(old)Puppy Linux Discussion Forum

Thanks! Works perfect with 4.3.1

I was wondering if anybody uses the high performance GPU client with Puppy?

My skill level is not so hot, the PET packages have me spoiled. Don't know how to do anything the hard way cause so far I've always been able to find a PET that works.

Anybody know where to get a GPU PET?

or how to set up a GPU client the hard way?

There is help for Ubuntu and Arch but I was thinking Puppy would be awesome since Puppy is so fast.

TIA!

Does anyone still have this *.pet? The original link is way broken.

Seconding that request here, tried compiling my own pet for FAH and failed miserably and can't find original pet anywhere.

http://cid-92fde94f233d97a1.skydrive.li ... 6.2.15.pet

found this one

Nice, Berkeley's Version of FAH thanks alot

DPUP5520 wrote:Nice, Berkeley's Version of FAH thanks alot

you're welcome

that's just the way we roll

Found it, don't know if it's the right one but here's what I found haven't tried it yet

Just set up an old computer (Pentium D) with FAH SMP and I'm about 50% through my very first Work Unit. (I used Team Puppy Linux - User Sunny).

Frugal install of FatDog-521 on a USB Stick. That fired right up and is running very stable on my machine -- nice job on that distribution guys. I've been using Puppy since version 2 ... this is the first 64-bit puppy I've tried.

I put the following in rc.local to help minimize power consumption:
swapoff -a
hdparm -S 24 /dev/sda
echo "1" > /sys/devices/system/cpu/cpufreq/ondemand/ignore_nice_load

The first two lines are used to put the hard drive into standby. The third line is used to throttle back the cpu so that FAH does not run it at 100% ... those Pentium D processors run really hot.

I run this computer headless using x11vnc-server & have turned off the "Save Session" in Puppy Event Manager.

I installed FAH using the instructions on the site for Linux SMP. I had to compile Curl, but that went without a hitch. (Note that I had to use the fd64-32bit-libs-6.sfs & fd64-devx_521.sfs files to do the compile.)

I would try the FAH GPU program using Wine, but I've only got a 7600gt card in this machine.

Anyway, FatDog-64 & the FAH program have been running really stable for about a day now as I been tweaking it.

My name is Haut_Dawg. I just joined the team. Just wanted to introduce myself.
Cheers!

My First Certificate!! Woo Hoo!!

Decided to contribute 2 of my machines to the cause , an old emachines T1090 900mhz celeron and a server I don't use anymore running an 8320 eight-core AMD and Nvidia GTX 650 TI(Kelper) with all three running projects the two machines are getting about 17000 PPD.

I acquired an old Asus en9600gt Silent graphics card and decided to install it in the PC I was using for SMP Folding with FatDog-521. This is the procedure I used in case anyone else is interested in doing GPU folding with FatDog. Note that the SMP client runs in linux, but the GPU client must be run from FatDog using Wine.

I followed much of the guide provided here:
http://linuxfah.info/mediawiki/index.ph ... =Main_Page

Step 1) I started with a clean frugal installation of FatDog-521. I installed the nvidia-280.13-for-520-final.pet for my 64-bit nvidia driver. I also loaded the fd64-dev_521.sfs and fd64-32bit-libs-6.sfs packages so I could compile a couple of programs.

Step 2) I downloaded the cudatoolkit_3.0_linux_32_rhel4.8.run program from nivida. This is a 32-bit cuda tool kit package which is needed as indicated in the reference guide. I quit the X-server and executed this program using the sh command. When this is done, it provides a couple of PATH entries that I added to /etc/profile for PATH & LD_LIBRARY_PATH.

Step 3) This step was optional. I wanted to use the FahMon tool and this pkg requires wxGTK. There is a pet package available for wxwidgets that may work, but I decided to compile wxGTK myself. I downloaded the source for wxGTK-2.8.12 and compiled/installed it using "./configure --prefix=/usr --enable-unicode --enable-shared". I then downloaded the source for FahMon-2.3.99.3 and compiled/installed it using "./configure --prefix=/usr"

Step 4) This step was optional. At this point my puppy save file is pretty big because the nvidia driver and cuda toolkit are huge ... so I decided to remaster my FatDog CD. I unloaded all sfs packages and used the "Remaster Puppy live-CD" program to do a quick remaster.

Step 5) I booted my remastered FatDog which now includes the nvidia 64-bit driver, the 32-bit cuda toolkit, the wxGTK package and FahMon. At this point, it is necessary to load the fd64-32bit-libs-6.sfs and wine-1.3.25-i486.sfs packages at bootup. In order to setup the wine directories, I ran the "wine notepad" command in a terminal. Using the reference guide, I then downloaded and saved the cuda wrappers cudart.dll.so & cufft.dll.so into the ~/.wine/drive_c/windows/system32 directory. Next, I created the symbolic links required as shown in the reference guide.

Step 6) Finally, I installed the Folding@home-Win32-GPU_XP-641.zip console client from the Stanford site. I extracted this and removed the dll files from the directory. I execute this program with the "nice -n 19 wine Folding@home-Win32-GPU.exe -forcegpu nvidia_g80" command.

I am currently running this FatDog from a USB stick with frugal install. I turn off the swap and shut down the hard drive using a "hdparm -S" command. I used nvidia-settings to overclock my GPU and the SMP/GPU clients run concurrently. With an old Pentium D and 9600gt, I can get around 4000 ppd. CPU and GPU both run under 55 degrees C.

Hi there!

Very nice PET!! (seems to work perfect under Precise 5.7.1)
As a researcher and a Puppy enthusiast I am really glad to find that there is a Puppy Linux Team!

I've joined the team fellows!
I am currently using 25% of my CPU capacity. The computer I am running now (work computer) has 4 cores. How can I set FahCore to use at least 2 cores?

Best wishes!

joaomcteixeira ...

"Very nice PET!! (seems to work perfect under Precise 5.7.1)"

If you are using the PET contained in this thread for folding, you may be using a pretty old version (V6) of the FAH software.

I have described installation of the latest V7 FAH software on 32-bit Puppy here (April 5, 2013 post):
https://foldingforum.org/viewtopic.php?f=89&t=24017

In that thread, I also discuss installation of FAH for SMP & GPU folding on the 64-bit Fatdog.

If you have specific questions on the configuration of FAH, you will get very quick responses to your questions if you post them on the Folding Forum:
https://foldingforum.org/index.php

You should be able to specify how many cores you want to use in the configuration menus of FAHControl (you can also do it when starting from the command line). If you are using FAHControl, make sure the Folding Power Slider is set to full.

Be sure to check out that Folding Forum & thanks for joining the Puppy Team.

sunny

Hi Sunny!

Yes you are right!

I then changed to the newest V7 version and I correctly configured it to run with three cores under Precise 32bit with the help of the people in the Folding Forum.

https://foldingforum.org/viewtopic.php?f=88&t=25767

I do want to try FatDog because now I am on a 64-bit computer. So I will take a look at your post!

I am really enjoying Puppy Linux I am using it in my work computer, I am at the University of Barcelona, lets see if I can put people around loving pets

For now.. folding with the Puppy Linux Team!

In an old post, I described the steps to install FAH v7 in FatDog_521:
http://www.murga-linux.com/puppy/viewtopic.php?t=84587

Those steps have to be modified somewhat if you want to install FAH v7 in FatDog_630:

Step 1) Installation of FAHControl
FAHControl is used to configure/monitor/control the version 7 CPU client.

FAHControl requires python and pygtk. You can get these packages at this site:
http://distro.ibiblio.org/fatdog/pets/600/

Use the python-2.6.6.pet file. I could not get the python-2.7.5 version to work due to a problem with gtk.
(Note that python-2.6.6 is included in fd64-devx_630.sfs so you may not need the pet file if you always boot with that sfs file loaded.)

After installing python-2.6.6.pet, then download and install pygtk-2.24-x86_64.pet

Now, download fahcontrol_7.3.6-1_all.deb from Folding@home website and click on it to install it. Then, go into the /usr/shared/pyshared directory and copy/move the two directories (fah & FAHControl-7.3.6.egg-info) to the /usr/lib64/python2.6/site-packages directory.

I then went into /usr/share/applications and edited FAHControl.desktop to add an appropriate Category so that it would show up in my menu (use terminal command "fixmenus" to update the menu). At this point, you should be able to select FAHControl in your menu and it should open up correctly.

Step 2) Installation of FAHClient

Download fahclient_7.3.6_amd64.deb from Folding@home website and click on it to install it.

I disconnected from the web at this point so that I could get the FAHClient configured before it downloaded any WUs. I then edited the file /etc/init.d/FAHClient ... I changed USER=fahclient to USER=root and I changed HOME= to the directory I wanted it to use for the work directory. Save the file and then start the client from the /etc/init.d directory by typing: "./FAHClient start"

The client should start, and you can now configure it using FAHControl (installed in Step 1). Type in your identity and hopefully you will be using Team Puppy Linux (157623). Also set the slider to full if you want to use all your cores for folding. Save the configuration, and you are now ready to start folding. You can just reconnect to the web at this point to grab a WU.

One minor detail ... the config.xml file gets saved in your work directory initially. This seems to work fine, but I noticed that /etc/init.d/FAHClient points to /etc/fahclient/config.xml You could either change the entry in /etc/init.d/FAHClient to point to your work directory, or you could move config.xml to /etc/fahclient

Step 3) Installation of FAHViewer
This is mostly eye candy, so it is not really needed. (Don't think it works with the vesa driver as it probably needs to be run with direct rendering ... works fine on my machine once I configured the intel driver for the onboard graphics).

Download fahviewer_7.3.6_amd64.deb from Folding@home website and click on it to install it.

Then, go into /usr/share/applications and edited FAHViewer.desktop to add an appropriate Category so that it will show up in the menu (use terminal command "fixmenus" to update the menu). At this point, you should be able to select FAHViewer in your menu and it should open up correctly. Normally, this is opened from FAHControl by clicking on "View".

This should get you up and running with SMP Folding on FatDog_630. If you have a Fermi (or newer) nVidia GPU, then it is easily configured at this point for folding (these will fold natively on FatDog without wine).

Hello Sunny!!

I finally got time to make FatDog64 running on this machine

Successfully installed FAH Client following your instructions!

Now I guess I will have to spend some time for setting up the GPU

joaomcteixeira:

Glad you got the FAH Client running in FatDog! If you are going to try and fold with your GPU, then the steps you need to do depend on which GPU you are using.

You can natively fold on FatDog if you have a nVidia Fermi or newer board. With these boards, you will be using FAHcore 0x17 which requires at least version 15 of glibc (which is newer than the one provided in FatDog).

For FatDog Version 630, you have to first compile and install binutils (configure binutils with: "configure --prefix=/usr --build=x86_64-t2-linux-gnu"). Note that for FatDog Version 521, you do not need to compile/install binutils.

Now compile and install glibc-2.18.0 (when compiling glibc, use "configure --prefix=/usr").

Once the new glibc is installed, use FAHControl to configure your gpu client using "client-type=advanced" and you should be ready to go.

This native configuration for the Fermi and newer boards is nice since you do not need to fool with wine or the cuda toolkit installation. My GPU also runs about 10 degrees C cooler running the FAHcore 0x17 and v7 Client (verses using the v6 GPU Client with wine).

If you do not have a Fermi or newer GPU, then you can still run a v6 GPU client on your machine using wine. My post on Feb. 10, 2013 of this current thread describes how I installed the v6 GPU client and FAHMon on FatDog.

Hi Sunny,

Thanks a lot for your tips!
By now I will continue solely on CPU because doing what you told me may require some more time but I will definitively look for it.

I noticed that in fatdog the temp of my CPUs is about 5ºC higher, roughly.

There is also the process kswap0 that is almost continuously occurring, which also contributes to the temperature increase. But I guess that is an fatdog issue I've to try to understand somewhere else

Puppy does really work amazingly when one understands it

keep in touch,

There is also the process kswap0 that is almost continuously occurring

I have not noticed this problem when folding in any of the Fatdog releases (and I have done CPU folding with Fatdog_630-Final). An excessive kswap0 is probably a kernal bug. The way the folding activity is interacting with your particular hardware may be initiating the problem.

First question I would ask is what kind of swapfile you are using. Fatdog_630 did not automatically recognize my linux swap partition. I had to include it in fstab in order for Fatdog to recognize it. If you do not have a swap partition, you may want to set up a Linux swap file in RAM and see if that clears up the problem with kswap0.

If an active swap partition (or swap file) does not clear up the problem, you may want to try folding on an older version of Fatdog_630 to see if the problem is kernel dependent. A frugal install does not take very long to set up just to try it out. Fatdog_630_rc1 uses linux kernel 3.11.4 (and Fatdog_630_Final uses linux kernel 3.12.9).

I would also note that you may not have seen this kswap0 problem when folding on one of the 32-bit puppies. Firstly, they use different kernels. Secondly, the folding cores and work units are different for 32 & 64 bit machines.