PC crashing - BSOD Watchdog violation 1x133 (possibly nVidia issue)

I am running a pair of 2080 TIs in SLI mode, water cooled using Phanteks water blocks. No leaks.

The system has been running steadily for the past 6 or so weeks and then suddenly, two days ago, I can't run games anymore.  My screen goes blank and the computer resets. I checked out WhoCrashed and I am getting the assessment you see below. There is a big problem with the Nvidia nvlddmkm.sys drivers and the kernel. Yes. I have clean uninstalled and reinstalled the drivers using DDU. Yes. I have clean reinstalled Windows. The system is stable when not gaming, only when I begin to draw on the cards during gaming does it crash. Could it be a power supply issue (but I'm using a 1300w supply - I doubt it)?

On Sat 1/12/2019 2:43:33 PM your computer crashed or a problem was reported

crash dump file: C:\WINDOWS\Minidump\011219-17046-01.dmp

This was probably caused by the following module: ntoskrnl.exe (nt+0x1B1B40) 

Bugcheck code: 0x133 (0x0, 0x501, 0x500, 0xFFFFF803091EF380)

Error: DPC_WATCHDOG_VIOLATION

file path: C:\WINDOWS\system32\ntoskrnl.exe

product: Microsoft® Windows® Operating System

company: Microsoft Corporation

description: NT Kernel & System

Bug check description: The DPC watchdog detected a prolonged run time at an IRQL of DISPATCH_LEVEL or above. This could be caused by either a non-responding driver or non-responding hardware. This bug check can also occur because of overheated CPUs (thermal issue). 

The crash took place in the Windows kernel. Possibly this problem is caused by another driver that cannot be identified at this time.

On Sat 1/12/2019 2:43:33 PM your computer crashed or a problem was reported

crash dump file: C:\WINDOWS\MEMORY.DMP

This was probably caused by the following module: nvlddmkm.sys (nvlddmkm+0x2ab9e6) 

Bugcheck code: 0x133 (0x0, 0x501, 0x500, 0xFFFFF803091EF380)

Error: DPC_WATCHDOG_VIOLATION

file path: C:\WINDOWS\System32\DriverStore\FileRepository\nv_dispi.inf_amd64_e7b3660b4830c245\nvlddmkm.sys

product: NVIDIA Windows Kernel Mode Driver, Version 417.35

company: NVIDIA Corporation

description: NVIDIA Windows Kernel Mode Driver, Version 417.35 

Bug check description: The DPC watchdog detected a prolonged run time at an IRQL of DISPATCH_LEVEL or above. This could be caused by either a non-responding driver or non-responding hardware. This bug check can also occur because of overheated CPUs (thermal issue). 

A third party driver was identified as the probable root cause of this system error. It is suggested you look for an update for the following driver: nvlddmkm.sys (NVIDIA Windows Kernel Mode Driver, Version 417.35 , NVIDIA Corporation). 

Google query: nvlddmkm.sys NVIDIA Corporation DPC_WATCHDOG_VIOLATION

To note, your setup looks similar to what I'm running right now. I also have two RTX 2080 Ti cards in NVLink SLI and have been getting these same issues for weeks now. I have a 1600W PSU so the power supply is not the issue. My motherboard is an Asus ROG Zenith Extreme running the latest BIOS (ver. 1601), and my CPU is an AMD Ryzen Threadripper 1950X. I wasn't able to see if my motherboard uses the PLX PEX chip, but suspect it may as it is capable of 4x SLI and is a higher-end board which seems common for the PLX chips.

I did all of the steps you outlined in your post as well as what others have recommended (reinstall after doing a DDU clean uninstall, five reinstallations of Windows 10, rollback BIOS, etc.). I've tried the MSI_util_V2 workaround recommended for the 1080 Ti (though again I have the 2080 Ti) to enable MSI on the cards, but with no luck there either. Unfortunately with the RTX 2080 Ti, we can't go back too far with GeForce drivers as the card is too new and supported at 411.63. I tried running just one of the RTX 2080 Ti cards, but still get the BSODs and crashing.

All told, this must be a problem with BOTH the Pascal (GTX 10xx series) and Turing (RTX 20xx) architectures, as I tried running my old GTX Titan X (Maxwell architecture) I got back in 2015 and I have yet to get any issues with that almost 4-year old card.

I've tried emailing Asus (my motherboard manufacturer) for their take in case this might also be due to incompatibility between Asus motherboard and these new architectures though.

I am running a pair of 2080 TIs in SLI mode, water cooled using Phanteks water blocks. No leaks.

The system has been running steadily for the past 6 or so weeks and then suddenly, two days ago, I can't run games anymore.  My screen goes blank and the computer resets. I checked out WhoCrashed and I am getting the assessment you see below. There is a big problem with the Nvidia nvlddmkm.sys drivers and the kernel. Yes. I have clean uninstalled and reinstalled the drivers using DDU. Yes. I have clean reinstalled Windows. The system is stable when not gaming, only when I begin to draw on the cards during gaming does it crash. Could it be a power supply issue (but I'm using a 1300w supply - I doubt it)?

On Sat 1/12/2019 2:43:33 PM your computer crashed or a problem was reported

crash dump file: C:\WINDOWS\Minidump\011219-17046-01.dmp

This was probably caused by the following module: ntoskrnl.exe (nt+0x1B1B40) 

Bugcheck code: 0x133 (0x0, 0x501, 0x500, 0xFFFFF803091EF380)

Error: DPC_WATCHDOG_VIOLATION

file path: C:\WINDOWS\system32\ntoskrnl.exe

product: Microsoft® Windows® Operating System

company: Microsoft Corporation

description: NT Kernel & System

Bug check description: The DPC watchdog detected a prolonged run time at an IRQL of DISPATCH_LEVEL or above. This could be caused by either a non-responding driver or non-responding hardware. This bug check can also occur because of overheated CPUs (thermal issue). 

The crash took place in the Windows kernel. Possibly this problem is caused by another driver that cannot be identified at this time.

On Sat 1/12/2019 2:43:33 PM your computer crashed or a problem was reported

crash dump file: C:\WINDOWS\MEMORY.DMP

This was probably caused by the following module: nvlddmkm.sys (nvlddmkm+0x2ab9e6) 

Bugcheck code: 0x133 (0x0, 0x501, 0x500, 0xFFFFF803091EF380)

Error: DPC_WATCHDOG_VIOLATION

file path: C:\WINDOWS\System32\DriverStore\FileRepository\nv_dispi.inf_amd64_e7b3660b4830c245\nvlddmkm.sys

product: NVIDIA Windows Kernel Mode Driver, Version 417.35

company: NVIDIA Corporation

description: NVIDIA Windows Kernel Mode Driver, Version 417.35 

Bug check description: The DPC watchdog detected a prolonged run time at an IRQL of DISPATCH_LEVEL or above. This could be caused by either a non-responding driver or non-responding hardware. This bug check can also occur because of overheated CPUs (thermal issue). 

A third party driver was identified as the probable root cause of this system error. It is suggested you look for an update for the following driver: nvlddmkm.sys (NVIDIA Windows Kernel Mode Driver, Version 417.35 , NVIDIA Corporation). 

Google query: nvlddmkm.sys NVIDIA Corporation DPC_WATCHDOG_VIOLATION

I was to see the side of the manufacturer "Gigabyte" since I have a gigabyte 2080 .... the only remark he offers me is to make a replacement of the card or repair ....

I tested a 1080 Ti gtx and I have no problem. it's since I installed this card ... I do not understand

Reading your post again, noting your system specs, I see that you're using an MSI board.  I know initially Asus x99 motherboard users were experiencing this crash and the workaround seems to work for these boards.  I wonder if your issue is perhaps due to other issues.  My only advice would be to contact Nvidia support directly.  They're hit and miss with tech support quality but generally pretty good.

J'ai déjà essayé, en validant chaque option, de redémarrer la machine ... le problème est toujours présent