Inconclusive Work Units Running AP Ver 6


log in

Advanced search

Message boards : Number crunching : Inconclusive Work Units Running AP Ver 6

Previous · 1 . . . 5 · 6 · 7 · 8 · 9 · 10 · Next
Author Message
Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 24860
Credit: 34,402,553
RAC: 13,924
Germany
Message 1231737 - Posted: 13 May 2012, 21:05:19 UTC
Last modified: 13 May 2012, 21:05:31 UTC

Thats in case of the nvidia bug.
1305 has a fix.

ATI´s dont have this issue.
____________

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4205
Credit: 34,456,912
RAC: 21,520
United Kingdom
Message 1231740 - Posted: 13 May 2012, 21:10:41 UTC - in response to Message 1231727.
Last modified: 13 May 2012, 21:14:07 UTC

Don't know whats wrong with this:
2428927751

This rig has been crunching for awhile now without issues before this.

Try using the r1305 app (aka 6.03) and AstroPulse_Kernels_r1305.cl from Seti Beta, that has the fix.

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb

http://boinc2.ssl.berkeley.edu/beta/download/AstroPulse_Kernels_r1305.cl

Claggy



What? Is it OK to just start using a Beta app here on main, before it has been released officially?

Why then the extensive Beta testing in the first place?

It has been Alpha tested, and in is the process of being Beta tested at Seti Beta (on mass by hundreds of computers),
Normally the GPU Astropulse apps get tested by a couple of Alpha testers, then maybe a few Beta testers before release, so far more testers have tested it than normal,
What is worse, users running Released/Beta apps that do overflow when they shouldn't, causing resends, or running a fixed version that shouldn't?

Claggy

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4205
Credit: 34,456,912
RAC: 21,520
United Kingdom
Message 1231741 - Posted: 13 May 2012, 21:12:13 UTC - in response to Message 1231737.
Last modified: 13 May 2012, 21:12:28 UTC

Thats in case of the nvidia bug.
1305 has a fix.

ATI´s dont have this issue.

ATI version does have the issue, I've had it, and seen other hosts that have it too, there's just less ATI hosts round here,

Claggy

Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 24860
Credit: 34,402,553
RAC: 13,924
Germany
Message 1231743 - Posted: 13 May 2012, 21:16:24 UTC - in response to Message 1231741.

Thats in case of the nvidia bug.
1305 has a fix.

ATI´s dont have this issue.

ATI version does have the issue, I've had it, and seen other hosts that have it too, there's just less ATI hosts round here,

Claggy


We should discuss this at Lunatics.

____________

Sten-Arne
Volunteer tester
Send message
Joined: 1 Nov 08
Posts: 3672
Credit: 21,179,505
RAC: 9,207
Sweden
Message 1231745 - Posted: 13 May 2012, 21:21:14 UTC - in response to Message 1231740.
Last modified: 13 May 2012, 21:25:17 UTC

Don't know whats wrong with this:
2428927751

This rig has been crunching for awhile now without issues before this.

Try using the r1305 app (aka 6.03) and AstroPulse_Kernels_r1305.cl from Seti Beta, that has the fix.

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb

http://boinc2.ssl.berkeley.edu/beta/download/AstroPulse_Kernels_r1305.cl

Claggy



What? Is it OK to just start using a Beta app here on main, before it has been released officially?

Why then the extensive Beta testing in the first place?

It has been Alpha tested, and in is the process of being Beta tested at Seti Beta (on mass by hundreds of computers),
Normally the GPU Astropulse apps get tested by a couple of Alpha testers, then maybe a few Beta testers before release, so far more testers have tested it than normal,
What is worse, users running Released/Beta apps that do overflow when they shouldn't, causing resends, or running a fixed version that shouldn't?

Claggy


Oh I apologize. I thought it was SETI staff and in this case Eric that decided when it was time to release Beta apps on main. I was obviously wrong, it is you who decide that, and not SETI staff/Mr Korpela.

I just wished he could announce that he stepped down from that position.

(Geeze, have I talked on Beta before on the issue of anarchy?)
____________

Profile MikeProject donor
Volunteer tester
Avatar
Send message
Joined: 17 Feb 01
Posts: 24860
Credit: 34,402,553
RAC: 13,924
Germany
Message 1231752 - Posted: 13 May 2012, 21:26:03 UTC
Last modified: 13 May 2012, 21:27:33 UTC

Yes, you are Sten.
Its a Lunatics app and we are responsible.
We want to get it fixed, same like Eric.

So more Info we get the better.
____________

Sten-Arne
Volunteer tester
Send message
Joined: 1 Nov 08
Posts: 3672
Credit: 21,179,505
RAC: 9,207
Sweden
Message 1231756 - Posted: 13 May 2012, 21:31:42 UTC - in response to Message 1231752.
Last modified: 13 May 2012, 21:45:41 UTC

Yes, you are Sten.
Its a Lunatics app and we are responsible.
We want to get it fixed, same like Eric.

So more Info we get the better.


So the project and Eric does not decide what app to release on main? Is that what the F you are saying? It is anarchy with other words, and everybody is free to grab any F'ing Beta app and move it over to main?

If that's the case, to he** with the Science (and scientific control which is the most important thing, in order to be able to release any results to the scientific community), and let's rock with apps from here to kingdom comes, and chase credits and toasters and everything that moves.

I believe I have lots of older apps I can use by just adjusting the app_info to make it look as if what I run is V6, or whatever comes down the pipes. They will all error out of course, but what does that matter, when it's rock and roll days and nights, when we can run whatever app we want.

Fun times ahead, thanks for clearing things up.

Edit: Oh, I have an idea, to get rid of inconclusives altogether. I can rewrite the app, so that it first crunch the WU, and then looks if the wingman have returned his task, and if he has it checks the already sent back result from the wingman, and then send back its own result agreeing with the one already returned. If the wingman haven't returned the task yet, it waits for a day and then makes the same try again.

Wouldn't that be a neat solution? Can I implement that one here on main too, if I Alpha and Beta test it first myself?
____________

Profile BilBg
Volunteer tester
Avatar
Send message
Joined: 27 May 07
Posts: 2879
Credit: 6,448,147
RAC: 3,032
Bulgaria
Message 1231765 - Posted: 13 May 2012, 22:30:52 UTC - in response to Message 1231756.


I don't think you can access the result files "sent back from the wingman"
(you probably can check the stderr but this is useless for validation)

And really - if they have known bug in their previous app and already have (supposedly) fixed and "sufficiently" tested new app
it will be better for someone that notices errors on his tasks with the old app to:
A) change to the new app; or
B) stop using the old (any) app until the new app is double or triple "sufficiently" tested


____________



- ALF - "Find out what you don't do well ..... then don't do it!" :)

Wembley
Volunteer tester
Avatar
Send message
Joined: 16 Sep 09
Posts: 415
Credit: 888,257
RAC: 0
United States
Message 1232275 - Posted: 15 May 2012, 1:05:35 UTC - in response to Message 1231713.

Don't know whats wrong with this:
2428927751

This rig has been crunching for awhile now without issues before this.

Try using the r1305 app (aka 6.03) and AstroPulse_Kernels_r1305.cl from Seti Beta, that has the fix.

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb

http://boinc2.ssl.berkeley.edu/beta/download/AstroPulse_Kernels_r1305.cl

Claggy


I tried to get the new AP app from beta and all I get is this:
2012-05-14 08:04:20 PM | SETI@home Beta Test | Started download of astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe 2012-05-14 08:04:28 PM | SETI@home Beta Test | Finished download of astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe 2012-05-14 08:04:28 PM | SETI@home Beta Test | Started download of libfftw3f-3.dll 2012-05-14 08:04:28 PM | SETI@home Beta Test | [error] Unable to verify astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe using certificates 2012-05-14 08:04:28 PM | SETI@home Beta Test | [error] Checksum or signature error for astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe 2012-05-14 08:04:38 PM | SETI@home Beta Test | [sched_op] Deferring communication for 1 min 8 sec 2012-05-14 08:04:38 PM | SETI@home Beta Test | [sched_op] Reason: Unrecoverable error for task ap_20au10ae_B0_P1_00280_20120514_13983.wu_0 (app_version download error: couldn't get input files:<file_xfer_error> <file_name>astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe</file_name> <error_code>-123</error_code></file_xfer_error>) 2012-05-14 08:04:43 PM | SETI@home Beta Test | Finished download of libfftw3f-3.dll 2012-05-14 08:04:43 PM | SETI@home Beta Test | Started download of ap_cmdline_6.03_windows_intelx86__opencl_nvidia.txt 2012-05-14 08:04:43 PM | SETI@home Beta Test | [error] Unable to verify libfftw3f-3.dll using certificates 2012-05-14 08:04:43 PM | SETI@home Beta Test | [error] Checksum or signature error for libfftw3f-3.dll 2012-05-14 08:04:44 PM | SETI@home Beta Test | Finished download of ap_cmdline_6.03_windows_intelx86__opencl_nvidia.txt 2012-05-14 08:04:44 PM | SETI@home Beta Test | Started download of astropulse_6.03_opencl_nvidia_AUTHORS 2012-05-14 08:04:44 PM | SETI@home Beta Test | [error] Unable to verify ap_cmdline_6.03_windows_intelx86__opencl_nvidia.txt using certificates 2012-05-14 08:04:44 PM | SETI@home Beta Test | [error] Checksum or signature error for ap_cmdline_6.03_windows_intelx86__opencl_nvidia.txt 2012-05-14 08:04:45 PM | SETI@home Beta Test | Finished download of astropulse_6.03_opencl_nvidia_AUTHORS 2012-05-14 08:04:45 PM | SETI@home Beta Test | Started download of astropulse_6.03_opencl_nvidia_COPYING 2012-05-14 08:04:45 PM | SETI@home Beta Test | [error] Unable to verify astropulse_6.03_opencl_nvidia_AUTHORS using certificates 2012-05-14 08:04:45 PM | SETI@home Beta Test | [error] Checksum or signature error for astropulse_6.03_opencl_nvidia_AUTHORS 2012-05-14 08:04:46 PM | SETI@home Beta Test | Finished download of astropulse_6.03_opencl_nvidia_COPYING 2012-05-14 08:04:46 PM | SETI@home Beta Test | Started download of astropulse_6.03_opencl_nvidia_COPYRIGHT 2012-05-14 08:04:46 PM | SETI@home Beta Test | [error] Unable to verify astropulse_6.03_opencl_nvidia_COPYING using certificates 2012-05-14 08:04:46 PM | SETI@home Beta Test | [error] Checksum or signature error for astropulse_6.03_opencl_nvidia_COPYING 2012-05-14 08:04:47 PM | SETI@home Beta Test | Finished download of astropulse_6.03_opencl_nvidia_COPYRIGHT 2012-05-14 08:04:47 PM | SETI@home Beta Test | Started download of astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb 2012-05-14 08:04:47 PM | SETI@home Beta Test | [error] Unable to verify astropulse_6.03_opencl_nvidia_COPYRIGHT using certificates 2012-05-14 08:04:47 PM | SETI@home Beta Test | [error] Checksum or signature error for astropulse_6.03_opencl_nvidia_COPYRIGHT 2012-05-14 08:05:23 PM | SETI@home Beta Test | Finished download of astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb 2012-05-14 08:05:23 PM | SETI@home Beta Test | Started download of AstroPulse_Kernels_r1305.cl 2012-05-14 08:05:23 PM | SETI@home Beta Test | [error] Unable to verify astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb using certificates 2012-05-14 08:05:23 PM | SETI@home Beta Test | [error] Checksum or signature error for astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb 2012-05-14 08:05:25 PM | SETI@home Beta Test | Finished download of AstroPulse_Kernels_r1305.cl 2012-05-14 08:05:25 PM | SETI@home Beta Test | Started download of ap_20au10ae_B0_P1_00280_20120514_13983.wu 2012-05-14 08:05:25 PM | SETI@home Beta Test | [error] Unable to verify AstroPulse_Kernels_r1305.cl using certificates 2012-05-14 08:05:25 PM | SETI@home Beta Test | [error] Checksum or signature error for AstroPulse_Kernels_r1305.cl

____________


Donate with your searches and online buys:
http://www.goodsearch.com/toolbar/university-of-california-setihome

JohnDKProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 00
Posts: 873
Credit: 48,310,172
RAC: 36,932
Denmark
Message 1232452 - Posted: 15 May 2012, 12:39:13 UTC - in response to Message 1231713.

Try using the r1305 app (aka 6.03) and AstroPulse_Kernels_r1305.cl from Seti Beta, that has the fix.

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.exe

http://boinc2.ssl.berkeley.edu/beta/download/astropulse_6.03_windows_intelx86__opencl_nvidia_100.pdb

http://boinc2.ssl.berkeley.edu/beta/download/AstroPulse_Kernels_r1305.cl

Claggy

I'm getting some errors using this app, WU completes but there's warnings. I've been running r560 without problems.

<core_client_version>6.10.60</core_client_version>
<![CDATA[
<stderr_txt>
Number of app instances per device set to:2
DATA_CHUNK_UNROLL at default:2
FFA thread block override value:6144
FFA thread fetchblock override value:1536
DATA_CHUNK_UNROLL set to:12
Running on device number: 0
DATA_CHUNK_UNROLL at default:12
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
GPU type not found in init_data.xml
OpenCL platform detected: NVIDIA Corporation
WARNING: BOINC supplied wrong platform!
BOINC assigns device 0
WARNING: BOINC failed to provide OpenCL device, using own enumeration abilities
Used GPU device parameters are:
Number of compute units: 4
Single buffer allocation size: 256MB
max WG size: 1024

Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE2 x86
CPUID: Intel(R) Core(TM) i7-2670QM CPU @ 2.20GHz

Cache: L1=64K L2=256K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3
AstroPulse v.6
Non-graphics FFTW USE_CONVERSION_OPT
Windows x86 rev 1305, V6 match, by Raistmer with support of Lunatics.kwsn.net team. SSE2

OpenCL version by Raistmer

ffa threshold mods by Joe Segur
SSE3 dechirping by JDWhale
Combined dechirp kernel by Frizz
Built with uncommitted modificaions
Number of OpenCL platforms: 1


OpenCL Platform Name: NVIDIA CUDA
Number of devices: 1
Max compute units: 4
Max work group size: 1024
Max clock frequency: 1550Mhz
Max memory allocation: 795459584
Cache type: Read/Write
Cache line size: 128
Cache size: 65536
Global memory size: 3181838336
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 49152
Queue properties:
Out-of-Order: Yes
Name: GeForce GTX 560M
Vendor: NVIDIA Corporation
Driver version: 268.37
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64


state.fold_buf_size_short=65536; state.fold_buf_size_long=262144
INFO: can't open binary kernel file: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\AstroPulse_Kernels_r1305.cl_GeForceGTX560M.bin_V6, continue with recompile...
Info : Building Program (source, clBuildProgram):main kernels: OK code 0

: Considering profile 'compute_20' for gpu='sm_21' in 'cuModuleLoadDataEx_4'
: Retrieving binary for 'cuModuleLoadDataEx_4', for gpu='sm_21', usage mode=' '
: Considering profile 'compute_20' for gpu='sm_21' in 'cuModuleLoadDataEx_4'
: Control flags for 'cuModuleLoadDataEx_4' disable search path
: Ptx binary found for 'cuModuleLoadDataEx_4', architecture='compute_20'
: Ptx compilation for 'cuModuleLoadDataEx_4', for gpu='sm_21', ocg options=' '
INFO: binary kernel file created
WARNING: can't open binary kernel file for oclFFT plan: C:\ProgramData\BOINC/projects/setiathome.berkeley.edu\oclFFTplan_GeForceGTX560M_32768_r1305.bin, continue with recompile...

single pulses: 2
repetitive pulses: 0
percent blanked: 73.67
class T_remove_radar: total=2.25e+009, N=1, <>=2.25e+009, min=2.25e+009, max=2.25e+009
class T_main_loop_L1: total=3.78e+013, N=111, <>=3.41e+011, min=3.17e+011, max=4.02e+011
class T_FFT_forward: total=8.53e+011, N=151848, <>=5.62e+006, min=2.47e+004, max=2.86e+009
class T_remove_radar_randomize: total=1.61e+013, N=1817736, <>=8.86e+006, min=3.44e+002, max=1.11e+010
class T_build_chirp_table: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite: total=8.46e+011, N=116328, <>=7.27e+006, min=1.58e+006, max=2.86e+009
class T_DataWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=6.25e+006, N=151848, <>=4.10e+001, min=2.40e+001, max=2.01e+005
class T_ChirpWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_dechirp: total=7.56e+009, N=151848, <>=4.98e+004, min=4.24e+004, max=1.74e+007
class Dechirp_ns: total=0, N=0, <>=0, min=0 max=0
class Half_ns: total=0, N=0, <>=0, min=0 max=0
class T_PC_single_pulse_kernel_FFA_update: total=9.48e+012, N=151848, <>=6.24e+007, min=3.03e+007, max=1.88e+009
class PC_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=6.25e+006, N=151848, <>=4.10e+001, min=2.40e+001, max=2.01e+005
class T_oclWriteBuf: total=8.46e+011, N=116328, <>=7.27e+006, min=1.58e+006, max=2.86e+009
class T_FFT_inverse: total=3.63e+009, N=151848, <>=2.39e+004, min=1.88e+004, max=1.65e+007
class T_ffa: total=1.09e+013, N=1998, <>=5.45e+009, min=2.03e+009, max=3.19e+010
class T_GPU_buffer_read_backs: total=2, N=2, <>=1, min=1 max=1
USE_OPENCL OPENCL_WRITE USE_INCREASED_PRECISION SMALL_CHIRP_TABLE COMBINED_DECHIRP_KERNEL
rev 1305
19:45:05 (5260): called boinc_finish


http://setiathome.berkeley.edu/result.php?resultid=2441995069

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4205
Credit: 34,456,912
RAC: 21,520
United Kingdom
Message 1232454 - Posted: 15 May 2012, 12:48:14 UTC - in response to Message 1232452.
Last modified: 15 May 2012, 12:54:08 UTC

Those aren't problems, they all should be Info Only Messages, Basically Raistmer has used his own device detection,
and when the app first runs it needs to compile AstroPulse_Kernels_r1305.cl_GeForceGTX560M.bin_V6 and oclFFTplan_GeForceGTX560M_32768_r1305.bin, once they are compiled they won't need to be compiled again,
If you run the latest ATI MBv7 app there are quite a few more oclFFTplans compiled.

Claggy

JohnDKProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 00
Posts: 873
Credit: 48,310,172
RAC: 36,932
Denmark
Message 1232456 - Posted: 15 May 2012, 12:54:08 UTC - in response to Message 1232454.

Those aren't problems, they all should be Info Only Messages, Basically Raistmer has used his own device detection,
and when the app first runs it needs to compile AstroPulse_Kernels_r1305.cl_GeForceGTX560M.bin_V6 and oclFFTplan_GeForceGTX560M_32768_r1305.bin, once they are compiled they won't need to be compiled again,

Claggy

OK, but what about this warning: BOINC failed to provide OpenCL device, using own enumeration abilities

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8755
Credit: 52,704,587
RAC: 29,998
United Kingdom
Message 1232459 - Posted: 15 May 2012, 12:57:41 UTC - in response to Message 1232456.

Those aren't problems, they all should be Info Only Messages, Basically Raistmer has used his own device detection,
and when the app first runs it needs to compile AstroPulse_Kernels_r1305.cl_GeForceGTX560M.bin_V6 and oclFFTplan_GeForceGTX560M_32768_r1305.bin, once they are compiled they won't need to be compiled again,

Claggy

OK, but what about this warning: BOINC failed to provide OpenCL device, using own enumeration abilities

That's because you're using the outdated BOINC v6.10.60, which doesn't have built-in OpenCL device detection. You need to upgrade to BOINC v7 before BOINC can provide an OpenCL device number.

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4205
Credit: 34,456,912
RAC: 21,520
United Kingdom
Message 1232461 - Posted: 15 May 2012, 13:03:20 UTC - in response to Message 1232456.

Those aren't problems, they all should be Info Only Messages, Basically Raistmer has used his own device detection,
and when the app first runs it needs to compile AstroPulse_Kernels_r1305.cl_GeForceGTX560M.bin_V6 and oclFFTplan_GeForceGTX560M_32768_r1305.bin, once they are compiled they won't need to be compiled again,

Claggy

OK, but what about this warning: BOINC failed to provide OpenCL device, using own enumeration abilities

You're running Boinc 6.10.60, and this is an OpenCL app, Boinc 6.10.60 has told the app to use a Cuda device when it's expecting to use a OpenCL device,

This is what Boinc 7.0.27 on my 9800GTX+ reports:

<core_client_version>7.0.27</core_client_version>
<![CDATA[
<stderr_txt>
Running on device number: 0
DATA_CHUNK_UNROLL at default:2
DATA_CHUNK_UNROLL at default:2
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
BOINC assigns device 0
Info: BOINC provided device ID used
Used GPU device parameters are:
Number of compute units: 16
Single buffer allocation size: 128MB
max WG size: 512

Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE2 x86
CPUID: Intel(R) Core(TM)2 Duo CPU E8500 @ 3.16GHz

Cache: L1=64K L2=6144K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3
AstroPulse v.6
Non-graphics FFTW USE_CONVERSION_OPT
Windows x86 rev 1305, V6 match, by Raistmer with support of Lunatics.kwsn.net team. SSE2

OpenCL version by Raistmer

ffa threshold mods by Joe Segur
SSE3 dechirping by JDWhale
Combined dechirp kernel by Frizz
Built with uncommitted modificaions
Number of OpenCL platforms: 1


OpenCL Platform Name: NVIDIA CUDA
Number of devices: 1
Max compute units: 16
Max work group size: 512
Max clock frequency: 1900Mhz
Max memory allocation: 134217728
Cache type: None
Cache line size: 0
Cache size: 0
Global memory size: 536870912
Constant buffer size: 65536
Max number of constant args: 9
Local memory type: Scratchpad
Local memory size: 16384
Queue properties:
Out-of-Order: Yes
Name: GeForce 9800 GTX/9800 GTX+
Vendor: NVIDIA Corporation
Driver version: 301.24
Version: OpenCL 1.0 CUDA
Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics


state.fold_buf_size_short=65536; state.fold_buf_size_long=262144
Info : Building Program (binary, clBuildProgram):main kernels: OK code 0


Running on device number: 0
DATA_CHUNK_UNROLL at default:2
DATA_CHUNK_UNROLL at default:2
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
BOINC assigns device 0
Info: BOINC provided device ID used
Used GPU device parameters are:
Number of compute units: 16
Single buffer allocation size: 128MB
max WG size: 512

Build features: Non-graphics OpenCL USE_OPENCL_NV COMBINED_DECHIRP_KERNEL FFTW USE_INCREASED_PRECISION USE_SSE2 x86
CPUID: Intel(R) Core(TM)2 Duo CPU E8500 @ 3.16GHz

Cache: L1=64K L2=6144K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3
### Restart at 88.29 percent.
state.fold_buf_size_short=65536; state.fold_buf_size_long=262144
Info : Building Program (binary, clBuildProgram):main kernels: OK code 0



single pulses: 0
repetitive pulses: 0
percent blanked: 76.94
class T_remove_radar: total=1.98e+009, N=1, <>=1.98e+009, min=1.98e+009, max=1.98e+009
class T_main_loop_L1: total=7.82e+012, N=12, <>=6.52e+011, min=6.48e+011, max=6.76e+011
class T_FFT_forward: total=8.05e+010, N=98304, <>=8.19e+005, min=7.22e+004, max=3.35e+009
class T_remove_radar_randomize: total=1.37e+012, N=196512, <>=6.96e+006, min=6.84e+002, max=3.83e+008
class T_build_chirp_table: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_DataWrite: total=7.19e+010, N=75936, <>=9.47e+005, min=7.43e+005, max=3.35e+009
class T_DataWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=3.80e+006, N=98304, <>=3.80e+001, min=2.80e+001, max=1.46e+005
class T_ChirpWrite: total=0.00e+000, N=0, <>=0.00e+000, min=1.84e+019, max=0.00e+000
class T_ChirpWrite_ns: total=0, N=0, <>=0, min=0 max=0
class T_dechirp: total=1.24e+010, N=98304, <>=1.26e+005, min=1.18e+005, max=4.94e+007
class Dechirp_ns: total=0, N=0, <>=0, min=0 max=0
class Half_ns: total=0, N=0, <>=0, min=0 max=0
class T_PC_single_pulse_kernel_FFA_update: total=1.40e+012, N=98304, <>=1.43e+007, min=1.29e+007, max=8.95e+007
class PC_ns: total=0, N=0, <>=0, min=0 max=0
class T_oclReadBuf: total=3.80e+006, N=98304, <>=3.80e+001, min=2.80e+001, max=1.46e+005
class T_oclWriteBuf: total=7.19e+010, N=75936, <>=9.47e+005, min=7.43e+005, max=3.35e+009
class T_FFT_inverse: total=7.23e+009, N=98304, <>=7.35e+004, min=6.94e+004, max=4.93e+007
class T_ffa: total=4.90e+012, N=216, <>=2.27e+010, min=8.85e+009, max=1.34e+011
class T_GPU_buffer_read_backs: total=0, N=0, <>=0, min=0 max=0
USE_OPENCL OPENCL_WRITE USE_INCREASED_PRECISION SMALL_CHIRP_TABLE COMBINED_DECHIRP_KERNEL
rev 1305
13:15:59 (4416): called boinc_finish

</stderr_txt>
]]>


http://setiweb.ssl.berkeley.edu/beta/result.php?resultid=10820754

Claggy

JohnDKProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 00
Posts: 873
Credit: 48,310,172
RAC: 36,932
Denmark
Message 1232467 - Posted: 15 May 2012, 13:30:15 UTC

OK, just strange I didn't get the warning with r560 which I assume is also an OpenCL app.

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8755
Credit: 52,704,587
RAC: 29,998
United Kingdom
Message 1232486 - Posted: 15 May 2012, 14:10:33 UTC - in response to Message 1232467.

OK, just strange I didn't get the warning with r560 which I assume is also an OpenCL app.

It's a chicken and egg situation. Until there was a version of BOINC which supplies OpenCL device numbers, Raistmer ccouldn't write an application which used the device numbers which BOINC wasn't supplying yet. And if there was no way of getting the right numbers, there wasn't really much point in bellyaching about getting the wrong numbers.

Now that there's a way of getting it right (upgrade to BOINC v7.0.27), it's become worth pointing out that it's being done wrong - while at the same time falling back on the workround which allowed it to work before.

Profile perryjay
Volunteer tester
Avatar
Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 16,209,067
RAC: 7,840
United States
Message 1232679 - Posted: 16 May 2012, 0:03:27 UTC - in response to Message 1232486.

Another inconclusive from today... http://setiathome.berkeley.edu/workunit.php?wuid=990731598
____________


PROUD MEMBER OF Team Starfire World BOINC

Profile perryjay
Volunteer tester
Avatar
Send message
Joined: 20 Aug 02
Posts: 3377
Credit: 16,209,067
RAC: 7,840
United States
Message 1232944 - Posted: 18 May 2012, 19:22:56 UTC - in response to Message 1232679.

Okay, my last inconclusive came in today. All three of us validated. http://setiathome.berkeley.edu/workunit.php?wuid=990731598
____________


PROUD MEMBER OF Team Starfire World BOINC

WinterKnight
Volunteer tester
Send message
Joined: 18 May 99
Posts: 8737
Credit: 25,592,010
RAC: 13,895
United Kingdom
Message 1233426 - Posted: 19 May 2012, 14:10:17 UTC

Just got one, my computer reported minutes ago.

http://setiathome.berkeley.edu/workunit.php?wuid=975800759

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8755
Credit: 52,704,587
RAC: 29,998
United Kingdom
Message 1233438 - Posted: 19 May 2012, 14:32:26 UTC - in response to Message 1233426.

Just got one, my computer reported minutes ago.

http://setiathome.berkeley.edu/workunit.php?wuid=975800759

So yours is the one with Jason's r557, against stock? Need to keep an eye on the final outcome of that one.

Previous · 1 . . . 5 · 6 · 7 · 8 · 9 · 10 · Next

Message boards : Number crunching : Inconclusive Work Units Running AP Ver 6

Copyright © 2014 University of California