskybox 1 --interbinning 2 --useDiriWin 10 --mmfu 0.15 --reftime 55471 --debug 1 --device 0
output files: 'results.cand.out' '../../projects/einstein.phys.uwm.edu/LATeah0092C_96.0_20295_-9.8e-11_1_0' 'results.cand.out.cohfu' '../../projects/einstein.phys.uwm.edu/LATeah0092C_96.0_20295_-9.8e-11_1_1'
11:01:44 (8743): [debug]: Flags: X64 SSE SSE2 GNUC X86 GNUX86
11:01:44 (8743): [debug]: glibc version/release: 2.15/stable
11:01:44 (8743): [debug]: Set up communication with graphics process.
boinc_get_opencl_ids returned [0x1d9c770 , 0x1d9c6d0]
Using OpenCL platform provided by: NVIDIA Corporation
Using OpenCL device "GeForce GTX 460" by: NVIDIA Corporation
Max allocation limit: 268222464
% Opening inputfile: ../../projects/einstein.phys.uwm.edu/LATeah0092C.dat
% Total amount of photon times: 10000
% Preparing toplist of length: 5
read_checkpoint(): Couldn't open file 'results.cand.out.cpt': No such file or directory (2)
% fft_size: 33554432 (0x2000000)
% Sky point 1/99
% Creating FFT plan.
Result of plan generation ( 0)
% Starting semicoherent search over f0 and f1.
% nf1dots: 123 df1dot: 8.207629151e-15 f1dot_start: -9.9e-11 f1dot_band: 1e-12
Error during OpenCL FFT (error: -4)
11:01:45 (8743): [CRITICAL]: ERROR: MAIN() returned with error '5'
FPU status flags: PRECISION
Error in OpenCL context: CL_MEM_OBJECT_ALLOCATION_FAILURE error executing CL_COMMAND_NDRANGE_KERNEL on GeForce GTX 460 (Device 0).

mv: cannot stat `results.cand.out': No such file or directory
mv: cannot stat `results.cand.out': No such file or directory
mv: cannot stat `results.cand.out': No such file or directory
mv: cannot stat `results.cand.out': No such file or directory
mv: cannot stat `results.cand.out': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
mv: cannot stat `results.cand.out.cohfu': No such file or directory
11:01:56 (8743): [normal]: done. calling boinc_finish(69).
11:01:56 (8743): called boinc_finish

]]>

Claggy
Claggy
Joined: 29 Dec 06
Posts: 560
Credit: 2694028
RAC: 0

RE: Perhaps along the same

Quote:

Perhaps along the same line here but also having problems with memory allocation failures but with Nvidia card.
History shows about 18 tasks that have failed of LATeah0092C_..... projects and 1 success past month all with same error message

PB0013_.... and PB0012_.... seems to be ticking along nicely.


What distro are you on? Is there any chance of you upgrading Boinc to 7.0.65, Boinc 7.0.27 has a Wacky Nvidia GPU memory reporting Bug, where eithier the available GPU memory or the Total GPU memory, or both, is reported wrong,
hence your GTX460 is reported as having 134214655MB total, and not 1024MB,

Claggy

Technojunkie
Technojunkie
Joined: 14 Nov 12
Posts: 3
Credit: 8397831
RAC: 0

Currently on: Ubuntu

Currently on:

Ubuntu 12.04LTS
Linux 3.2.0-61-generic

I did not suspect boinc version or distro as possible cause since the binary radio pulse packages were running ok.

Will take a while before I can upgrade since some packages for climateprediction that still have about 155 hrs left to completion. Read that it is better to upgrade when you have no tasks on hand.

Been postponing upgrade since previous attempt not being to successful and ending up reverting to my current version 7.0.27.

Thanks for the suggestion.

Comment viewing options

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