Help with Ubuntu 16.04 TLS & Headless GPU Computing

Message boards : Number crunching : Help with Ubuntu 16.04 TLS & Headless GPU Computing
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Mitchell Tuckness
Volunteer tester
Avatar

Send message
Joined: 16 Apr 99
Posts: 46
Credit: 21,421,544
RAC: 5
United States
Message 1837393 - Posted: 22 Dec 2016, 22:09:52 UTC

Hi,

I am trying to run Boinc client on a server I use to run Zoneminder for Security Cameras around the house. The CPU works fine for doing the projects, but I wanted to have the client use the GPU's of some spare cards I had around the house since it is a headless (no video / desktop) server and the GPU's were doing nothing.

So I have three ATI cards in the system, here is some system information below.

I have a few problems, concerns, questions. I am not a Linux guru, still learning a lot, but pretty good at Google. My problem is, I am not sure if these cards are functioning, compatible and functioning. I have tried to get the latest drivers installed, but it seems something changed in Ubuntu 16.04 and AMD / ATI cards and their support drivers etc. What I am trying to find out is if these cards GPU's will work and if I have the correct / best drivers, hoping a real guru can help out or a few :)

Another issue is my results:

Here is a link to a typical failed work unit for SETI. https://setiathome.berkeley.edu/result.php?resultid=5377275627

A link to the computer and it's work units: https://setiathome.berkeley.edu/results.php?hostid=8122337

I am not sure if these are coming from one of the cards, all of the cards, driver or what. Any ideas? Thanks!

Here is some info of the drivers the cards are using:

sudo lshw -c video
*-display
description: VGA compatible controller
product: Curacao PRO [Radeon R7 370 / R9 270/370 OEM]
vendor: Advanced Micro Devices, Inc. [AMD/ATI]
physical id: 0
bus info: pci@0000:03:00.0
version: 00
width: 64 bits
clock: 33MHz
capabilities: pm pciexpress msi vga_controller bus_master cap_list rom
configuration: driver=amdgpu latency=0
resources: irq:36 memory:e0000000-efffffff memory:f7800000-f783ffff ioport:b000(size=256) memory:f7840000-f785ffff
*-display
description: VGA compatible controller
product: Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]
vendor: Advanced Micro Devices, Inc. [AMD/ATI]
physical id: 0
bus info: pci@0000:04:00.0
version: 00
width: 64 bits
clock: 33MHz
capabilities: pm pciexpress msi vga_controller bus_master cap_list rom
configuration: driver=amdgpu latency=0
resources: irq:37 memory:d0000000-dfffffff memory:f7700000-f773ffff ioport:a000(size=256) memory:f7740000-f775ffff
*-display
description: VGA compatible controller
product: Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]
vendor: Advanced Micro Devices, Inc. [AMD/ATI]
physical id: 0
bus info: pci@0000:05:00.0
version: 00
width: 64 bits
clock: 33MHz
capabilities: pm pciexpress msi vga_controller bus_master cap_list rom
configuration: driver=amdgpu latency=0
resources: irq:38 memory:c0000000-cfffffff memory:f7600000-f763ffff ioport:9000(size=256) memory:f7640000-f765ffff




Distributor ID: Ubuntu
Description: Ubuntu 16.04.1 LTS
Release: 16.04
Codename: xenial

03:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Curacao PRO [Radeon R7 370 / R9 270/370 OEM]
04:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]
05:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]



03:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Curacao PRO [Radeon R7 370 / R9 270/370 OEM] (prog-if 00 [VGA controller])
Subsystem: PC Partner Limited / Sapphire Technology Curacao PRO [Radeon R7 370 / R9 270/370 OEM]
Flags: bus master, fast devsel, latency 0, IRQ 36
Memory at e0000000 (64-bit, prefetchable) [size=256M]
Memory at f7800000 (64-bit, non-prefetchable) [size=256K]
I/O ports at b000 [size=256]
Expansion ROM at f7840000 [disabled] [size=128K]
Capabilities: <access denied>
Kernel driver in use: amdgpu
Kernel modules: radeon, amdgpu

03:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Subsystem: PC Partner Limited / Sapphire Technology Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Flags: bus master, fast devsel, latency 0, IRQ 41
Memory at f7860000 (64-bit, non-prefetchable) [size=16K]
Capabilities: <access denied>
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel

04:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP] (prog-if 00 [VGA controller])
Subsystem: Hightech Information System Ltd. Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]
Flags: bus master, fast devsel, latency 0, IRQ 37
Memory at d0000000 (64-bit, prefetchable) [size=256M]
Memory at f7700000 (64-bit, non-prefetchable) [size=256K]
I/O ports at a000 [size=256]
Expansion ROM at f7740000 [disabled] [size=128K]
Capabilities: <access denied>
Kernel driver in use: amdgpu
Kernel modules: radeon, amdgpu

04:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Subsystem: Hightech Information System Ltd. Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Flags: bus master, fast devsel, latency 0, IRQ 42
Memory at f7760000 (64-bit, non-prefetchable) [size=16K]
Capabilities: <access denied>
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel

05:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP] (prog-if 00 [VGA controller])
Subsystem: Hightech Information System Ltd. Pitcairn PRO [Radeon HD 7850 / R7 265 / R9 270 1024SP]
Flags: bus master, fast devsel, latency 0, IRQ 38
Memory at c0000000 (64-bit, prefetchable) [size=256M]
Memory at f7600000 (64-bit, non-prefetchable) [size=256K]
I/O ports at 9000 [size=256]
Expansion ROM at f7640000 [disabled] [size=128K]
Capabilities: <access denied>
Kernel driver in use: amdgpu
Kernel modules: radeon, amdgpu

05:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Subsystem: Hightech Information System Ltd. Cape Verde/Pitcairn HDMI Audio [Radeon HD 7700/7800 Series]
Flags: bus master, fast devsel, latency 0, IRQ 43
Memory at f7660000 (64-bit, non-prefetchable) [size=16K]
Capabilities: <access denied>
Kernel driver in use: snd_hda_intel
Kernel modules: snd_hda_intel

[/i]
ID: 1837393 · Report as offensive
Profile Mitchell Tuckness
Volunteer tester
Avatar

Send message
Joined: 16 Apr 99
Posts: 46
Credit: 21,421,544
RAC: 5
United States
Message 1837394 - Posted: 22 Dec 2016, 22:11:59 UTC

Looks like there is a GPU thread, if possible this could be moved there if needed!
ID: 1837394 · Report as offensive
Profile Mitchell Tuckness
Volunteer tester
Avatar

Send message
Joined: 16 Apr 99
Posts: 46
Credit: 21,421,544
RAC: 5
United States
Message 1837868 - Posted: 25 Dec 2016, 17:26:25 UTC

No one has any ideas? Seems a waste of GPU's by them constantly failing, arg, I know there is a reason Linux can get frustrating and great, when it works and when it doesn't. Maybe I should revert to Ubuntu 14 instead of 16 and see. I just wish I knew if it was hardware or driver.
ID: 1837868 · Report as offensive
Profile Brent Norman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 2786
Credit: 685,657,289
RAC: 835
Canada
Message 1837873 - Posted: 25 Dec 2016, 17:52:02 UTC - in response to Message 1837868.  

This discussion is about NVIDIA, but I would think the same procedure should work for ATI.
http://setiathome.berkeley.edu/forum_thread.php?id=80464&postid=1831817
ID: 1837873 · Report as offensive
TBar
Volunteer tester

Send message
Joined: 22 May 99
Posts: 5204
Credit: 840,779,836
RAC: 2,768
United States
Message 1837877 - Posted: 25 Dec 2016, 18:18:59 UTC - in response to Message 1837868.  

No one has any ideas? Seems a waste of GPU's by them constantly failing, arg, I know there is a reason Linux can get frustrating and great, when it works and when it doesn't. Maybe I should revert to Ubuntu 14 instead of 16 and see. I just wish I knew if it was hardware or driver.

Yes, I think Ubuntu 14.04.x would be a much better choice. Ubuntu/AMD completely changed the drivers with 16.04. None of the older Working fglrx drivers work with 16.04, and from what I've seen the New AMD drivers aren't working very well. The best choice would be to use the OS that has known working drivers for your GPUs. You should be fine with Ubuntu 14.04.5, the drivers from the Repository, and applying this fix for multiple GPUs, http://setiathome.berkeley.edu/forum_thread.php?id=80636&postid=1835926#1835926. If you have the BOINC problem about No GPUs found, you can probably fix that by adding a link to the OpenCL library in usr/lib named libOpenCL.so. The drivers are different, some don't have the problem with the link to the OpenCL library.
ID: 1837877 · Report as offensive
Profile Mitchell Tuckness
Volunteer tester
Avatar

Send message
Joined: 16 Apr 99
Posts: 46
Credit: 21,421,544
RAC: 5
United States
Message 1837912 - Posted: 25 Dec 2016, 23:33:09 UTC - in response to Message 1837877.  

Thanks, unfortunately I just realized I can't revert on this system due to it running Zoneminder and the changes to that would be too great and the board in this system is the only one that supports quad Video cards. I guess I can yank them out and distribute them around to other PC's if I have any not running 16.04.
ID: 1837912 · Report as offensive
Profile jason_gee
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 24 Nov 06
Posts: 7489
Credit: 91,093,184
RAC: 0
Australia
Message 1837980 - Posted: 26 Dec 2016, 14:30:34 UTC
Last modified: 26 Dec 2016, 14:55:03 UTC

Not sure if related/useful, but I've been wrestling getting 16.04 LTS operational (with X) on my 2009 Mac Pro, on which the primary GPU is a Radeon HD5870.

[Edit:] info sourced from https://laanwj.github.io/2016/05/06/opencl-ubuntu1604.html

The path things led down for this particular setup let to first finding the propietary AMD drivers for this older gen aren't out for 16.04 yet, though there is apparently OpenCL support for this in the newest Open Source drivers. I've not loaded up Boinc on the Linux host yet, but did manage to get OpenCL responding via some gymnastics:
[Edit:]
I did (likely some unneeded redundancy installing old then a newer ppa):
~$ sudo apt-get install mesa-utils
~$ sudo apt-get update
~$ sudo apt-get install mesa-utils
~$ sudo apt-get install mesa-opencl-icd
~$ sudo add-apt-repository ppa:paulo-miguel-dias/mesa
~$ sudo apt-get update
~$ sudo apt-get install libclc-amdgcn mesa-opencl-icd
~$ sudo apt-get install opencl-headers


Then compiled a small program to list the openCL device, and I get this:
$ gcc devices.c -o hello -O2 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 
$ ls
devices.c  hello
$ ./hello 
1. Platform
  Profile: FULL_PROFILE
  Version: OpenCL 1.1 Mesa 13.1.0-devel - padoka PPA
  Name: Clover
  Vendor: Mesa
  Extensions: cl_khr_icd
1. Device: AMD CYPRESS (DRM 2.43.0 / 4.4.0-57-generic, LLVM 4.0.0)
 1.1 Hardware version: OpenCL 1.1 Mesa 13.1.0-devel - padoka PPA
 1.2 Software version: 13.1.0-devel - padoka PPA
 1.3 OpenCL C version: OpenCL C 1.1 
 1.4 Parallel compute units: 10


Pretty sure newest devices have AMD drivers somewhere, but in my case even basic opencl1.1 enumeration is enough, since I don't really intend to crunch on the HD5870, ... during Australian summer anyway. Will probably try get Boinc up and running, and see if it'll detect these drivers/platforms in the morning.
"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.
ID: 1837980 · Report as offensive
Profile jason_gee
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 24 Nov 06
Posts: 7489
Credit: 91,093,184
RAC: 0
Australia
Message 1837988 - Posted: 26 Dec 2016, 15:34:31 UTC

[A bit Later:] Looks promising so far, with:
Tue 27 Dec 2016 01:52:29 ACDT | | Starting BOINC client version 7.6.31 for x86_64-pc-linux-gnu
Tue 27 Dec 2016 01:52:29 ACDT | | log flags: file_xfer, sched_ops, task
Tue 27 Dec 2016 01:52:29 ACDT | | Libraries: libcurl/7.47.0 OpenSSL/1.0.2g zlib/1.2.8 libidn/1.32 librtmp/2.3
Tue 27 Dec 2016 01:52:29 ACDT | | Data directory: /var/lib/boinc-client
Tue 27 Dec 2016 01:52:29 ACDT | | OpenCL: AMD/ATI GPU 0: AMD CYPRESS (DRM 2.43.0 / 4.4.0-57-generic, LLVM 4.0.0) (driver version 13.1.0-devel - padoka PPA, device version OpenCL 1.1 Mesa 13.1.0-devel - padoka PPA, 1024MB, 1024MB available, 680 GFLOPS peak)
Tue 27 Dec 2016 01:52:29 ACDT | | Creating new client state file
Tue 27 Dec 2016 01:52:29 ACDT | | Host name: jason-MacPro-Ubuntu
Tue 27 Dec 2016 01:52:29 ACDT | | Processor: 16 GenuineIntel Intel(R) Xeon(R) CPU X5677 @ 3.47GHz [Family 6 Model 44 Stepping 2]
Tue 27 Dec 2016 01:52:29 ACDT | | 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 arch_perfmon pebs bts nopl xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt aes lahf_lm tpr_shadow vnmi flexpriority ept vpid dtherm ida arat
Tue 27 Dec 2016 01:52:29 ACDT | | OS: Linux: 4.4.0-57-generic
Tue 27 Dec 2016 01:52:29 ACDT | | Memory: 31.41 GB physical, 61.99 GB virtual
...
Tue 27 Dec 2016 01:57:17 ACDT | SETI@home | Requesting new tasks for CPU and AMD/ATI GPU
...

No tasks for GPU yet... have dialled down the CPUs to use, and will see if it gets any.
"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.
ID: 1837988 · Report as offensive
TBar
Volunteer tester

Send message
Joined: 22 May 99
Posts: 5204
Credit: 840,779,836
RAC: 2,768
United States
Message 1837992 - Posted: 26 Dec 2016, 16:51:08 UTC - in response to Message 1837988.  

Nice to see the Open Source drivers showing potential. AMD classified everything lower than the Series 7 cards as Legacy long before Ubuntu 16.04 was released. As far as I know there aren't any AMD plans to support the Legacy cards with the New AMD drivers required for 16.04. That means if you have GPUs lower than Series 7, such as my 6870 and your 5870, AMD will not be releasing Drivers for 16.04. The New AMD drivers do support the OPs Series 7+ GPUs, it's just as with most major changes they don't work very well at present. I'd say give them a year...or two, and they might have them working correctly. That's why every AMD RX480 I've seen running in Ubuntu 16.04 is running at Half the Clock Speed and using Half the Compute Units as they do in Windows...Bad Drivers.

My 6870 is working quite well in Ubuntu 14.04 with the older fglrx driver, it works well on my 2008 Mac Pro with Ubuntu 14.04 as well. If you do get the Open Source driver to work in 16.04 you can compare it to my Device 0 here, https://setiathome.berkeley.edu/results.php?hostid=6906726&state=2. On that machine the 6870 is device 0 and the 6850 is device 1. The 6870 is pretty comparable to your 5870. It would be nice if the Open Source driver was faster, but, I'm not holding my breath ;-)
ID: 1837992 · Report as offensive
Profile jason_gee
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 24 Nov 06
Posts: 7489
Credit: 91,093,184
RAC: 0
Australia
Message 1837994 - Posted: 26 Dec 2016, 17:05:49 UTC - in response to Message 1837992.  

Yeah pretty Interesting situation. If I am forced to go 14.04 (which is more familiar to me) I'll probably end up doing so, however looks like the 2009 Mac Pro EFI/firmware/devices and 14.04 aren't friends, while 16.04 picks everything up fine (even the wifi). Would need to do some more research, or switch distro altogether if it comes to it. Fortunately have managed to familiarise with rEFInd boot manager pretty quickly. (Why can't Grub be made more like that ....)

Either way, there seem to be interesting comments that AMD made all the information available to create the Open Source drivers. Not entirely sure what will happen when a GPU task finally hits. It could be messy, lol.
"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.
ID: 1837994 · Report as offensive
Profile jason_gee
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 24 Nov 06
Posts: 7489
Credit: 91,093,184
RAC: 0
Australia
Message 1838073 - Posted: 27 Dec 2016, 3:51:06 UTC
Last modified: 27 Dec 2016, 3:53:44 UTC

next morning, and no amd/ati tasks, so I installed drivers for the 1050ti (making sure to use the --no-opengl-files option, so as not to break the desktop running on the Radeon). Lo' and behold, I receive nv openCL marked tasks straight away, which so far appear to be running as expected at defaults (will see when some finish). nvidia-smi confirms the process is running, and a temp rise on the device anyway.

Interestingly the application appears to see the radeon Cypress (still using the Open source driver), so guess some Boinc/scheduler limitation prevents me getting AMD marked tasks. Maybe will try under anon platform at some point just to see what happens (but not a priority).

As is, running the 1050ti for Compute & development, and the Radeon for display-only, is how I'd like to run anyway, So I'll probably stick on 16.04 LTS for now. At least until nv get something for the 1050ti on Sierra/el capitan, or I get around to dropping in the other spare SSD with Win10 on it.
"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.
ID: 1838073 · Report as offensive
Juha
Volunteer tester

Send message
Joined: 7 Mar 04
Posts: 388
Credit: 1,857,738
RAC: 0
Finland
Message 1838338 - Posted: 28 Dec 2016, 21:14:03 UTC - in response to Message 1838073.  

Interestingly the application appears to see the radeon Cypress (still using the Open source driver), so guess some Boinc/scheduler limitation prevents me getting AMD marked tasks. Maybe will try under anon platform at some point just to see what happens (but not a priority).


Multibeam plan classes are set up so that only AMD cards running with Catalyst/fglrx match them. I think there is one Astropulse plan class that can match Mesa but Astropulse AMD app doesn't work with Mesa. It's been a while since I last looked at it but I think the app is using some AMD specific compiler switch that Mesa doesn't like. Multibeam app is probably using the same compiler switches so I would keep my expectations low even if you go anon platform way.
ID: 1838338 · Report as offensive
Profile jason_gee
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 24 Nov 06
Posts: 7489
Credit: 91,093,184
RAC: 0
Australia
Message 1838387 - Posted: 29 Dec 2016, 2:10:00 UTC - in response to Message 1838338.  

Interestingly the application appears to see the radeon Cypress (still using the Open source driver), so guess some Boinc/scheduler limitation prevents me getting AMD marked tasks. Maybe will try under anon platform at some point just to see what happens (but not a priority).


Multibeam plan classes are set up so that only AMD cards running with Catalyst/fglrx match them. I think there is one Astropulse plan class that can match Mesa but Astropulse AMD app doesn't work with Mesa. It's been a while since I last looked at it but I think the app is using some AMD specific compiler switch that Mesa doesn't like. Multibeam app is probably using the same compiler switches so I would keep my expectations low even if you go anon platform way.


Seems reasonable. I wonder if an intel iGPU or NV build would work (tweaked build or otherwise). The same thing here as with Cuda is rubbing me the wrong way, which is the massive segmentation induced maintenance overhead, for what should be heading toward heterogeneous implementations. Well at least my FrankenMac experiment is starting to pay off, saying there are holes in both the Mac and Linux platforms. I'll be a little taken aback if when I put the last spare SSD in with Windows, both the Radeon and the 1050ti work. I suppose I shouldn't be all that surprised, with the gaming market driving things.
"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.
ID: 1838387 · Report as offensive

Message boards : Number crunching : Help with Ubuntu 16.04 TLS & Headless GPU Computing


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.