troublesome

Forum rules
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#1 troublesome

Post by davidbam »

... or is it just me who is troublesome?

Assuming the Primegrid will soon feature in a sprint, I've been investigating sub-projects which work for my machines (all Linux 64 bit).
  • nVidia GPU was easy. I chose Proth Prime Search Sieve (PPS-Sieve) as that was the only CUDA project & that works fine. I run it when GPUGRID hasn't work to do.
  • Haven't scored any points at all yet on AMD GPU - aborted one when it estimated 6 months to complete. Another got to 100% but never finished. Still looking so if anyone has got this working, please let me know which sub-project
  • CPU is fine on the first one I tried (Sophie Germain Prime Search) but I would like a bit more control. Specifically, how can I configure one machine to run Primegrid on CPU and GPU, but another to run it only on GPU?
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#2 Re: troublesome

Post by Bryan »

In your PG preferences you can setup different locations ie default, home, school, work etc. In each of those you can set what you want for preferences. You assign machines to those locations. When you click on "Computers on this account" and you see the list then just click on DETAILS. Towards the bottom you can set the location for a machine.

In the default location you can also set where new machines should be assigned. So assuming you've setup the Home and School locations. You can go to the default location set it for new hosts should be assigned to HOME. Then you attach the computer that fits that profile. Once you have all the machines attached for HOME then set the default location to School and then attach the machines that should use that profile.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#3 Re: troublesome

Post by davidbam »

Ah ha - many thanks. I must admit I never looked there - just assumed that it was time-of-day related. My bad.

Anything on the AMD GPU problem?
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Dirk Broer
Corsair
Corsair
Posts: 1962
Joined: Thu Feb 20, 2014 11:24 pm
Location: Leiden, South Holland, Netherlands
Contact:

#4 Re: troublesome

Post by Dirk Broer »

davidBAM wrote: Mon Oct 29, 2018 8:28 am Ah ha - many thanks. I must admit I never looked there - just assumed that it was time-of-day related. My bad.

Anything on the AMD GPU problem?
Which AMD GPU are you using? Under what OS?
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#5 Re: troublesome

Post by davidbam »

Thanks. I started a thread over here since this question will probably arise again : https://tsbt.co.uk/forum/viewtopic.php? ... 384#p63892

The machine which locked up - and it needed powered off before it would even reboot - was Ubuntu 18.04.1 with AMD rx580
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Dirk Broer
Corsair
Corsair
Posts: 1962
Joined: Thu Feb 20, 2014 11:24 pm
Location: Leiden, South Holland, Netherlands
Contact:

#6 Re: troublesome

Post by Dirk Broer »

davidBAM wrote: Tue Oct 30, 2018 10:10 am Thanks. I started a thread over here since this question will probably arise again : https://tsbt.co.uk/forum/viewtopic.php? ... 384#p63892

The machine which locked up - and it needed powered off before it would even reboot - was Ubuntu 18.04.1 with AMD rx580
Which driver are you using for the RX580? The distro's Open Source or AMD GPU-PRO? You need the AMD GPU-PRO for crunching on recent AMD cards.
Unfortunately AMD GPU support for older cards (HD generation), which was going downhill since Ubuntu 16.04.1 has reached a new all-time low in Ubuntu 18.04.1
Even the IGP of my Socket AM4 A12-9800E doesn't get recognized anymore....
Me myself I am preparing a massive roll-back to the pre-16.04 versions of Ubuntu, Xubuntu, Lubuntu and Mint
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#7 Re: troublesome

Post by davidbam »

70% of my entire Boinc points come from crunching Collatz on Ubuntu and AMD GPU.

All I do is PrimeGrid is the first thing I've tried crunching apart from Collatz so are you thinking that I am just avoiding the driver problems on Collatz?? Any other projects I could try it on please?
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Dirk Broer
Corsair
Corsair
Posts: 1962
Joined: Thu Feb 20, 2014 11:24 pm
Location: Leiden, South Holland, Netherlands
Contact:

#8 Re: troublesome

Post by Dirk Broer »

davidBAM wrote: Tue Oct 30, 2018 4:05 pm 70% of my entire Boinc points come from crunching Collatz on Ubuntu and AMD GPU.

All I do is PrimeGrid is the first thing I've tried crunching apart from Collatz so are you thinking that I am just avoiding the driver problems on Collatz?? Any other projects I could try it on please?
This is almost guaranteed not to work, BOINC-wise. Does BOINC see the GPU? If so, please post the first part of the BOINC log file (up to and including the mentioning of CPU and GPU and the OpenCL version).
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#9 Re: troublesome

Post by davidbam »

Dirk Broer wrote: Wed Oct 31, 2018 11:33 am This is almost guaranteed not to work
Thing is though, it is working :-) - at least on Collatz, to the tune of 6½ million credits per day across 6 different machines with 3 different types of AMD cards. One machine even has 2 cards fitted. The first problem I hit was on one of the Primegrid sub-projects which, granted, is the first project I've tried outside Collatz. These were all fresh installs incidentally

Here is what Collatz reports from the various machines
  • AMD Radeon RX 580 Series (POLARIS10 / DRM 3.23.0 / 4.15.0-36-generic, LLVM 6.0.0) (8189MB) OpenCL: 1.1
  • AMD Radeon RX 580 Series (POLARIS10 / DRM 3.23.0 / 4.15.0-38-generic, LLVM 6.0.0) (8189MB) OpenCL: 1.1
  • AMD AMD BONAIRE (DRM 2.50.0 / 4.15.0-38-generic, LLVM 6.0.0) (4096MB) OpenCL: 1.1 ... this is the Firepro W5100
  • AMD AMD CAPE VERDE (DRM 2.50.0 / 4.15.0-38-generic, LLVM 6.0.0) (2048MB) OpenCL: 1.1 ... all the rest are various R7-350 (which don't even claim to have OpenCL)
  • AMD AMD CAPE VERDE (DRM 2.50.0 / 4.15.0-38-generic, LLVM 6.0.0) (4096MB) OpenCL: 1.1
  • [2] AMD AMD CAPE VERDE (DRM 2.50.0 / 4.15.0-36-generic, LLVM 6.0.0) (2048MB) OpenCL: 1.1
Dirk Broer wrote: Wed Oct 31, 2018 11:33 am If so, please post the first part of the BOINC log file (up to and including the mentioning of CPU and GPU and the OpenCL version)
Not sure where BOINC log file goes TBH, sorry. This is the relevant part of dmesg output if that helps (from a Dell T5610 with two r7-350 fitted) ...

Code: Select all

$ dmesg | grep -i radeon
[    4.418696] [drm] radeon kernel modesetting enabled.
[    4.418774] fb: switching to radeondrmfb from VESA VGA
[    4.419249] radeon 0000:02:00.0: VRAM: 2048M 0x0000000000000000 - 0x000000007FFFFFFF (2048M used)
[    4.419250] radeon 0000:02:00.0: GTT: 2048M 0x0000000080000000 - 0x00000000FFFFFFFF
[    4.419342] [drm] radeon: 2048M of VRAM memory ready
[    4.419343] [drm] radeon: 2048M of GTT memory ready.
[    4.426155] [drm] radeon: dpm initialized
[    4.466489] radeon 0000:02:00.0: WB enabled
[    4.466491] radeon 0000:02:00.0: fence driver on ring 0 use gpu addr 0x0000000080000c00 and cpu addr 0x        (ptrval)
[    4.466492] radeon 0000:02:00.0: fence driver on ring 1 use gpu addr 0x0000000080000c04 and cpu addr 0x        (ptrval)
[    4.466494] radeon 0000:02:00.0: fence driver on ring 2 use gpu addr 0x0000000080000c08 and cpu addr 0x        (ptrval)
[    4.466495] radeon 0000:02:00.0: fence driver on ring 3 use gpu addr 0x0000000080000c0c and cpu addr 0x        (ptrval)
[    4.466496] radeon 0000:02:00.0: fence driver on ring 4 use gpu addr 0x0000000080000c10 and cpu addr 0x        (ptrval)
[    4.466660] radeon 0000:02:00.0: fence driver on ring 5 use gpu addr 0x0000000000075a18 and cpu addr 0x        (ptrval)
[    4.486594] radeon 0000:02:00.0: fence driver on ring 6 use gpu addr 0x0000000080000c18 and cpu addr 0x        (ptrval)
[    4.486595] radeon 0000:02:00.0: fence driver on ring 7 use gpu addr 0x0000000080000c1c and cpu addr 0x        (ptrval)
[    4.487424] radeon 0000:02:00.0: radeon: MSI limited to 32-bit
[    4.487466] radeon 0000:02:00.0: radeon: using MSI.
[    4.487484] [drm] radeon: irq initialized.
[    6.940808] [drm] Radeon Display Connectors
[    6.960581] [drm] Initialized radeon 2.50.0 20080528 for 0000:02:00.0 on minor 0
[    6.960647] radeon 0000:06:00.0: enabling device (0000 -> 0003)
[    7.514541] radeon 0000:06:00.0: VRAM: 2048M 0x0000000000000000 - 0x000000007FFFFFFF (2048M used)
[    7.514542] radeon 0000:06:00.0: GTT: 2048M 0x0000000080000000 - 0x00000000FFFFFFFF
[    7.514553] [drm] radeon: 2048M of VRAM memory ready
[    7.514553] [drm] radeon: 2048M of GTT memory ready.
[    7.523207] [drm] radeon: dpm initialized
[    7.533475] radeon 0000:06:00.0: WB enabled
[    7.533477] radeon 0000:06:00.0: fence driver on ring 0 use gpu addr 0x0000000080000c00 and cpu addr 0x        (ptrval)
[    7.533478] radeon 0000:06:00.0: fence driver on ring 1 use gpu addr 0x0000000080000c04 and cpu addr 0x        (ptrval)
[    7.533479] radeon 0000:06:00.0: fence driver on ring 2 use gpu addr 0x0000000080000c08 and cpu addr 0x        (ptrval)
[    7.533481] radeon 0000:06:00.0: fence driver on ring 3 use gpu addr 0x0000000080000c0c and cpu addr 0x        (ptrval)
[    7.533482] radeon 0000:06:00.0: fence driver on ring 4 use gpu addr 0x0000000080000c10 and cpu addr 0x        (ptrval)
[    7.534326] radeon 0000:06:00.0: fence driver on ring 5 use gpu addr 0x0000000000075a18 and cpu addr 0x        (ptrval)
[    7.554559] radeon 0000:06:00.0: fence driver on ring 6 use gpu addr 0x0000000080000c18 and cpu addr 0x        (ptrval)
[    7.554561] radeon 0000:06:00.0: fence driver on ring 7 use gpu addr 0x0000000080000c1c and cpu addr 0x        (ptrval)
[    7.554564] radeon 0000:06:00.0: radeon: MSI limited to 32-bit
[    7.554605] radeon 0000:06:00.0: radeon: using MSI.
[    7.554633] [drm] radeon: irq initialized.
[   10.236802] [drm] Radeon Display Connectors
[   10.268842] [drm] Initialized radeon 2.50.0 20080528 for 0000:06:00.0 on minor 1
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Dirk Broer
Corsair
Corsair
Posts: 1962
Joined: Thu Feb 20, 2014 11:24 pm
Location: Leiden, South Holland, Netherlands
Contact:

#10 Re: troublesome

Post by Dirk Broer »

The OpenCL 1.1 is at the one hand pathetic -Windows will gladly report OpenCL 2.0 for the same cards- and at the other hand indicative for the Open Source driver.
Collatz still runs with OpenCL 1.1, PrimeGrid seems to needs more. You can perhaps look into the WUs processed as to why they failed, but I turned up a missing libOpenCL.so with one of your failed WUs. Try to install via sudo apt install ocl-icd-libopencl1

A R7-350 should have OpenCL too, my own R3 had OpenCL 1.1 till Ubuntu 17.04 (under Windows another R3 of me has OpenCL 2.0 and validated a prime)
Unfortunately AMD does not mention the R7-350 as a card that can use the AMDGPU-PRO driver
BTW: the R7-350 looks like very much a re-branded HD-7750 to me (and wikipedia agrees)

For the better recent cards there is this guide
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#11 Re: troublesome

Post by Bryan »

I don't know if this is pertinent information or not. Mumps, a huge cruncher for SUSA, is a big time Linux user. I know that he has had problems with older AMD cards and the newer Linux kernels. Apparently there were "hooks" in the older linux distributions that the driver relied upon to make them work. Those hooks are no longer available so the old drivers won't work on the 18.x kernels. AMD is no longer supplying drivers for the older cards that will work with the new kernels. I know he has some machines running linux 14.0.x because he can't get the old cards to work on later versions of Linux.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#12 Re: troublesome

Post by davidbam »

Thanks both.

I'll try apt install on one of the machines and report back. I didn't even know that you could get stderr messages on each WU - but I do now :D :D :D
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Dirk Broer
Corsair
Corsair
Posts: 1962
Joined: Thu Feb 20, 2014 11:24 pm
Location: Leiden, South Holland, Netherlands
Contact:

#13 Re: troublesome

Post by Dirk Broer »

Bryan wrote: Wed Oct 31, 2018 3:05 pm I don't know if this is pertinent information or not. Mumps, a huge cruncher for SUSA, is a big time Linux user. I know that he has had problems with older AMD cards and the newer Linux kernels. Apparently there were "hooks" in the older linux distributions that the driver relied upon to make them work. Those hooks are no longer available so the old drivers won't work on the 18.x kernels. AMD is no longer supplying drivers for the older cards that will work with the new kernels. I know he has some machines running linux 14.0.x because he can't get the old cards to work on later versions of Linux.
The developer that worked at the so-called 'FGLRX' code has left AMD and AMD gave in to the Linux community, that screams for open drivers. Sadly the developers for that code do not see BOINC as one of their objectives and instead only seem to focus on recent gaming support. They also lack the drive to make older AMD cards work.
Basically we're at the same point as OS/2 video support at the end of the previous century: when you want a card to behave for certain software, you have to program the driver for it yourself.
I had an IBM colleague who could do that, write his own drivers for OS/2...the difference is that he made new cards work on an 'old' OS (OS/2 Warp 4 was not exactly old in 1998-99), while we want 'old' cards to work in a new OS.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#14 Re: troublesome

Post by davidbam »

Okay, the library was already there (different machine, same AMD card)

Code: Select all

$  sudo apt install ocl-icd-libopencl1
[sudo] password for david: 
Reading package lists... Done
Building dependency tree       
Reading state information... Done
ocl-icd-libopencl1 is already the newest version (2.2.11-1ubuntu1).
ocl-icd-libopencl1 set to manually installed.
0 to upgrade, 0 to newly install, 0 to remove and 3 not to upgrade.
The first PrimeGrid jobs have completed, validated and scored :clap: :clap: Different sub-project though (Genefer 15 v3.19 (openclatiGFN15))

I'll try a few other combos when I regain the will to live (I've had a long day on non-boinc things) as, to be perfectly honest, Collatz is working away without any input from me at all. Clearly though, if PrimeGrid arises in a sprint, I'd like to have GPUs working too
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#15 Re: troublesome

Post by davidbam »

Oh!! Primegrid pays over double what Collatz pays !!

I have regained the will to live :D
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#16 Re: troublesome

Post by Bryan »

davidBAM wrote: Wed Oct 31, 2018 5:50 pm Oh!! Primegrid pays over double what Collatz pays !!

I have regained the will to live :D
And Nvidia will blow the doors off of AMD on either project :lol:
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#17 Re: troublesome

Post by davidbam »

Credits per ££ is another matter - mind you an RX580 is only quarter of the price of an nVidia GTX1080 at the moment.
davidBAM wrote: Wed Oct 31, 2018 5:50 pm Oh!! Primegrid pays over double what Collatz pays !!
This is true only on R7-350. WU from the same Genefer 15 v3.19 project take roughly the same amount of time to run on an RX580 so they must not be able to take advantage of its superior hardware (and hence pay poorly)
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#18 Re: troublesome

Post by Bryan »

davidBAM wrote: Wed Oct 31, 2018 5:50 pm Oh!! Primegrid pays over double what Collatz pays !!
A stupid question, are you aware that you can optimize your card on Collatz and usually dramatically increase your credits?

I don't know about AMD cards, but there is no way that PG gives higher credits on outpay Collatz on Nvidias. My GTX 1080Ti does a little over 1M/day on PG and 10M/day on Collatz.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#19 Re: troublesome

Post by davidbam »

Not a stupid question at all. No, please tell me more
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#20 Re: troublesome

Post by Bryan »

I was editing my previous message and you replied so you may not have seen this:


I don't know about AMD cards, but on Nvidias there is no way that PG gives higher credits than Collatz. My GTX 1080Ti does a little over 3M/day on PG and 10M/day on Collatz. The highest paying project on PG is PPS Sieve.

In the Collatz project folder, on your BOINC client (thesonntags.com), there is a file named config.xml. You place or change the settings in that file so the executable performs differently for your particular GPU. It can make a HUGE difference.

See post number 71 HERE and you may find exactly what is needed. If not, then scroll through the thread and see if you can find it.

When you put that file in place "config.xml" the very next WU that is launched will pick it up and use those settings. If you want to try changing something then make the change and the next WU to start will use those changes. No need to stop and restart BOINC. You can make changes on the fly and then look at the completion times of the WU and see if it got better or worse.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#21 Re: troublesome

Post by davidbam »

Right! Sounds like a rainy-day project to get that optimised. Many thanks for the link
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#22 Re: troublesome

Post by Bryan »

davidBAM wrote: Wed Oct 31, 2018 7:35 pm Right! Sounds like a rainy-day project to get that optimised. Many thanks for the link
You're more than welcome ... good luck with it :-)

We've got to keep in mind that you are tilling new soil. Some of this stuff is 2nd nature to us old farts and we don't necessarily think to pass on the knowledge as early as we should. Our bad!
Image
User avatar
Alez
[ TSBT's Pirate ]
[ TSBT's Pirate ]
Posts: 10363
Joined: Thu Oct 04, 2012 1:22 pm
Location: roaming the planet

#23 Re: troublesome

Post by Alez »

For my 2 x 980's I'm running this and twice as fast as standard

["app_config.xml"]

<app_config>
<app>
<name>collatz_sieve</name>
<max_concurrent>2</max_concurrent>
<gpu_versions>
<gpu_usage>1.0</gpu_usage>
<cpu_usage>0.5</cpu_usage>
</gpu_versions>
</app>
</app_config>

use notepad to make this file and save as other. For a single card change <max_concurrent>2</max_concurrent> to <max_concurrent>1</max_concurrent>

For config

verbose=0
kernels_per_reduction=48
threads=8
lut_size=17
sleep=0
cache_sieve=1
reduce_cpu=0
sieve_size=30

This file is collatz_sieve_1.30_windows_x86_64_opencl_nvidia_gpu.config andwill be empty. Linux will obviously be slightly different name and you will be looking for the AMD version but in var/lib/boinc/projects/boinc.thesonntags.com_collatz

For different cards look HERE and pick closest.

edit using gedit. In terminal use gksudo gedit and then navigate to file. If you dont have gedit then first off sudo apt-get gedit wlll do the trick. Gdit is standard in ubuntu but not my prefered Lubunu.
Image
The best form of help from above is a sniper on the rooftop....
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#24 Re: troublesome

Post by davidbam »

Thanks, trying this now - on rx580
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#25 Re: troublesome

Post by davidbam »

Yup - big difference on the rx580 / ubuntu, thanks. Run-times cut by a third, in fairness points awarded cut slightly too tho. Provided they have enough WU to run 24/7, I should earn about 3.3M per day per card. I'm a happy bunny.

Still waiting for the first WU to arrive for the nVidia GPU. I do have it enabled in preferences so not quite sure why.

ETA: This is why (from event log)... Thu 01 Nov 2018 11:41:08 GMT | collatz | Not requesting tasks: don't need (CPU: job cache full; NVIDIA GPU: job cache full). Be patient David
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#26 Re: troublesome

Post by davidbam »

Three days later and Collatz hasn't sent me any work for the nVidia.

Event log says "collatz | Not requesting tasks: don't need (CPU: job cache full; NVIDIA GPU: job cache full)". Thing is, I am getting GPU work from other projects which have a lower resource share though.
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Alez
[ TSBT's Pirate ]
[ TSBT's Pirate ]
Posts: 10363
Joined: Thu Oct 04, 2012 1:22 pm
Location: roaming the planet

#27 Re: troublesome

Post by Alez »

The problem you are facing is the points given by Collatz. BOINC bases which projects you get units based on resource share you set but mainly RAC. Because Collatz pays so well, it will take ages for other projects to catch up and so Collatz will get no work. I basically only set one GPU project I want to get units for, at the moment Collatz. If I want to run Primegrid then I set Collatz to no new work and set Primegrid to receive new work. After all these years the BOINC manager is still dumb as a box of rocks in reality because it creator tried to have all projects give the same credit. As they don't the logic just doesn't work.
The best option is to set a GPU project you wish to crunch and add a second GPU project as a backup ( if you wish ) with a share of 0. That way it will only get work if your chosen project has no work. Alternatively, if you check your systems regularly as I do, then simply set one project at a time. I do the same for CPU's. I may run different projects at the same time, but I do it on different systems so I have control of what I crunch.
Alternatively you can do it with resource share but you end up setting ridiculous share percentages like 10,000 for Collatz to get any work. Micro-managment works best.
Image
The best form of help from above is a sniper on the rooftop....
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#28 Re: troublesome

Post by davidbam »

Alez wrote: Mon Nov 05, 2018 12:11 am you end up setting ridiculous share percentages like 10,000 for Collatz to get any work
SPOOKY - that is exactly the value I have set :lol: :lol: :lol:
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Alez
[ TSBT's Pirate ]
[ TSBT's Pirate ]
Posts: 10363
Joined: Thu Oct 04, 2012 1:22 pm
Location: roaming the planet

#29 Re: troublesome

Post by Alez »

davidBAM wrote: Mon Nov 05, 2018 12:15 am
Alez wrote: Mon Nov 05, 2018 12:11 am you end up setting ridiculous share percentages like 10,000 for Collatz to get any work
SPOOKY - that is exactly the value I have set :lol: :lol: :lol:
Not my first rodeo :lol: I've seen many different versions of the manager since I started doing this and they all suffer from the same issues due to dogma.
Image
The best form of help from above is a sniper on the rooftop....
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#30 Re: troublesome

Post by Bryan »

I rarely run my GPUs but when I do, I setup a 2nd instance of BOINC. One runs the CPUs and the other for the GPUs. That way the BOINC scheduler doesn't have to actually try to think ... it isn't very good at that :lol:
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#31 Re: troublesome

Post by davidbam »

[mention]Bryan[/mention] That sounds interesting. Would you happen to have a link please for how to do this under Linux?

How does boincmgr figure out which to connect to when both are on localhost?
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#32 Re: troublesome

Post by Bryan »

They run separate and independent. On one you enable your CPU project and on the other you enable GPU. If you attach to the same project, ie PG, then the project will see it as two different computers with both having the same name.

The method for setting up multiple BOINC clients is on TSBT somewhere ... I have trouble finding stuff like that. Maybe Alez can find it :D

EDIT: I found the one for Windows ... if someone can't find one for LInux then I'll write one up.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#33 Re: troublesome

Post by davidbam »

Bryan wrote: Wed Oct 31, 2018 6:56 pm My GTX 1080Ti does a little over 3M/day on PG and 10M/day on Collatz. The highest paying project on PG is PPS Sieve.
I finally got some Collatz work for nVidia by having a machine dedicated to running GPU (no CPU work). Using a GTX960 at the moment but I'll build a machine capable of taking both this and the GTX1080

My question is therefore, with 2 non-identical cards will I see two collatz_sieve_1.40_x86_64-pc-linux-gnu__opencl_nvidia.config files to allow me to optimise them independently ?? Maybe I should wait and see what happens and only optimise them after both are running together
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Alez
[ TSBT's Pirate ]
[ TSBT's Pirate ]
Posts: 10363
Joined: Thu Oct 04, 2012 1:22 pm
Location: roaming the planet

#34 Re: troublesome

Post by Alez »

Nope, only 1 collatz_sieve_1.40_x86_64-pc-linux-gnu__opencl_nvidia.config.
Image
The best form of help from above is a sniper on the rooftop....
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#35 Re: troublesome

Post by Bryan »

I hear it is difficult to get multiple GPUs that aren't identical to run in Linux. I can't speak from experience on this.

If you can get it working where BOINC recognizes both cards then you can setup 2 BOINC instances with a instance controlling only a single card. Then you can have 2 config files available.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#36 Re: troublesome

Post by davidbam »

I should probably learn to crawl before I start trying to run. Either that or sell/buy hardware to reduce variety :D
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#37 Re: troublesome

Post by davidbam »

Next question is whether the speed of CPU materially affects the performance of the GPU?

Background : I couldn't get nVidia card working in a Xeon / x79 motherboard (more questions on that later), so I moved it into an old HP machine (Pentium G3250 processor). This works but I am underwhelmed by the first results - it would maybe manage 220,000 credits per day on Collatz. Is it maybe related to the number of PCI lanes supported by CPU ??

Out of interest, an ageing ATI/AMD r7-350 in the HP machine manages about 340,000 per day on Collatz
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
User avatar
Bryan
Boinc Brigadier
Boinc Brigadier
Posts: 2621
Joined: Thu May 21, 2015 6:18 pm

#38 Re: troublesome

Post by Bryan »

Yes, the speed of the CPU can affect the results a GPU gets. As you mentioned the PCI lanes etc but it is more the processing speed.

Most GPU projects also use the CPU. The CPU gets things ready and then passes it to the GPU to crunch. When the GPU finishes crunching that batch it contacts the CPU to get the next batch. This happens over and over until the WU is totally finished.

I have 2 GTX 1080Tis in different machines. One is in a I7-3930K running at 4.2G w/ PCIe 2.0. The 2nd is in a E5-2683 V4 server running at 2.7G w/ PCIe 3.X. The GPU in the I7 machine always outperforms the other GPU even though it has PCIe 2 vs PCIe 3.

Also remember that on most GPU projects you need to reserve some CPU threads otherwise the GPU winds up waiting to be serviced by the CPU.
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#39 Re: troublesome

Post by davidbam »

Alez wrote: Thu Nov 01, 2018 2:43 am This file is collatz_sieve_1.30_windows_x86_64_opencl_nvidia_gpu.config andwill be empty. Linux will obviously be slightly different name
Is anyone crunching Collatz on nVidia under Linux please? I am beginning to think that Collatz doesn't use CUDA & that Linux drivers don't support OpenCL on nVidia.

I'd be DELIGHTED to be proved wrong though
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
davidbam
General Bitchin'
General Bitchin'
Posts: 6371
Joined: Wed Aug 15, 2018 1:15 pm
Location: Huntly, Scotland
Contact:

#40 Re: troublesome

Post by davidbam »

scratch that - I have that running myself on one machine.

Config file is called : collatz_sieve_1.40_x86_64-pc-linux-gnu__opencl_nvidia.config proving that opencl is used

It is only doing about 225K credits per day on Collatz though (unoptimised and fitted in a fairly old machine)

ETA : I can't remember which boinc client I loaded as I see there is a boinc-client-nvidia-cuda. Back to the drawing board :lol: :lol:
I think this is fool-proof but could you just try it for me please? • There are 10 types of people in the world; those who understand binary, and those who don’t
Image
Post Reply Previous topicNext topic

Return to “PrimeGrid”