Pages: [1] 2
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-02-17 03:48:40

Host details currently show the CPU model without the numthreads, while host details on BOINC project sites does include this info. Would be great to have it here, too.

Additionally, for coprocs, BS & SETI & PrimeGrid (picked as example projects) show different granularity of detail (examples below are for the very same host):

https://boincstats.com/en/bam/host/620929 shows:
4x CUDA
GeForce GTX TITAN X (4x)

http://www.primegrid.com/show_host_detail.php?hostid=505254 shows: [4] NVIDIA GeForce GTX TITAN X (4095MB ) driver: 37849, vbox 5.1.14

http://setiathome.berkeley.edu/show_host_detail.php?hostid=7856578 shows: [4] NVIDIA GeForce GTX TITAN X (4095MB ) driver: 378.49 OpenCL: 1.2

That means, the driver version, OpenCL version and the vbox version are avilable. That is very much in line with the info I am seeing in the Event Log:

2/16/2017 12:18:58 PM | | CUDA: NVIDIA GPU 0: GeForce GTX TITAN X (driver version 378.49, CUDA version 8.0, compute capability 5.2, 4096MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | CUDA: NVIDIA GPU 1: GeForce GTX TITAN X (driver version 378.49, CUDA version 8.0, compute capability 5.2, 4096MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | CUDA: NVIDIA GPU 2: GeForce GTX TITAN X (driver version 378.49, CUDA version 8.0, compute capability 5.2, 4096MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | CUDA: NVIDIA GPU 3: GeForce GTX TITAN X (driver version 378.49, CUDA version 8.0, compute capability 5.2, 4096MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | OpenCL: NVIDIA GPU 0: GeForce GTX TITAN X (driver version 378.49, device version OpenCL 1.2 CUDA, 12288MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | OpenCL: NVIDIA GPU 1: GeForce GTX TITAN X (driver version 378.49, device version OpenCL 1.2 CUDA, 12288MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | OpenCL: NVIDIA GPU 2: GeForce GTX TITAN X (driver version 378.49, device version OpenCL 1.2 CUDA, 12288MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | OpenCL: NVIDIA GPU 3: GeForce GTX TITAN X (driver version 378.49, device version OpenCL 1.2 CUDA, 12288MB, 3962MB available, 7468 GFLOPS peak)
2/16/2017 12:18:58 PM | | Processor: 16 GenuineIntel Intel(R) Core(TM) i7-5960X CPU @ 3.00GHz [Family 6 Model 63 Stepping 2]
2/16/2017 12:18:58 PM | | VirtualBox version: 5.1.14

It would be great to expose them all here, too, formatted correctly.

And, exposing at least the user-updateable info (driver, OpenCL and vbox versions) in the HostList table just like the Client Version would be very useful to be able to see in one quick look as to which hosts have what drivers & versions, and thus might be in need of upgrading.

Thanks
Tuna


[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-02-17 08:10:03

I do not believe this information is currently available to BAM!. Take a look at the "host_info" section of your acct_mgr_request.xml files. If the info is there then please post that section here. If it's not it has to be added by the BOINC devs.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-02-17 08:29:46
last modified: 2017-02-17 08:31:34

From acct_mgr_request.xml on my Dual Titan X machine, with certain things edited:


<host_info>
<timezone>-28800</timezone>
<domain_name>BlahBlah</domain_name>
<ip_addr>999.999.999.999</ip_addr>
<host_cpid>0123456789ABCDEF</host_cpid>

<p_ncpus>16</p_ncpus>
<p_vendor>GenuineIntel</p_vendor>
<p_model>Intel(R) Core(TM) i7-5960X CPU @ 3.00GHz [Family 6 Model 63 Stepping 2]</p_model>

<p_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 f16c rdrandsyscall nx lm avx avx2 vmx tm2 dca pbe fsgsbase bmi1 smep bmi2</p_features>
<p_fpops>4405485812.420026</p_fpops>
<p_iops>15986693011.577978</p_iops>
<p_membw>62500000.000000</p_membw>
<p_calculated>1485847151.483816</p_calculated>
<p_vm_extensions_disabled>0</p_vm_extensions_disabled>
<m_nbytes>34255212544.000000</m_nbytes>
<m_cache>262144.000000</m_cache>
<m_swap>39355486208.000000</m_swap>
<d_total>511515295744.000000</d_total>
<d_free>431047573504.000000</d_free>
<os_name>Microsoft Windows 10</os_name>
<os_version>Professional x64 Edition, (10.00.14393.00)</os_version>
<virtualbox_version>5.1.14</virtualbox_version>

<coprocs>
<coproc_cuda>
<count>2</count>
<name>GeForce GTX TITAN X</name>

<available_ram>4154589183.000000</available_ram>
<have_cuda>1</have_cuda>
<have_opencl>1</have_opencl>

<peak_flops>7621632000000.000000</peak_flops>
<cudaVersion>8000</cudaVersion>
<drvVersion>37849</drvVersion>

<totalGlobalMem>4294967295.000000</totalGlobalMem>
<sharedMemPerBlock>49152.000000</sharedMemPerBlock>
<regsPerBlock>65536</regsPerBlock>
<warpSize>32</warpSize>
<memPitch>2147483647.000000</memPitch>
<maxThreadsPerBlock>1024</maxThreadsPerBlock>
<maxThreadsDim>1024 1024 64</maxThreadsDim>
<maxGridSize>2147483647 65535 65535</maxGridSize>
<clockRate>1240500</clockRate>
<totalConstMem>65536.000000</totalConstMem>
<major>5</major>
<minor>2</minor>
<textureAlignment>512.000000</textureAlignment>
<deviceOverlap>1</deviceOverlap>
<multiProcessorCount>24</multiProcessorCount>
<coproc_opencl>
<name>GeForce GTX TITAN X</name>
<vendor>NVIDIA Corporation</vendor>
<vendor_id>4318</vendor_id>
<available>1</available>
<half_fp_config>0</half_fp_config>
<single_fp_config>191</single_fp_config>
<double_fp_config>63</double_fp_config>
<endian_little>1</endian_little>
<execution_capabilities>1</execution_capabilities>
<extensions>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 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts cl_khr_gl_event</extensions>
<global_mem_size>12884901888</global_mem_size>
<local_mem_size>49152</local_mem_size>
<max_clock_frequency>1240</max_clock_frequency>
<max_compute_units>24</max_compute_units>
<nv_compute_capability_major>5</nv_compute_capability_major>
<nv_compute_capability_minor>2</nv_compute_capability_minor>
<amd_simd_per_compute_unit>0</amd_simd_per_compute_unit>
<amd_simd_width>0</amd_simd_width>
<amd_simd_instruction_width>0</amd_simd_instruction_width>
<opencl_platform_version>OpenCL 1.2 CUDA 8.0.0</opencl_platform_version>
<opencl_device_version>OpenCL 1.2 CUDA</opencl_device_version>
<opencl_driver_version>378.49</opencl_driver_version>

</coproc_opencl>
<pci_info>
<bus_id>1</bus_id>
<device_id>0</device_id>
<domain_id>0</domain_id>
</pci_info>
<pci_info>
<bus_id>2</bus_id>
<device_id>0</device_id>
<domain_id>0</domain_id>
</pci_info>
</coproc_cuda>
</coprocs>
</host_info>


By the way, the preview of this reply looked awesome while composing it, but it looks crappy once posted. FYI.
[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-02-17 08:37:27

Some of the highlighted info is already imported into the database, I guestimate that adding the additional info will require 17GB of storage space (of the ~70GB left).

It'll also take some time to analyze the data, update scripts, databases and webcode.

Don't hold your breath.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-02-17 08:48:29

[BOINCstats Willy wrote:
Don't hold your breath.


....exhaling...
TeeVeeEss
  Donator
Tester - Translator - BOINCstats SOFA member
BAM!ID: 2648
Joined: 2006-06-27
Posts: 767
Credits: 12,368,898,860
World-rank: 247

2017-02-18 16:00:18

[BOINCstats Willy wrote:
I guestimate that adding the additional info will require 17GB of storage space (of the ~70GB left).

Ouch, makes you realize the huge number of hosts the website/database has to deal with
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-17 17:51:43

Tuna Ertemalp wrote:
[BOINCstats Willy wrote:
Don't hold your breath.
....exhaling...

Still not holding my breath... Should I start?
Dr Who Fan
BAM!ID: 1075
Joined: 2006-05-31
Posts: 639
Credits: 86,521,656
World-rank: 8,425

2017-04-18 05:43:23

Still not holding my breath... Should I start?

Tuna, you might want to ask Leslie Nielsen how long he was able to hold his breath...


https://youtu.be/Ojm_eRjINrI
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-18 05:52:10

Dr Who Fan wrote:

Still not holding my breath... Should I start?

Tuna, you might want to ask Leslie Nielsen how long he was able to hold his breath...


https://youtu.be/Ojm_eRjINrI




For the uninitiated about Mr Nielsen: http://www.popmatters.com/post/134276-appreciating-leslie-nielsen-he-could-hold-his-breath-for-a-long-time/
[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-04-27 11:48:50

Added the CUDA driver version for nVidia. If you want other data to be added like vbox or other GPU brands then I need examples, I don't have all that hardware.

This needs at least one sync between the host en BAM! and it is untested.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 16:38:31

I'll get u samples soon...
TeeVeeEss
  Donator
Tester - Translator - BOINCstats SOFA member
BAM!ID: 2648
Joined: 2006-06-27
Posts: 767
Credits: 12,368,898,860
World-rank: 247

2017-04-27 16:46:05

Startup lines from one of my hosts, BAM id 332368:
27-04-2017 18:39:59	CUDA: NVIDIA GPU 0: GeForce GT 720 (driver version 376.53, CUDA version 8.0, compute capability 3.5, 1024MB, 839MB available, 306 GFLOPS peak)	
27-04-2017 18:39:59 OpenCL: NVIDIA GPU 0: GeForce GT 720 (driver version 376.53, device version OpenCL 1.2 CUDA, 1024MB, 839MB available, 306 GFLOPS peak)
27-04-2017 18:39:59 Host name: (deleted)
27-04-2017 18:39:59 Processor: 8 GenuineIntel Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz [Family 6 Model 42 Stepping 7]
27-04-2017 18:39:59 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 cx16 sse4_1 sse4_2 popcnt aes syscall nx lm avx vmx smx tm2 pbe
27-04-2017 18:39:59 OS: Microsoft Windows 10: Core x64 Edition, (10.00.14393.00)
27-04-2017 18:39:59 Memory: 11.97 GB physical, 29.93 GB virtual
27-04-2017 18:39:59 Disk: 1.82 TB total, 759.81 GB free
27-04-2017 18:39:59 Local time is UTC +2 hours
27-04-2017 18:39:59 VirtualBox version: 5.1.18
Will try to paste the same from a host with an AMD GPU..
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 16:53:39

Tuna Ertemalp wrote:
I'll get u samples soon...

Oh, it seems I already did. Among all the bold lines in my previous sample of the XML, there is a line that shows:

"5.1.14"

That is what you need, no?

All my cards are either NVidia or Intel or non-existent, so can't test for anything else. All those look correct for my hosts.


Also:
Tuna Ertemalp wrote:
Host details currently show the CPU model without the numthreads, while host details on BOINC project sites does include this info. Would be great to have it here, too.


In my example, there is the entry:

"16"

Thanks!
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 16:55:59

Willy, I don't know what is going on but I type in msgs something like :

16

without the spaces, they look great in the preview, but once I post, the stuff between are gone!

I wonder how *this* msg is going to look...
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 16:56:55

Yup, the forum ate those, too... What?

Let's try newline...



16

Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 16:57:30

Yup, they are gone, too. Basically anything between LESS THAN and GREATER THAN seems to be eaten during posting. Sorry for hijacking the thread on this.
TeeVeeEss
  Donator
Tester - Translator - BOINCstats SOFA member
BAM!ID: 2648
Joined: 2006-06-27
Posts: 767
Credits: 12,368,898,860
World-rank: 247

2017-04-27 17:04:58

BAM id 705442, this one has an AMD GPU, vbox not installed.
do 27 apr 2017 18:48:07 CEST |  | Starting BOINC client version 7.6.31 for x86_64-pc-linux-gnu
do 27 apr 2017 18:48:07 CEST | | log flags: file_xfer, sched_ops, task
do 27 apr 2017 18:48:07 CEST | | Libraries: libcurl/7.47.0 OpenSSL/1.0.2g zlib/1.2.8 libidn/1.32 librtmp/2.3
do 27 apr 2017 18:48:07 CEST | | Data directory: /var/lib/boinc-client
do 27 apr 2017 18:48:07 CEST | | OpenCL: AMD/ATI GPU 0: AMD Radeon (TM) RX 480 Graphics (driver version 2264.10, device version OpenCL 1.2 AMD-APP (2264.10), 5703MB, 5703MB available, 6036 GFLOPS peak)
do 27 apr 2017 18:48:07 CEST | | Creating new client state file
do 27 apr 2017 18:48:07 CEST | | Host name: (deleted)
do 27 apr 2017 18:48:07 CEST | | Processor: 8 GenuineIntel Intel(R) Xeon(R) CPU E3-1275 v5 @ 3.60GHz [Family 6 Model 94 Stepping 3]
do 27 apr 2017 18:48:07 CEST | | 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 ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx rdseed adx smap clflushopt xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp
do 27 apr 2017 18:48:07 CEST | | OS: Linux: 4.8.0-46-generic
do 27 apr 2017 18:48:07 CEST | | Memory: 62.87 GB physical, 63.95 GB virtual
do 27 apr 2017 18:48:07 CEST | | Disk: 156.02 GB total, 141.11 GB free
do 27 apr 2017 18:48:07 CEST | | Local time is UTC +2 hours

TeeVeeEss
  Donator
Tester - Translator - BOINCstats SOFA member
BAM!ID: 2648
Joined: 2006-06-27
Posts: 767
Credits: 12,368,898,860
World-rank: 247

2017-04-27 17:06:48

Tuna Ertemalp wrote:

Yup, they are gone, too. Basically anything between LESS THAN and GREATER THAN seems to be eaten during posting. Sorry for hijacking the thread on this.

The check on injecting code is quite rigid. You should remove some elements to make it "invalid" xml...
[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-04-27 17:32:48

I need the acct mgr request XML. Seems you can't post that at the moment so please wait for a fix for that.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-27 21:39:39

[BOINCstats Willy wrote:

I need the acct mgr request XML. Seems you can't post that at the moment so please wait for a fix for that.


Look at my post "Posted 2017-02-17 08:29:46 , last modified: 2017-02-17 08:31:34". It is all in there, bolded, the vbox and CPU count...
[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-04-28 06:59:53

Tuna Ertemalp wrote:

[BOINCstats Willy wrote:

I need the acct mgr request XML. Seems you can't post that at the moment so please wait for a fix for that.


Look at my post "Posted 2017-02-17 08:29:46 , last modified: 2017-02-17 08:31:34". It is all in there, bolded, the vbox and CPU count...

Yes, it is. For one brand. I need to be sure what other GPU brands look like so I won't break the BAM! code.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-28 08:32:08

I hope I am not confusing you, but here is the detailed breakdown:

1) CPU thread count: Currently NOT listed in the host details page. It is available in the XML as the p_ncpus key under host_info. That is the first bold line in my example in that 2017-02-17 post of mine. You are already reading & reporting p_model, and it would be great if you just added something like "(p_ncpus threads)" next to it. Also, you might want to consider reporting the p_vendor value in front of the p_model value. I don't know why BOINC decided to make vendor & model separate values, but there might be some merit to it.

2) VirtualBox version: Currently NOT listed in the host details page. It is available in the XML as the virtualbox_version key under host_info. You probably will want to create a new section right after CPU and Coprocessor to report VirtualBox as virtualbox_version or None.

3) GPU data: Currently listed in the host details page after your work yesterday. Thankful for that. I could only verify for NVidia cards, unfortunately. All my 12 hosts are a mix of Dual/Quad new/old NVidia cards, or Intel integrated graphics, or none. In all those cases, your work seems to be fine (but, see below). I cannot speak for AMD etc., so I hope someone can post what they have after you fix the XML posting bug in the forum.

3a ) All that said, I have a suggestion for CUDA. It seems you are reporting it using "opencl_device_version/opencl_driver_version". That is under-reporting a little bit, and it has a problem with older non-openCL NVidia cards. You might instead want to use "opencl_platform_version (driver opencl_driver_version)". This way, you will capture the CUDA version as well, in addition to the driver version. So, instead of reporting "OpenCL 1.2 CUDA/381.65", you'd be reporting "OpenCL 1.2 CUDA 8.0.0 (driver 381.65)"

3b ) Exception to 3a: If the NVidia card is old and does not support OpenCL, then have_opencl is 0 instead of 1, and the misc opencl_* keys are not available for what you are doing. This is probably why my host 698917 only shows "GeForce 8600 GT" without the driver version. In such cases, you can use the cudaVersion and drvVersion keys that seem to be available at all times, but they would require some string manipulation, like turning "6050" to "6.0.5" for CUDA, and "34201" to "341.01" for driver. Or, you can simply use those values as-is, like "OpenCL none CUDA cudaVersion (driver drvVersion)" to get "OpenCL none CUDA 6050 (driver 34201)" for an inexact but acceptable display of information for such older cards.

So, #1 and #2 is missing and can be implemented by the data provided in my 2017-02-17 post and above explanation. That data is not brand-specific, at all, so I think you have all you need.

#3 needs improvement for NVidia GPUs, and data & verification from other users for other GPUs.

Thanks!
Tuna

PS: Also of note is that this doesn't deal with any of the other coprocessors, i.e. the ASICs. I have not yet installed the few USB sticks I have, so I have no idea what the XML has about them. If/when I do install them (BitcoinUtopia is shutting down in a few months), I will report back on that.

PSS: When you receive the XMLs from the hosts, can you not make a copy for a few select ones you would be interested in, and therefore have actual data to look at instead of depending what people like me to copy/paste stuff to here?
Tuna Ertemalp
    Donator
Tester
BAM!ID: 37744
Joined: 2007-10-31
Posts: 531
Credits: 10,150,919,467
World-rank: 279

2017-04-28 10:03:23

Slight follow up to #3a & #3b: Just found major and minor under coproc_cuda that indicate compute capability. So, my suggestions below should be modified to become:

#3a: "opencl_platform_version (driver opencl_driver_version, compute capability major.minor)": e.g. "OpenCL 1.2 CUDA 8.0.0 (driver 381.65, compute capability 3.5)"

#3b: "OpenCL none CUDA cudaVersion (driver drvVersion, compute capability major.minor)": e.g. "OpenCL none CUDA 6050 (driver 34201, compute capability 1.1)"

Also, if you decide to parse cudaVersion and drvVersion, I noticed (by the way BOINCMgr reports it) that CUDA 6050 means CUDA 6.5, not 6.0.5.0. I am going to guess that "6050" actually means (major.minor.minorminor) "0000006"."05"."0", and by removing leading zeroes and ignoring any zero minorminor, this becomes 6.5, to allow future values like "123285" to mean "123.28.5".
TeeVeeEss
  Donator
Tester - Translator - BOINCstats SOFA member
BAM!ID: 2648
Joined: 2006-06-27
Posts: 767
Credits: 12,368,898,860
World-rank: 247

2017-04-28 22:46:42

hostinfo section from acct_mgr_request.xml with AMD GPU, replaced all GT with [ and ST with ]
[host_info]
[timezone]7200[/timezone]
[domain_name](deleted)[/domain_name]
[ip_addr](deleted)[/ip_addr]
[host_cpid]137bf6a93593a29dcf5514ca28ac999e[/host_cpid]
[p_ncpus]8[/p_ncpus]
[p_vendor]GenuineIntel[/p_vendor]
[p_model]Intel(R) Xeon(R) CPU E3-1275 v5 @ 3.60GHz [Family 6 Model 94 Stepping 3][/p_model]
[p_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 ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx rdseed adx smap clflushopt xsaveopt xsavec xgetbv1 xsaves dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp[/p_features]
[p_fpops]4390710491.620427[/p_fpops]
[p_iops]17664882708.097450[/p_iops]
[p_membw]1000000000.000000[/p_membw]
[p_calculated]1493312264.668261[/p_calculated]
[p_vm_extensions_disabled]0[/p_vm_extensions_disabled]
[m_nbytes]67509411840.000000[/m_nbytes]
[m_cache]8388608.000000[/m_cache]
[m_swap]68664946688.000000[/m_swap]
[d_total]167522004992.000000[/d_total]
[d_free]151532302336.000000[/d_free]
[os_name]Linux[/os_name]
[os_version]4.8.0-46-generic[/os_version]
[coprocs]
[coproc_ati]
[count]1[/count]
[name]AMD Radeon (TM) RX 480 Graphics[/name]
[available_ram]5980540928.000000[/available_ram]
[have_cal]0[/have_cal]
[have_opencl]1[/have_opencl]
[peak_flops]6036480000000.000000[/peak_flops]
[CALVersion][/CALVersion]
[target]0[/target]
[localRAM]5703[/localRAM]
[uncachedRemoteRAM]0[/uncachedRemoteRAM]
[cachedRemoteRAM]0[/cachedRemoteRAM]
[engineClock]1310[/engineClock]
[memoryClock]0[/memoryClock]
[wavefrontSize]0[/wavefrontSize]
[numberOfSIMD]0[/numberOfSIMD]
[doublePrecision]0[/doublePrecision]
[pitch_alignment]0[/pitch_alignment]
[surface_alignment]0[/surface_alignment]
[maxResource1DWidth]0[/maxResource1DWidth]
[maxResource2DWidth]0[/maxResource2DWidth]
[maxResource2DHeight]0[/maxResource2DHeight]
[coproc_opencl]
[name]AMD Radeon (TM) RX 480 Graphics[/name]
[vendor]Advanced Micro Devices, Inc.[/vendor]
[vendor_id]4098[/vendor_id]
[available]1[/available]
[half_fp_config]0[/half_fp_config]
[single_fp_config]190[/single_fp_config]
[double_fp_config]63[/double_fp_config]
[endian_little]1[/endian_little]
[execution_capabilities]1[/execution_capabilities]
[extensions]cl_khr_fp64 cl_amd_fp64 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_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event[/extensions]
[global_mem_size]5980540928[/global_mem_size]
[local_mem_size]32768[/local_mem_size]
[max_clock_frequency]1310[/max_clock_frequency]
[max_compute_units]36[/max_compute_units]
[nv_compute_capability_major]0[/nv_compute_capability_major]
[nv_compute_capability_minor]0[/nv_compute_capability_minor]
[amd_simd_per_compute_unit]4[/amd_simd_per_compute_unit]
[amd_simd_width]16[/amd_simd_width]
[amd_simd_instruction_width]1[/amd_simd_instruction_width]
[opencl_platform_version]OpenCL 2.0 AMD-APP (2264.10)[/opencl_platform_version]
[opencl_device_version]OpenCL 1.2 AMD-APP (2264.10)[/opencl_device_version]
[opencl_driver_version]2264.10[/opencl_driver_version]
[/coproc_opencl]
[/coproc_ati]
[/coprocs]
[/host_info]
[BOINCstats] Willy
 
Forum moderator - Administrator - Developer - Tester - Translator
BAM!ID: 1
Joined: 2006-01-09
Posts: 9155
Credits: 348,905,383
World-rank: 3,153

2017-04-29 06:25:36
last modified: 2017-04-29 07:03:30

Added AMD, Intel and VirtualBox.
Please do not PM, IM or email me for support (they will go unread/ignored). Use the forum for support.
Pages: [1] 2

Index :: Comments and suggestions :: Would be nice to get #cores, GPU drivers and vbox version on host details
Reason: