Advanced search

Message boards : News : New Beta app for AMD GPUs

Author Message
Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39746 - Posted: 27 Jan 2015 | 14:55:54 UTC

Hi,

If you've an AMD graphics card, please subscribe to beta applications and see if you get the "amdmd" application. For now, it's just a place-holder, but this'll change soon.

Matt

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39747 - Posted: 27 Jan 2015 | 15:50:04 UTC

Will do with pleasure :)

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39750 - Posted: 27 Jan 2015 | 16:18:02 UTC

The Server tells me that i should update my driver. I got the AMD Catalyst 14.12 which is the latest (non Beta) driver.

So could you please fix this?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39751 - Posted: 27 Jan 2015 | 16:26:49 UTC - in response to Message 39750.

lolmaster - what's your computer ID?

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39753 - Posted: 27 Jan 2015 | 16:49:44 UTC - in response to Message 39751.

196772

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39754 - Posted: 27 Jan 2015 | 16:57:36 UTC - in response to Message 39753.

Do you have the amdmd application selected too?

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39755 - Posted: 27 Jan 2015 | 17:02:59 UTC
Last modified: 27 Jan 2015 | 17:04:28 UTC

Use ATI GPU: yes

Use Testapplication: yes

Run only the selected applications: all (no amdmd selectable)

If no work for selected applications is available, accept work from other applications?: yes

Use Graphics Processing Unit (GPU) if available: yes

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39758 - Posted: 27 Jan 2015 | 17:11:45 UTC - in response to Message 39755.

keep banging on "update", the server's going to need some fettling.

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39759 - Posted: 27 Jan 2015 | 17:13:01 UTC

2015-01-27 18:12:05 | GPUGRID | Requesting new tasks for AMD/ATI GPU
2015-01-27 18:12:07 | GPUGRID | Scheduler request completed: got 0 new tasks
2015-01-27 18:12:07 | GPUGRID | No tasks sent
2015-01-27 18:12:07 | GPUGRID | No tasks are available for Short runs (2-3 hours on fastest card)
2015-01-27 18:12:07 | GPUGRID | No tasks are available for ACEMD beta version
2015-01-27 18:12:07 | GPUGRID | No tasks are available for Long runs (8-12 hours on fastest card)


There is no work already?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39760 - Posted: 27 Jan 2015 | 17:26:08 UTC - in response to Message 39759.

You need to go subscribe to the project on your preferences page. It's "Molecular Dynamics on AMD GPUs"

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39761 - Posted: 27 Jan 2015 | 17:30:05 UTC

Strange thing. I have checked preferences 10 minutes ago and there wasn't this option. Now it is. I'm 100% sure.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39762 - Posted: 27 Jan 2015 | 17:30:49 UTC - in response to Message 39761.

Yeah, I just added it...

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39764 - Posted: 27 Jan 2015 | 17:33:46 UTC

That explains a lot :)

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39766 - Posted: 27 Jan 2015 | 17:56:20 UTC
Last modified: 27 Jan 2015 | 18:01:07 UTC

The error still exists. Sometimes when i hit update everything is fine an sometimes i get the error i described ...

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39769 - Posted: 27 Jan 2015 | 19:06:32 UTC - in response to Message 39750.

The Server tells me that i should update my driver. I got the AMD Catalyst 14.12 which is the latest (non Beta) driver.


Same story here.

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39774 - Posted: 27 Jan 2015 | 20:18:07 UTC

1/27/2015 2:19:46 PM | GPUGRID | update requested by user
1/27/2015 2:19:49 PM | GPUGRID | Sending scheduler request: Requested by user.
1/27/2015 2:19:49 PM | GPUGRID | Requesting new tasks for CPU and AMD/ATI GPU
1/27/2015 2:19:50 PM | GPUGRID | Scheduler request completed: got 0 new tasks
1/27/2015 2:19:50 PM | GPUGRID | No tasks sent


Cheers!
____________

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39775 - Posted: 27 Jan 2015 | 20:44:55 UTC - in response to Message 39774.

No idea why the scheduler's not playing ball. Will look tomorrow.

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39780 - Posted: 27 Jan 2015 | 23:05:07 UTC

Thought this might help. I am getting an http error.

1/27/2015 4:37:03 PM | GPUGRID | Sending scheduler request: To fetch work.
1/27/2015 4:37:03 PM | GPUGRID | Requesting new tasks for AMD/ATI GPU
1/27/2015 4:37:03 PM | GPUGRID | [http] HTTP_OP::init_post(): http://www.ps3grid.net/PS3GRID_cgi/cgi
1/27/2015 4:37:03 PM | GPUGRID | [http] HTTP_OP::libcurl_exec(): ca-bundle set
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Adding handle: conn: 0x6148440
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Adding handle: send: 0
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Adding handle: recv: 0
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Curl_addHandleToPipeline: length: 1
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: - Conn 10398 (0x6148440) send_pipe: 1, recv_pipe: 0
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: About to connect() to www.ps3grid.net port 80 (#10398)
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Trying 193.146.190.61...
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Info: Connected to www.ps3grid.net (193.146.190.61) port 80 (#10398)
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: POST /PS3GRID_cgi/cgi HTTP/1.1
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: User-Agent: BOINC client (windows_x86_64 7.4.27)
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Host: www.ps3grid.net
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Accept: */*
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Accept-Encoding: deflate, gzip
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Content-Type: application/x-www-form-urlencoded
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Accept-Language: en_US
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Content-Length: 17471
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server: Expect: 100-continue
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Sent header to server:
1/27/2015 4:37:03 PM | GPUGRID | [http] [ID#1] Received header from server: HTTP/1.1 100 Continue
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: HTTP/1.1 500 Internal Server Error
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: Date: Tue, 27 Jan 2015 22:35:24 GMT
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Info: Server Apache/2.2.3 (CentOS) is not blacklisted
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: Server: Apache/2.2.3 (CentOS)
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: Content-Length: 614
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: Connection: close
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server: Content-Type: text/html; charset=iso-8859-1
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Received header from server:
1/27/2015 4:37:04 PM | GPUGRID | [http] [ID#1] Info: Closing connection 10398
1/27/2015 4:37:05 PM | GPUGRID | Scheduler request failed: HTTP internal server error


Running Windows 7, an AMD 6950 GPU with Catalyst 13.1 drivers. Please let me know if I need to update my drivers.

Finally was able to download 2 AMD GPU jobs. Both ran for a few seconds then aborted with a computation error. Computer number is 169280.

<core_client_version>7.4.27</core_client_version>
<![CDATA[
<message>
(unknown error) - exit code -1073741701 (0xc000007b)
</message>
]]>

Let me know if you want me to try something different.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 13,417,802,393
RAC: 71,624,153
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39781 - Posted: 27 Jan 2015 | 23:07:01 UTC


Four units errored in few seconds

<core_client_version>7.2.42</core_client_version>
<![CDATA[
<message>
Función incorrecta.
(0x1) - exit code 1 (0x1)
</message>
]]>

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39782 - Posted: 27 Jan 2015 | 23:16:47 UTC
Last modified: 27 Jan 2015 | 23:16:59 UTC

1108 GPUGRID 1/27/2015 6:17:32 PM Scheduler request completed: got 0 new tasks
1109 GPUGRID 1/27/2015 6:17:32 PM No tasks sent
1110 GPUGRID 1/27/2015 6:17:32 PM No tasks are available for OpenCL for AMD GPUs


:-(

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39783 - Posted: 27 Jan 2015 | 23:46:47 UTC
Last modified: 27 Jan 2015 | 23:59:36 UTC

http://www.gpugrid.net/results.php?hostid=182282

All end in errors but are coming through.

Windows 8.1 64bit. 2x 7870 2gig GPU memory each.

1/27/2015 5:46:35 PM | GPUGRID | Requesting new tasks for CPU and AMD/ATI GPU
1/27/2015 5:46:37 PM | GPUGRID | Scheduler request completed: got 4 new tasks
1/27/2015 5:46:39 PM | GPUGRID | Started download of 27-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:39 PM | GPUGRID | Started download of 154-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:43 PM | GPUGRID | Finished download of 27-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:43 PM | GPUGRID | Finished download of 154-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:43 PM | GPUGRID | Started download of 155-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:43 PM | GPUGRID | Started download of 72-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:46:43 PM | GPUGRID | [coproc] Assigning ATI instance 0 to 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1
1/27/2015 5:46:43 PM | GPUGRID | [coproc] Assigning ATI instance 1 to 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1
1/27/2015 5:46:43 PM | GPUGRID | Starting task 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1
1/27/2015 5:46:45 PM | GPUGRID | Computation for task 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1 finished
1/27/2015 5:46:45 PM | GPUGRID | Output file 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1_0 for task 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1 absent
1/27/2015 5:46:45 PM | GPUGRID | Output file 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1_1 for task 154-MJHARVEY_AMDDHFR3-0-1-RND5863_1 absent
1/27/2015 5:46:45 PM | GPUGRID | [coproc] Assigning ATI instance 0 to 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1
1/27/2015 5:47:01 PM | GPUGRID | [coproc] Assigning ATI instance 0 to 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1
1/27/2015 5:47:01 PM | GPUGRID | Starting task 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1
1/27/2015 5:47:02 PM | GPUGRID | Computation for task 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1 finished
1/27/2015 5:47:02 PM | GPUGRID | Output file 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1_0 for task 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1 absent
1/27/2015 5:47:02 PM | GPUGRID | Output file 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1_1 for task 27-MJHARVEY_AMDDHFR3-0-1-RND4509_1 absent
1/27/2015 5:47:25 PM | GPUGRID | Finished download of 72-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:47:25 PM | GPUGRID | [coproc] Assigning ATI instance 0 to 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1
1/27/2015 5:47:25 PM | GPUGRID | Starting task 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1
1/27/2015 5:47:26 PM | GPUGRID | Computation for task 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1 finished
1/27/2015 5:47:26 PM | GPUGRID | Output file 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1_0 for task 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1 absent
1/27/2015 5:47:26 PM | GPUGRID | Output file 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1_1 for task 72-MJHARVEY_AMDDHFR3-0-1-RND2692_1 absent
1/27/2015 5:47:45 PM | GPUGRID | Finished download of 155-MJHARVEY_AMDDHFR3-0-input
1/27/2015 5:47:45 PM | GPUGRID | [coproc] Assigning ATI instance 0 to 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1
1/27/2015 5:47:45 PM | GPUGRID | Starting task 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1
1/27/2015 5:47:46 PM | GPUGRID | Computation for task 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1 finished
1/27/2015 5:47:46 PM | GPUGRID | Output file 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1_0 for task 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1 absent
1/27/2015 5:47:46 PM | GPUGRID | Output file 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1_1 for task 155-MJHARVEY_AMDDHFR3-0-1-RND6671_1 absent

____________

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39785 - Posted: 28 Jan 2015 | 0:13:52 UTC

Still getting nada. Win 7 64bit R270X.

Profile Sabroe_SMC
Send message
Joined: 30 Aug 08
Posts: 24
Credit: 562,737,085
RAC: 1,952
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39787 - Posted: 28 Jan 2015 | 4:44:05 UTC

I've got 34 Jobs but all errored out with error 201 "Exit_missing_coproc"

Name 60-MJHARVEY_AMDDHFR3-0-1-RND0004_0
Arbeitspaket 10595434
Erstellt 27 Jan 2015 | 16:56:30 UTC
Gesendet 27 Jan 2015 | 23:00:21 UTC
Empfangen 27 Jan 2015 | 23:00:58 UTC
Serverstatus Abgeschlossen
Resultat Berechnungsfehler
Clientstatus Abbruch durch Benutzer
Endstatus 201 (0xc9) EXIT_MISSING_COPROC
Computer ID 196795
Ablaufdatum 7 Apr 2015 | 23:00:21 UTC
Laufzeit 0.00
CPU Zeit 0.00
Prüfungsstatus Ungültig
Punkte 0.00
Anwendungsversion OpenCL for AMD GPUs v9.05 (ati)
Stderr Ausgabe
<core_client_version>7.4.36</core_client_version>

Viktor Svantner
Send message
Joined: 13 Feb 11
Posts: 25
Credit: 7,511,012,523
RAC: 26,197
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39788 - Posted: 28 Jan 2015 | 6:35:31 UTC

Hello.

It doesn't work for me either... (2 290x sapphire).

It says:

28.1.2015 7:31:13 | | cc_config.xml not found - using defaults
28.1.2015 7:31:13 | | Starting BOINC client version 7.2.42 for windows_x86_64
28.1.2015 7:31:13 | | log flags: file_xfer, sched_ops, task
28.1.2015 7:31:13 | | Libraries: libcurl/7.25.0 OpenSSL/1.0.1 zlib/1.2.6
28.1.2015 7:31:13 | | Data directory: C:\ProgramData\BOINC
28.1.2015 7:31:13 | |
28.1.2015 7:31:13 | | OpenCL: AMD/ATI GPU 0: Hawaii (driver version 1573.4 (VM), device version OpenCL 1.2 AMD-APP (1573.4), 3072MB, 3072MB available, 3626 GFLOPS peak)
28.1.2015 7:31:13 | | OpenCL: AMD/ATI GPU 1: Hawaii (driver version 1573.4 (VM), device version OpenCL 1.2 AMD-APP (1573.4), 3072MB, 3072MB available, 3626 GFLOPS peak)
28.1.2015 7:31:13 | | OpenCL CPU: Intel(R) Xeon(R) CPU E3-1241 v3 @ 3.50GHz (OpenCL driver vendor: Advanced Micro Devices, Inc., driver version 1573.4 (sse2,avx), device version OpenCL 1.2 AMD-APP (1573.4))
28.1.2015 7:31:13 | | App version needs CAL but GPU doesn't support it
28.1.2015 7:31:13 | GPUGRID | Application uses missing ATI GPU
28.1.2015 7:31:13 | |
28.1.2015 7:31:13 | | Processor: 8 GenuineIntel Intel(R) Xeon(R) CPU E3-1241 v3 @ 3.50GHz [Family 6 Model 60 Stepping 3]
28.1.2015 7:31:13 | | 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 smx tm2 pbe
28.1.2015 7:31:13 | | OS: Microsoft Windows 7: Home Premium x64 Edition, Service Pack 1, (06.01.7601.00)
28.1.2015 7:31:13 | | Memory: 15.95 GB physical, 31.90 GB virtual
28.1.2015 7:31:13 | | Disk: 232.88 GB total, 165.61 GB free
28.1.2015 7:31:13 | | Local time is UTC +1 hours

Any idea?

Profile Mumak
Avatar
Send message
Joined: 7 Dec 12
Posts: 92
Credit: 225,897,225
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 39793 - Posted: 28 Jan 2015 | 9:36:43 UTC
Last modified: 28 Jan 2015 | 9:41:35 UTC

Wow, finally an OpenCL app, so GPUGrid will deserve it's name ;-)
I'm curious how the HD 280(X)/290(X) will compete here against NVIDIA's top cards..

No tasks here either. GPU is 280X.


GPUGRID 1/28/2015 10:42:35 AM Requesting new tasks for ATI
GPUGRID 1/28/2015 10:42:37 AM Scheduler request completed: got 0 new tasks
GPUGRID 1/28/2015 10:42:37 AM No tasks sent
GPUGRID 1/28/2015 10:42:37 AM No tasks are available for ACEMD beta version
GPUGRID 1/28/2015 10:42:37 AM No tasks are available for Long runs (8-12 hours on fastest card)
GPUGRID 1/28/2015 10:42:37 AM No tasks are available for OpenCL for AMD GPUs

saiz
Send message
Joined: 25 Nov 10
Posts: 1
Credit: 1,054,210,939
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39799 - Posted: 28 Jan 2015 | 14:16:59 UTC

2015/1/28 22:12:48 | | CUDA: NVIDIA GPU 0: GeForce GTX 970 (driver version 347.25, CUDA version 7.0, compute capability 5.2, 4096MB, 3844MB available, 4508 GFLOPS peak)
2015/1/28 22:12:48 | | CAL: ATI GPU 0: AMD Radeon HD 7870/7950/7970/R9 280X series (Tahiti) (CAL version 1.4.1848, 3072MB, 3032MB available, 8602 GFLOPS peak)
2015/1/28 22:12:48 | | OpenCL: NVIDIA GPU 0: GeForce GTX 970 (driver version 347.25, device version OpenCL 1.1 CUDA, 4096MB, 3844MB available, 4508 GFLOPS peak)
2015/1/28 22:12:48 | | OpenCL: AMD/ATI GPU 0: AMD Radeon HD 7870/7950/7970/R9 280X series (Tahiti) (driver version 1642.5 (VM), device version OpenCL 1.2 AMD-APP (1642.5), 3072MB, 3032MB available, 8602 GFLOPS peak)
2015/1/28 22:12:48 | | OpenCL CPU: Intel(R) Core(TM) i5-2550K CPU @ 3.40GHz (OpenCL driver vendor: Advanced Micro Devices, Inc., driver version 1642.5 (sse2,avx), device version OpenCL 1.2 AMD-APP (1642.5))
2015/1/28 22:13:00 | GPUGRID | update requested by user
2015/1/28 22:13:04 | GPUGRID | Sending scheduler request: Requested by user.
2015/1/28 22:13:04 | GPUGRID | Requesting new tasks for NVIDIA GPU and AMD/ATI GPU
2015/1/28 22:13:12 | GPUGRID | Scheduler request completed: got 0 new tasks
2015/1/28 22:13:12 | GPUGRID | No tasks sent
2015/1/28 22:13:12 | GPUGRID | This computer has reached a limit on tasks in progress


970 running one task with three left,it turns out that 7950 fails to fetch more.[/code]

Old man
Send message
Joined: 24 Jan 09
Posts: 42
Credit: 16,676,387
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39800 - Posted: 28 Jan 2015 | 14:17:50 UTC

No tasks. :(

I need wait now.

SETI.USA Hydra
Send message
Joined: 31 Jan 12
Posts: 1
Credit: 50,280,716
RAC: 0
Level
Thr
Scientific publications
watwat
Message 39801 - Posted: 28 Jan 2015 | 16:04:46 UTC

4 work units received, all failed with computation errors. Running HD 7950 at stock clocks on Win7 64.
http://www.gpugrid.net/show_host_detail.php?hostid=196866

Profile Stoneageman
Avatar
Send message
Joined: 25 May 09
Posts: 224
Credit: 34,057,224,498
RAC: 0
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39803 - Posted: 28 Jan 2015 | 18:01:22 UTC

All 39 errored on W7
Incorrect function.
(0x1) - exit code 1 (0x1)

Did not get any on Linux hosts.

zablociak
Send message
Joined: 2 Jul 12
Posts: 9
Credit: 302,966,028
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39806 - Posted: 28 Jan 2015 | 18:20:49 UTC

W7 64bit, AMD 7970 @1000 MHz.
All WUs fail without even touching the GPU core with computation error:

28-Jan-15 19:14:57 | GPUGRID | Starting task 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7
28-Jan-15 19:14:58 | GPUGRID | Computation for task 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7 finished
28-Jan-15 19:14:58 | GPUGRID | Output file 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7_0 for task 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7 absent
28-Jan-15 19:14:58 | GPUGRID | Output file 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7_1 for task 44-MJHARVEY_AMDDHFR3-0-1-RND1943_7 absent
28-Jan-15 19:15:15 | GPUGRID | Starting task 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6
28-Jan-15 19:15:16 | GPUGRID | Computation for task 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6 finished
28-Jan-15 19:15:16 | GPUGRID | Output file 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6_0 for task 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6 absent
28-Jan-15 19:15:16 | GPUGRID | Output file 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6_1 for task 81-MJHARVEY_AMDDHFR3-0-1-RND5122_6 absent



Regards
Luke

Profile bcavnaugh
Send message
Joined: 8 Nov 13
Posts: 56
Credit: 1,002,640,163
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39807 - Posted: 28 Jan 2015 | 19:25:24 UTC
Last modified: 28 Jan 2015 | 19:26:24 UTC

I am told to update the newest driver and I am on the newest driver so maybe we need to install the current BETA Driver.

The current Beta is older than the current driver. Do I need to install the older Beta Version?

2 Each R9 290X GPUs

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39808 - Posted: 28 Jan 2015 | 19:36:48 UTC

Still have received no tasks. Why would these tasks need the latest driver if an older one has all the components needed? Aren't most ATI driver updates for gamers?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39809 - Posted: 28 Jan 2015 | 19:49:23 UTC

There'll be a new app along soon.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39810 - Posted: 28 Jan 2015 | 21:03:49 UTC

906 is the new app. 64b Windows only.

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39811 - Posted: 28 Jan 2015 | 21:04:53 UTC
Last modified: 28 Jan 2015 | 21:08:50 UTC

I got some wu's, all failed immediate.
http://www.gpugrid.net/result.php?resultid=13752906

<core_client_version>7.4.36</core_client_version>
<![CDATA[
<message>
(unknown error) - exit code -1073741701 (0xc000007b)
</message>
]]>

28.01.2015 07:41:12 | | CAL: ATI GPU 0: AMD Radeon HD 7870/7950/7970/R9 280X series (Tahiti) (CAL version 1.4.1848, 2048MB, 2008MB available, 7488 GFLOPS peak)

28.01.2015 07:41:12 | | OpenCL: AMD/ATI GPU 0: AMD Radeon HD 7870/7950/7970/R9 280X series (Tahiti) (driver version 1573.4 (VM), device version OpenCL 1.2 AMD-APP (1573.4), 2048MB, 2008MB available, 7488 GFLOPS peak)

Alexander

Edit: win7 x64

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39812 - Posted: 28 Jan 2015 | 21:18:28 UTC - in response to Message 39811.

Werkstatt,

Sure that is version 906?

Would you mind running mdrun-906.exe through dependency walker
http://www.dependencywalker.com/
and telling me what DLLs it's missing?

Matt

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39814 - Posted: 28 Jan 2015 | 21:35:13 UTC - in response to Message 39813.


Sure that is version 906?


Unfortunately I'm shure it was version 905
Where can I select to run only 906 version? In my preferences I can only select amd gpu and Molecular Dynamics on AMD GPUs: yes

Alexander

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39815 - Posted: 28 Jan 2015 | 21:37:38 UTC - in response to Message 39814.

Delete the binary - that will force the client will get the updated version

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39816 - Posted: 28 Jan 2015 | 21:40:35 UTC
Last modified: 28 Jan 2015 | 21:43:32 UTC

I'm just getting mdrun-905.exe and not mdrun-906.exe. Reseting the project din't help.

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39817 - Posted: 28 Jan 2015 | 21:44:03 UTC
Last modified: 28 Jan 2015 | 21:55:55 UTC

Tried a second machine. Still no tasks. Same config as other machine except the version of BOINC.



69342 GPUGRID 1/28/2015 4:44:36 PM Requesting new tasks for CPU and miner_asic and AMD/ATI GPU
69343 GPUGRID 1/28/2015 4:44:38 PM Scheduler request completed: got 0 new tasks
69344 GPUGRID 1/28/2015 4:44:38 PM No tasks sent
69345 GPUGRID 1/28/2015 4:44:38 PM No tasks are available for OpenCL for AMD GPUs

EDIT Machine just tried to download tasks. Download failed.


9481 GPUGRID 1/28/2015 4:51:52 PM [error] File vcomp100.dll has wrong size: expected 51024, got 57168
9482 GPUGRID 1/28/2015 4:51:52 PM [error] Checksum or signature error for vcomp100.dll

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39818 - Posted: 28 Jan 2015 | 21:44:22 UTC

I just enabled tha app on another pc. Same thing, got a 905 app there.

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39819 - Posted: 28 Jan 2015 | 21:47:35 UTC - in response to Message 39815.

Delete the binary - that will force the client will get the updated version


Deleted - got the same version again.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39820 - Posted: 28 Jan 2015 | 22:00:15 UTC - in response to Message 39819.

try again, please

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39821 - Posted: 28 Jan 2015 | 22:03:41 UTC - in response to Message 39820.

try again, please


Sorry, again 905

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39822 - Posted: 28 Jan 2015 | 22:08:06 UTC - in response to Message 39819.

Delete the binary - that will force the client will get the updated version


Deleted - got the same version again.

Same here.

<core_client_version>7.4.22</core_client_version>
<![CDATA[
<message>
Incorrect function.
(0x1) - exit code 1 (0x1)
</message>
]]>

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39823 - Posted: 28 Jan 2015 | 22:14:27 UTC - in response to Message 39822.

Same here as well.

Delete the binary - that will force the client will get the updated version


Deleted - got the same version again.

Same here.

<core_client_version>7.4.22</core_client_version>
<![CDATA[
<message>
Incorrect function.
(0x1) - exit code 1 (0x1)
</message>
]]>


____________

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39824 - Posted: 28 Jan 2015 | 22:16:58 UTC
Last modified: 28 Jan 2015 | 22:21:28 UTC

Get checksum download errors on one machine.


9686 GPUGRID 1/28/2015 5:15:06 PM [error] File vcomp100.dll has wrong size: expected 51024, got 57168
9687 GPUGRID 1/28/2015 5:15:06 PM [error] Checksum or signature error for vcomp100.dll
9692 GPUGRID 1/28/2015 5:15:10 PM [error] File msvcr100.dll has wrong size: expected 773968, got 829264
9693 GPUGRID 1/28/2015 5:15:10 PM [error] Checksum or signature error for msvcr100.dll
9697 GPUGRID 1/28/2015 5:15:17 PM [error] File libfftw3f-3.dll has wrong size: expected 1527650, got 2604934
9698 GPUGRID 1/28/2015 5:15:17 PM [error] Checksum or signature error for libfftw3f-3.dll

Completed downloads but computation errors on the other.

Wonder if the download errors have something to do with the BOINC version. Download errors are on 7.4.36 which uses a special asic tag in the cc_config file. [non_gpu/]

Completed downloads with computation errors are on 7.4.22

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 13,417,802,393
RAC: 71,624,153
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39826 - Posted: 28 Jan 2015 | 23:15:05 UTC

No way to download the 9.06 version. Only 9.05 which errors all units inmediately.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39831 - Posted: 29 Jan 2015 | 14:16:23 UTC - in response to Message 39826.
Last modified: 29 Jan 2015 | 14:24:32 UTC

Have another go... the app you get should be version 906 for "amdmd"
A reminder that you need to have the "Molecular Dynamics on AMD GPUs" application selected as well as "Accept beta work".

Matt

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39832 - Posted: 29 Jan 2015 | 14:48:17 UTC - in response to Message 39831.

Still getting an error.
1/29/2015 8:48:56 AM | GPUGRID | [error] App version uses non-existent ATI GPU

This is a new one.
1/29/2015 8:50:10 AM | | App version needs CAL but GPU doesn't support it

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39833 - Posted: 29 Jan 2015 | 14:59:42 UTC - in response to Message 39832.

Still getting an error.
1/29/2015 8:48:56 AM | GPUGRID | [error] App version uses non-existent ATI GPU

This is a new one.
1/29/2015 8:50:10 AM | | App version needs CAL but GPU doesn't support it



Progress of a sort. Is the app downloading at least?

[CSF] Isabelle Pierre
Send message
Joined: 22 Nov 14
Posts: 3
Credit: 33,754,350
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 39834 - Posted: 29 Jan 2015 | 15:02:18 UTC
Last modified: 29 Jan 2015 | 15:08:31 UTC

WU Download is ok but error:

http://www.gpugrid.net/result.php?resultid=13762192

29/01/2015 16:09:02 | GPUGRID | Finished download of 215-MJHARVEY_AMDDHFR3-0-input
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | Finished download of 215-MJHARVEY_AMDDHFR3-0-input
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)

We're on the right way :)

Profile Mumak
Avatar
Send message
Joined: 7 Dec 12
Posts: 92
Credit: 225,897,225
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 39835 - Posted: 29 Jan 2015 | 15:16:40 UTC

I'm still not getting anything.

[CSF] Isabelle Pierre
Send message
Joined: 22 Nov 14
Posts: 3
Credit: 33,754,350
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 39836 - Posted: 29 Jan 2015 | 15:20:38 UTC - in response to Message 39835.

I'm still not getting anything.

And then nomore WU :(

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39837 - Posted: 29 Jan 2015 | 15:28:16 UTC

Nothing here.

Seems like yesterday, there was an option in the GPUGRID preferences to "Use AMD GPU" and today that option is not there. Am I losing my mind or did the option disappear?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39838 - Posted: 29 Jan 2015 | 15:28:32 UTC - in response to Message 39834.

WU Download is ok but error:

http://www.gpugrid.net/result.php?resultid=13762192

29/01/2015 16:09:02 | GPUGRID | Finished download of 215-MJHARVEY_AMDDHFR3-0-input
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | Finished download of 215-MJHARVEY_AMDDHFR3-0-input
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)
29/01/2015 16:09:02 | GPUGRID | [error] Process creation failed: (unknown error) - error code 193 (0xc1)

We're on the right way :)


Ok, it's not going to work for you because it's 64b only.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39839 - Posted: 29 Jan 2015 | 16:31:31 UTC - in response to Message 39833.

Still getting an error.
1/29/2015 8:48:56 AM | GPUGRID | [error] App version uses non-existent ATI GPU

This is a new one.
1/29/2015 8:50:10 AM | | App version needs CAL but GPU doesn't support it



Progress of a sort. Is the app downloading at least?



Yes.

Rymorea
Send message
Joined: 17 Nov 14
Posts: 4
Credit: 18,705,675
RAC: 0
Level
Pro
Scientific publications
watwatwat
Message 39840 - Posted: 29 Jan 2015 | 16:36:31 UTC
Last modified: 29 Jan 2015 | 17:05:41 UTC

No option for use AMD GPU at preferences ? Do i miss something here ?

I have AMD radeon r9 270x but cant get beta wu.

zablociak
Send message
Joined: 2 Jul 12
Posts: 9
Credit: 302,966,028
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39841 - Posted: 29 Jan 2015 | 16:39:42 UTC
Last modified: 29 Jan 2015 | 17:24:05 UTC

Unfortunately BOINC doesnt't even download the GPU app itself (yesterday v9.05 was failing and today I resetted the project in order to get v9.06 ):

29-Jan-15 17:37:16 | GPUGRID | No tasks sent
29-Jan-15 17:37:16 | GPUGRID | No tasks are available for OpenCL for AMD GPUs


Edit:
OpencL app disappeared from http://www.gpugrid.net/apps so it can explain the problem.
Edit2:
The only available "OpenCL for AMD GPUs" app now is: 9.06 (mt)
Luke

[CSF] Isabelle Pierre
Send message
Joined: 22 Nov 14
Posts: 3
Credit: 33,754,350
RAC: 0
Level
Val
Scientific publications
watwatwatwat
Message 39842 - Posted: 29 Jan 2015 | 16:46:10 UTC - in response to Message 39838.

Ok, it's not going to work for you because it's 64b only.


Thanks @MJH for answer. So it's not for me.

Good job.

GGPA [E.R.]
Send message
Joined: 6 Jan 10
Posts: 3
Credit: 489,304,773
RAC: 0
Level
Gln
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 39843 - Posted: 29 Jan 2015 | 16:46:18 UTC
Last modified: 29 Jan 2015 | 16:47:06 UTC

I have stil this error:

ATI GPU: Aggiorna i driver all'ultima versione per eseguire i lavori che utilizzano la GPU del tuo computer (update driver to the last version)

but my driver are the last version

29/01/2015 13:50:18 | | Starting BOINC client version 7.4.36 for windows_x86_64

29/01/2015 13:50:18 | | OpenCL: AMD/ATI GPU 0: Tahiti (driver version 1642.5 (VM), device version OpenCL 1.2 AMD-APP (1642.5), 3072MB, 3072MB available, 2106 GFLOPS peak)
29/01/2015 13:50:18 | | OpenCL: AMD/ATI GPU 1: Hawaii (driver version 1642.5 (VM), device version OpenCL 2.0 AMD-APP (1642.5), 4096MB, 4096MB available, 3309 GFLOPS peak)
29/01/2015 13:50:18 | | OpenCL CPU: AMD FX(tm)-8350 Eight-Core Processor (OpenCL driver vendor: Advanced Micro Devices, Inc., driver version 1642.5 (sse2), device version OpenCL 1.2 AMD-APP (1642.5))
29/01/2015 13:50:18 | | App version needs CAL but GPU doesn't support it
29/01/2015 13:50:18 | GPUGRID | Application uses missing ATI GPU

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39844 - Posted: 29 Jan 2015 | 16:54:54 UTC - in response to Message 39843.

If you are having problems downloading the application, check the output of the job o the server. If you see this:


<![CDATA[
<message>
app_version download error: couldn't get input files:
<file_xfer_error>
<file_name>libfftw3f-3.dll</file_name>
<error_code>-200 (wrong size)</error_code>
</file_xfer_error>
<file_xfer_error>
<file_name>msvcp100.dll</file_name>
<error_code>-200 (wrong size)</error_code>
</file_xfer_error>
<file_xfer_error>
<file_name>msvcr100.dll</file_name>
<error_code>-200 (wrong size)</error_code>
</file_xfer_error>
<file_xfer_error>
<file_name>vcomp100.dll</file_name>
<error_code>-200 (wrong size)</error_code>
</file_xfer_error>

</message>
]]>


Go and delete those files from the GPUGRID project directory.
The ones we are using now differ from those used by the older CPU application, and it is confusing the client.

Profile Stoneageman
Avatar
Send message
Joined: 25 May 09
Posts: 224
Credit: 34,057,224,498
RAC: 0
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39845 - Posted: 29 Jan 2015 | 17:20:07 UTC

Errored out with the following:

Incorrect function.
(0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
BOINC wrapper for GROMACS.
Arg 0 [projects/www.gpugrid.net/mdrun-906.exe]
Arg 1 [--nthreads]
Arg 2 [8]
BOINC running with [8] threads
BOINC resolving [traj.xtc] to [traj.xtc]
BOINC resolving [topol.tpr] to [topol.tpr]
BOINC resolving [progress.log] to [progress.log]
BOINC resolving [state.cpt] to [state.cpt]
GROMACS: mdrun-906, VERSION 5.1-dev

GROMACS: mdrun-906, VERSION 5.1-dev
Executable: C:\ProgramData\BOINC\slots\12\projects\www.gpugrid.net\mdrun-906.exe

-------------------------------------------------------
Program: mdrun-906, VERSION 5.1-dev
Source file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\utility\path.cpp (line 191)
Function: bool __cdecl gmx::Path::isEquivalent(const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &,const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &)

System I/O error:
Path::isEquivalent called with two invalid files

Profile Sabroe_SMC
Send message
Joined: 30 Aug 08
Posts: 24
Credit: 562,737,085
RAC: 1,952
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39846 - Posted: 29 Jan 2015 | 17:25:17 UTC

29.01.2015 18:23:38 | GPUGRID | Requesting new tasks for CPU and AMD/ATI GPU
29.01.2015 18:23:40 | GPUGRID | Scheduler request completed: got 1 new tasks
29.01.2015 18:23:40 | GPUGRID | Your current settings do not allow tasks from this project. To fix this, you can change Project Preferences on the project's web site.
29.01.2015 18:23:42 | GPUGRID | Started download of mdrun-906.exe
29.01.2015 18:23:42 | GPUGRID | Started download of ishift.h
29.01.2015 18:23:42 | GPUGRID | Started download of libfftw3f-3.dll
29.01.2015 18:23:42 | GPUGRID | Started download of msvcp100.dll
29.01.2015 18:23:42 | GPUGRID | Started download of msvcr100.dll
29.01.2015 18:23:42 | GPUGRID | Started download of nbnxn_consts.h
29.01.2015 18:23:42 | GPUGRID | Started download of nbnxn_ocl_kernel_amd.clh
29.01.2015 18:23:42 | GPUGRID | Started download of nbnxn_ocl_kernel_nowarp.clh
29.01.2015 18:23:42 | GPUGRID | Started download of nbnxn_ocl_kernel_nvidia.clh
29.01.2015 18:23:42 | GPUGRID | Started download of nbnxn_ocl_kernels.clh
29.01.2015 18:23:43 | GPUGRID | Finished download of nbnxn_consts.h
29.01.2015 18:23:43 | GPUGRID | Finished download of nbnxn_ocl_kernel_amd.clh
29.01.2015 18:23:43 | GPUGRID | Finished download of nbnxn_ocl_kernel_nowarp.clh
29.01.2015 18:23:43 | GPUGRID | Started download of nbnxn_ocl_kernels.cl
29.01.2015 18:23:43 | GPUGRID | Started download of nbnxn_ocl_kernels_fastgen.clh
29.01.2015 18:23:43 | GPUGRID | Started download of nbnxn_ocl_kernel_utils.clh
29.01.2015 18:23:44 | GPUGRID | Finished download of nbnxn_ocl_kernel_nvidia.clh
29.01.2015 18:23:44 | GPUGRID | Finished download of nbnxn_ocl_kernels.cl
29.01.2015 18:23:44 | GPUGRID | Finished download of nbnxn_ocl_kernels_fastgen.clh
29.01.2015 18:23:44 | GPUGRID | Finished download of nbnxn_ocl_kernel_utils.clh
29.01.2015 18:23:44 | GPUGRID | Started download of OpenCL.dll
29.01.2015 18:23:44 | GPUGRID | Started download of vcomp100.dll
29.01.2015 18:23:44 | GPUGRID | Started download of vectype_ops.clh
29.01.2015 18:23:44 | GPUGRID | Started download of 166-MJHARVEY_AMDDHFR3-0-input
29.01.2015 18:23:45 | GPUGRID | Finished download of msvcp100.dll
29.01.2015 18:23:45 | GPUGRID | Finished download of msvcr100.dll
29.01.2015 18:23:45 | GPUGRID | Finished download of OpenCL.dll
29.01.2015 18:23:45 | GPUGRID | Finished download of vcomp100.dll
29.01.2015 18:23:45 | GPUGRID | Finished download of vectype_ops.clh
29.01.2015 18:23:45 | GPUGRID | Started download of logogpugrid.png
29.01.2015 18:23:45 | GPUGRID | Started download of project_1.png
29.01.2015 18:23:45 | GPUGRID | Started download of project_2.png
29.01.2015 18:23:45 | GPUGRID | Started download of project_3.png
29.01.2015 18:23:46 | GPUGRID | Finished download of ishift.h
29.01.2015 18:23:46 | GPUGRID | Finished download of nbnxn_ocl_kernels.clh
29.01.2015 18:23:46 | GPUGRID | Finished download of logogpugrid.png
29.01.2015 18:23:46 | GPUGRID | Finished download of project_1.png
29.01.2015 18:23:46 | GPUGRID | Finished download of project_2.png
29.01.2015 18:23:46 | GPUGRID | Finished download of project_3.png
29.01.2015 18:23:47 | GPUGRID | Finished download of libfftw3f-3.dll
29.01.2015 18:23:48 | GPUGRID | Finished download of 166-MJHARVEY_AMDDHFR3-0-input
29.01.2015 18:24:02 | GPUGRID | Finished download of mdrun-906.exe
29.01.2015 18:24:45 | GPUGRID | Starting task 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7
29.01.2015 18:24:48 | GPUGRID | Computation for task 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7 finished
29.01.2015 18:24:48 | GPUGRID | Output file 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7_0 for task 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7 absent
29.01.2015 18:24:48 | GPUGRID | Output file 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7_1 for task 166-MJHARVEY_AMDDHFR3-0-1-RND7742_7 absent
29.01.2015 18:25:44 | GPUGRID | work fetch suspended by user
29.01.2015 18:25:59 | GPUGRID | Sending scheduler request: To report completed tasks.
29.01.2015 18:25:59 | GPUGRID | Reporting 1 completed tasks
29.01.2015 18:25:59 | GPUGRID | Not requesting tasks: "no new tasks" requested via Manager
29.01.2015 18:26:00 | GPUGRID | Scheduler request completed

<core_client_version>7.4.36</core_client_version>
<![CDATA[
<message>
Unzul�ssige Funktion.
(0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
BOINC wrapper for GROMACS.
Arg 0 [projects/www.gpugrid.net/mdrun-906.exe]
Arg 1 [--nthreads]
Arg 2 [7]
BOINC running with [7] threads
BOINC resolving [traj.xtc] to [traj.xtc]
BOINC resolving [topol.tpr] to [topol.tpr]
BOINC resolving [progress.log] to [progress.log]
BOINC resolving [state.cpt] to [state.cpt]
GROMACS: mdrun-906, VERSION 5.1-dev

GROMACS is written by:
Emile Apol Rossen Apostolov Herman J.C. Berendsen Par Bjelkmar
Aldert van Buuren Rudi van Drunen Anton Feenstra Sebastian Fritsch
Gerrit Groenhof Christoph Junghans Peter Kasson Carsten Kutzner
Per Larsson Justin A. Lemkul Magnus Lundborg Pieter Meulenhoff
Erik Marklund Teemu Murtola Szilard Pall Sander Pronk
Roland Schulz Alexey Shvetsov Michael Shirts Alfons Sijbers
Peter Tieleman Christian Wennberg Maarten Wolf Dimitrios Karkoulis
StreamComputing (Vincent Hindriksen, Anca Hamuraru, Teemu Virolainen)
and the project leaders:
Mark Abraham, Berk Hess, Erik Lindahl, and David van der Spoel

Copyright (c) 1991-2000, University of Groningen, The Netherlands.
Copyright (c) 2001-2014, The GROMACS development team at
Uppsala University, Stockholm University and
the Royal Institute of Technology, Sweden.
check out http://www.gromacs.org for more information.

GROMACS is free software; you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License
as published by the Free Software Foundation; either version 2.1
of the License, or (at your option) any later version.

GROMACS: mdrun-906, VERSION 5.1-dev
Executable: C:\BOINC_Data\slots\10\projects\www.gpugrid.net\mdrun-906.exe

-------------------------------------------------------
Program: mdrun-906, VERSION 5.1-dev
Source file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\utility\path.cpp (line 191)
Function: bool __cdecl gmx::Path::isEquivalent(const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &,const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &)

System I/O error:
Path::isEquivalent called with two invalid files

For more information and tips for troubleshooting, please check the GROMACS
website at http://www.gromacs.org/Documentation/Errors
-------------------------------------------------------
18:24:45 (2132): called boinc_finish(1)

</stderr_txt>

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39847 - Posted: 29 Jan 2015 | 18:48:23 UTC

Now we are getting somewhere! I'll do some debugging and put out a new app shortly.

Matt

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39849 - Posted: 29 Jan 2015 | 18:58:56 UTC


1/29/2015 12:29:06 PM | | Fetching configuration file from http://www.gpugrid.net/get_project_config.php
1/29/2015 12:29:21 PM | GPUGRID | Master file download succeeded
1/29/2015 12:29:30 PM | GPUGRID | Started download of mdrun-906.exe
1/29/2015 12:29:30 PM | GPUGRID | Started download of ishift.h
1/29/2015 12:29:32 PM | GPUGRID | Finished download of ishift.h
1/29/2015 12:29:32 PM | GPUGRID | Started download of libfftw3f-3.dll
1/29/2015 12:29:40 PM | GPUGRID | Finished download of libfftw3f-3.dll
1/29/2015 12:29:40 PM | GPUGRID | Started download of msvcp100.dll
1/29/2015 12:29:44 PM | GPUGRID | Finished download of msvcp100.dll
1/29/2015 12:29:44 PM | GPUGRID | Started download of msvcr100.dll
1/29/2015 12:29:48 PM | GPUGRID | Finished download of msvcr100.dll
1/29/2015 12:29:48 PM | GPUGRID | Started download of nbnxn_consts.h
1/29/2015 12:29:49 PM | GPUGRID | Finished download of nbnxn_consts.h
1/29/2015 12:29:49 PM | GPUGRID | Started download of nbnxn_ocl_kernel_amd.clh
1/29/2015 12:29:50 PM | GPUGRID | Finished download of mdrun-906.exe
1/29/2015 12:29:50 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_amd.clh
1/29/2015 12:29:50 PM | GPUGRID | Started download of nbnxn_ocl_kernel_nowarp.clh
1/29/2015 12:29:50 PM | GPUGRID | Started download of nbnxn_ocl_kernel_nvidia.clh
1/29/2015 12:29:51 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_nowarp.clh
1/29/2015 12:29:51 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_nvidia.clh
1/29/2015 12:29:51 PM | GPUGRID | Started download of nbnxn_ocl_kernels.clh
1/29/2015 12:29:51 PM | GPUGRID | Started download of nbnxn_ocl_kernels.cl
1/29/2015 12:29:52 PM | GPUGRID | Finished download of nbnxn_ocl_kernels.clh
1/29/2015 12:29:52 PM | GPUGRID | Finished download of nbnxn_ocl_kernels.cl
1/29/2015 12:29:52 PM | GPUGRID | Started download of nbnxn_ocl_kernels_fastgen.clh
1/29/2015 12:29:52 PM | GPUGRID | Started download of nbnxn_ocl_kernel_utils.clh
1/29/2015 12:29:53 PM | GPUGRID | Finished download of nbnxn_ocl_kernels_fastgen.clh
1/29/2015 12:29:53 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_utils.clh
1/29/2015 12:29:53 PM | GPUGRID | Started download of OpenCL.dll
1/29/2015 12:29:53 PM | GPUGRID | Started download of vcomp100.dll
1/29/2015 12:29:54 PM | GPUGRID | Finished download of vcomp100.dll
1/29/2015 12:29:54 PM | GPUGRID | Started download of vectype_ops.clh
1/29/2015 12:29:56 PM | GPUGRID | Finished download of OpenCL.dll
1/29/2015 12:29:56 PM | GPUGRID | Finished download of vectype_ops.clh
1/29/2015 12:29:56 PM | GPUGRID | Started download of 34-MJHARVEY_AMDDHFR3-0-input
1/29/2015 12:29:56 PM | GPUGRID | Started download of logogpugrid.png
1/29/2015 12:29:57 PM | GPUGRID | Finished download of logogpugrid.png
1/29/2015 12:29:57 PM | GPUGRID | Started download of project_1.png
1/29/2015 12:29:58 PM | GPUGRID | Finished download of project_1.png
1/29/2015 12:29:58 PM | GPUGRID | Started download of project_2.png
1/29/2015 12:29:59 PM | GPUGRID | Finished download of project_2.png
1/29/2015 12:29:59 PM | GPUGRID | Started download of project_3.png
1/29/2015 12:30:00 PM | GPUGRID | Finished download of project_3.png
1/29/2015 12:30:00 PM | GPUGRID | No tasks sent
1/29/2015 12:30:03 PM | GPUGRID | Finished download of 34-MJHARVEY_AMDDHFR3-0-input
1/29/2015 12:30:03 PM | GPUGRID | Starting task 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7
1/29/2015 12:30:06 PM | GPUGRID | Computation for task 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7 finished
1/29/2015 12:30:06 PM | GPUGRID | Output file 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7_0 for task 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7 absent
1/29/2015 12:30:06 PM | GPUGRID | Output file 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7_1 for task 34-MJHARVEY_AMDDHFR3-0-1-RND9363_7 absent


Stderr output
<core_client_version>7.4.36</core_client_version>
<![CDATA[
<message>
Incorrect function.
(0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
BOINC wrapper for GROMACS.
Arg 0 [projects/www.gpugrid.net/mdrun-906.exe]
Arg 1 [--nthreads]
Arg 2 [6]
BOINC running with [6] threads
BOINC resolving [traj.xtc] to [traj.xtc]
BOINC resolving [topol.tpr] to [topol.tpr]
BOINC resolving [progress.log] to [progress.log]
BOINC resolving [state.cpt] to [state.cpt]
GROMACS: mdrun-906, VERSION 5.1-dev

____________

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39850 - Posted: 29 Jan 2015 | 21:18:06 UTC

Updated app 907. Still wont work, but has more debug in the output.

MJH

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39851 - Posted: 29 Jan 2015 | 21:33:19 UTC

What happened to the use AMD GPU selection from the preferences page? When I hit update BOINC doesn't even ask for OpenCl AMD tasks anymore.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39852 - Posted: 29 Jan 2015 | 21:47:32 UTC - in response to Message 39851.

What do you see? Here's what you should get:

Run only the selected applications
ACEMD short runs (2-3 hours on fastest card): no
ACEMD beta: no
ACEMD long runs (8-12 hours on fastest GPU): yes
Docking CPU only app: no
Molecular Dynamics on CPU: no
Molecular Dynamics on AMD GPUs: yes

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39853 - Posted: 29 Jan 2015 | 21:47:39 UTC

Still getting 9.06 app. GPUGRID project removed and re-attached. Still getting 9.06 app.

Anything else we need to do?

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39854 - Posted: 29 Jan 2015 | 22:04:04 UTC - in response to Message 39850.

Updated app 907. Still wont work, but has more debug in the output.

MJH

Version 9.07, as displayed on http://www.gpugrid.net/apps.php, doesn't show an ATI plan class. I suspect that will make BOINC (both server and client) treat it as a pure CPU app.

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39855 - Posted: 29 Jan 2015 | 22:11:11 UTC - in response to Message 39853.
Last modified: 29 Jan 2015 | 22:13:36 UTC

Still getting 9.06 app. GPUGRID project removed and re-attached. Still getting 9.06 app.

Anything else we need to do?

Quoted wrong post. My bad

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39856 - Posted: 29 Jan 2015 | 22:12:48 UTC - in response to Message 39852.
Last modified: 29 Jan 2015 | 22:17:29 UTC

What do you see? Here's what you should get:

Run only the selected applications
ACEMD short runs (2-3 hours on fastest card): no
ACEMD beta: no
ACEMD long runs (8-12 hours on fastest GPU): yes
Docking CPU only app: no
Molecular Dynamics on CPU: no
Molecular Dynamics on AMD GPUs: yes


This is what I see.

Resource share
Determines the proportion of your computer's resources allocated to this project. Example: if you participate in two BOINC projects with resource shares of 100 and 200, the first will get 1/3 of your resources and the second will get 2/3. 10
Use CPU
Enforced by version 6.10+ no
Use NVIDIA GPU
Enforced by version 6.10+ no
Use AMD GPU <-- This is now missing from the preferences page
Run test applications?
This helps us develop applications, but may cause jobs to fail on your computer no
Maximum CPU % for graphics
0 ... 100 20
Run only the selected applications ACEMD short runs (2-3 hours on fastest card): no
ACEMD beta: yes
ACEMD long runs (8-12 hours on fastest GPU): no
Docking CPU only app: no
Molecular Dynamics on CPU: no
Molecular Dynamics on AMD GPUs: yes
If no work for selected applications is available, accept work from other applications? no
Use Graphics Processing Unit (GPU) if available yes
Use Central Processing Unit (CPU) yes

When I hit update in the BOINC client this is what I get in the event log. No mention of AMD/ATI GPU.



77647 GPUGRID 1/29/2015 4:38:40 PM update requested by user
77648 GPUGRID 1/29/2015 4:38:41 PM Sending scheduler request: Requested by user.
77649 GPUGRID 1/29/2015 4:38:41 PM Requesting new tasks for miner_asic
77650 GPUGRID 1/29/2015 4:38:43 PM Scheduler request completed: got 0 new tasks

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39857 - Posted: 29 Jan 2015 | 22:19:12 UTC - in response to Message 39856.

Oh, don't worry about that. It's not a necessary option.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39858 - Posted: 29 Jan 2015 | 22:19:26 UTC

908's up.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39859 - Posted: 29 Jan 2015 | 22:32:37 UTC - in response to Message 39858.

Still getting:
1/29/2015 4:34:08 PM | GPUGRID | Your current settings do not allow tasks from this project. To fix this, you can change Project Preferences on the project's web site.

Profile Stoneageman
Avatar
Send message
Joined: 25 May 09
Posts: 224
Credit: 34,057,224,498
RAC: 0
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39860 - Posted: 29 Jan 2015 | 22:41:24 UTC

From BOINC:
Not requesting tasks:don't need. AMD/ATI GPU:no applications

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39861 - Posted: 29 Jan 2015 | 22:43:19 UTC

I detached and reattached. This is the first logs from the event viewer.



17980 GPUGRID 1/29/2015 5:38:59 PM Requesting new tasks for CPU and miner_asic and AMD/ATI GPU
17981 GPUGRID 1/29/2015 5:39:01 PM Scheduler request completed: got 0 new tasks
17982 GPUGRID 1/29/2015 5:39:01 PM No tasks sent
17983 GPUGRID 1/29/2015 5:39:01 PM No tasks are available for ACEMD beta version
17984 GPUGRID 1/29/2015 5:39:01 PM No tasks are available for OpenCL for AMD GPUs
17985 GPUGRID 1/29/2015 5:39:01 PM Tasks for CPU are available, but your preferences are set to not accept them

When I manually update BOINC this is what the event viewer shows. It doesn't ask for OpenCl for AMD GPUs. Same message with any following manual updates.



18001 GPUGRID 1/29/2015 5:39:35 PM update requested by user
18002 GPUGRID 1/29/2015 5:39:38 PM Sending scheduler request: Requested by user.
18003 GPUGRID 1/29/2015 5:39:38 PM Requesting new tasks for miner_asic
18004 GPUGRID 1/29/2015 5:39:40 PM Scheduler request completed: got 0 new tasks


Profile Conan
Send message
Joined: 25 Mar 09
Posts: 25
Credit: 582,385
RAC: 0
Level
Gly
Scientific publications
wat
Message 39862 - Posted: 29 Jan 2015 | 23:01:08 UTC
Last modified: 29 Jan 2015 | 23:05:30 UTC

I don't have an AMD GPU installed in my computer that just downloaded a OPEN CL AMDGPU work unit.

I only have CPU selected in my preferences as I don't allow GPU processing, the GPU I do have is an old 8800 NVIDIA just for the monitor to work.

I only have the 2 CPU apps selected in my preferences as well but somehow BOINC has downloaded an GPU app, 9.07 I think it is.

Use CPU
Enforced by version 6.10+ yes
Use NVIDIA GPU
Enforced by version 6.10+ no
Run test applications?
This helps us develop applications, but may cause jobs to fail on your computer yes
Run only the selected applications ACEMD short runs (2-3 hours on fastest card): no
ACEMD beta: no
ACEMD long runs (8-12 hours on fastest GPU): no
Docking CPU only app: yes
Molecular Dynamics on CPU: yes
Molecular Dynamics on AMD GPUs: no
If no work for selected applications is available, accept work from other applications? no
Use Graphics Processing Unit (GPU) if available no
Use Central Processing Unit (CPU) yes

Conan

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39863 - Posted: 29 Jan 2015 | 23:02:05 UTC

All (13) 9.08 tasks errored out, GPUGRID re-attached before.
Host ID 159956
Part of stderr

1 GPU detected:
#0: name: Tahiti, vendor: Advanced Micro Devices, Inc. device version: OpenCL 1.2 AMD-APP (1445.5), comp. units: 28, stat: compatible

1 compatible GPU is present, with ID 0
1 GPU auto-selected for this run.
Mapping of GPU ID to the 1 PP rank in this node: Tahiti

-------------------------------------------------------
Program mdrun-908, VERSION 5.1-dev
Source code file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_jit_support.cpp, line: 237

Fatal error:
On rank 0 failed to compile NBNXN kernels for GPU #Tahiti: OpenCL error -11
For more information and tips for troubleshooting, please check the GROMACS
website at http://www.gromacs.org/Documentation/Errors

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39865 - Posted: 29 Jan 2015 | 23:21:19 UTC - in response to Message 39863.

Thanks nenym. That's progress.

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39866 - Posted: 29 Jan 2015 | 23:39:18 UTC
Last modified: 29 Jan 2015 | 23:43:08 UTC

By the way - the <app_version> seems to be a bit weird to me.
1. missing "gpu" part maybe similar to:

<coproc>
<type>ATI</type>
<count>1.000000</count>
</coproc>
<gpu_ram>268435456.000000</gpu_ram>
<dont_throttle/>

I have noticed it before running tasks and suspended other GPU project.
2. is a reference to mdrun-907.exe file correct? It is the last reference.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39867 - Posted: 30 Jan 2015 | 0:02:50 UTC - in response to Message 39866.

By the way - the <app_version> seems to be a bit weird to me.
1. missing "gpu" part maybe similar to:

That reinforces my observation that these apps aren't being deployed as GPU apps. BOINC needs to be told what GPU resources are required, via the plan_class mechanism. If that information is supplied, then the 'Use AMD/ATI GPU' preference option will automagically reappear.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39868 - Posted: 30 Jan 2015 | 0:08:05 UTC

911 up now

kashi
Send message
Joined: 29 Jan 15
Posts: 3
Credit: 76,300,087
RAC: 0
Level
Thr
Scientific publications
wat
Message 39869 - Posted: 30 Jan 2015 | 0:25:08 UTC

That's strange, I detached and reattached and it downloaded 9.10 again.
BOINC 7.4.36, HD 7790, Catalyst 13.4.

Anyhow here's part of stderr_txt for 9.10 task which errored immediately:


1 GPU detected:
#0: name: Bonaire, vendor: Advanced Micro Devices, Inc. device version: OpenCL 1.2 AMD-APP (1124.2), comp. units: 14, stat: compatible

1 compatible GPU is present, with ID 0
1 GPU auto-selected for this run.
Mapping of GPU ID to the 1 PP rank in this node: Bonaire
Loading kernel source from .gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_kernels.cl

-------------------------------------------------------
Program mdrun-910, VERSION 5.1-dev
Source code file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_jit_support.cpp, line: 237

Fatal error:
On rank 0 failed to compile NBNXN kernels for GPU #Bonaire: OpenCL error -11

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39870 - Posted: 30 Jan 2015 | 0:28:35 UTC - in response to Message 39869.

try again please

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39871 - Posted: 30 Jan 2015 | 0:30:01 UTC

Hmm...9.10 mt or 9.11 amd?
stderr:

GROMACS: mdrun-910, VERSION 5.1-dev
Executable: E:\BOINC_data\Data\slots\15\projects\www.gpugrid.net\mdrun-910.exe
Library dir: C:\Program Files\Gromacs\share\gromacs\top
Command line:
mdrun-910 -ntomp 6 -nt 6 -x traj.xtc -s topol.tpr -g progress.log

Reading file topol.tpr, VERSION 4.6.3 (single precision)
Note: file tpx version 83, software tpx version 100
Changing nstlist from 10 to 40, rlist from 0.9 to 0.995

Using 1 MPI thread
Using 6 OpenMP threads

The current CPU can measure timings more accurately than the code in
mdrun-910 was configured to use. This might affect your simulation
speed as accurate timings are needed for load-balancing.
Please consider rebuilding mdrun-910 with the GMX_USE_RDTSCP=OFF CMake option.


1 GPU detected:
#0: name: Tahiti, vendor: Advanced Micro Devices, Inc. device version: OpenCL 1.2 AMD-APP (1445.5), comp. units: 28, stat: compatible

1 compatible GPU is present, with ID 0
1 GPU auto-selected for this run.
Mapping of GPU ID to the 1 PP rank in this node: Tahiti
Loading kernel source from .gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_kernels.cl

-------------------------------------------------------
Program mdrun-910, VERSION 5.1-dev
Source code file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_jit_support.cpp, line: 237

Fatal error:
On rank 0 failed to compile NBNXN kernels for GPU #Tahiti: OpenCL error -11
Gromacs seems to prepare multiCPU running.

Is that part of app_version correct?
<app_name>amdmd</app_name>
<version_num>910</version_num>
<platform>windows_intelx86</platform>
<avg_ncpus>1.001038</avg_ncpus>
<max_ncpus>6.000000</max_ncpus>
<flops>729447896.677004</flops>
<plan_class>mt</plan_class>
<api_version>7.5.0</api_version>
<cmdline>--nthreads 6</cmdline>

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39872 - Posted: 30 Jan 2015 | 0:33:12 UTC - in response to Message 39871.

911 is current, not 910.

yes, the app_version is just fine.

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39873 - Posted: 30 Jan 2015 | 0:37:41 UTC

9.11
part of stderr

----
clCreateProgramWithSource
Compilation of source file failed!
-- Used build options: -DWARP_SIZE_TEST=64 -D_AMD_SOURCE_ -I"C:/Program Files/Gromacs/bin/opencl" -I.gromacs\mdlib\nbnxn_ocl -I.gromacs\gmxlib\ocl_tools -I.gromacs\pbcutil -I.gromacs\mdlib
--------------LOG START---------------
"C:\Users\Vendula\AppData\Local\Temp\OCL4480T8.cl", line 57: catastrophic error:
cannot open source file "nbnxn_ocl_kernels.clh"
#include FLAVOR_LEVEL_GENERATOR
^

1 catastrophic error detected in the compilation of "C:\Users\Vendula\AppData\Local\Temp\OCL4480T8.cl".
Compilation terminated.

Frontend phase failed compilation.
---------------LOG END----------------

-------------------------------------------------------
Program mdrun-911, VERSION 5.1-dev
Source code file: ..\..\..\..\gromacs-opencl\gromacs\src\gromacs\mdlib\nbnxn_ocl\nbnxn_ocl_jit_support.cpp, line: 237

Fatal error:
On rank 0 failed to compile NBNXN kernels for GPU #Tahiti: OpenCL error -11

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39874 - Posted: 30 Jan 2015 | 0:44:00 UTC - in response to Message 39873.

912's up.

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39875 - Posted: 30 Jan 2015 | 0:57:11 UTC
Last modified: 30 Jan 2015 | 0:59:36 UTC

It has happen twice.
30/01/2015 01:58:54 | GPUGRID | Finished download of mdrun-912.exe
30/01/2015 01:58:54 | GPUGRID | [error] Signature verification failed for mdrun-912.exe
30/01/2015 01:58:54 | GPUGRID | [error] Checksum or signature error for mdrun-912.exe
std err:

app_version download error: couldn't get input files:
<file_xfer_error>
<file_name>mdrun-912.exe</file_name>
<error_code>-120 (RSA key check failed for file)</error_code>
<error_message>signature verification failed</error_message>
</file_xfer_error>

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39876 - Posted: 30 Jan 2015 | 1:02:49 UTC

and now 913.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39877 - Posted: 30 Jan 2015 | 1:05:33 UTC - in response to Message 39876.

I'm getting this error again.
1/29/2015 7:07:37 PM | GPUGRID | Your current settings do not allow tasks from this project. To fix this, you can change Project Preferences on the project's web site.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39878 - Posted: 30 Jan 2015 | 1:08:18 UTC

914

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39879 - Posted: 30 Jan 2015 | 1:11:08 UTC
Last modified: 30 Jan 2015 | 1:13:41 UTC

Why is referenced the -912 version in 9.14 app?

<file_xfer_error>
<file_name>mdrun-912.exe</file_name>
<error_code>-120 (RSA key check failed for file)</error_code>
<error_message>signature verification failed</error_message>
</file_xfer_error>


I must re-attach the project to get a new task. Could you add a profile selections for ATI/AMD GPU?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39880 - Posted: 30 Jan 2015 | 1:13:01 UTC - in response to Message 39879.

good question. try 915.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39881 - Posted: 30 Jan 2015 | 1:13:32 UTC - in response to Message 39879.

Why is referenced the -912 version in 9.14 app?
<file_xfer_error>
<file_name>mdrun-912.exe</file_name>
<error_code>-120 (RSA key check failed for file)</error_code>
<error_message>signature verification failed</error_message>
</file_xfer_error>



I'm getting this too.
1/29/2015 7:15:02 PM | GPUGRID | [error] Signature verification failed for mdrun-912.exe
1/29/2015 7:15:02 PM | GPUGRID | [error] Checksum or signature error for mdrun-912.exe

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39882 - Posted: 30 Jan 2015 | 1:15:26 UTC - in response to Message 39881.

that should be fixed with 915

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39883 - Posted: 30 Jan 2015 | 1:22:14 UTC - in response to Message 39882.

This is a good sign.
1/29/2015 7:23:58 PM | GPUGRID | Starting task 237-MJHARVEY_AMDDHFR3-0-1-RND8127_4

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39884 - Posted: 30 Jan 2015 | 1:24:52 UTC - in response to Message 39883.

Already finished and won't get any more taskes unless I detach and re-attach.

http://www.gpugrid.net/result.php?resultid=13764062

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39885 - Posted: 30 Jan 2015 | 1:26:20 UTC

Excellent, it's working.
That's it for tonight, thanks for your help.

Matt

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39886 - Posted: 30 Jan 2015 | 1:27:11 UTC
Last modified: 30 Jan 2015 | 1:28:13 UTC

Well, finished, but GPU load was very very low (time to time <20%, but mostly no GPU load, only CPU load).
I must re-attach the project to get a new task. Could you add a profile selections for ATI/AMD GPU?

Excellent, it's working.
That's it for tonight, thanks for your help.

Matt
You are welcome.

Sean
Send message
Joined: 28 Aug 10
Posts: 2
Credit: 1,150,152
RAC: 0
Level
Ala
Scientific publications
wat
Message 39887 - Posted: 30 Jan 2015 | 1:42:12 UTC

I got my first task for my 5770 but it errored out. :(




30/01/2015 12:01:22 PM | GPUGRID | Finished download of mdrun-912.exe
30/01/2015 12:01:22 PM | GPUGRID | [error] Signature verification failed for mdrun-912.exe
30/01/2015 12:01:22 PM | GPUGRID | [error] Checksum or signature error for mdrun-912.exe
30/01/2015 12:02:57 PM | GPUGRID | Sending scheduler request: To report completed tasks.

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39888 - Posted: 30 Jan 2015 | 2:39:21 UTC
Last modified: 30 Jan 2015 | 2:42:03 UTC

Finally got a task to run but now there are 2 problems.

19252 GPUGRID 1/29/2015 9:11:39 PM Starting task 196-MJHARVEY_AMDDHFR3-0-1-RND2231_5

Problem #1. There is almost no work being done on the GPU. Only an occasional spike to 12% load that lasts about 1 second. CPU load is 99%. Looks like a CPU app to me.
Problem #2. Estimated run time is 55 DAYS. (1336 hours) 0.028% complete after 30 minutes. R9 270X

I'll let it run over night but I don't hold out much hope.

http://www.gpugrid.net/result.php?resultid=13763843

Profile Sabroe_SMC
Send message
Joined: 30 Aug 08
Posts: 24
Credit: 562,737,085
RAC: 1,952
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39889 - Posted: 30 Jan 2015 | 4:54:10 UTC

http://www.gpugrid.net/result.php?resultid=13763875
First Task ready. But as was said, only liitle gpu work, mostly cpu. I set 100% cpu time for gpugrid and the wu run with all cpu-cores it could get( as mt predicted)
The max gpu was around 80% for 0,3 sec

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39893 - Posted: 30 Jan 2015 | 8:33:04 UTC

I tried to download amd wu's.
Message says: 30.01.2015 09:30:34 | GPUGRID | Not requesting tasks: don't need (CPU: job cache full; NVIDIA GPU: job cache full; AMD/ATI GPU: ; Intel GPU: job cache full)

I have no amd wu eunning, only a nvidia wu and a intel wu.

Seems that the gpu detection does not work correct. Works fine with POEM.

Refers to this pc http://www.gpugrid.net/show_host_detail.php?hostid=187043

When setting the nVidia wu to hold and manually update GPUGRID the sceduler asks for gpu wu's for nVidia and for AMD. Returned message says: no work available. nVidia wu's set to run only short runs.

Alexander

Peciak
Send message
Joined: 31 May 11
Posts: 8
Credit: 73,588,036
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39894 - Posted: 30 Jan 2015 | 9:32:11 UTC
Last modified: 30 Jan 2015 | 9:32:36 UTC

:-)
Run time 254.09
CPU time 838.10
-----------------
score 6,025.54

http://www.gpugrid.net/results.php?hostid=197040

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39895 - Posted: 30 Jan 2015 | 9:42:42 UTC
Last modified: 30 Jan 2015 | 9:53:48 UTC

The AMD application has reached a working state.

To access it you will need to change your preferences to
* enable "Accept Test work"
* enable the application "Molecular Dynamics on AMD GPUs"
* enable "Use CPU"

You will also need a 64bit Operating System, Windows 7 or higher.

Unlike the application for NVIDIA cards, this one requires as much CPU as you can assign it.[1]

For technical reasons BOINC considers this application a CPU only app - it won't show up as requiring a GPU. Despite that, you will only receive work if the client reports that the machine has an AMD GPU installed. The WU group name is AMDTEST1.

I am putting through a lot of short test WUs to start to gauge performance estimates and failure modes.


Known issues are:
* Checkpoint restart not working
* BOINC progress reporting not working
* If GPU is incompatible (HD4000/5000), will fall back to CPU execution
* No GPU assignment - will always run on first GPU in system (beware if you have mixed AMD/NVIDIA system)

Matt

[1] It's based on the old - now deprecated - CPU app, but uses a GPU for additional acceleration.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39898 - Posted: 30 Jan 2015 | 10:13:27 UTC - in response to Message 39895.

[1] It's based on the old - now deprecated - CPU app, but uses a GPU for additional acceleration.

This makes it very much a niche app, and people running it need to watch out for unexpected behaviour.

In particular, I would expect that most BOINC users who have AMD/ATI GPUs will already be attached to other BOINC projects which have fully-specified AMD/ATI applications. In this mode of operation, BOINC will schedule both projects to use the same device at the same time - that may have an impact on your performance statistics.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39899 - Posted: 30 Jan 2015 | 10:35:23 UTC - in response to Message 39898.
Last modified: 30 Jan 2015 | 10:36:32 UTC



In particular, I would expect that most BOINC users who have AMD/ATI GPUs will already be attached to other BOINC projects which have fully-specified AMD/ATI applications. In this mode of operation, BOINC will schedule both projects to use the same device at the same time - that may have an impact on your performance statistics.


Yes, I'm aware of the limitations but it's the best we can do given our current server software.
The current situation is acceptable for now, while we are still in the testing phase.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 39900 - Posted: 30 Jan 2015 | 12:11:13 UTC - in response to Message 39899.

I'm only getting one task and won't get another one unless I detach and reattach. Also getting this when trying to get new work.

1/30/2015 6:10:49 AM | GPUGRID | No tasks are available for OpenCL for AMD GPUs

Peciak
Send message
Joined: 31 May 11
Posts: 8
Credit: 73,588,036
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39901 - Posted: 30 Jan 2015 | 12:16:06 UTC
Last modified: 30 Jan 2015 | 12:16:31 UTC

I'm only getting one task and won't get another one unless I detach and reattach. Also getting this when trying to get new work.

+1

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39902 - Posted: 30 Jan 2015 | 12:21:41 UTC - in response to Message 39895.
Last modified: 30 Jan 2015 | 12:25:22 UTC

The AMD application has reached a working state.

To access it you will need to change your preferences to
* enable "Accept Test work"
* enable the application "Molecular Dynamics on AMD GPUs"
* enable "Use CPU"
Doesn't work for me. I have tried all possible combinations of checkboxes without any success. The only way to get a task is re-attaching the project.
30/01/2015 13:11:18 | GPUGRID | Requesting new tasks for CPU
30/01/2015 13:11:24 | GPUGRID | Scheduler request completed: got 0 new tasks
30/01/2015 13:11:24 | GPUGRID | No tasks sent
30/01/2015 13:11:24 | GPUGRID | No tasks are available for OpenCL for AMD GPUs
30/01/2015 13:11:52 | GPUGRID | update requested by user
30/01/2015 13:12:35 | GPUGRID | Sending scheduler request: Requested by user.
30/01/2015 13:12:35 | GPUGRID | Requesting new tasks for CPU
30/01/2015 13:12:38 | GPUGRID | Scheduler request completed: got 0 new tasks
30/01/2015 13:12:38 | GPUGRID | No tasks sent
30/01/2015 13:12:38 | GPUGRID | No tasks are available for OpenCL for AMD GPUs
30/01/2015 13:12:50 | GPUGRID | Resetting project
30/01/2015 13:12:50 | GPUGRID | Detaching from project
30/01/2015 13:13:01 | | Fetching configuration file from http://www.gpugrid.net/get_project_config.php
30/01/2015 13:13:18 | GPUGRID | Master file download succeeded
30/01/2015 13:13:23 | GPUGRID | Sending scheduler request: Project initialization.
30/01/2015 13:13:23 | GPUGRID | Requesting new tasks for CPU and ATI
30/01/2015 13:13:26 | GPUGRID | Scheduler request completed: got 1 new tasks

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 39903 - Posted: 30 Jan 2015 | 12:29:00 UTC - in response to Message 39895.

The AMD application has reached a working state.


Are you sure? My AMD R9 290 says the opposite.
http://www.gpugrid.net/result.php?resultid=13763788


If GPU is incompatible (HD4000/5000), will fall back to CPU execution


I got an AMD Mobility 5650 in my Laptop and it's working fine (~87 % GPU load).

nanoprobe
Send message
Joined: 26 Feb 12
Posts: 184
Credit: 222,376,233
RAC: 0
Level
Leu
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39904 - Posted: 30 Jan 2015 | 12:29:59 UTC - in response to Message 39899.



In particular, I would expect that most BOINC users who have AMD/ATI GPUs will already be attached to other BOINC projects which have fully-specified AMD/ATI applications. In this mode of operation, BOINC will schedule both projects to use the same device at the same time - that may have an impact on your performance statistics.


Yes, I'm aware of the limitations but it's the best we can do given our current server software.
The current situation is acceptable for now, while we are still in the testing phase.

I appreciate the effort to get an AMD app to run on GPUGrid but I'm going to pass on this one. IMHO an MT GPU app that requires so much CPU power is no more than a glorified CPU app. Good luck. I'll keep an eye on this and if it ever develops into a true GPU app I'll try again.

Jozef J
Send message
Joined: 7 Jun 12
Posts: 112
Credit: 1,129,795,172
RAC: 353,053
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 39906 - Posted: 30 Jan 2015 | 13:20:35 UTC

I can not get a couple of days jobs from amd beta..

Jozef J
Send message
Joined: 7 Jun 12
Posts: 112
Credit: 1,129,795,172
RAC: 353,053
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 39907 - Posted: 30 Jan 2015 | 15:13:21 UTC

AMD cards are very inefficient. to my 3 7970 1200I corsair must watt at full throttle power supply. include cpu
maybe people want to help their suppliers of electricity.-) dumb
but the path to a stable amd applications will be long and seamless.
Now amd it was cheaper to 290x card which I returned after 14 days due to black screeen problem. and still be switched to throtle mod. absolutely useless. It was the time when she was a complete novelty and become full price.
AMD card can now buy just a fool like me.

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39908 - Posted: 30 Jan 2015 | 15:44:14 UTC
Last modified: 30 Jan 2015 | 16:18:19 UTC

Got one running now. I get it, this is the old multi-threaded CPU app that has been enhanced to share some of the processing onto the GPU.

When the task is running, BOINC manager shows that it is using 1 CPUs + 1 ATI/AMD GPUs. However when I look at the Stderr.txt, it shows that the task is using 16 threads (all that is available on this machine). And I can confirm that task manager showed 100% cpu utilization.

BOINC wrapper for GROMACS.
Arg 0 [projects/www.gpugrid.net/mdrun-915.exe]
Arg 1 [--nthreads]
Arg 2 [16]
BOINC running with [16] threads


And at that, it only uses the GPU part of the time. When the GPU is being used, it is being used at 90% (on an AMD 6950). Then it goes for a minute or so of 0% being used.

Task ran for ~20 minutes and now shows as completed and validated.

Edit:

When I add the GPUGRID project and ask for "OpenCL for AMD GPUs" tasks, BOINC manager requests tasks for CPU and AMD GPU. It gets one task. After it gets that one task, whenever it requests new tasks, it only requests tasks for CPU. Then it never gets another task. The only way to get another task is to detach and re-attach, then BOINC Manager will request tasks for CPU and AMD GPU.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39909 - Posted: 30 Jan 2015 | 16:37:00 UTC - in response to Message 39908.

Got one running now. I get it, this is the old multi-threaded CPU app that has been enhanced to share some of the processing onto the GPU.


More or less, yes.


When the task is running, BOINC manager shows that it is using 1 CPUs + 1 ATI/AMD GPUs. However when I look at the Stderr.txt, it shows that the task is using 16 threads (all that is available on this machine). And I can confirm that task manager showed 100% cpu utilization.


It should have the same behaviour as the old CPU app, using whatever CPU you have allocated to the project in the preferences. (I can see that's working for other clients)


And at that, it only uses the GPU part of the time. When the GPU is being used, it is being used at 90% (on an AMD 6950). Then it goes for a minute or so of 0% being used.


Shouldn't have a duty cycle like that. The peak load is very likely to be below 100% until we've tuned the CPU/GPU balance, but it shouldn't spend a long time idle.



When I add the GPUGRID project and ask for "OpenCL for AMD GPUs" tasks, BOINC manager requests tasks for CPU and AMD GPU. It gets one task. After it gets that one task, whenever it requests new tasks, it only requests tasks for CPU. Then it never gets another task. The only way to get another task is to detach and re-attach, then BOINC Manager will request tasks for CPU and AMD GPU.


Yes, a lot of people have reported that. Could you show me the client output showing that behaviour, please?

Matt

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39910 - Posted: 30 Jan 2015 | 17:12:21 UTC - in response to Message 39909.

When I add the GPUGRID project and ask for "OpenCL for AMD GPUs" tasks, BOINC manager requests tasks for CPU and AMD GPU. It gets one task. After it gets that one task, whenever it requests new tasks, it only requests tasks for CPU. Then it never gets another task. The only way to get another task is to detach and re-attach, then BOINC Manager will request tasks for CPU and AMD GPU.


Yes, a lot of people have reported that. Could you show me the client output showing that behaviour, please?

Matt

From captainjack's description, it's probably the line

<no_ati_apps>1</no_ati_apps>

which I've copied from your sched_reply_www.gpugrid.net.xml file (below the project preferences block, and just before the <gui_urls>).

I don't have any computers with an AMD/ATI card, but that probably translates into a line

<no_rsc_apps>ATI</no_rsc_apps>

in the <project> section of client_state.xml, and having the effect of preventing BOINC making any further requests for AMD/ATI work.

[I have <no_rsc_apps>NVIDIA</no_rsc_apps> from another project, and that has the effect of making

30/01/2015 17:10:55 | LHC@home 1.0 | [work_fetch] share 0.000 no applications

appear in the <work_fetch_debug> event logs]

Someone could try searching for <no_rsc_apps>ATI</no_rsc_apps> in client_state after processing their first test app, and see if removing it allows a second bite of the cherry.

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39912 - Posted: 30 Jan 2015 | 17:56:18 UTC - in response to Message 39910.
Last modified: 30 Jan 2015 | 18:02:14 UTC

You are right, Richard.

<project>
<master_url>http://www.gpugrid.net/</master_url>
<project_name>GPUGRID</project_name>
.
.
<no_rsc_apps>ATI</no_rsc_apps>
.
.
</project>
The project has no ATI app => a clinet doesn't ask for ATI work.

Jozef J
Send message
Joined: 7 Jun 12
Posts: 112
Credit: 1,129,795,172
RAC: 353,053
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwat
Message 39916 - Posted: 30 Jan 2015 | 18:51:19 UTC

Guys calm down and do not make pressure on MJH. need some time to create stable applications for AMD cards. even if done any applications. still it will not be a cash cow for rac credit. As it is now, for example Collatz or pps sieve. not stress <-)













kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39917 - Posted: 30 Jan 2015 | 18:56:24 UTC

I do not care about points, I'm interested in scientific results.

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39918 - Posted: 30 Jan 2015 | 19:17:40 UTC
Last modified: 30 Jan 2015 | 19:35:27 UTC

Matt asked:

Yes, a lot of people have reported that. Could you show me the client output showing that behaviour, please?

Matt


Per your request, I just detached and re-attached. Both of the messages that I referred to are in the log. 6th line down is where it asks for tasks for CPU and AMD/ATI GPU. The 5th line from the bottom is where it asks for tasks for CPU after it has first downloaded an amdmd task.

1/30/2015 1:04:41 PM | GPUGRID | Resetting project
1/30/2015 1:04:41 PM | GPUGRID | Detaching from project
1/30/2015 1:05:01 PM | | Fetching configuration file from http://www.gpugrid.net/get_project_config.php
1/30/2015 1:05:20 PM | GPUGRID | Master file download succeeded
1/30/2015 1:05:25 PM | GPUGRID | Sending scheduler request: Project initialization.
1/30/2015 1:05:25 PM | GPUGRID | Requesting new tasks for CPU and AMD/ATI GPU
1/30/2015 1:05:27 PM | GPUGRID | Scheduler request completed: got 1 new tasks
1/30/2015 1:05:29 PM | GPUGRID | Started download of mdrun-915.exe
1/30/2015 1:05:29 PM | GPUGRID | Started download of ishift.h
1/30/2015 1:05:29 PM | GPUGRID | Started download of libfftw3f-3.dll.64
1/30/2015 1:05:29 PM | GPUGRID | Started download of msvcp100.dll.64
1/30/2015 1:05:30 PM | GPUGRID | Finished download of ishift.h
1/30/2015 1:05:30 PM | GPUGRID | Started download of msvcr100.dll.64
1/30/2015 1:05:33 PM | GPUGRID | Finished download of msvcp100.dll.64
1/30/2015 1:05:33 PM | GPUGRID | Started download of nbnxn_consts.h
1/30/2015 1:05:34 PM | GPUGRID | Finished download of nbnxn_consts.h
1/30/2015 1:05:34 PM | GPUGRID | Started download of nbnxn_ocl_kernel_amd.clh
1/30/2015 1:05:35 PM | GPUGRID | Finished download of msvcr100.dll.64
1/30/2015 1:05:35 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_amd.clh
1/30/2015 1:05:35 PM | GPUGRID | Started download of nbnxn_ocl_kernel_nowarp.clh
1/30/2015 1:05:35 PM | GPUGRID | Started download of nbnxn_ocl_kernel_nvidia.clh
1/30/2015 1:05:36 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_nowarp.clh
1/30/2015 1:05:36 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_nvidia.clh
1/30/2015 1:05:36 PM | GPUGRID | Started download of nbnxn_ocl_kernels.clh
1/30/2015 1:05:36 PM | GPUGRID | Started download of nbnxn_ocl_kernels.cl
1/30/2015 1:05:40 PM | GPUGRID | Finished download of nbnxn_ocl_kernels.clh
1/30/2015 1:05:40 PM | GPUGRID | Finished download of nbnxn_ocl_kernels.cl
1/30/2015 1:05:40 PM | GPUGRID | Started download of nbnxn_ocl_kernels_fastgen.clh
1/30/2015 1:05:40 PM | GPUGRID | Started download of nbnxn_ocl_kernel_utils.clh
1/30/2015 1:05:42 PM | GPUGRID | Finished download of nbnxn_ocl_kernels_fastgen.clh
1/30/2015 1:05:42 PM | GPUGRID | Finished download of nbnxn_ocl_kernel_utils.clh
1/30/2015 1:05:42 PM | GPUGRID | Started download of OpenCL.dll.64
1/30/2015 1:05:42 PM | GPUGRID | Started download of vcomp100.dll.64
1/30/2015 1:05:43 PM | Poem@Home | task poempp_1vii_1422558127_1302132832_0 suspended by user
1/30/2015 1:05:44 PM | GPUGRID | Finished download of vcomp100.dll.64
1/30/2015 1:05:44 PM | GPUGRID | Started download of vectype_ops.clh
1/30/2015 1:05:45 PM | GPUGRID | Finished download of OpenCL.dll.64
1/30/2015 1:05:45 PM | GPUGRID | Finished download of vectype_ops.clh
1/30/2015 1:05:45 PM | GPUGRID | Started download of 490-MJHARVEY_AMDDHFR3-0-input
1/30/2015 1:05:45 PM | GPUGRID | Started download of logogpugrid.png
1/30/2015 1:05:46 PM | GPUGRID | Finished download of logogpugrid.png
1/30/2015 1:05:46 PM | GPUGRID | Started download of project_1.png
1/30/2015 1:05:47 PM | GPUGRID | Finished download of project_1.png
1/30/2015 1:05:47 PM | GPUGRID | Started download of project_2.png
1/30/2015 1:05:48 PM | GPUGRID | Finished download of project_2.png
1/30/2015 1:05:48 PM | GPUGRID | Started download of project_3.png
1/30/2015 1:05:50 PM | GPUGRID | Finished download of libfftw3f-3.dll.64
1/30/2015 1:05:50 PM | GPUGRID | Finished download of 490-MJHARVEY_AMDDHFR3-0-input
1/30/2015 1:05:50 PM | GPUGRID | Finished download of project_3.png
1/30/2015 1:06:00 PM | GPUGRID | Sending scheduler request: To fetch work.
1/30/2015 1:06:00 PM | GPUGRID | Requesting new tasks for CPU
1/30/2015 1:06:02 PM | GPUGRID | Finished download of mdrun-915.exe
1/30/2015 1:06:02 PM | GPUGRID | Scheduler request completed: got 0 new tasks
1/30/2015 1:06:02 PM | GPUGRID | No tasks sent
1/30/2015 1:06:02 PM | GPUGRID | No tasks are available for OpenCL for AMD GPUs


Let me know if you need more information.
captainjack

Edit: added more test results:

And at that, it only uses the GPU part of the time. When the GPU is being used, it is being used at 90% (on an AMD 6950). Then it goes for a minute or so of 0% being used.


Shouldn't have a duty cycle like that. The peak load is very likely to be below 100% until we've tuned the CPU/GPU balance, but it shouldn't spend a long time idle.


When I tested earlier, there were some other things running and CPU utilization was pegged at 100%. The GPU may have been starved for some CPU cycles. I changed some of the parameters so that it is running with less than 100& CPU utilization and ran a new task. Now it is seeing consistent utilization of the GPU.

zablociak
Send message
Joined: 2 Jul 12
Posts: 9
Credit: 302,966,028
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39933 - Posted: 31 Jan 2015 | 11:27:51 UTC

I am not very familiar with the development of GPUGRID, but as fas as I can tell the new mt-opencl application for AMD gpus has something to do with porting GROMACS to OpenCL. http://streamcomputing.eu/blog/2014-11-01/ported-gromacs-cuda-opencl/
Am I right?

Regards
Luke

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39934 - Posted: 31 Jan 2015 | 11:48:26 UTC - in response to Message 39933.

Luke,

That's right, that's the code we're testing.

Matt

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39936 - Posted: 31 Jan 2015 | 11:49:20 UTC - in response to Message 39918.

Thanks Captain Jack,

I've made a change that should fix that.

Matt

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39940 - Posted: 31 Jan 2015 | 15:11:32 UTC

Matt,

Here's what I am getting this morning after a detach and re-attach:

1/31/2015 9:05:32 AM | | Fetching configuration file from http://www.gpugrid.net/get_project_config.php
1/31/2015 9:06:04 AM | GPUGRID | Master file download succeeded
1/31/2015 9:06:09 AM | GPUGRID | Sending scheduler request: Project initialization.
1/31/2015 9:06:09 AM | GPUGRID | Requesting new tasks for CPU and AMD/ATI GPU
1/31/2015 9:06:11 AM | GPUGRID | Scheduler request completed: got 0 new tasks
1/31/2015 9:06:11 AM | GPUGRID | No tasks sent
1/31/2015 9:06:11 AM | GPUGRID | No tasks are available for OpenCL for AMD GPUs
1/31/2015 9:06:13 AM | GPUGRID | Started download of logogpugrid.png
1/31/2015 9:06:13 AM | GPUGRID | Started download of project_1.png
1/31/2015 9:06:13 AM | GPUGRID | Started download of project_2.png
1/31/2015 9:06:13 AM | GPUGRID | Started download of project_3.png
1/31/2015 9:06:14 AM | GPUGRID | Finished download of logogpugrid.png
1/31/2015 9:06:14 AM | GPUGRID | Finished download of project_1.png
1/31/2015 9:06:14 AM | GPUGRID | Finished download of project_2.png
1/31/2015 9:06:14 AM | GPUGRID | Finished download of project_3.png
1/31/2015 9:06:47 AM | GPUGRID | Sending scheduler request: To fetch work.
1/31/2015 9:06:47 AM | GPUGRID | Requesting new tasks for CPU
1/31/2015 9:06:49 AM | GPUGRID | Scheduler request completed: got 0 new tasks
1/31/2015 9:06:49 AM | GPUGRID | No tasks sent
1/31/2015 9:06:49 AM | GPUGRID | No tasks are available for OpenCL for AMD GPUs


From then on, it only asks for CPU tasks.

Let me know if there is other information that I can provide.

captainjack

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39947 - Posted: 1 Feb 2015 | 0:27:37 UTC - in response to Message 39940.

Captainjack - are you getting work now?

MJH

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39948 - Posted: 1 Feb 2015 | 0:57:08 UTC
Last modified: 1 Feb 2015 | 1:23:06 UTC

I got 6 tasks just using update without needing to detach and reattach. They ran for 2 minutes 5 seconds and errored. Ran a short time on GPU at about 30% and used all six CPU cores at about 35-40%.

It has started to download more without me doing anything.

Cheers!


EDIT:
Uploading and Downloading and all is acting fine. Occasionally second GPU goes to 100% for a second or 2 and sometimes some action on first GPU.
____________

Peciak
Send message
Joined: 31 May 11
Posts: 8
Credit: 73,588,036
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39952 - Posted: 1 Feb 2015 | 8:48:41 UTC

All WU counted correctly. Intel I7 (CPU @4.5) + ATI 7970 (OC)
mt CPU (95 - 98%)
ATI (91-95%)
Credits allocated very very small.
Run time 1.440
CPU time 10.400
Credits ->200

Credits allocated correctly?

Sean
Send message
Joined: 28 Aug 10
Posts: 2
Credit: 1,150,152
RAC: 0
Level
Ala
Scientific publications
wat
Message 39953 - Posted: 1 Feb 2015 | 10:38:31 UTC - in response to Message 39887.
Last modified: 1 Feb 2015 | 10:55:36 UTC

I got my first task for my 5770 but it errored out. :(




30/01/2015 12:01:22 PM | GPUGRID | Finished download of mdrun-912.exe
30/01/2015 12:01:22 PM | GPUGRID | [error] Signature verification failed for mdrun-912.exe
30/01/2015 12:01:22 PM | GPUGRID | [error] Checksum or signature error for mdrun-912.exe
30/01/2015 12:02:57 PM | GPUGRID | Sending scheduler request: To report completed tasks.



This is indeed fixed with 915, work units are finishing on my HD 5770 in about 45 minutes with 60-70% GPU utilisation (CPU is the Q6600). :D


One thing that's odd in the Event log though is these lines:
1/02/2015 9:12:49 PM | GPUGRID | Message from task: 0

I guessing nothing to worry about?


EDIT: AMD Catalyst = 14.12, OS = Windows 7 64bit, BOINC = 7.4.36

zablociak
Send message
Joined: 2 Jul 12
Posts: 9
Credit: 302,966,028
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39956 - Posted: 1 Feb 2015 | 11:51:15 UTC
Last modified: 1 Feb 2015 | 12:20:10 UTC

AMD 7970 @1000 MHz (Catalyst 14.9); i5 4460K @3.20 GHz; Win7 64bit.
Tasks running fine, fully loaded CPU (4 threads) and GPU at 50-60% range: http://www.gpugrid.net/results.php?hostid=196889
The screenshot sums it up: http://i.imgur.com/5R8Iqjc.png?1
Edit:
The application seems to be really CPU-bound. Just compare my GPU load and the one reported by Peciak in http://www.gpugrid.net/forum_thread.php?id=3995&nowrap=true#39952

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39957 - Posted: 1 Feb 2015 | 11:58:48 UTC - in response to Message 39952.

Peciak,

Yes, the credits are off, I've not fixed that yet.

Matt

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39958 - Posted: 1 Feb 2015 | 12:15:00 UTC

I've tweaked the credits, and changed the allocation strategy. WUs will now only be assigned to machines with 1 AMD card and no NVIDIA cards.

No more than 8 CPU cores will be used.

Matt

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39959 - Posted: 1 Feb 2015 | 12:22:29 UTC

Overnight 54 of these AMD ran on my 5870 but all ended in error. This is the first part of the file:
Stderr output

<core_client_version>7.4.36</core_client_version>
<![CDATA[
<message>
Incorrect function.
(0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
BOINC wrapper for GROMACS.
Arg 0 [projects/www.gpugrid.net/mdrun-915.exe]
Arg 1 [--nthreads]
Arg 2 [6]
BOINC running with [6] threads
BOINC resolving [traj.xtc] to [traj.xtc]
BOINC resolving [topol.tpr] to [topol.tpr]
BOINC resolving [progress.log] to [progress.log]
BOINC resolving [state.cpt] to [state.cpt]
ARG 0 [projects/www.gpugrid.net/mdrun-915.exe]
ARG 1 [-ntomp]
ARG 2 [6]
ARG 3 [-nt]
ARG 4 [6]
ARG 5 [-x]
ARG 6 [traj.xtc]
ARG 7 [-s]
ARG 8 [topol.tpr]
ARG 9 [-g]
ARG 10 [progress.log]
GROMACS: mdrun-915, VERSION 5.1-dev


If you need more information let me know.
Win7 x64 ultimate, BOINC 7.4.36
____________
Greetings from TJ

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39960 - Posted: 1 Feb 2015 | 12:49:36 UTC - in response to Message 39959.

TJ - the application doesn't cope well with multiple GPUs. I'm now resticting WUs to hosts with only a single AMD GPU.

Matt

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39961 - Posted: 1 Feb 2015 | 13:37:40 UTC - in response to Message 39960.

TJ - the application doesn't cope well with multiple GPUs. I'm now resticting WUs to hosts with only a single AMD GPU.

Matt


Sorry, this disqualifies most of my pc's. I'll keep that watching and come back later when the amd app is in a more progressed state.

Alexander

[AF>FAH-Addict.net]toTOW
Send message
Joined: 28 Oct 10
Posts: 9
Credit: 25,781,299
RAC: 0
Level
Val
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39962 - Posted: 1 Feb 2015 | 13:45:54 UTC

Something must be wrong with this application ... although I get work for application OpenCL for AMD GPUs 9.15 (mt), this application is only using my 8 CPU cores.

In Status column, it says Compiting (8 CPUs) but it doesn't requires any ATI GPU ...

The application is running and using 8 cores of my CPU, the GPU has kicked in performance mode, but it is not used (GPU usage stays at 0% and it barely gets hotter).

When I start another project using the GPU, it gets works and starts computing and using the GPU ... if the GPUGRID application really needs the GPU, someting is wonrg and they will compete for GPU access ...

Also, the AMDTEST1 WUs are estimated to run for 8 seconds, but it is stuck at 100% for more than 20 minutes now ... and the AMDDHFR3 ones are estimated to run 14 minutes, but I fear how long they will last ...

Is something wrong with Hawaii GPUs or is it the expected behaviour of this application ?

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39963 - Posted: 1 Feb 2015 | 13:57:49 UTC - in response to Message 39960.

TJ - the application doesn't cope well with multiple GPUs. I'm now resticting WUs to hosts with only a single AMD GPU.

Matt


Okay thanks Matt. I will try again later when it works with multiple.

____________
Greetings from TJ

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39964 - Posted: 1 Feb 2015 | 13:59:37 UTC - in response to Message 39962.
Last modified: 1 Feb 2015 | 14:00:40 UTC

Something must be wrong with this application ... although I get work for application OpenCL for AMD GPUs 9.15 (mt), this application is only using my 8 CPU cores.

In Status column, it says Compiting (8 CPUs) but it doesn't requires any ATI GPU ...


This app is at the moment appearing to BOINC as a multithreaded CPU only application.

I'll have to wait until your machine's returned some work before I can comment on exactly what resources were used.

Matt

captainjack
Send message
Joined: 9 May 13
Posts: 171
Credit: 3,058,396,788
RAC: 8,820,285
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39965 - Posted: 1 Feb 2015 | 14:06:54 UTC

Captainjack - are you getting work now?

MJH



Yep, I just got 16 tasks. One is running now.

It is running on all 16 CPU threads and shows 98% GPU utilization on an AMD 6950.

As reported earlier, it shows 100% complete after about 90 seconds of run time, but it is going ahead with its calculations.

Let me know if you need more information.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39966 - Posted: 1 Feb 2015 | 14:11:44 UTC - in response to Message 39965.


As reported earlier, it shows 100% complete after about 90 seconds of run time, but it is going ahead with its calculations.


Yes, it's not reporting progress yet.

Matt

tazzduke
Send message
Joined: 7 Aug 09
Posts: 2
Credit: 125,098,918
RAC: 33,888
Level
Cys
Scientific publications
watwatwatwatwatwat
Message 39968 - Posted: 1 Feb 2015 | 14:21:32 UTC - in response to Message 39966.

Greetings MJH

Running a WIN 7 x64 Quad8400 with an AMD HD 5850 1GB

1 am reporting I have 4 tasks. One is running now.

It is running on all 4 CPU threads and shows 68% GPU utilization on an AMD 5850.

Also as reported earlier, it shows 100% complete after about 90 seconds of run time but continues to run until it is completed.

I have completed a couple of validated tasks as well.

Hope this helps with the indication another AMD user is having some success.

Regards


zablociak
Send message
Joined: 2 Jul 12
Posts: 9
Credit: 302,966,028
RAC: 0
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39971 - Posted: 1 Feb 2015 | 14:48:30 UTC - in response to Message 39962.

Something must be wrong with this application ... although I get work for application OpenCL for AMD GPUs 9.15 (mt), this application is only using my 8 CPU cores.

This also happened to me. But at the time mt GPUGrid app started to run another CPU app was still running. It acted like this even though I set 100% of CPU time and processors in BOINC preferences. When CPU WU (Universe@home) finished the GPUGrid mt app kicked in and GPU was at 60%.

[AF>FAH-Addict.net]toTOW
Send message
Joined: 28 Oct 10
Posts: 9
Credit: 25,781,299
RAC: 0
Level
Val
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39972 - Posted: 1 Feb 2015 | 15:01:30 UTC - in response to Message 39964.

Something must be wrong with this application ... although I get work for application OpenCL for AMD GPUs 9.15 (mt), this application is only using my 8 CPU cores.

In Status column, it says Compiting (8 CPUs) but it doesn't requires any ATI GPU ...


This app is at the moment appearing to BOINC as a multithreaded CPU only application.

I'll have to wait until your machine's returned some work before I can comment on exactly what resources were used.

Matt

Thanks for your answer ... it seems to be running fine now but it's now fully using the GPU : I see spikes from 0 to 100% every couple of seconds ... and the GPU is only pulling 100W where it can pull up to 250W when fully used.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39973 - Posted: 1 Feb 2015 | 15:12:23 UTC - in response to Message 39972.
Last modified: 1 Feb 2015 | 15:13:14 UTC


Thanks for your answer ... it seems to be running fine now but it's now fully using the GPU : I see spikes from 0 to 100% every couple of seconds ... and the GPU is only pulling 100W where it can pull up to 250W when fully used.


Yes. Getting the balance right between CPU and GPU is going to be a challenge to do automatically. f you have a look at the output
http://www.gpugrid.net/result.php?resultid=13773682 you'll see a message:

NOTE: The GPU has >25% less load than the CPU. This imbalance causes performance loss

Try dialing down the amount of CPU you are allocating to the the application until that message goes away. Go too far and you'll get a message saying the GPU has too much load.

Note that the CPU use is assigned when the job is sent to your client, so you can't change it for any jobs you have already received, even if they are still queued.

Matt

JugNut
Send message
Joined: 27 Nov 11
Posts: 11
Credit: 1,021,749,297
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39974 - Posted: 1 Feb 2015 | 15:24:39 UTC

The trial rig I used ask's for work but is told there is "No tasks are available for OpenCL for AMD GPUs" although there seems to be plenty available by the server status. I'm guessing my problem is that I have mixed rigs and they are not supported yet? Is that right?
I have no rigs with single AMD's in them all I have is 3 rigs with mixed GPU's both ATI & Nvidia in the same box which work extremely well with mixed boinc projects but apparently not here ATM. I sure hope they will in the future.
I guess like others i'm out of luck until things progress further.

Your most definitely to be commended for trying something new. Good luck with it.

[AF>FAH-Addict.net]toTOW
Send message
Joined: 28 Oct 10
Posts: 9
Credit: 25,781,299
RAC: 0
Level
Val
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39975 - Posted: 1 Feb 2015 | 15:26:11 UTC
Last modified: 1 Feb 2015 | 15:36:13 UTC

In my logs, Gormacs says also that you should use SSE 4.2 on my CPU instead of SSE 2 ... I don't know if you can do that automatically.

In fact, you're going through what I've alread known in Folding@Home when they experimented with Gromacs, SMP and GPUs :

- I've seen a MPI Gromacs core which was using MPI and processes approach which required the installation of OpenMPI which was causing many troubles (performances issues on Windows, computations errors when a netowrk device was plugged/unplugged, ...)
- They then moved to a threaded approach in Gormacs which is much more reliable and faster on a signle computer environment. These cores are still in production and didn't change for almost a couple of years ... the only flaw of this core is that it's still 32 bits and using quite an old codebase now but I don't know if they plan on using Gromacs in the future core versions ...
- Gromacs has been the base of many GPU cores too, starting with DirectX implementation which turned to be unusable outside a lab and going through CAL/Brook+ ATI cores and CUDA cores. ATI versions are already deprecated and no longer supported, and NV ones support is progressively being dropped.
- Since the move to using OpenCL on ATI and NV platforms, Stanford is now using their own code called OpenMM. These applications are GPU only and don't compute on CPU (although they might need one free CPU thread to feed the GPU efficiently).

This is fun to see the history being reapeated here in this project ... I hope you won't have as much troubles as they had while developing these tools.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39976 - Posted: 1 Feb 2015 | 15:31:29 UTC - in response to Message 39973.

Try dialing down the amount of CPU you are allocating to the the application until that message goes away. Go too far and you'll get a message saying the GPU has too much load.

Note that the CPU use is assigned when the job is sent to your client, so you can't change it for any jobs you have already received, even if they are still queued.

Matt

Matt,

I'm not quite sure how you're advocating that people "dial down the amount of CPU you are allocating". BOINC doesn't really have a mechanism for users to control how much CPU is allocated to a particular application.

There is the website (or local) preference "On multiprocessors, use at most xxx% of the processors", but this controls how many CPU cores BOINC can use as a whole, across all projects - within that limit, any MT task will be set (on assignment) to use every core available to BOINC. There's no way, using the web or GUI tools, to adjust the number of cores available to this AMD Beta app, while still allowing BOINC to use other cores for other applications or projects.

It is, however, possible to use an Application configuration (app_config.xml) file to control this, providing you are running at least v7.2.42 of the BOINC client.

You can set both

<avg_ncpus>x</avg_ncpus> <cmdline>--nthreads n</cmdline>

for an mt plan_class (recommended that x == n), and even change the values in mid-run by stopping and restarting the application - though this will mess up Matt's test statistics, and it might be preferable to change parameters between tasks, rather than during a run.

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39977 - Posted: 1 Feb 2015 | 17:14:36 UTC

Do you expect that in the future ATI app will work exactly like app for NV? I mean low CPU usage, high GPU usage, multi GPUs?

[AF>FAH-Addict.net]toTOW
Send message
Joined: 28 Oct 10
Posts: 9
Credit: 25,781,299
RAC: 0
Level
Val
Scientific publications
watwatwatwatwatwatwatwatwat
Message 39982 - Posted: 1 Feb 2015 | 18:16:55 UTC

I'm seeing some unexplainable discrepencies in points attributions ...

Here are some examples :

13765549 10604022 197813 1 Feb 2015 | 14:54:24 UTC 1 Feb 2015 | 15:12:24 UTC Terminé et validé 1,061.62 7,840.83 8,721.16 OpenCL for AMD GPUs v9.15 (mt)
13765548 10604021 197813 1 Feb 2015 | 16:07:56 UTC 1 Feb 2015 | 18:13:03 UTC Terminé et validé 1,076.36 7,901.26 237.89 OpenCL for AMD GPUs v9.15 (mt)
13765546 10604019 197813 1 Feb 2015 | 15:50:46 UTC 1 Feb 2015 | 17:54:40 UTC Terminé et validé 1,133.30 8,401.45 232.80 OpenCL for AMD GPUs v9.15 (mt)
13765530 10604003 197813 1 Feb 2015 | 15:12:24 UTC 1 Feb 2015 | 17:19:47 UTC Terminé et validé 1,456.66 10,339.33 277.93 OpenCL for AMD GPUs v9.15 (mt)
13765525 10603998 197813 1 Feb 2015 | 14:56:11 UTC 1 Feb 2015 | 16:07:56 UTC Terminé et validé 1,029.07 7,702.50 152.70 OpenCL for AMD GPUs v9.15 (mt)
13765523 10603996 197813 1 Feb 2015 | 14:57:24 UTC 1 Feb 2015 | 16:38:51 UTC Terminé et validé 921.62 6,911.97 150.75 OpenCL for AMD GPUs v9.15 (mt)
13765522 10603995 197813 1 Feb 2015 | 14:56:47 UTC 1 Feb 2015 | 16:23:26 UTC Terminé et validé 930.95 6,987.43 146.14 OpenCL for AMD GPUs v9.15 (mt)
13765498 10603971 197813 1 Feb 2015 | 15:03:01 UTC 1 Feb 2015 | 16:55:29 UTC Terminé et validé 995.72 7,425.57 174.81 OpenCL for AMD GPUs v9.15 (mt)
13765494 10603967 197813 1 Feb 2015 | 13:32:03 UTC 1 Feb 2015 | 14:52:31 UTC Terminé et validé 998.30 7,420.52 8,201.05 OpenCL for AMD GPUs v9.15 (mt)
13765493 10603966 197813 1 Feb 2015 | 13:32:03 UTC 1 Feb 2015 | 14:52:31 UTC Terminé et validé 989.75 7,359.32 8,130.77 OpenCL for AMD GPUs v9.15 (mt)
13765492 10603965 197813 1 Feb 2015 | 13:32:03 UTC 1 Feb 2015 | 14:52:31 UTC Terminé et validé 996.33 7,397.32 8,184.82 OpenCL for AMD GPUs v9.15 (mt)

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39984 - Posted: 1 Feb 2015 | 20:14:23 UTC

I could not resist and rearranged 3 of my systems to have only amd gpu's available.

http://www.gpugrid.net/results.php?hostid=161299 is a i3 with a HD7770 gpu-load ~57% cpu-load ~57%

http://www.gpugrid.net/results.php?hostid=196771 is a AMD A10 7700 APU gpu-load up to 100%, cpu-load ~ 60%

http://www.gpugrid.net/results.php?hostid=197814 is a AMD Phaenom x4 with a HD6950 gpu, gpu load ~74%, cpu-load ~67%

All run win7 x64
all finish and validate
all systems run gpugrid only
cpu load as of win task manager, gpu load as gpu-z reports it. All systems set to use 2 cpu's. Giving more cores did not increase gpu load.

If any further info may helpful pls request it here.

Alexander

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2343
Credit: 16,201,255,749
RAC: 0
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39985 - Posted: 1 Feb 2015 | 22:24:14 UTC - in response to Message 39982.

I'm seeing some unexplainable discrepencies in points attributions ...

Here are some examples :

For everyone, who wants to share their data which is actually a spreadsheet, I'd like to give some tips on how to format the data the way others can read it, and see the data in a similar way as it appeared at its origin.
1. Use the "pre" tag, as it marks the enclosed text as pre-formatted text, so the forum's web engine won't do its own formatting, like filtering multiple spaces, and the enclosed text will be displayed using a non-proportional font, so every letter will have exactly the same width.
2. Delete the unnecessary white spaces and tabulators, and add white spaces to align numbers to the right.
After that this spreadsheet will look like this:
13765549 10604022 197813 | 1 Feb 2015 | 14:54:24 UTC | 1 Feb 2015 | 15:12:24 UTC Terminé et validé 1,061.62 7,840.83 8,721.16 OpenCL for AMD GPUs v9.15 (mt) 13765548 10604021 197813 | 1 Feb 2015 | 16:07:56 UTC | 1 Feb 2015 | 18:13:03 UTC Terminé et validé 1,076.36 7,901.26 237.89 OpenCL for AMD GPUs v9.15 (mt) 13765546 10604019 197813 | 1 Feb 2015 | 15:50:46 UTC | 1 Feb 2015 | 17:54:40 UTC Terminé et validé 1,133.30 8,401.45 232.80 OpenCL for AMD GPUs v9.15 (mt) 13765530 10604003 197813 | 1 Feb 2015 | 15:12:24 UTC | 1 Feb 2015 | 17:19:47 UTC Terminé et validé 1,456.66 10,339.33 277.93 OpenCL for AMD GPUs v9.15 (mt) 13765525 10603998 197813 | 1 Feb 2015 | 14:56:11 UTC | 1 Feb 2015 | 16:07:56 UTC Terminé et validé 1,029.07 7,702.50 152.70 OpenCL for AMD GPUs v9.15 (mt) 13765523 10603996 197813 | 1 Feb 2015 | 14:57:24 UTC | 1 Feb 2015 | 16:38:51 UTC Terminé et validé 921.62 6,911.97 150.75 OpenCL for AMD GPUs v9.15 (mt) 13765522 10603995 197813 | 1 Feb 2015 | 14:56:47 UTC | 1 Feb 2015 | 16:23:26 UTC Terminé et validé 930.95 6,987.43 146.14 OpenCL for AMD GPUs v9.15 (mt) 13765498 10603971 197813 | 1 Feb 2015 | 15:03:01 UTC | 1 Feb 2015 | 16:55:29 UTC Terminé et validé 995.72 7,425.57 174.81 OpenCL for AMD GPUs v9.15 (mt) 13765494 10603967 197813 | 1 Feb 2015 | 13:32:03 UTC | 1 Feb 2015 | 14:52:31 UTC Terminé et validé 998.30 7,420.52 8,201.05 OpenCL for AMD GPUs v9.15 (mt) 13765493 10603966 197813 | 1 Feb 2015 | 13:32:03 UTC | 1 Feb 2015 | 14:52:31 UTC Terminé et validé 989.75 7,359.32 8,130.77 OpenCL for AMD GPUs v9.15 (mt) 13765492 10603965 197813 | 1 Feb 2015 | 13:32:03 UTC | 1 Feb 2015 | 14:52:31 UTC Terminé et validé 996.33 7,397.32 8,184.82 OpenCL for AMD GPUs v9.15 (mt)

This is still too wide, also we don't know the type of data contained in each column, but there are constant columns, and columns containing irrelevant data, let's delete them, and let's name the columns:
TASK | WORK | Run Time | CPU Time | Credits 13765549 | 10604022 | 1,061.62 | 7,840.83 | 8,721.16 13765548 | 10604021 | 1,076.36 | 7,901.26 | 237.89 13765546 | 10604019 | 1,133.30 | 8,401.45 | 232.80 13765530 | 10604003 | 1,456.66 | 10,339.33 | 277.93 13765525 | 10603998 | 1,029.07 | 7,702.50 | 152.70 13765523 | 10603996 | 921.62 | 6,911.97 | 150.75 13765522 | 10603995 | 930.95 | 6,987.43 | 146.14 13765498 | 10603971 | 995.72 | 7,425.57 | 174.81 13765494 | 10603967 | 998.30 | 7,420.52 | 8,201.05 13765493 | 10603966 | 989.75 | 7,359.32 | 8,130.77 13765492 | 10603965 | 996.33 | 7,397.32 | 8,184.82

Well, that's a self-explanatory spreadsheet.
If the constant data is relevant, you can include them before or after the spreadsheet.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39986 - Posted: 1 Feb 2015 | 22:31:45 UTC - in response to Message 39977.

Do you expect that in the future ATI app will work exactly like app for NV? I mean low CPU usage, high GPU usage, multi GPUs?


No, it's a very different code - it's always going to need both.

Matt

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39987 - Posted: 1 Feb 2015 | 22:33:00 UTC - in response to Message 39982.


I'm seeing some unexplainable discrepencies in points attributions ...


The credit allocation still isn't addressed yet.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39989 - Posted: 1 Feb 2015 | 22:35:37 UTC - in response to Message 39976.

Richard,


There is the website (or local) preference "On multiprocessors, use at most xxx% of the processors", but this controls how many CPU cores BOINC can use as a whole, across all projects


I was under the impression that that's per project. (Otherwise, ¿how does that setting work when a client's attached to multiple projects?). In fact, I'm pretty sure changing that setting that will do the job, as I'm seeing jobs go out with odd numbers of cores assigned.

Matt

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 39990 - Posted: 1 Feb 2015 | 22:41:44 UTC - in response to Message 39986.


No, it's a very different code - it's always going to need both.

Matt


Well... That's bad. My ATI's will be supporting folding@home :(

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39991 - Posted: 1 Feb 2015 | 23:05:18 UTC - in response to Message 39989.

Richard,


There is the website (or local) preference "On multiprocessors, use at most xxx% of the processors", but this controls how many CPU cores BOINC can use as a whole, across all projects


I was under the impression that that's per project. (Otherwise, ¿how does that setting work when a client's attached to multiple projects?). In fact, I'm pretty sure changing that setting that will do the job, as I'm seeing jobs go out with odd numbers of cores assigned.

Matt


Sorry MJH, but you are wrong on how that setting works.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 39993 - Posted: 1 Feb 2015 | 23:28:21 UTC - in response to Message 39991.


Sorry MJH, but you are wrong on how that setting works.


So how does the client resolve conflicting settings from different projects?

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39995 - Posted: 1 Feb 2015 | 23:54:21 UTC - in response to Message 39989.

There is the website (or local) preference "On multiprocessors, use at most xxx% of the processors", but this controls how many CPU cores BOINC can use as a whole, across all projects

I was under the impression that that's per project. (Otherwise, ¿how does that setting work when a client's attached to multiple projects?). In fact, I'm pretty sure changing that setting that will do the job, as I'm seeing jobs go out with odd numbers of cores assigned.

Matt

Well, for a start it's in the global preferences section: http://www.gpugrid.net/prefs.php?subset=global

and that section is headed (I copy from the GPUGrid website)

"These apply to all BOINC projects in which you participate.
On computers participating in multiple projects, the most recently modified preferences will be used."

Since the projects don't actually communicate directly between each other, this works by each user's host computer(s) acting as a message relay between all the projects that computer is attached to.

Each scheduler contact (both request and reply) contains the user's current global preference settings. That includes:

Current values (for all four venues)
Timestamp of last change
Project where the most recent update is believed to have been made

If any RPC contains different values from those held by the receiver, and if the timestamp is newer, then the receiving computer/project updates its internal records.

Provided there is a continuous chain connecting every project, and every computer, on the user's account, eventually all computers and all projects end up with an identical set of preference values for that global set. It only breaks down if a user has computers 1,2,3 attached to projects A,B,C - and computers 4,5,6 attached to projects D,E,F with no overlap. Then, there's no migration route between the first cluster and the second cluster.

Jacob Klein
Send message
Joined: 11 Oct 08
Posts: 1127
Credit: 1,901,927,545
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 39996 - Posted: 1 Feb 2015 | 23:58:30 UTC
Last modified: 2 Feb 2015 | 0:04:44 UTC


Sorry MJH, but you are wrong on how that setting works.


So how does the client resolve conflicting settings from different projects?


The computer has resources, and the client keeps the resources occupied.

Unless a task is in jeopardy of missing deadline, the client feeds coprocessor resources first, and then feeds the rest of the CPUs. If a coprocessor job has been included in the "run-list", the client schedules [ncpus + 1] work of work. Otherwise, if only CPU jobs, it schedules [ncpus] worth of work. If a multithreading job enters the run-list, we are allowed to overcommit the CPU.

As an example, let's say we have a quad-core hyperthreaded machine, such that Windows sees 8 virtual CPUs. Let's say I have 2 ASIC coprocessor devices, 2 AMD GPU coprocessors that are the exact same model, and 3 NVIDIA GPU coprocessors that are all different models. Let's say we're attached to 30 different projects.

So, a possible schedule for this might be:
ASIC + 0.05 CPU
ASIC + 0.05 CPU
AMD + 0.25 CPU
AMD + 0.25 CPU
NVIDIA + 0.3 CPU
NVIDIA + 0.4 CPU
NVIDIA + 0.5 CPU
7 single-threaded CPU tasks
... all of differing projects. Note: The coprocessor CPU portions add up to: 1.8, and ncpus is 8, and so BOINC schedules 7 CPU tasks, such that the sum of CPU is 8.8, which is less than 9 [ncpus + 1].

Let's say we have the "Use at most x% CPUs" setting set to 75%, such that BOINC knows we only want to schedule for 6 virtual CPUs. Now a schedule might be:
ASIC + 0.05 CPU
ASIC + 0.05 CPU
AMD + 0.7 CPU
AMD + 0.7 CPU
NVIDIA + 0.3 CPU
NVIDIA + 0.4 CPU
NVIDIA + 0.5 CPU
1 6-threaded MT CPU task
... all of differing projects. In this example, for the coprocessor jobs, the sum of CPU portions is 2.7. Even though 2.7 + 6 = 8.7 is larger than [ncpus + 1 = 7], we are allowed to overcommit the CPU to get that MT task to process.

Hope this helps explain the scheduler a bit better. TLDR; The "Use at most X% CPUs" just tells BOINC how many CPUs it should consider available for it to allocate across the list of projects and tasks.

Your app here is the first I've ever seen that is both MT and GPU Coprocessor. I expect you to have some scheduling problems with it :)

One final note: The server only knows the make/model of the highest-powered GPU, for each GPU type (NVIDIA or AMD or Intel), I believe. You probably already knew this. Not sure if that will affect your task assignment logic.

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40007 - Posted: 2 Feb 2015 | 21:08:12 UTC

If you allow multi-gpu setups to get work we can limit GPUGRID.net to one GPU via the <exclude_gpu> tag in cc_config.xml.


____________

hangya2
Send message
Joined: 15 Apr 12
Posts: 1
Credit: 121,031
RAC: 0
Level

Scientific publications
wat
Message 40015 - Posted: 3 Feb 2015 | 5:57:31 UTC
Last modified: 3 Feb 2015 | 6:00:13 UTC

about the AMDTEST wu:s
-on linux they did not download at all; same driver version as on w7; boinc asked only for cpu wu:s, even if it detected the amd card in the logs
-on w7 they finish without error, but do not follow the amount of dedicated cpu:s, they run on 4 cores regardless of local specification

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40016 - Posted: 3 Feb 2015 | 6:54:16 UTC - in response to Message 40015.

about the AMDTEST wu:s
-on linux they did not download at all; same driver version as on w7; boinc asked only for cpu wu:s, even if it detected the amd card in the logs
-on w7 they finish without error, but do not follow the amount of dedicated cpu:s, they run on 4 cores regardless of local specification


If you read through this thread you can read that Matt says, it is Windows x64 only. Hope this helps.

____________
Greetings from TJ

Profile tito
Send message
Joined: 21 May 09
Posts: 22
Credit: 1,465,988,678
RAC: 6,476,315
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwat
Message 40018 - Posted: 3 Feb 2015 | 14:15:17 UTC - in response to Message 40016.

No more WUs?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40019 - Posted: 3 Feb 2015 | 18:42:24 UTC - in response to Message 40018.

No more WUs?


Filled up now.

Profile nenym
Send message
Joined: 31 Mar 09
Posts: 137
Credit: 1,308,230,581
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40020 - Posted: 3 Feb 2015 | 19:18:29 UTC - in response to Message 40019.
Last modified: 3 Feb 2015 | 19:29:03 UTC

The fix credit 1500 per WU set. or?
Some tasks errored out after only-CPU stage. This and that.
part of stderr

clCreateProgramWithSource
starting mdrun 'Protein in water'
200000 steps, 400.0 ps.
Inner product between old and new vector <= 0.0!
constraint #0 atoms 1730 and 1731
Wrote pdb files with previous and current coordinates

WARNING: Listed nonbonded interaction between particles 1713 and 1731
at distance 2.985 which is larger than the table limit 1.995 nm.

This is likely either a 1,4 interaction, or a listed interaction inside
a smaller molecule you are decoupling during a free energy calculation.
Since interactions at distances beyond the table cannot be computed,
they are skipped until they are inside the table limit again. You will
only see this message once, even if it occurs for several interactions.

IMPORTANT: This should not happen in a stable simulation, so there is
probably something wrong with your system. Only change the table-extension
distance in the mdp file if you are really sure that is the reason.


Inner product between old and new vector <= 0.0!
constraint #0 atoms 73 and 74
Wrote pdb files with previous and current coordinates


Unhandled Exception Detected...

- Unhandled Exception Record -
Reason: Access Violation (0xc0000005) at address 0x000000013F573B37 read attempt to address 0x123DE8A0

Engaging BOINC Windows Runtime Debugger...

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40022 - Posted: 3 Feb 2015 | 20:41:38 UTC - in response to Message 40007.

If you allow multi-gpu setups to get work we can limit GPUGRID.net to one GPU via the <exclude_gpu> tag in cc_config.xml.



Is this a possibility?

Would groveling help? :D





lol

Cheers!
____________

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40023 - Posted: 3 Feb 2015 | 21:31:56 UTC - in response to Message 40022.

Not just yet. It will require a change in the application too

Matt

Profile tito
Send message
Joined: 21 May 09
Posts: 22
Credit: 1,465,988,678
RAC: 6,476,315
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwat
Message 40032 - Posted: 4 Feb 2015 | 18:18:28 UTC

How about credits? How are they calculated per WU? For now it's 1500 per WU but on XEON 1230V2 + 7950@1100 it gives ~ 160000 daily? Sounds little disappointing cause it takes 8 threads of CPU. Do You plan any adjustment in future or is it final?

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40033 - Posted: 4 Feb 2015 | 18:46:24 UTC - in response to Message 40032.
Last modified: 4 Feb 2015 | 18:47:31 UTC

How about credits? How are they calculated per WU? For now it's 1500 per WU but on XEON 1230V2 + 7950@1100 it gives ~ 160000 daily? Sounds little disappointing cause it takes 8 threads of CPU. Do You plan any adjustment in future or is it final?


A fixed amount of credits are now allocated per WU - like acemdlong , it's 1000 + 50% bonus for prompt return.

The actual amount of credits are still a placeholder value, while we are in beta.

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40034 - Posted: 4 Feb 2015 | 19:40:11 UTC
Last modified: 4 Feb 2015 | 19:41:01 UTC

At the moment this is a beta app which does not make good use of the gpu and it does not make much differece how many cpu's are used.
Unfortunately the project does not allow to download and run 2 or even mor wu's. So I looked for a way to increase the gpu usage to values from 93% to 100%.
https://dl.dropboxusercontent.com/u/50246791/gpugrid%20setup%201.JPG
Works on three pc's, all wu finish and validate. But may be different with a new version.

Alexander

Profile caffeineyellow5
Avatar
Send message
Joined: 30 Jul 14
Posts: 225
Credit: 2,658,976,345
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwat
Message 40035 - Posted: 4 Feb 2015 | 21:58:26 UTC - in response to Message 40034.

I just did a new build that has onboard AMD Radeon(TM) R7 Graphics. The driver version is Catalyst 14.12. I am not getting any work for this task on it.

MSI Afterburner is seeing 5 different lines/instances for this GPU. I also put 2 GTX780 cards in this build. I have the device management (for the profile called home on the GPUGRID preferences page of the website) set to use 100% of everything and to run everything except the CPU specific items. (As follows)
--------------------------------------------------------
Resource share 100
Use CPU yes
Use NVIDIA GPU yes
Run test applications? yes
Is it OK for GPUGRID and your team (if any) to email you? yes
Should GPUGRID show your computers on its web site? yes
Default computer location home
Maximum CPU % for graphics 100
Run only the selected applications
ACEMD short runs (2-3 hours on fastest card): yes
ACEMD beta: yes
ACEMD long runs (8-12 hours on fastest GPU): yes
Docking CPU only app: no
Molecular Dynamics on CPU: no
Molecular Dynamics on AMD GPUs: yes
If no work for selected applications is available, accept work from other applications? no
Use Graphics Processing Unit (GPU) if available yes
Use Central Processing Unit (CPU) yes
---------------------------------------------------------

Regardless of these settings and the fact the there are WUs showing on the Server Status page, this system is not getting any of these units. It did get one unit as I was building, before I added the GTX cards and it had an error while computing. This was my fault for adding software while still adding hardware. I was adding cards as they finished WUs on their originally installed computer before transferring to this new one. The new system is http://www.gpugrid.net/results.php?hostid=197994 This ADM GPU is showing as AMD Spectre (762MB) on the PC reference page here http://www.gpugrid.net/show_host_detail.php?hostid=197994

Do I have a setting or misconfiguration or do you need more info to determine? Or is this GPU just m=not able to do the work? Thx
____________
1 Corinthians 9:16 "For though I preach the gospel, I have nothing to glory of: for necessity is laid upon me; yea, woe is unto me, if I preach not the gospel!"
Ephesians 6:18-20, please ;-)
http://tbc-pa.org

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40036 - Posted: 4 Feb 2015 | 22:23:04 UTC - in response to Message 40035.

Tasks aren't assigned to machines with both Nvidia and AMD cards.

Matt

Profile caffeineyellow5
Avatar
Send message
Joined: 30 Jul 14
Posts: 225
Credit: 2,658,976,345
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwat
Message 40037 - Posted: 4 Feb 2015 | 22:32:09 UTC - in response to Message 40036.

Tasks aren't assigned to machines with both Nvidia and AMD cards.

Matt
OK, Thanks. I went AMD over Intel on the board so that maybe I could double up the tasks being done with AMD and NVidia. Hopefully I can get use out of the onboard GPU somewhere.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40038 - Posted: 4 Feb 2015 | 22:53:09 UTC

916 is up.
Should report progress and run on hosts with multiple gpus

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40041 - Posted: 5 Feb 2015 | 1:29:41 UTC

That explains why my 2x AMD GPU rig got 6 tasks. Says they are 9.15 (mt) though.


Never underestimate the power of proper groveling. ;-)


Cheers!
____________

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40042 - Posted: 5 Feb 2015 | 1:59:38 UTC
Last modified: 5 Feb 2015 | 2:00:26 UTC

Vista 6 core 2x 7870 GPUs machine got 9.15 (mt). Using <exclude_gpu> it was on GPU 0. Seldom touched the GPU CPU usage was 0-100 on all cores bouncing around. While Time Remaining stoped after about 10 minutes WU continued for, well it is at 97% and has run 44:55.

Windows 8.1 6 core 2 x 7870 9.15 (mt) did hit the gpus for 30% for a few minutes then to 0% for a few. CPU was all cores at about 20-30% and computation error after 119-122 seconds.
____________

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40043 - Posted: 5 Feb 2015 | 3:57:07 UTC - in response to Message 40042.

Vista 6 core 2x 7870 GPUs machine got 9.15 (mt). Using <exclude_gpu> it was on GPU 0. Seldom touched the GPU CPU usage was 0-100 on all cores bouncing around. While Time Remaining stoped after about 10 minutes WU continued for, well it is at 97% and has run 44:55.



After running for 2:46:41 and 14 minutes of that at 100% complete I aborted.

____________

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 40045 - Posted: 5 Feb 2015 | 8:12:14 UTC

I3 4130 (2 cores, HT off, I've checked, it's faster without it), Radeon 7790. AVG GPU load 48-51%, depends on WU.

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40048 - Posted: 5 Feb 2015 | 11:36:05 UTC

On my oldest machine 3/4 of the wu's fail with -1073741819 (0xffffffffc0000005) Unknown error number
http://www.gpugrid.net/result.php?resultid=13789647
http://www.gpugrid.net/result.php?resultid=13786661
http://www.gpugrid.net/result.php?resultid=13783126

all fail with - Unhandled Exception Record -
Reason: Access Violation (0xc0000005) at address 0x000000013F483B37 read attempt to address 0x0C4D5EB0

Its a AMD Phenom X4 with an AMD HD6950 GPU. Running win7 x64
Same setup works with HD7770 or on an A10 7700. Might be an issue with older hardware. I will change my setup.

BTW, still getting 915 wu's, not 916.

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 40049 - Posted: 5 Feb 2015 | 12:32:21 UTC - in response to Message 40048.


BTW, still getting 915 wu's, not 916.


Same here.

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40050 - Posted: 5 Feb 2015 | 14:20:40 UTC

Try again. The Applications page says that 9.17 was deployed at 13:40 UTC today.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 13,417,802,393
RAC: 71,624,153
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40053 - Posted: 5 Feb 2015 | 21:07:04 UTC

I've finished the first wu with sucess using 9.17 in a dual 7950 system.

So, good progress :))

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40058 - Posted: 5 Feb 2015 | 23:19:27 UTC
Last modified: 5 Feb 2015 | 23:33:01 UTC

My Win 8.1 box completed successfully a work unit. It used 95-98% of CPU and 50-63% of 1 GPU. Second GPU was not touched.

I tried using the <exclude_gpu> in cc_config.xml and ran 2 e@h apps on other gpu. CPU usage by mdrun-917 went from 98% to 65% and GPU for GPUgrid wu went from 65% to 43%. When I suspended the E@H project the GPUgrid numbers returned.

I know Vista was not listed on the list of OSes but my Vista box did get work units. Remaining time or completed time is always 100% and there is some activity on CPU, erratic and only a few spikes on GPU occasionally. I will disable it from getting apps unless you want to continue testing Vista 64bit.

Cheers!
____________

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40059 - Posted: 5 Feb 2015 | 23:30:27 UTC

Vista 64bit 2x 7870 6 core CPU.



____________

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40060 - Posted: 5 Feb 2015 | 23:34:54 UTC - in response to Message 40058.
Last modified: 5 Feb 2015 | 23:37:54 UTC

My Win 8.1 box completed successfully a work unit. It used 95-98% of CPU and 50-63% of 1 GPU. Second GPU was not touched.


Jobs will only ever run on the first GPU. <exclude_gpu> is not respected.



I know Vista was not listed on the list of OSes but my Vista box did get work units. Remaining time or completed time is always 100% and there is some activity on CPU, erratic and only a few spikes on GPU occasionally running about 30% for an extended time, several minutes. I will disable it from getting apps unless you want to continue testing Vista 64bit.


We can't support Vista. If it works good, but if not, better just disable it.

Matt

poppageek
Avatar
Send message
Joined: 4 Jul 09
Posts: 76
Credit: 114,610,402
RAC: 0
Level
Cys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40062 - Posted: 5 Feb 2015 | 23:58:28 UTC - in response to Message 40060.

My Win 8.1 box completed successfully a work unit. It used 95-98% of CPU and 50-63% of 1 GPU. Second GPU was not touched.


Jobs will only ever run on the first GPU. <exclude_gpu> is not respected.



I know Vista was not listed on the list of OSes but my Vista box did get work units. Remaining time or completed time is always 100% and there is some activity on CPU, erratic and only a few spikes on GPU occasionally running about 30% for an extended time, several minutes. I will disable it from getting apps unless you want to continue testing Vista 64bit.


We can't support Vista. If it works good, but if not, better just disable it.

Matt


That's cool. Just trying to be helpful. Not sure what info helps.

Cheers!

____________

Carlos Augusto Engel
Send message
Joined: 5 Jun 09
Posts: 38
Credit: 2,880,758,878
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40066 - Posted: 6 Feb 2015 | 12:45:05 UTC

I have one rig with AMD Hainan running 'POEM++ OpenCL version v2.17 (opencl_ati_101)' and 'OpenCL for AMD GPUs v9.15 (mt)' at the same time.

http://www.gpugrid.net/show_host_detail.php?hostid=196913

____________

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40067 - Posted: 6 Feb 2015 | 13:33:18 UTC - in response to Message 40066.

I have one rig with AMD Hainan running 'POEM++ OpenCL version v2.17 (opencl_ati_101)' and 'OpenCL for AMD GPUs v9.15 (mt)' at the same time.

http://www.gpugrid.net/show_host_detail.php?hostid=196913


Yes, that's because as far as BOINC is concerned our AMD GPU app is a CPU-only app. If you're not happy with the two tasks sharing the GPU, your best option is to opt out of the AMD GPU app.

Matt

Carlos Augusto Engel
Send message
Joined: 5 Jun 09
Posts: 38
Credit: 2,880,758,878
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40068 - Posted: 6 Feb 2015 | 13:43:23 UTC - in response to Message 40067.

Thats ok. I like them both.
____________

511513y
Send message
Joined: 15 Apr 14
Posts: 5
Credit: 6,433,630
RAC: 0
Level
Ser
Scientific publications
wat
Message 40069 - Posted: 6 Feb 2015 | 14:29:27 UTC

I've heard people on here say the app isn't well optimized yet, and I wonder if it's simply not scaling with GPU power at the moment.

On my system, it seems to run consistently at around 35 minutes each
My specs are as follows
CPU: Intel i7-4710HQ http://ark.intel.com/products/78930/Intel-Core-i7-4710HQ-Processor-6M-Cache-up-to-3_50-GHz
GPU: AMD Radeon R9 M265X http://www.notebookcheck.net/AMD-Radeon-R9-M265X.114535.0.html
RAM: 16 GB @ 1600 MHz
SSD: Toshiba Q-series (256 GB)

I've got it set for 5 threads, so it can potentially use a little HT if it helps. If it doesn't, for most apps its not much of a performance hit.
I also have the CPU set not to exceed 2.45 GHz, for thermal reasons.

Afterburner says the GPU utilization is about 74.25%
As of right now, I believe I'm CPU limited. If I allow the CPU to use Turbo Boost, it will go up to 2.9 GHz and the GPU utilization will increase to 78%

On my Nvidia system, with the 650M, utilization is usually around 90%, so, 74% isn't too far off.
Although the Nvidia app uses almost no CPU resources, it typically takes 23 hours to return even the smallests WUs on the laptop

I rather like the behavior of the AMD app using the CPU/GPU in unison.

What is the average run time for the AMD beta tasks?
and what kind of utilization and bottlenecks are you guys encountering?

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40074 - Posted: 6 Feb 2015 | 17:18:28 UTC

The situation is different between
laptop an desktop pc
well developed app and beta app

Most posts refer to desktop pc's. It's usually no problem to run them @ 95% gpu load 7/24 and that's what people like to see. The beta app uses on my HD7770 not more than 55% regardless how many of the 4 cpu's are involved. This is why I try to run 2 wu's on the gpu. I would prefer to run two gpugrid app at a time but this is inhibited by system settings. So I try to run 2 different apps on the gpu which works fine now since 2 days.
The goals are different for Matt and the volunteers. Matt tryes to have a stable app and will try to optimize it later. I want my gpu's to run near 100%. You want to keep your notebook alive by limiting the temp.

Alexander

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40075 - Posted: 6 Feb 2015 | 17:23:56 UTC - in response to Message 40069.

I've heard people on here say the app isn't well optimized yet, and I wonder if it's simply not scaling with GPU power at the moment.


This application is quite different to ACEMD. Whereas ACEMD really only needs a good GPU, this new one needs a good GPU, good CPU *and* good PCIe connectivity.

Inevitably, one of these will be a bottleneck - I'd never expect to see full utilisation of CPU and GPU- a realistic aim is to have both above 75%.

The current WUs are deliberately very short, so we get quick returns and good stats on failure rates.

Production work is probably a month or two away, but we'll ramp up WU sizes between now and then.

Matt

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 40076 - Posted: 6 Feb 2015 | 19:33:36 UTC - in response to Message 40075.

Can't wait till full production. Until then my 5960x and 290x are happily curching away.

zombie67 [MM]
Avatar
Send message
Joined: 16 Jul 07
Posts: 209
Credit: 3,058,436,456
RAC: 2,990,068
Level
Arg
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40097 - Posted: 8 Feb 2015 | 3:56:41 UTC
Last modified: 8 Feb 2015 | 4:23:26 UTC

I have a machine with two 7970s. The app appears to be using only one. Is this expected? It won't use them both?

Edit:

Also, it uses only 8 threads on a 12 thread machine. I have no restrictions set in any .xml files.

Arg 0 [projects/www.gpugrid.net/mdrun-917.exe]
Arg 1 [--nthreads]
Arg 2 [8]
BOINC running with [8] threads


CPU load confirms only 8 of 12.
____________
Reno, NV
Team: SETI.USA

TJ
Send message
Joined: 26 Jun 09
Posts: 815
Credit: 1,470,385,294
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40102 - Posted: 8 Feb 2015 | 6:29:32 UTC - in response to Message 40097.

A little down in this thread:

My Win 8.1 box completed successfully a work unit. It used 95-98% of CPU and 50-63% of 1 GPU. Second GPU was not touched.



Jobs will only ever run on the first GPU. <exclude_gpu> is not respected.


So yes only on GPU is used.

____________
Greetings from TJ

Old man
Send message
Joined: 24 Jan 09
Posts: 42
Credit: 16,676,387
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40105 - Posted: 8 Feb 2015 | 9:35:39 UTC

Working. Gpu usage is little bit over 50%. It using all of my 4 theards.

http://www.gpugrid.net/result.php?resultid=13800417

lolmaster
Send message
Joined: 22 Oct 09
Posts: 7
Credit: 78,506
RAC: 0
Level

Scientific publications
wat
Message 40106 - Posted: 8 Feb 2015 | 16:46:21 UTC
Last modified: 8 Feb 2015 | 16:47:23 UTC

Matt are you working on the Access Violation problem?

http://www.gpugrid.net/result.php?resultid=13790793
http://www.gpugrid.net/result.php?resultid=13795778
http://www.gpugrid.net/result.php?resultid=13801334
http://www.gpugrid.net/result.php?resultid=13801633

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40114 - Posted: 8 Feb 2015 | 20:48:51 UTC - in response to Message 40106.

No,

I'm not too bothered about those - the incidence rate is low and it always happens very soon after the task's started so little effort is wasted.

Matt

marcellino[CactusCo]
Send message
Joined: 17 Nov 11
Posts: 4
Credit: 55,077,408
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwat
Message 40117 - Posted: 8 Feb 2015 | 23:11:30 UTC
Last modified: 8 Feb 2015 | 23:31:00 UTC

After many WUs errored I reset my Radeon 7950 (100% stable on folding@home @1005MHz, watercooled, no overvolt) back to its factory clock of 880MHz and now it magically seems to work without error on GPUGRID 9.17(mt).
(AthlonX4 610e 2.4GHz, four CPUs used, 54% GPU load).

Edit:"without error" could be too much, but it could, at least once, work...
____________

kain
Send message
Joined: 3 Sep 14
Posts: 152
Credit: 708,332,245
RAC: 2,064,986
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 40121 - Posted: 9 Feb 2015 | 1:08:30 UTC

What is your avg PPD in f@h with this card and clock?

Profile X1900AIW
Send message
Joined: 12 Sep 08
Posts: 74
Credit: 23,566,124
RAC: 0
Level
Pro
Scientific publications
watwatwatwatwatwatwatwatwatwat
Message 40125 - Posted: 9 Feb 2015 | 11:00:32 UTC
Last modified: 9 Feb 2015 | 11:03:49 UTC

2 (old) errors with 9.15, 111 valids with 9.17.

HD7950 boost core clock@1000Mhz, undervolted, running very smooth, 7 cpu threads (8 available), gpu usage 58-59 percent, gpu 50-52 degrees Celsius, idle-BOINC@90 percent cpu usage (57-174) +118 watts.

Congratulation to this well-oiled Beta AMD support ! Wake up from hibernate with no lags from checkpointing.


marcellino[CactusCo]
Send message
Joined: 17 Nov 11
Posts: 4
Credit: 55,077,408
RAC: 0
Level
Thr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwat
Message 40137 - Posted: 9 Feb 2015 | 23:20:13 UTC - in response to Message 40121.
Last modified: 9 Feb 2015 | 23:22:11 UTC

I would say about 83'000 ppd on folding@home.
http://folding.extremeoverclocking.com/user_summary.php?s=&u=654291
____________

[VENETO] boboviz
Send message
Joined: 10 Sep 10
Posts: 158
Credit: 388,132
RAC: 0
Level

Scientific publications
wat
Message 40139 - Posted: 10 Feb 2015 | 6:41:56 UTC

Strange behaviour:
1) My client request only work for cpu, but i download gpu amd app
2) My client says it's using 6 cpu core and not an amd gpu (like, for example poem): (1cpu+1gpu) in boinc manager
3) Gpu-z gives me 90% gpu load, so app is using gpu[/img]

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40140 - Posted: 10 Feb 2015 | 10:24:28 UTC - in response to Message 40139.
Last modified: 10 Feb 2015 | 10:24:56 UTC

Strange behaviour:
1) My client request only work for cpu, but i download gpu amd app
2) My client says it's using 6 cpu core and not an amd gpu (like, for example poem): (1cpu+1gpu) in boinc manager
3) Gpu-z gives me 90% gpu load, so app is using gpu[/img]


But all expected and correct.
For technical reasons we have to deploy this as appearing to BOINC as CPU-only.

The old "CPU" app is gone now.
Matt

Richard Haselgrove
Send message
Joined: 11 Jul 09
Posts: 1617
Credit: 8,122,944,351
RAC: 17,866,091
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40141 - Posted: 10 Feb 2015 | 11:04:08 UTC - in response to Message 40140.

Matt,

Could you expand a little on those "technical reasons", please - primarily for the benefit of us BOINC-watchers in the community?

I'm familiar with Specifying plan classes in C++ and Specifying plan classes in XML: I also remember you saying that the BOINC server here doesn't have all the latest features, which may restrict the degree to which you can use the XML route.

But I think you're perhaps the first project developer who has attempted to combine the features of MT and ATI plan_class specifications. That could be useful to other projects as well, if the new gromacs version is a success.

Are you perhaps finding that this requirement is inhibiting you from combining the two features?

GPU plan classes
Note: plan classes containing the substrings 'nvidia', 'cuda', and 'ati' are reserved for GPU applications. Plan classes for AMD GPUs must contain the substring 'ati'; plan classes for NVIDIA GPUs much contain either 'nvidia' or 'cuda' as a substring; plan classes for OpenCL applications must include 'opencl' as a substring.

(from Plan classes)

If so, we ought to draw it to the BOINC developers' attention, so that the limitation can be lifted or worked round in the next release of BOINC server software. I'd be happy to try and help liaise with David Anderson, if that's the case.

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40142 - Posted: 10 Feb 2015 | 14:01:06 UTC - in response to Message 40141.

Matt,

Could you expand a little on those "technical reasons", please - primarily for the benefit of us BOINC-watchers in the community?



Sure. Our BOINC scheduler is too old to understand the OpenCL plan class, and if we use the "ati" plan class the BOINC client rejects the application if the CAL runtime isn't available (which is the case with any new AMD driver set).

Eventually we'll upgrade the server, but that's not happening any time soon.

Matt

[VENETO] boboviz
Send message
Joined: 10 Sep 10
Posts: 158
Credit: 388,132
RAC: 0
Level

Scientific publications
wat
Message 40153 - Posted: 12 Feb 2015 | 13:39:38 UTC - in response to Message 39895.


Known issues are:
* Checkpoint restart not working


Hope in the next version....

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40154 - Posted: 12 Feb 2015 | 17:43:07 UTC - in response to Message 40153.


Known issues are:
* Checkpoint restart not working


Hope in the next version....


Actually it might be. give it a go and tell me.

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 40155 - Posted: 12 Feb 2015 | 18:27:32 UTC - in response to Message 40154.


Known issues are:
* Checkpoint restart not working


Hope in the next version....


Actually it might be. give it a go and tell me.


No.

[VENETO] boboviz
Send message
Joined: 10 Sep 10
Posts: 158
Credit: 388,132
RAC: 0
Level

Scientific publications
wat
Message 40158 - Posted: 13 Feb 2015 | 9:24:55 UTC - in response to Message 40155.
Last modified: 13 Feb 2015 | 9:25:38 UTC


Actually it might be. give it a go and tell me.

No.


+1. If i restart my pc, wus restart from 0%

Profile MJH
Project administrator
Project developer
Project scientist
Send message
Joined: 12 Nov 07
Posts: 696
Credit: 27,266,655
RAC: 0
Level
Val
Scientific publications
watwat
Message 40163 - Posted: 13 Feb 2015 | 14:32:22 UTC - in response to Message 40158.


Actually it might be. give it a go and tell me.

No.


+1. If i restart my pc, wus restart from 0%


Can you direct me to the output of a job where a restart has happened please?

Werkstatt
Send message
Joined: 23 May 09
Posts: 121
Credit: 326,340,386
RAC: 55,368
Level
Asp
Scientific publications
watwat