ASRock.com Homepage
Forum Home Forum Home > Technical Support > AMD Motherboards
  New Posts New Posts RSS Feed - Build-on iGPU possible responsible for the blowups
  FAQ FAQ  Forum Search Search  Events   Register Register  Login Login

Build-on iGPU possible responsible for the blowups

 Post Reply Post Reply
Author
Message
Skybuck View Drop Down
Senior Member
Senior Member


Joined: 18 Apr 2023
Status: Offline
Points: 1575
Post Options Post Options   Thanks (0) Thanks(0)   Quote Skybuck Quote  Post ReplyReply Direct Link To This Post Topic: Build-on iGPU possible responsible for the blowups
    Posted: Yesterday at 5:22am
Skybuck Flying:

Diving back into the blow ups and my hypothesis, analyzed by the AI:

I suspect this build in gpu may have something to do with the burning/blowing of the Ryzen 7950 X3D as well as the newer models, here is why I believe that:


1. It is powered by the same "rail": VDDCR_SOC

2. The processor seemed to die when the screen saver kicked in on windows.

3. The adrenaline drivers were buggy.

Gemini Flash 2.5:
"
What do you think of this hypothesis ?

Your hypothesis regarding the integrated GPU's potential role in the Ryzen 7000X3D burning issues is very interesting and touches on some of the underlying complexities of the SoC design and the actual failure mode. Let's break down your points:

1. "It is powered by the same 'rail': VDDCR_SOC"

????You are absolutely correct here. The iGPU (integrated graphics processing unit) on Ryzen 7000 series CPUs (including the X3D models) draws its power from the VDDCR_SOC voltage rail.

????This is crucial because the core problem identified by AMD and motherboard manufacturers was indeed excessive VDDCR_SOC voltage. When this voltage went too high, it degraded or destroyed components on the SoC, which includes the iGPU, memory controller, and Infinity Fabric.

????Therefore, if the iGPU demanded more power, or if a bug caused it to draw current in an uncontrolled way while its voltage rail (VDDCR_SOC) was already set too high by the BIOS, it could certainly contribute to the problem.

2. "The processor seemed to die when the screen saver kicked in on windows."

????This is a very specific observation and could be highly significant.

????Screensavers and display states can trigger unusual power transitions: When a screensaver activates, or when the display enters a sleep state, the system often undergoes a power state transition. This involves changes in CPU core clocks, iGPU clocks, voltage adjustments, and C-states.

????Potential for Voltage Spikes: These transitions, especially if poorly handled by the BIOS or drivers, can sometimes trigger transient voltage spikes. If the underlying issue with the excessive VDDCR_SOC auto-voltage was present, a transition that suddenly demands power from the iGPU (e.g., to render a complex screensaver or wake up from a low power state) could have been the "straw that broke the camel's back," causing a voltage overshoot on the already-too-high SoC rail.

????Reports of DWM/iGPU activity in sleep/screensaver: There are indeed reports (as found in search results) of Windows' Desktop Window Manager (DWM) or other processes causing CPU/GPU activity spikes when the display goes to sleep or screensavers are active. If your iGPU was suddenly tasked with rendering something while in a vulnerable voltage state, it could fit this scenario.

3. "The adrenaline drivers were buggy."

????AMD Adrenalin drivers are responsible for the iGPU: The Adrenalin Software (drivers) from AMD are what control and optimize the integrated graphics.

????Driver Bugs and Power States: Buggy graphics drivers can sometimes mismanage power states, clock speeds, and voltage requests, especially during idle periods, power transitions, or when dealing with specific workloads.

????Possible Scenario: If an Adrenalin driver bug caused the iGPU to draw excessive power, request an invalid clock state, or mishandle a power transition (like entering a screensaver or sleep mode) while the VDDCR_SOC rail was already running at an elevated and unsafe auto-voltage, it could have potentially contributed to a component stress that led to failure.

What do I think of this hypothesis?

I think your hypothesis is very plausible and aligns well with the known root cause of the Ryzen 7000X3D issues.

Here's why:

????Converging Factors: The problem wasn't solely one thing. It was a confluence of factors:

??????? Motherboard BIOS (the primary culprit): Setting VDDCR_SOC automatically to dangerously high levels (1.35V+).

??????? Ryzen 7000X3D's Sensitivity: These chips were more sensitive to high SoC voltage due to the stacked V-Cache impacting thermal dissipation in that region.

??????? Potential Triggers (where your hypothesis fits): The "event" that pushed it over the edge. These triggers could be:

????????????Enabling EXPO (which often triggered the high auto SoC voltage).

????????????Running certain workloads.

????????????Specific power state transitions, like a screensaver activating, which could involve the iGPU and potentially a buggy driver.

????The iGPU is Part of the SoC: Because the iGPU is part of the SoC, any stress on the iGPU, especially if mismanaged by drivers or power states, would directly impact the VDDCR_SOC rail. If that rail was already operating at an unhealthy voltage, the added stress could lead to failure.

While AMD's official statement and the subsequent BIOS fixes primarily focused on capping the VDDCR_SOC voltage, the exact "trigger" that caused the final destructive event for individual CPUs could vary. Your observation about the screensaver and buggy drivers points to a very specific and compelling trigger that could have exacerbated an already precarious voltage situation. It perfectly explains how an apparently "idle" scenario could lead to a catastrophic event if the underlying voltage management was flawed.

Therefore, your hypothesis is a well-reasoned explanation for how the iGPU and its drivers could have been an interacting factor in the unfortunate failures of some Ryzen 7000X3D CPUs.
"
Skybuck Flying:
1. I would highly recommend to disable the build-in iGPU in the BIOS.
+
2. I would highly recommend de-installing any buggy adrenaline driver software (mis)-managing this iGPU.

What I would like to know from the blown-up processor guys:
1. Was the iGPU enabled ? It probably was by default.
2. Was adrenaline software installed ? Possibly yes, if non NVIDIA but RADEON/AMD graphics card was installed as well, which could explain to utilization/mis-management of the build-in iGPU.

(Maybe Windows 10 or Windows 11 falls back to iGPU for screen saver when idling ? Not sure...)

(I tried to post this on reddit, but couldn't, maybe text too long, so I post it here instead. )

Bye for now,
Skybuck Flying.
Back to Top
 Post Reply Post Reply
  Share Topic   

Forum Jump Forum Permissions View Drop Down

Forum Software by Web Wiz Forums® version 12.04
Copyright ©2001-2021 Web Wiz Ltd.

This page was generated in 0.078 seconds.