• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.
  • The forums have been upgraded with support for dark mode. By default it will follow the setting on your system/browser. You may override it by scrolling to the end of the page and clicking the gears icon.

How do I spot the vram FBI0B1

R

Rocketman36

New Member
Joined
Apr 1, 2023
Messages
2 (0.00/day)
Hello, I recently bought a RTX 2080 SUPER Rog Strix who as artefacts to try fixing it so i ran NVIDIA Modular diagnostic software to find if a vram was faulty then found out there was FBI0B1 that has troubles but i don't know how to find it on the board.
Hopefully if someone can help me.
 

Attachments

  • IMG_0587.jpg
    IMG_0587.jpg
    720.8 KB · Views: 413
  • front.jpg
    front.jpg
    363.2 KB · Views: 299
Judging by some other searches and this photo as an example. It looks like its always counter clockwise and each chip represents a part of the address space.

1680372147467.png


1680372177729.png


These photos are in line with the rest that I have seen online, but I cant find anything specifically for the TU104. If I had to guess I would assume it was based off the TU102 pattern like other 2xxx series cards, That would make "M9" the chip that is bad on your card.
 
For MATS:
Memory modules are counted counter clockwise starting from the OPPOSITE corner of the golden arrow on the core. Starting from A1, A0, B1, B0... to X1, X0. (X being the last channel)/quote]
Click to expand...
@Solaris17, Second image defers from the first one, and it appears that the starting point is indeed A1.
 
Night said:
For MATS:

@Solaris17, Second image defers from the first one, and it appears that the starting point is indeed A1.
Click to expand...

yeah I tried to allude to that, because those are images of TU102 and TU106 I am not sure if it changes between arcs, but if thats what the mats documents say then the chip in his case is "M10" assuming an A1 start.

EDIT:: Its of course always possible the second image is just wrong and it doesnt differ at all between arcs. /shrug I would go by the mats docs if its a quote.
 
Solaris17 said:
yeah I tried to allude to that, because those are images of TU102 and TU106 I am not sure if it changes between arcs, but if thats what the mats documents say then the chip in his case is "M10" assuming an A1 start.
Click to expand...
I would say it doesn't change, same logic was used for Pascal and Turing on this page:

It's important to start opposite to the golden triangle and starting with A1, then A0 and so on. That's what it says at least.
 
You must log in or register to reply here.
Back
Top