Linux 32-bit ATI App
log in

Advanced search

Message boards : Number crunching : Linux 32-bit ATI App

Author Message
[AF>Libristes] ElGuillermo
Send message
Joined: 19 May 11
Posts: 1
Credit: 22,870,538
RAC: 152
Message 14856 - Posted: 10 Oct 2012, 23:07:59 UTC
Last modified: 10 Oct 2012, 23:20:56 UTC

Hi !

I'm using the experimental ati 32 bits linux executable, but all the WUs I get crash in error after 1 second of calculation.

My 4870 AGP video card is getting WUs from Moo! and Primegrid, and crunches them to the end with no error.

Oh ! "Install a 64 bits version" isn't possible : I'm running Ubuntu on a 32 bits P4.

Advices welcome :)

terencewee*
Send message
Joined: 20 Dec 10
Posts: 12
Credit: 39,717,409
RAC: 0
Message 11882 - Posted: 30 Mar 2011, 8:31:40 UTC - in response to Message 11766.


If it's possible, install a 64 bit linux. That way you won't have that problem.


I was having some free time last week and had reinstalled the machine with 64bit linux (ubuntu 10.10 x64).

I'm happy to report after following required steps - we got (mini) joy!

Crunching normal WU will hang the system after a random number of hours. I can't be sure whether it's the app or the BOINC client, but I would go with the former as...

Crunching mini WU finishes in about 5hrs40min mark, works fine and validated (here and here).

@Crunch3r: since your are the original Crunch3r, I've named the system as cruncher02. :)

Thanks guys.

Profile Crunch3r
Volunteer moderator
Project developer
Project tester
Avatar
Send message
Joined: 30 Jun 09
Posts: 219
Credit: 7,515,663,568
RAC: 12,058
Message 11766 - Posted: 17 Mar 2011, 21:32:53 UTC - in response to Message 11765.

It seems like it isn't picking up the BRT_PERMIT_READ_WRITE_ALIASING variable for some reason. After setting it, when you run printenv does it show up? If not, have you tried logging out and then back in so it will reload the system profile?



research@jeeven:~$ printenv
TERM=xterm
SHELL=/bin/bash
XDG_SESSION_COOKIE=e350922e192797d9d45b0ea24c6ee93c-1300394556.63737-284112045
SSH_CLIENT=xx.xx.xx.xx xxxxx xxxx
SSH_TTY=/dev/pts/0
USER=research
LS_COLORS=rs=0:di=01
MAIL=/var/mail/research
PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games
PWD=/home/research
LANG=en_US.UTF-8
SPEECHD_PORT=7560
SHLVL=1
HOME=/home/research
LOGNAME=research
BRT_PERMIT_READ_WRITE_ALIASING=1
SSH_CONNECTION=xx.xx.xx.xx xxxxx xxx.xxx.x.xx xxxx
LESSOPEN=| /usr/bin/lesspipe %s
LESSCLOSE=/usr/bin/lesspipe %s %s
_=/usr/bin/printenv


I had also tried restarting the machine.
BOINC-client is running as a daemon.



I know ATI made the suggestion that read-write was not suggested. I wonder if newer versions of the CAL no longer support that option. I'll have to do some research on that.


Anything else you want me to find out over here?


Thanks Slicker - hope to get collatz running on linux GPU-crunchers.


If it's possible, install a 64 bit linux. That way you won't have that problem.

____________

Team BOINC United.Join Science that matters.

terencewee*
Send message
Joined: 20 Dec 10
Posts: 12
Credit: 39,717,409
RAC: 0
Message 11765 - Posted: 17 Mar 2011, 20:51:37 UTC - in response to Message 11764.

It seems like it isn't picking up the BRT_PERMIT_READ_WRITE_ALIASING variable for some reason. After setting it, when you run printenv does it show up? If not, have you tried logging out and then back in so it will reload the system profile?



research@jeeven:~$ printenv
TERM=xterm
SHELL=/bin/bash
XDG_SESSION_COOKIE=e350922e192797d9d45b0ea24c6ee93c-1300394556.63737-284112045
SSH_CLIENT=xx.xx.xx.xx xxxxx xxxx
SSH_TTY=/dev/pts/0
USER=research
LS_COLORS=rs=0:di=01
MAIL=/var/mail/research
PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games
PWD=/home/research
LANG=en_US.UTF-8
SPEECHD_PORT=7560
SHLVL=1
HOME=/home/research
LOGNAME=research
BRT_PERMIT_READ_WRITE_ALIASING=1
SSH_CONNECTION=xx.xx.xx.xx xxxxx xxx.xxx.x.xx xxxx
LESSOPEN=| /usr/bin/lesspipe %s
LESSCLOSE=/usr/bin/lesspipe %s %s
_=/usr/bin/printenv


I had also tried restarting the machine.
BOINC-client is running as a daemon.



I know ATI made the suggestion that read-write was not suggested. I wonder if newer versions of the CAL no longer support that option. I'll have to do some research on that.


Anything else you want me to find out over here?


Thanks Slicker - hope to get collatz running on linux GPU-crunchers.

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 11764 - Posted: 17 Mar 2011, 19:37:25 UTC

It seems like it isn't picking up the BRT_PERMIT_READ_WRITE_ALIASING variable for some reason. After setting it, when you run printenv does it show up? If not, have you tried logging out and then back in so it will reload the system profile?

I know ATI made the suggestion that read-write was not suggested. I wonder if newer versions of the CAL no longer support that option. I'll have to do some research on that.

terencewee*
Send message
Joined: 20 Dec 10
Posts: 12
Credit: 39,717,409
RAC: 0
Message 11756 - Posted: 16 Mar 2011, 19:24:59 UTC - in response to Message 6361.

I'd been tinkering with linux GPU apps these few weeks as I wanted to learn as much first hand before committing to building new crunchers.

I am now trying out collatz-app for linux-32 ATI.

boinc-client start up messages:

1: 17-Mar-2011 02:27:45 (low) [] Starting BOINC client version 6.12.15 for i686-pc-linux-gnu
2: 17-Mar-2011 02:27:45 (low) [] Config: report completed tasks immediately
3: 17-Mar-2011 02:27:45 (low) [] Config: use all coprocessors
4: 17-Mar-2011 02:27:45 (low) [] Config: GUI RPC allowed from:
5: 17-Mar-2011 02:27:45 (low) [] Config: 192.168.1.5
6: 17-Mar-2011 02:27:45 (low) [] Config: localhost
7: 17-Mar-2011 02:27:45 (low) [] Config: 127.0.0.1
8: 17-Mar-2011 02:27:45 (low) [] log flags: file_xfer, sched_ops, task
9: 17-Mar-2011 02:27:45 (low) [] Libraries: libcurl/7.19.7 OpenSSL/0.9.8k zlib/1.2.3.3 libidn/1.15
10: 17-Mar-2011 02:27:45 (low) [] Data directory: /var/lib/boinc-client
11: 17-Mar-2011 02:27:45 (low) [] Processor: 2 GenuineIntel Intel(R) Core(TM)2 Duo CPU E4600 @ 2.40GHz [Family 6 Model 15 Stepping 13]
12: 17-Mar-2011 02:27:45 (low) [] Processor: 2.00 MB cache
13: 17-Mar-2011 02:27:45 (low) [] Processor features: fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx lm constant_tsc arch_perfmon pebs bts aperfmperf pni dtes64 monitor ds_cpl est tm2 ssse3 cx16 xtpr pdcm lahf_lm
14: 17-Mar-2011 02:27:45 (low) [] OS: Linux: 2.6.32-29-generic
15: 17-Mar-2011 02:27:45 (low) [] Memory: 1.96 GB physical, 5.75 GB virtual
16: 17-Mar-2011 02:27:45 (low) [] Disk: 287.75 GB total, 269.92 GB free
17: 17-Mar-2011 02:27:45 (low) [] Local time is UTC +8 hours
18: 17-Mar-2011 02:27:45 (low) [] ATI GPU 0: ATI Radeon HD 2300/2400/3200 (RV610) (CAL version 1.4.900, 256MB, 50 GFLOPS peak)
19: 17-Mar-2011 02:27:45 (low) [Collatz Conjecture] Found app_info.xml; using anonymous platform
20: 17-Mar-2011 02:27:45 (low) [SETI@home] Found app_info.xml; using anonymous platform


ATI RV610 detected, CAL 1.4.900 (Catalyst 10.12) - runs DNETC fine (albeit extremely slow, but hey! it works and WU got validated).


Downloaded [collatz_2.09_i686-pc-linux-gnu__ati14.tar.bz2 (Linux 32-bit ATI - EXPERIMENTAL!!!) 2.09 ATI CAL 1.4 01/17/2010 21:32 CST]

unpacked, copied *.so to /usr/lib, ldd =

linux-gate.so.1 => (0x00a43000)
libm.so.6 => /lib/tls/i686/cmov/libm.so.6 (0x00207000)
libbrook.so => /usr/lib/libbrook.so (0x008c7000)
libaticalrt.so => /usr/lib/fglrx/libaticalrt.so (0x00779000)
libc.so.6 => /lib/tls/i686/cmov/libc.so.6 (0x0022d000)
/lib/ld-linux.so.2 (0x00a09000)
libpthread.so.0 => /lib/tls/i686/cmov/libpthread.so.0 (0x0017b000)
libstdc++.so.6 => /usr/lib/libstdc++.so.6 (0x00d36000)
libgcc_s.so.1 => /lib/libgcc_s.so.1 (0x00ca3000)
librt.so.1 => /lib/tls/i686/cmov/librt.so.1 (0x0019f000)
libdl.so.2 => /lib/tls/i686/cmov/libdl.so.2 (0x0059c000)
libXext.so.6 => /usr/lib/libXext.so.6 (0x0049b000)
libX11.so.6 => /usr/lib/libX11.so.6 (0x005a0000)
libxcb.so.1 => /usr/lib/libxcb.so.1 (0x00471000)
libXau.so.6 => /usr/lib/libXau.so.6 (0x00b9a000)
libXdmcp.so.6 => /usr/lib/libXdmcp.so.6 (0x003db000)


Added BRT_PERMIT_READ_WRITE_ALIASING=1 into /etc/profile

Added collatz project and got WUs.

Computation error thru-out.

An example: http://boinc.thesonntags.com/collatz/result.php?resultid=77799570


<core_client_version>6.12.15</core_client_version>
<![CDATA[
<message>
process exited with code 1 (0x1, -255)
</message>
<stderr_txt>

Running Collatz Conjecture (3x+1) ATI GPU application version 2.09 by Gipsel (Win32, CAL 1.3)
instructed by BOINC client to use device 0
Reading input file ... done.
Checking 824633720832 numbers starting with 2368591747413562861928
CAL Runtime: 1.4.900
Found 1 CAL device

Device 0: ATI Radeon HD2350/2400/3200/3400 (RV610/620) 256 MB local RAM (remote 247 MB cached + 875 MB uncached)
GPU core clock: 0 MHz, memory clock: 0 MHz
40 shader units organized in 1 SIMDs with 8 VLIW units (5-issue), wavefront size 32 threads
not supporting double precision

Initializing lookup table (16384 kB) ... done
Starting WU on GPU 0
Copy lookup table to GPU memory (16384 kB)
Initialize step array on GPU (64 MB)
predicted runtime per iteration is 2 ms (33.3333 ms are allowed)
borders of the domains at 0 4096
No checkpoint data found.
0 Kernel Execution : Input stream is same as output stream.
Binding kernels read-write is prohibited.

02:28:45 (1514): called boinc_finish

</stderr_txt>
]]>


I've tried commenting out export BRT_PERMIT_READ_WRITE_ALIASING=1; same result.

Can anyone offer help?

Thanks.

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 6361 - Posted: 26 Feb 2010, 22:24:46 UTC - in response to Message 6323.

Hi,

i am testing collatz_2.09_i686-pc-linux-gnu__ati14.tgz

1. untar
2. copy libbrook.so to /usr/lib/
3. starting collatz_2.09_i686-pc-linux-gnu__ati14
Result:
Shared Object NOT Found! libbrook_cal.so

This file is missing in collatz_2.09_i686-pc-linux-gnu__ati14.tgz


I created a new file which includes the libbrook_cal.so and also updated the app_info.xml to include it as well.

collatz_2.09_i686-pc-linux-gnu__ati14.tar.bz2

I'm starting to think gcc will only link libstdc++ dynamically because the brook library is dynamic and probably calls it.

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 6358 - Posted: 26 Feb 2010, 21:37:35 UTC

First, I think the 32-bit app will only work on 1 GPU at present, just like the 64-bit version. Gipsel has custom code in his altered brook.dll to handle switching devices. CAL 1.4 has the support built-in (if called), but I don't think it is calling it properly.

Second, I haven't had any luck compiling with a static libstdc++ while using the dynamic libs for brook and the cal runtime. For cpu apps with gcc, I just add -static and it works, but I can't do that as there are no static libs for CAL/Brook. I've tried using the -Bstatic and -Bdynamic but so far without luck. The -static-libgcc doesn't seem to work as it always finds the .so first. Even with a symbolic link to the local folder it doesn't appear to work. Anyone have some suggestions?

Profile DeleteNull
Volunteer tester
Avatar
Send message
Joined: 18 Sep 09
Posts: 29
Credit: 2,087,516,533
RAC: 0
Message 6323 - Posted: 24 Feb 2010, 21:41:38 UTC - in response to Message 5762.

Hi,

i am testing collatz_2.09_i686-pc-linux-gnu__ati14.tgz

1. untar
2. copy libbrook.so to /usr/lib/
3. starting collatz_2.09_i686-pc-linux-gnu__ati14
Result:
Shared Object NOT Found! libbrook_cal.so

This file is missing in collatz_2.09_i686-pc-linux-gnu__ati14.tgz

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 5762 - Posted: 23 Jan 2010, 0:44:16 UTC - in response to Message 5749.

Ok i'm fixing the problem with the library with

cp libbrook.so /usr/lib

But when i run the executable i think it quit after one or two second.

In my system i'have installed the latest Ati proprietary driver.

When i launch boinc manager(the latest stable version) i see it not recognize the GPU in fact my CPU works on other project(Seti) and Collatz is in attempt..



1. I don't see any computers registered in the Collatz project under your account, so have you attached to the Collatz project?

2. Does the BOINC message log show that you have an ATI coprocessor installed?

3. Does the BOINC message log show that you are using an anonymous application for the Collatz project?

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 5745 - Posted: 22 Jan 2010, 15:08:14 UTC - in response to Message 5737.

Hi guys, i'm on Debian Linux, i've downloaded the optimized app for linux-32.

Uncompressing the .tgz
Chmod +x collatz_2.09_i686-pc-linux-gnu__ati14
and
./collatz_2.09_i686-pc-linux-gnu__ati14

This is the result:

./collatz_2.09_i686-pc-linux-gnu__ati14: error while loading shared libraries: libbrook.so: cannot open shared object file: No such file or directory

I've done something wrong or what?

Thanks in advance!


I assume you have already installed ATI drivers.

Note that when BOINC runs the app, it adds the current path to the LD_LIBRARY_PATH environment variable so that the app can find the libbrook.so file, or at least the latest versions do.

To run it in standalone mode (not through BOINC) you will need to add the current folder.

export LD_LIBRARY_PATH=.:$LD_LIBRARY_PATH

The alternative is to copy the libbrook.so to the /usr/lib folder or leave it in the project folder and create a link to it in the /usr/lib folder.

Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 5639 - Posted: 19 Jan 2010, 15:06:24 UTC - in response to Message 5638.

collatz_2.09_i686-pc-linux-gnu__ati14.tgz (Linux 32-bit ATI - EXPERIMENTAL!!!) 2.09 ATI CAL 1.4 01/17/2009 21:32 CST

date i think must be 01/17/2010 or not?

cu, hf, stephan



Thanks. It has been corrected.

Profile Stephan Volkmann
Send message
Joined: 8 Dec 09
Posts: 4
Credit: 61,542,708
RAC: 175,239
Message 5638 - Posted: 19 Jan 2010, 14:27:46 UTC

collatz_2.09_i686-pc-linux-gnu__ati14.tgz (Linux 32-bit ATI - EXPERIMENTAL!!!) 2.09 ATI CAL 1.4 01/17/2009 21:32 CST

date i think must be 01/17/2010 or not?

cu, hf, stephan



Profile Slicker
Volunteer moderator
Project administrator
Project developer
Project tester
Project scientist
Avatar
Send message
Joined: 11 Jun 09
Posts: 2525
Credit: 740,580,099
RAC: 1
Message 5618 - Posted: 18 Jan 2010, 4:14:33 UTC

I added an experimental app to the power apps page for Linux 32-bit. At present, it is totally untested, so any feedback is welcome.

There were a couple people asking for it, so I'm hoping they are still reading the MB and are willing to help test. It is compiled with Brook/CAL 1.4, so you will need Catalyst 9.2 or higher drivers.

You may have to set the environment variable BRT_PERMIT_READ_WRITE_ALIASING
The documentation is not very good, so I have no idea what the value should be. My guess is either that just having it might work. If not, try setting the value to 1.

I did not include the libbrook_cal.so in the gzipped tar file, so if you find you need it (via ldd command), let me know.


Post to thread

Message boards : Number crunching : Linux 32-bit ATI App


Main page · Your account · Message boards


Copyright © 2018 Jon Sonntag; All rights reserved.