It seems that a lot of GPU problems revolve around specific versions of drivers. Though NVidia has their own support structure, you can often learn from information reported by others who fold.
Applefreak wrote:Note: Even though the GTX 970 is on a x1 slot it almost always has the highest Estimated PPD. Is Maxwell better at folding than Pascal
11:42:05: GPU 0: Bus:6 Slot:0 NVIDIA:5 GM204 [GeForce GTX 970] (Bus runs at x1)
11:42:05: GPU 1: Bus:4 Slot:0 NVIDIA:5 GP104 [GeForce GTX 1070] (Bus runs at x8)
11:42:05: GPU 2: Bus:4 Slot:0 NVIDIA:5 GP104 [GeForce GTX 1070] (Bus runs at x8)
11:42:05: GPU 3: Bus:4 Slot:0 NVIDIA:5 GP104 [GeForce GTX 1070] (Bus runs at x16)
More likely is that the slot numbering / naming is wrong. GTX 970 will be ~300k and 1070 at ~550k. What happens if you start each GPU slot up one at a time and see which one loads and heats up? The latest beta clients are meant to be an improvement in this regard, but the previous client was rarely (never?) correct.
I agree it's odd. I moved it to a x16 slot with 16x riser. Then all the bus speeds switched. Each GTX 1070 is a different brand so that helps sort them out: Asus, EVGA & Gigabyte.
I got the bus speed from GPU-Z. It should match since I only have one GTX 970 on the MB.
I lost ATT internet and everything's a mess. I'll look at it again later after all GPUs have new WUs.
SombraGuerrero wrote:I tend to air on the conservative side, but honestly, if you're able to fold with the driver you currently have, I wouldn't mess with it. If you're experiencing the bug with 0x21 though, I would recommend pinning your kernel and installing the hotfix driver if you're comfortable with manual driver installation. In my experience, pinning the kernel is necessary, especially if you want to keep your system stable, because every time the kernel upgrades, manually installed Nvidia drivers tend to break.
I'm asking, because i experience the 0x21 bug. I'm using the NVIDIA-Linux-x86_64-375.26 driver. Manually installed. The 1050 Ti is offically supported since the 375.10
I figured. We just haven't had many *nix users chime into this conversation, so I didn't want to make any assumptions. I just realized that everything I've said up to this point is in error because I had it in my head that Nvidia had a Linux package available of the hotfix. This does not appear to be the case. They did release a beta driver just four days ago that, by revision number, I would assume includes the hotfix code. Perhaps you'd have luck with that. Beta 378.09. From the looks of it, Linux support for the other cards in the 10x series has followed the same release cycle, so the older drivers that worked on the Windows side aren't available either. This beta is probably one of the only potential paths forward for now.
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
SombraGuerrero wrote:I tend to air on the conservative side, but honestly, if you're able to fold with the driver you currently have, I wouldn't mess with it. If you're experiencing the bug with 0x21 though, I would recommend pinning your kernel and installing the hotfix driver if you're comfortable with manual driver installation. In my experience, pinning the kernel is necessary, especially if you want to keep your system stable, because every time the kernel upgrades, manually installed Nvidia drivers tend to break.
I'm asking, because i experience the 0x21 bug. I'm using the NVIDIA-Linux-x86_64-375.26 driver. Manually installed. The 1050 Ti is offically supported since the 375.10
I figured. We just haven't had many *nix users chime into this conversation, so I didn't want to make any assumptions. I just realized that everything I've said up to this point is in error because I had it in my head that Nvidia had a Linux package available of the hotfix. This does not appear to be the case. They did release a beta driver just four days ago that, by revision number, I would assume includes the hotfix code. Perhaps you'd have luck with that. Beta 378.09. From the looks of it, Linux support for the other cards in the 10x series has followed the same release cycle, so the older drivers that worked on the Windows side aren't available either. This beta is probably one of the only potential paths forward for now.
I tried 378.09 but it wouldn't work for me. Fell back to 370.28.
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
I just downloaded 370.28 driver off of Nvidia website. You have to be on Linux when you go to the site. hen I tried Windows 7, I could not find them. Good luck.
Windows driver WHQL 378.49 released. Fixed: [Folding @ Home] Work unit errors occur
Linux driver 378.09 - BETA fix still missing! Should nvidia be pushed somehow to also include the fix in the linux driver 378.xx?
There's hope. FAH has been working on a new version of FAHCore_21 which avoids the bug in nVidia's OpenCL driver. Once that revision has had some time for beta testing, it will be released to everyone. Hopefully it will also avoid the performance degradation introduced in the hot-fix driver.
foldy wrote:Windows driver WHQL 378.49 released. Fixed: [Folding @ Home] Work unit errors occur
Linux driver 378.09 - BETA fix still missing! Should nvidia be pushed somehow to also include the fix in the linux driver 378.xx?
Does this mean I can run install the latest driver on my Windows machine for use with F@H? Not sure what this is saying.
foldy wrote:Windows driver WHQL 378.49 released. Fixed: [Folding @ Home] Work unit errors occur
Linux driver 378.09 - BETA fix still missing! Should nvidia be pushed somehow to also include the fix in the linux driver 378.xx?
I've been filing bug reports since the 375.xx drivers released. The only acknowledgement of the issue I've seen, was a response to my post on the GEForce forums that said "We'll look into this".
foldy wrote:Windows driver WHQL 378.49 released. Fixed: [Folding @ Home] Work unit errors occur
Linux driver 378.09 - BETA fix still missing! Should nvidia be pushed somehow to also include the fix in the linux driver 378.xx?
Does this mean I can run install the latest driver on my Windows machine for use with F@H? Not sure what this is saying.
No, the conversation has gotten a little criss-crossed here because we had someone ask a couple posts back about Linux driver suggestions. The latest Linux beta does not contain the workaround that Nvidia put into the Windows hotfixe drivers, which some of us are griping is pretty unfair. Most Linux folders should be fine, except if they own a 1050Ti. If they do, then the only option currently would be to find a way to "hack" an older Linux driver like how we earlier discovered how to "hack" the older Windows drivers.
Hannibal13 wrote:Does this mean I can run install the latest driver on my Windows machine for use with F@H? Not sure what this is saying.
Not yet.
Wait until you see an announcement of the release of the new revision of FAHCore_21 which contains a work-around for the problems with every driver version since 375.57 except 376.48. My previous post was just do show that FAH-Development is working on a better solution that the one contained in 376.48 and that work-around is being beta tested.
