Intel GPU app hosts with failures - please post here


log in

Advanced search

Message boards : Number crunching : Intel GPU app hosts with failures - please post here

1 · 2 · Next
Author Message
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar
Send message
Joined: 16 Jun 01
Posts: 3421
Credit: 46,560,984
RAC: 10,529
Russia
Message 1481009 - Posted: 23 Feb 2014, 19:34:03 UTC

If browsing through own or wingman results you see host with numerous failures from intel GPU apps please post link to such host here.
Thanks.
____________

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4194
Credit: 114,886,228
RAC: 147,837
United States
Message 1481081 - Posted: 23 Feb 2014, 22:48:18 UTC

So far I have had 0 invalid or error on my two.
So far none of the inconclusive I have had have been against Intel GPU. Just against NVIDIA or Radeon GPU tossing out to many spikes. Very low rate for me though. Total of 35 inconclusive in 1200 returned results.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile mr.mac52Project donor
Avatar
Send message
Joined: 18 Mar 03
Posts: 28
Credit: 82,302,144
RAC: 103,619
United States
Message 1482518 - Posted: 27 Feb 2014, 22:18:20 UTC

OK, I'll bite, tell me what I'm doing wrong. I know it is something stupid but I'm not seeing it at this time. Also sorry that I don't recall how to make links active any more.

The host is 5409093, BIGmac, an i7-4770K

http://setiathome.berkeley.edu/show_host_detail.php?hostid=5409093

NVIDIA GeForce GTX 670 (2048MB) driver: 331.65 OpenCL: 1.01, INTEL Intel(R) HD Graphics 4600 (1624MB) OpenCL: 1.02

All my errors show up like this workunit: 1438660832

http://setiathome.berkeley.edu/workunit.php?wuid=1438660832

<core_client_version>7.2.39</core_client_version>
<![CDATA[
<message>
too many boinc_temporary_exit()s
</message>
<stderr_txt>
Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
WARNING: boinc_get_opencl_ids failed with code -1
OpenCL platform detected: NVIDIA Corporation
OpenCL platform detected: Intel(R) Corporation
WARNING: BOINC supplied wrong platform!
ERROR: OpenCL kernel/call 'clGetDeviceIDs' call failed (-1) in file ..\..\..\src\GPU_lock.cpp near line 672.
Waiting 30 sec before restart...
Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
WARNING: boinc_get_opencl_ids failed with code -1
OpenCL platform detected: NVIDIA Corporation
OpenCL platform detected: Intel(R) Corporation
WARNING: BOINC supplied wrong platform!
ERROR: OpenCL kernel/call 'clGetDeviceIDs' call failed (-1) in file ..\..\..\src\GPU_lock.cpp near line 672.
.
.
.

app_info.xml
<app_info>
<app>
<name>setiathome_v7</name>
</app>
<file_info>
<name>setiathome_7.03_windows_intelx86__opencl_intel_gpu_sah.exe</name>
<executable/>
</file_info>
<file_info>
<name>MultiBeam_Kernels_r2061_windows_intel_gpu.cl</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3.dll</name>
<executable/>
</file_info>
<file_info>
<name>mb_cmdline-7.03-opencl_intel_gpu_sah.txt</name>
</file_info>
<app_version>
<app_name>setiathome_v7</app_name>
<version_num>703</version_num>
<platform>windows_intelx86</platform>
<coproc>
<type>intel_gpu</type>
<count>1</count>
</coproc>
<plan_class>opencl_intel_gpu_sah</plan_class>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.04</max_ncpus>
<file_ref>
<file_name>setiathome_7.03_windows_intelx86__opencl_intel_gpu_sah.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>MultiBeam_Kernels_r2061_windows_intel_gpu.cl</file_name>
<open_name>MultiBeam_Kernels_r2061.cl</open_name>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>mb_cmdline-7.03-opencl_intel_gpu_sah.txt</file_name>
<open_name>mb_cmdline.txt</open_name>
</file_ref>
</app_version>
<app>
<name>setiathome_v7</name>
</app>
<file_info>
<name>AKv8c_Bb_r1846_winx86_AVXx.exe</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3.dll</name>
<executable/>
</file_info>
<file_info>
<name>AKv8c_Bb_r1846_winx86_AVXx.txt</name>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.txt</file_name>
<open_name>mb_cmdline.txt</open_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_v7</app_name>
<version_num>700</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.txt</file_name>
<open_name>mb_cmdline.txt</open_name>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>AKv8c_Bb_r1846_winx86_AVXx.exe</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3.dll</name>
<executable/>
</file_info>
<file_info>
<name>AKv8c_Bb_r1846_winx86_AVXx.txt</name>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>603</version_num>
<platform>windows_x86_64</platform>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>AKv8c_Bb_r1846_winx86_AVXx.txt</file_name>
<open_name>mb_cmdline.txt</open_name>
</file_ref>
</app_version>
<app>
<name>astropulse_v6</name>
</app>
<file_info>
<name>AP6_win_x86_SSE2_OpenCL_NV_r1843.exe</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3.dll</name>
<executable/>
</file_info>
<file_info>
<name>ap_cmdline_win_x86_SSE2_OpenCL_NV.txt</name>
</file_info>
<file_info>
<name>AstroPulse_Kernels_r1843.cl</name>
</file_info>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<platform>windows_x86_64</platform>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<plan_class>cuda_opencl_100</plan_class>
<cmdline></cmdline>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1843.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>ap_cmdline_win_x86_SSE2_OpenCL_NV.txt</file_name>
<open_name>ap_cmdline.txt</open_name>
</file_ref>
<file_ref>
<file_name>AstroPulse_Kernels_r1843.cl</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>604</version_num>
<platform>windows_x86_64</platform>
<avg_ncpus>0.04</avg_ncpus>
<max_ncpus>0.2</max_ncpus>
<plan_class>opencl_nvidia_100</plan_class>
<cmdline></cmdline>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>AP6_win_x86_SSE2_OpenCL_NV_r1843.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>ap_cmdline_win_x86_SSE2_OpenCL_NV.txt</file_name>
<open_name>ap_cmdline.txt</open_name>
</file_ref>
<file_ref>
<file_name>AstroPulse_Kernels_r1843.cl</file_name>
</file_ref>
</app_version>
<app>
<name>astropulse_v6</name>
</app>
<file_info>
<name>AP6_win_x86_SSE_CPU_r1797.exe</name>
<executable/>
</file_info>
<file_info>
<name>libfftw3f-3.dll</name>
<executable/>
</file_info>
<file_info>
<name>ap_cmdline_win_x86_SSE_CPU.txt</name>
</file_info>
<app_version>
<app_name>astropulse_v6</app_name>
<version_num>601</version_num>
<platform>windows_x86_64</platform>
<cmdline></cmdline>
<file_ref>
<file_name>AP6_win_x86_SSE_CPU_r1797.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>libfftw3f-3.dll</file_name>
</file_ref>
<file_ref>
<file_name>ap_cmdline_win_x86_SSE_CPU.txt</file_name>
<open_name>ap_cmdline.txt</open_name>
</file_ref>
</app_version>
<app>
<name>setiathome_v7</name>
</app>
<file_info>
<name>Lunatics_x41zc_win32_cuda50.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart32_50_35.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft32_50_35.dll</name>
<executable/>
</file_info>
<file_info>
<name>mbcuda.cfg</name>
</file_info>
<app_version>
<app_name>setiathome_v7</app_name>
<version_num>700</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda50</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x41zc_win32_cuda50.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>mbcuda.cfg</file_name>
</file_ref>
</app_version>
<app>
<name>setiathome_enhanced</name>
</app>
<file_info>
<name>Lunatics_x41zc_win32_cuda50.exe</name>
<executable/>
</file_info>
<file_info>
<name>cudart32_50_35.dll</name>
<executable/>
</file_info>
<file_info>
<name>cufft32_50_35.dll</name>
<executable/>
</file_info>
<file_info>
<name>mbcuda.cfg</name>
</file_info>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>610</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda_fermi</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x41zc_win32_cuda50.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>mbcuda.cfg</file_name>
</file_ref>
</app_version>
<app_version>
<app_name>setiathome_enhanced</app_name>
<version_num>608</version_num>
<platform>windows_x86_64</platform>
<plan_class>cuda</plan_class>
<avg_ncpus>0.040000</avg_ncpus>
<max_ncpus>0.040000</max_ncpus>
<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>
<file_ref>
<file_name>Lunatics_x41zc_win32_cuda50.exe</file_name>
<main_program/>
</file_ref>
<file_ref>
<file_name>cudart32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>cufft32_50_35.dll</file_name>
</file_ref>
<file_ref>
<file_name>mbcuda.cfg</file_name>
</file_ref>
</app_version>
</app_info>



From my BOINC Manager log file:

2/27/2014 3:14:21 PM | | cc_config.xml not found - using defaults
2/27/2014 3:14:21 PM | | Starting BOINC client version 7.2.39 for windows_x86_64
2/27/2014 3:14:21 PM | | log flags: file_xfer, sched_ops, task
2/27/2014 3:14:21 PM | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
2/27/2014 3:14:21 PM | | Data directory: M:\John McClelland Data\ProgramData\BOINC
2/27/2014 3:14:21 PM | | Running under account John McClelland
2/27/2014 3:14:21 PM | | CUDA: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, CUDA version 6.0, compute capability 3.0, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, device version OpenCL 1.1 CUDA, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 1.2, device version OpenCL 1.2 (Build 66956))
2/27/2014 3:14:21 PM | SETI@home | Found app_info.xml; using anonymous platform
2/27/2014 3:14:21 PM | | app version refers to missing GPU type intel_gpu
2/27/2014 3:14:21 PM | SETI@home | [error] State file error: bad application name setiathome_enhanced
2/27/2014 3:14:21 PM | | app version refers to missing GPU type intel_gpu
2/27/2014 3:14:21 PM | SETI@home | Missing coprocessor for task 16my13ab.18736.7811.438086664208.12.184_1
2/27/2014 3:14:21 PM | SETI@home | Missing coprocessor for task 16my13ab.18736.7811.438086664208.12.188_0
2/27/2014 3:14:21 PM | SETI@home | Missing coprocessor for task 16my13ab.18736.7811.438086664208.12.186_0
2/27/2014 3:14:21 PM | SETI@home | Missing coprocessor for task 26au13aa.21194.15200.438086664204.12.77_2
2/27/2014 3:14:21 PM | | Host name: bigMAC
2/27/2014 3:14:21 PM | | Processor: 8 GenuineIntel Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz [Family 6 Model 60 Stepping 3]
2/27/2014 3:14:21 PM | | Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 fma cx16 sse4_1 sse4_2 movebe popcnt aes syscall nx lm vmx tm2 pbe
2/27/2014 3:14:21 PM | | OS: Microsoft Windows 7: Ultimate x64 Edition, Service Pack 1, (06.01.7601.00)
2/27/2014 3:14:21 PM | | Memory: 7.89 GB physical, 15.78 GB virtual
2/27/2014 3:14:21 PM | | Disk: 1.82 TB total, 1.33 TB free
2/27/2014 3:14:21 PM | | Local time is UTC -7 hours
2/27/2014 3:14:21 PM | SETI@home | Found app_config.xml
2/27/2014 3:14:21 PM | SETI@home | URL http://setiathome.berkeley.edu/; Computer ID 5409093; resource share 5000
2/27/2014 3:14:21 PM | SETI@home | General prefs: from SETI@home (last modified 08-Jun-2013 18:38:46)
2/27/2014 3:14:21 PM | SETI@home | Computer location: home
2/27/2014 3:14:21 PM | SETI@home | General prefs: no separate prefs for home; using your defaults
2/27/2014 3:14:21 PM | | Reading preferences override file
2/27/2014 3:14:21 PM | | Preferences:
2/27/2014 3:14:21 PM | | max memory usage when active: 7675.05MB
2/27/2014 3:14:21 PM | | max memory usage when idle: 8079.00MB
2/27/2014 3:14:21 PM | | max disk usage: 500.00GB
2/27/2014 3:14:21 PM | | (to change preferences, visit a project web site or select Preferences in the Manager)
2/27/2014 3:14:21 PM | | Not using a proxy
2/27/2014 3:14:24 PM | | Running CPU benchmarks
2/27/2014 3:14:24 PM | | Suspending computation - CPU benchmarks in progress
[/url]
____________

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4100
Credit: 33,074,590
RAC: 9,088
United Kingdom
Message 1482521 - Posted: 27 Feb 2014, 22:30:25 UTC - in response to Message 1482518.
Last modified: 27 Feb 2014, 22:33:31 UTC

2/27/2014 3:14:21 PM | | CUDA: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, CUDA version 6.0, compute capability 3.0, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, device version OpenCL 1.1 CUDA, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 1.2, device version OpenCL 1.2 (Build 66956))

Boinc doesn't detect your Intel GPU, only your GTX670.

To get Boinc to detect your Intel GPU either connect a monitor to it, a dummy plug, or just extend the desktop onto the Intel GPU.

That is right click on the desktop, choose 'screen resolution', go 'detect', chose the display that is on your Intel GPU, you'll have to force it detect the GPU by 'try and connect anyway on: VGA', then on 'multiple displays', chose 'extend these displays'

Claggy

Profile Wiggo
Avatar
Send message
Joined: 24 Jan 00
Posts: 6971
Credit: 94,698,915
RAC: 74,062
Australia
Message 1482522 - Posted: 27 Feb 2014, 22:34:13 UTC
Last modified: 27 Feb 2014, 22:34:52 UTC

OK, I'll bite, tell me what I'm doing wrong. I know it is something stupid but I'm not seeing it at this time. Also sorry that I don't recall how to make links active any more.

Firstly you need to activate the Intel GPU either by connecting a monitor or dummy plug to it, or seeing if extending the Desktop and forcing it to use VGA to get it detected.

Until the computer details shows the Intel video there it will not work.

[edit] Claggy beat me to it.

Cheers.

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8508
Credit: 50,002,007
RAC: 49,380
United Kingdom
Message 1482523 - Posted: 27 Feb 2014, 22:36:42 UTC - in response to Message 1482518.

I think you might have a driver installation problem.

2/27/2014 3:14:21 PM | | OpenCL CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 1.2, device version OpenCL 1.2 (Build 66956))
2/27/2014 3:14:21 PM | SETI@home | Found app_info.xml; using anonymous platform
2/27/2014 3:14:21 PM | | app version refers to missing GPU type intel_gpu

The difference is that the device detected is a CPU (C-Charlie), whereas the application expects a GPU (G-Golf).

Go back to the Intel website, and look for the Intel Graphics drivers - it'll be a HD 4600 GPU in that Haswell chip. I'll have a look for the link when I get back from the pub, if you haven't found it by then.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4194
Credit: 114,886,228
RAC: 147,837
United States
Message 1482536 - Posted: 27 Feb 2014, 23:17:12 UTC - in response to Message 1482521.

2/27/2014 3:14:21 PM | | CUDA: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, CUDA version 6.0, compute capability 3.0, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL: NVIDIA GPU 0: GeForce GTX 670 (driver version 331.65, device version OpenCL 1.1 CUDA, 2048MB, 1948MB available, 2915 GFLOPS peak)
2/27/2014 3:14:21 PM | | OpenCL CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 1.2, device version OpenCL 1.2 (Build 66956))

Boinc doesn't detect your Intel GPU, only your GTX670.

To get Boinc to detect your Intel GPU either connect a monitor to it, a dummy plug, or just extend the desktop onto the Intel GPU.

That is right click on the desktop, choose 'screen resolution', go 'detect', chose the display that is on your Intel GPU, you'll have to force it detect the GPU by 'try and connect anyway on: VGA', then on 'multiple displays', chose 'extend these displays'

Claggy

With my i5-4670K machines I found a dummy plug on the VGA connector was not sufficient & have to use the "extend these displays" option.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile mr.mac52Project donor
Avatar
Send message
Joined: 18 Mar 03
Posts: 28
Credit: 82,302,144
RAC: 103,619
United States
Message 1482549 - Posted: 27 Feb 2014, 23:55:30 UTC

Ok, I checked and I do have an dummy plug in the motherboard VGA port. So I followed HAL9000 and extended the desktop to that VGA adapter and restarted BOINC. My log file now has two lines about the Intel GPU:

2/27/2014 4:32:24 PM | | OpenCL: Intel GPU 0: Intel(R) HD Graphics 4600 (driver version 9.18.10.3257, device version OpenCL 1.2, 1624MB, 1624MB available, 208 GFLOPS peak)
2/27/2014 4:32:24 PM | | OpenCL CPU: Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 1.2, device version OpenCL 1.2 (Build 66956))

I did go to the Intel web site and down loaded 15.31.17.64.3257 version, file name: Win64_153117 which I believe is the correct one. The internal date in the file is: August 2, 2013. However the device manager is reporting a version of: 9.18.10.3257 which I can not explain.

So I'll wait until I see another error show up or if anyone has any other ideas as to what else is wrong...

I do appreciate everyone's assistance on this!

John
____________

Profile Wiggo
Avatar
Send message
Joined: 24 Jan 00
Posts: 6971
Credit: 94,698,915
RAC: 74,062
Australia
Message 1482556 - Posted: 28 Feb 2014, 0:04:25 UTC

Your computer details now show the Intel video so hopefully you should be fine.

Cheers.

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4100
Credit: 33,074,590
RAC: 9,088
United Kingdom
Message 1482566 - Posted: 28 Feb 2014, 0:15:55 UTC - in response to Message 1482549.
Last modified: 28 Feb 2014, 0:17:21 UTC

I did go to the Intel web site and down loaded 15.31.17.64.3257 version, file name: Win64_153117 which I believe is the correct one. The internal date in the file is: August 2, 2013. However the device manager is reporting a version of: 9.18.10.3257 which I can not explain.

Intel give two driver versions for each driver, for example there are two driver versions later than yours:

15.33.8.64.3345 (10.18.10.3345) dated 20th Nov 2013

https://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=23405&lang=eng

15.33.14.64.3412 (10.18.10.3412) dated 29th Jan 2014

https://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=23639&lang=eng

Claggy

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8508
Credit: 50,002,007
RAC: 49,380
United Kingdom
Message 1482600 - Posted: 28 Feb 2014, 1:10:54 UTC - in response to Message 1482566.

Depending on your preferences for a backup project, you might want to stick with what you have already.

Version 9.18.10.3257 (as per your device manager) is fine here, and also fine at Einstein. The newer v10 range of drivers are also fine here, but have been known to cause errors at Einstein: so perhaps v9 is the best general-purpose choice.

MikeN
Send message
Joined: 24 Jan 11
Posts: 301
Credit: 31,615,611
RAC: 40,000
United Kingdom
Message 1482769 - Posted: 28 Feb 2014, 13:26:27 UTC - in response to Message 1482600.

Just got my first Intel GPU invalid

http://setiathome.berkeley.edu/workunit.php?wuid=1427904058

Its early days, but looking through my results lists I seem to have 2 valids, 8 inconclusives and 1 invalid from the Intel GPU. The Intel GPU has been happily crunching Collatz for the last 5 months as there was nothing else for it to do. Looks like it may not like SETI.
____________

Profile mr.mac52Project donor
Avatar
Send message
Joined: 18 Mar 03
Posts: 28
Credit: 82,302,144
RAC: 103,619
United States
Message 1482770 - Posted: 28 Feb 2014, 13:35:52 UTC

I checked my overnight runs and have successfully processed my first Intel GPU work unit.

Thanks to all who contributed to getting this going!

John
____________

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8508
Credit: 50,002,007
RAC: 49,380
United Kingdom
Message 1482773 - Posted: 28 Feb 2014, 14:04:09 UTC - in response to Message 1482769.

Just got my first Intel GPU invalid

http://setiathome.berkeley.edu/workunit.php?wuid=1427904058

Its early days, but looking through my results lists I seem to have 2 valids, 8 inconclusives and 1 invalid from the Intel GPU. The Intel GPU has been happily crunching Collatz for the last 5 months as there was nothing else for it to do. Looks like it may not like SETI.

Looks like you are getting a lot of autocorrs, and sometimes a false overflow on autocorrs. That's exactly the sort of problem that Raistmer was looking for when he started this thread. He may want to come and ask more questions about your setup.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4194
Credit: 114,886,228
RAC: 147,837
United States
Message 1482783 - Posted: 28 Feb 2014, 14:43:49 UTC - in response to Message 1482773.

Just got my first Intel GPU invalid

http://setiathome.berkeley.edu/workunit.php?wuid=1427904058

Its early days, but looking through my results lists I seem to have 2 valids, 8 inconclusives and 1 invalid from the Intel GPU. The Intel GPU has been happily crunching Collatz for the last 5 months as there was nothing else for it to do. Looks like it may not like SETI.

Looks like you are getting a lot of autocorrs, and sometimes a false overflow on autocorrs. That's exactly the sort of problem that Raistmer was looking for when he started this thread. He may want to come and ask more questions about your setup.

Might this be the issue?
Driver version: 9.17.10.3040
Version: OpenCL 1.1

____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

ClaggyProject donor
Volunteer tester
Send message
Joined: 5 Jul 99
Posts: 4100
Credit: 33,074,590
RAC: 9,088
United Kingdom
Message 1482945 - Posted: 28 Feb 2014, 22:00:07 UTC - in response to Message 1482783.
Last modified: 28 Feb 2014, 22:00:42 UTC

Just got my first Intel GPU invalid

http://setiathome.berkeley.edu/workunit.php?wuid=1427904058

Its early days, but looking through my results lists I seem to have 2 valids, 8 inconclusives and 1 invalid from the Intel GPU. The Intel GPU has been happily crunching Collatz for the last 5 months as there was nothing else for it to do. Looks like it may not like SETI.

Looks like you are getting a lot of autocorrs, and sometimes a false overflow on autocorrs. That's exactly the sort of problem that Raistmer was looking for when he started this thread. He may want to come and ask more questions about your setup.

Might this be the issue?
Driver version: 9.17.10.3040
Version: OpenCL 1.1

Especially since I asked at Seti Beta for the app to be sent to hosts with OpenCL 1.2 drivers only, seems no one listened.

Claggy

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4194
Credit: 114,886,228
RAC: 147,837
United States
Message 1482954 - Posted: 28 Feb 2014, 22:22:03 UTC - in response to Message 1482945.

Just got my first Intel GPU invalid

http://setiathome.berkeley.edu/workunit.php?wuid=1427904058

Its early days, but looking through my results lists I seem to have 2 valids, 8 inconclusives and 1 invalid from the Intel GPU. The Intel GPU has been happily crunching Collatz for the last 5 months as there was nothing else for it to do. Looks like it may not like SETI.

Looks like you are getting a lot of autocorrs, and sometimes a false overflow on autocorrs. That's exactly the sort of problem that Raistmer was looking for when he started this thread. He may want to come and ask more questions about your setup.

Might this be the issue?
Driver version: 9.17.10.3040
Version: OpenCL 1.1

Especially since I asked at Seti Beta for the app to be sent to hosts with OpenCL 1.2 drivers only, seems no one listened.

Claggy

Perhps there is an issue with version detection similar to the ATI driver detection Eric was having.

There does seem to be a disconnect between the client detecting this:
2/26/2014 7:44:59 AM OpenCL: Intel GPU 0: Intel(R) HD Graphics 4600
(driver version 10.18.10.3412, device version OpenCL 1.2, 1496MB, 1496MB available, 32 GFLOPS peak)
Then telling the server this:
INTEL Intel(R) HD Graphics 4600 (1496MB) OpenCL: 1.02

____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8508
Credit: 50,002,007
RAC: 49,380
United Kingdom
Message 1482969 - Posted: 28 Feb 2014, 23:04:43 UTC - in response to Message 1482954.

Perhps there is an issue with version detection similar to the ATI driver detection Eric was having.

There does seem to be a disconnect between the client detecting this:
2/26/2014 7:44:59 AM OpenCL: Intel GPU 0: Intel(R) HD Graphics 4600
(driver version 10.18.10.3412, device version OpenCL 1.2, 1496MB, 1496MB available, 32 GFLOPS peak)
Then telling the server this:
INTEL Intel(R) HD Graphics 4600 (1496MB) OpenCL: 1.02

Well, what the client actually sends is:

<coproc_opencl>
<name>Intel(R) HD Graphics 4600</name>
<vendor>Intel(R) Corporation</vendor>
<vendor_id>32902</vendor_id>
...
<opencl_platform_version>OpenCL 1.2</opencl_platform_version>
<opencl_device_version>OpenCL 1.2</opencl_device_version>
<opencl_driver_version>9.18.10.3055</opencl_driver_version>
</coproc_opencl>

(from sched_request_setiathome.berkeley.edu.xml)

It just seems as if the two different GUIs (client and web from server) parse the text to numeric, and render the numeric, slightly differently.

MikeN
Send message
Joined: 24 Jan 11
Posts: 301
Credit: 31,615,611
RAC: 40,000
United Kingdom
Message 1483143 - Posted: 1 Mar 2014, 8:42:59 UTC - in response to Message 1482969.

I now have 8 valid, 13 inconclusive and 4 invalid from the INTEL GPU. Is it worth crunching the remaining WUs (over 50) allocated to this GPU or should I just abort them?

The problem will eventually go away for this host as last week I put a new NVIDEA GPU in it alongside the INTEL GPU and made it an astropulse only (for SETI) machine. Thus it is not asking for new wus, just crunching those it already has. The INTEL GPU will then go back to crunching collatz until either DELL release an Einstein compatible driver or an astropulse app for INTEL GPU becomes available.
____________

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4194
Credit: 114,886,228
RAC: 147,837
United States
Message 1483156 - Posted: 1 Mar 2014, 9:18:22 UTC - in response to Message 1483143.

I now have 8 valid, 13 inconclusive and 4 invalid from the INTEL GPU. Is it worth crunching the remaining WUs (over 50) allocated to this GPU or should I just abort them?

The problem will eventually go away for this host as last week I put a new NVIDEA GPU in it alongside the INTEL GPU and made it an astropulse only (for SETI) machine. Thus it is not asking for new wus, just crunching those it already has. The INTEL GPU will then go back to crunching collatz until either DELL release an Einstein compatible driver or an astropulse app for INTEL GPU becomes available.

If were to install the a driver with the required OpenCL support then it certainly would be. Otherwise it is doing you no good here. It was mentioned that there was a version of the newer Intel driver that Einstein may not like. So you may need to find out from them which one they prefer if you want to use the Intel GPU there as well.
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

1 · 2 · Next

Message boards : Number crunching : Intel GPU app hosts with failures - please post here

Copyright © 2014 University of California