Bad GPU work units (114 = 0x72)

If you're new to FAH and need help getting started or you have very basic questions, start here.

Moderators: Site Moderators, FAHC Science Team

bruce
Posts: 20910
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: Bad work units.

Post by bruce »

Your GeForce GTX 760 uses a GK104 chip. You said you had 15 GPUs. Do any of them use a similar chip?

What is the make an model of your system? What Motherboard is in it? Do any of your GPUs use risers ... if so what speed? Is anything overclocked? Has your system crashed within say, the last month? If so, why?

I've been assuming you have a plain-vanilla system containing reliable hardware, but one of the possible causes for Bad State errors is anything than might cause hardware errors. I'd like to be able to rule that out.
toTOW
Site Moderator
Posts: 6296
Joined: Sun Dec 02, 2007 10:38 am
Location: Bordeaux, France
Contact:

Re: Bad work units.

Post by toTOW »

bruce, you missed that SteveWillis also posted in the thread. He's the one with 15 GPUs. ;)
Image

Folding@Home beta tester since 2002. Folding Forum moderator since July 2008.
SteveWillis
Posts: 409
Joined: Fri Apr 15, 2016 12:42 am
Hardware configuration: PC 1:
Linux Mint 17.3
three gtx 1080 GPUs One on a powered header
Motherboard = [MB-AM3-AS-SB-990FXR2] qty 1 Asus Sabertooth 990FX(+59.99)
CPU = [CPU-AM3-FX-8320BR] qty 1 AMD FX 8320 Eight Core 3.5GHz(+41.99)

PC2:
Linux Mint 18
Open air case
Motherboard: ASUS Crosshair V Formula-Z AM3+ AMD 990FX SATA 6Gb/s USB 3.0 ATX AMD
AMD FD6300WMHKBOX FX-6300 6-Core Processor Black Edition with Cooler Master Hyper 212 EVO - CPU Cooler with 120mm PWM Fan
three gtx 1080,
one gtx 1080 TI on a powered header

Re: Bad work units.

Post by SteveWillis »

Just thought I'd mention that all my gpus are 1080 and 1080TI except for one lonely 960 (iirc), including the TI that won't fold, spread over 4 pcs with 2 (including the one that won't fold now mining ETH),5,4, and 5 gpus respectively all running Linux Mint. The bad gpu was tried in multiple slots on multiple pcs and the problem followed the bad gpu. I also tried underclocking both clock and memory in various combinations on that gpu but it didn't help. It generally would fold for a while and I'd get my hopes up but then before a WU would complete it would fail with a bad WU and then quickly start failing WUs over and over. The gpus are mostly on risers but I didn't move the risers when I moved the problem gpu. The motherboards and memory were substantially similar on the rigs I tried it on and it just occurred to me that my most recent rig build (built since the problem developed) has a much different MB and memory and it might be worth the effort to try moving it to that rig but since it would be a lot of trouble and I'm not optimistic of success my inclination is to not bother. The problem gpu is currently in the box with 2 gpus and not on a riser.

I only brought it up at all thinking there is a remote possibility that the OP also has a flakey gpu.
Image

1080 and 1080TI GPUs on Linux Mint
bruce
Posts: 20910
Joined: Thu Nov 29, 2007 10:13 pm
Location: So. Cal.

Re: Bad GPU work units (114 = 0x72)

Post by bruce »

Agreed. The possibility of a flakey GPU or a bad slot is exactly what I'm considering, but like I said earlier, that's really difficult for us to diagnose.
Post Reply