The new NVidia driver 376.09 WHQL released today still has no fix for FaH (Core21 WUs fail on Maxwell/Pascal GPUs).
So driver 373.06 WHQL is still the latest good working driver for FaH.
 
See NVidia forum post of Manuel Guzman:
Official 376.09 Game Ready WHQL Display Driver Feedback Thread (released 11/28/16)
 

villageidiot182 said:
Any Updates on Folding@Home?
------------------
 
ManuelGuzman:
We still have not resolved this issue.

 
 
EDIT:  Update December 5,
 
NVidia released new drivers 376.19 WHQL today, but still no fix for FaH.
See NVidia forum post of Manuel Guzman:
Official 376.19 Game Ready WHQL Display Driver Feedback Thread (Released 12/5/16)
 

MammothJerk said:
Any update on the F@H WU problems?
-----------------------
 
ManuelGuzman:
No fix in this driver for that issue. It is one of our top priority bugs though.

 
See also this post of Manuel Guzman:
Official 376.19 Game Ready WHQL Display Driver Feedback Thread (Released 12/5/16)
 

bb30994 said:
@Manuel: Do you have enough information to reproduce the F@H problems?
 
I do not see it listed as an Open Issue.
----------------------
 
ManuelGuzman:
Yes.  We just have not yet narrowed down the root cause.

 
EDIT-2:  Update December 14,
 
NVidia released new drivers 376.33 WHQL today, but no fix for FaH yet.
See NVidia forum post of Manuel Guzman:
Official 376.33 Game Ready WHQL Display Driver Feedback Thread (Released 12/14/16)
 

silverpulser said:
Has the issue with Folding@home been addressed?
---------------------------------------
 
ManuelGuzman:
No. Changes in our R375 driver exposed an application bug with Folding@Home. We are trying to get an application side fix but in the meantime, our team is still trying to come up with a driver side workaround. This is close to being done but not yet complete. We'll likely post a hotfix driver as soon as a driver side workaround is available.

 
See also an update from NVidia posted by Scott:
Got word from NVIDIA and this issue they are working on.--UPDATED 12/14
 

scott@bjorn3d
12/14 Update

Hey Scott,

Our efforts to get a resolution out by 12/14 has run into some roadblocks. The change suggestion we made for OpenMM needs more tweaks and our driver side workaround is close to being done but not complete yet. We plan to post a hotfix driver to unblock the Folding@Home users as soon as we have a workaround to share (within the next few days).

We’ll keep you posted.

Regards,
Team NV

 
EDIT-3: 
Changed thread title to:  "Drivers 376.09/.19/.33 still no fix for FaH [Edit: Fixed with Core21 v0.0.18]"
NVidia first fixed this with the Hot Fix Driver 376.48 and later Stanford fixed it with the New Core21 v0.0.18.

So that is now the 4th update, and still broken.... Crazy

rjohnson11
Just to let everyone know that I've spoken with NVIDIA. They are still aware of this and still investigating/working on it. Sorry but that is all the info I have at the moment.

thanks for asking and keeping us in the loop

i blame bloatware. they cram too much crap into "drivers" nowadays and not simply work on creating a useful driver. its like installing off CD's back in the hay day where it would give you a ton of useless crap and not just the driver.

Either way, there's a distinct cut off that they can use as an A:B test - Drivers before this point worked, drivers after don't - What is the change that happened at that point and WHY is it breaking things? 

I know Nvidia won't divulge the inner workings of their drivers to protect their IP, but at least a high level acknowledgement that they've at least narrowed it down that far and are trying to reconcile the change in a way that will let F@H use the hardware to it's fullest would be a great deal more info that 'We're working on it'.
d

Thank you Dutch! I have a dream.....One day we can have a driver that folds and lets you play BF. 

I wish they'd drop it in the open issues in the docs.

Hmm. I get BAD WORK UNIT only when using Core 21!  All other Core units worked properly.

These kind of issues are hard to track down. Games with lousy optimization and weird graphics code are bad enough. But trying to fix cuda/OpenCL is even worse. The big money needs those code paths to be extremely robust, which is why the long wait is concerning. These are the critical code paths that the supercomputers built with Tesla and Quadro need to be error free and the fact that the most advanced core 21 units from F@h fail is concerning. It is also possible that this is a bug in the core 21 code as well, which makes this a PITA for any group of developers/bug hunters.

bcavnaugh
It is not like Core 22 came out and having driver issues.
Core 21 has been out to long for a driver issue to have started.

It could be that the newer drivers are less tolerant to errors in the core 21 code that may have been there from day 1 and just haven't been caught up till now.

Thanks for the info Bcav! All I want for Christmas is a driver that works [for both]. 

Yeah, it is pretty much like:
 

FAH: Your driver broke our stuff.
NV: No, we fixed some bugs and made some improvements. You were running into a bug and doing it wrong. You are trying utilize this bug as if it was a feature and need to fix it on your side.
FAH: It worked in the previous version driver so you need to fix it.

 
I see this quite frequent in software with finger pointing dragging out issues out longer than they need to be. Someone just needs to step up and fix the issue. At the end, it is the end user that suffers. Hopefully, it will be fixed soon.

drougnor Yes I do know, But is why is Folding @ Home Not saying anything at all.
I will stop posting about the last 6 Drivers Failing and allow once more for them to correct the OpenMM bug.

valkyriesII
Yeah, it is pretty much like:
 

FAH: Your driver broke our stuff.
NV: No, we fixed some bugs and made some improvements. You were running into a bug and doing it wrong. You are trying utilize this bug as if it was a feature and need to fix it on your side.
FAH: It worked in the previous version driver so you need to fix it.

 
I see this quite frequent in software with finger pointing dragging out issues out longer than they need to be. Someone just needs to step up and fix the issue. At the end, it is the end user that suffers. Hopefully, it will be fixed soon.

Aye. Just ran into this whole mess two days ago, really hope they get it sorted out before everyone bails for the holidays. Six weeks is an absurd length of time for it to persist.

Just to keep this thread updated,
 
NVidia released new drivers 376.33 WHQL today, but no fix for FaH yet.
See NVidia forum post of Manuel Guzman:
Official 376.33 Game Ready WHQL Display Driver Feedback Thread (Released 12/14/16)
 

silverpulser said:
Has the issue with Folding@home been addressed?
---------------------------------------
 
ManuelGuzman:
No. Changes in our R375 driver exposed an application bug with Folding@Home. We are trying to get an application side fix but in the meantime, our team is still trying to come up with a driver side workaround. This is close to being done but not yet complete. We'll likely post a hotfix driver as soon as a driver side workaround is available.

 
See also an update from NVidia posted by Scott:
Got word from NVIDIA and this issue they are working on.--UPDATED 12/14
 

scott@bjorn3d
12/14 Update

Hey Scott,

Our efforts to get a resolution out by 12/14 has run into some roadblocks. The change suggestion we made for OpenMM needs more tweaks and our driver side workaround is close to being done but not complete yet. We plan to post a hotfix driver to unblock the Folding@Home users as soon as we have a workaround to share (within the next few days).

We’ll keep you posted.

Regards,
Team NV