PowerEdge: AMD erratum 1474 description

Summary: An AMD CPU core may stop responding after about 1044 days according to AMD erratum 1474.

This article applies to This article does not apply to This article is not tied to any specific product. Not all product versions are identified in this article.
Check out other resources

Symptoms

This issue affects the AMD EPYC™ 7002 Series (Rome). See the table of CPUs below for reference. 

A core fails to exit core-C6 (CC6) sleep state around 1044 days after the last reboot.

The time of failure varies depending on the spread spectrum and REFCLK frequency.

The following symptoms are not exhaustive, but may help to identify the issue:

  • On Windows, the system stops responding with blue screen which shows Bug Check 0x101
  • On Linux, there are no obvious symptoms
  • Uptime is beyond 1044 days. This condition is the major indicator of the AMD erratum 1474 issue.

  

DPN Model Name
YVKJ6 7742
C59HD 7642
8JWMD 7542
5PG5C 7702
835TD 7702P
3J0XY 7552
FG4GY 7502
3NFJT 7502P
542T2 7402
YK5KC 7402P
Y96PT 7452
F9NJ5 7352
V99P3 7302
3425F 7302P
XPY7D 7262
J1X8V 7282
XJG06 7252
DH26K 7232P
V0K1X 7272
GX27F 7662
CPHXD 7532
P5HDY 7F72
HVVJX 7F52
PDC7R 7F32
MTHGK 7H12

Cause

It is a public information provided by AMD as the following link (page 55), and the purpose of this PSQN is to remind TS and customer when a system encounter a hang-like issue after 1044 days of uptime, may relate to the root cause of this AMD erratum describes.

https://www.amd.com/system/files/TechDocs/56323-PUB_1.01.pdfThis hyperlink is taking you to a website outside of Dell Technologies.
 

Resolution

There are two workarounds:

  • Option 1: Disable C-state in the BIOS to prevent the CPU core entering cc6 state.
  • Option 2: Reboot the system before it has an uptime of 1044 days. This could be a warm or cold reboot.

When the system stops responding uptime is above 1044 days, a single reboot can work around the issue.
A further reboot must occur within the subsequent 1044 days when the counter once again resets.

Affected Products

AX-6515, AX-7525, OEMR R6515, OEMR R6525, OEMR R7515, OEMR R7525, PowerEdge C6525, PowerEdge R6515, PowerEdge R6525, PowerEdge R7515, PowerEdge R7525, PowerFlex appliance R6525, PowerFlex custom node R6525, Dell EMC vSAN R6515 Ready Node , Dell EMC vSAN R7515 Ready Node, PowerFlex appliance R7525, Dell EMC XC Core XC7525 ...
Article Properties
Article Number: 000215732
Article Type: Solution
Last Modified: 10 Jun 2025
Version:  4
Find answers to your questions from other Dell users
Support Services
Check if your device is covered by Support Services.