Nvidia GPU Tips and Tricks: Difference between revisions

From HPCWIKI
Jump to navigation Jump to search
(Phase 4.4: NVIDIA GPUs 메인 페이지 링크 추가)
(Fix: remove --- horizontal lines (7 removed))
 
(2 intermediate revisions by the same user not shown)
Line 1: Line 1:
== See Also ==
{{Status
|status=Draft
|owner=Knowledge Agent
|last_update=2026-07-16
|review=Pending
}}
 
{{TOC}}
 
== Overview ==
 
Nvidia GPU Tips and Tricks에 대한 기술 문서입니다.
 
=== Summary ===
 
* 무엇인가? - Nvidia GPU Tips and Tricks
* 왜 필요한가? - HPC 및 서버 환경에서 필수 개념
* 언제 사용하는가? - 서버 구성, 성능 튜닝, 문제 해결 시
 
 
== Purpose ==
 
이 문서가 존재하는 이유
 
* Goal: Nvidia GPU Tips and Tricks에 대한 기술 정보 제공
* Scope: Nvidia GPU Tips and Tricks의 개념, 사용법, 설정
* Non-goals: 다른 주제로의 확장
 
 
== Key Concepts ==
 
{| class="wikitable"
! Concept
! Description
! Related
|-
| Nvidia GPU Tips and Tricks
| HPC/서버 환경에서 중요한 기술 개념
| [[Linux]], [[Server]]
|}
 
 
== Detailed Explanation ==
 
* [[NVIDIA GPUs]]
* [[NVIDIA GPUs]]
== XID 62 or 119 error ==
Based on many cases, XID 62 and 119 error caused by incompatible driver version issues. it's recommended to install right version of GPU driver based on customer [[CUDA]] application version.<syntaxhighlight lang="bash">
Based on many cases, XID 62 and 119 error caused by incompatible driver version issues. it's recommended to install right version of GPU driver based on customer [[CUDA]] application version.<syntaxhighlight lang="bash">
Remove Nvidia GPU driver on Ubuntu
Remove Nvidia GPU driver on Ubuntu
$sudo apt-get remove --purge '^nvidia-.*'
$sudo apt-get remove --purge '^nvidia-.*'
apt search or get download GPU driver from nvidia then install and test
apt search or get download GPU driver from nvidia then install and test
</syntaxhighlight>
</syntaxhighlight>
== Xid errors along with the potential causes for each<ref>https://docs.nvidia.com/deploy/xid-errors/index.html</ref> ==
{| class="wikitable"
{| class="wikitable"
! colspan="1" rowspan="1" |XID
! colspan="1" rowspan="1" |XID
! colspan="1" rowspan="1" |[[NVIDIA GPU|Nvidia GPU]] Failure
! colspan="1" rowspan="1" |[[NVIDIA GPU|Nvidia GPU]] Failure
![[Linux]] Kernel message
![[Linux]] [[Kernel]] message
! colspan="7" rowspan="1" |Causes
! colspan="7" rowspan="1" |Causes
|-
|-
Line 26: Line 63:
! colspan="1" rowspan="1" |System Memory Corruption
! colspan="1" rowspan="1" |System Memory Corruption
! colspan="1" rowspan="1" |Bus Error
! colspan="1" rowspan="1" |Bus Error
! colspan="1" rowspan="1" |Thermal Issue
! colspan="1" rowspan="1" |FB Corruption
|-
| colspan="1" rowspan="1" |1
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |2
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |3
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |4
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |GPU semaphore timeout
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |5
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |6
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |7
| colspan="1" rowspan="1" |Invalid or corrupted push buffer address
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |8
| colspan="1" rowspan="1" |GPU stopped processing
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |9
| colspan="1" rowspan="1" |Driver error programming GPU
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |10
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |11
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |12
| colspan="1" rowspan="1" |Driver error handling GPU exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |13
| colspan="1" rowspan="1" |Graphics Engine Exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |14
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |15
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |16
| colspan="1" rowspan="1" |Display engine hung
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |17
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |18
| colspan="1" rowspan="1" |Bus mastering disabled in PCI Config Space
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |19
| colspan="1" rowspan="1" |Display Engine error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |20
| colspan="1" rowspan="1" |Invalid or corrupted Mpeg push buffer
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |21
| colspan="1" rowspan="1" |Invalid or corrupted Motion Estimation push buffer
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |22
| colspan="1" rowspan="1" |Invalid or corrupted Video Processor push buffer
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |23
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |24
| colspan="1" rowspan="1" |GPU semaphore timeout
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |25
| colspan="1" rowspan="1" |Invalid or illegal push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |26
| colspan="1" rowspan="1" |Framebuffer timeout
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |27
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |28
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |29
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |30
| colspan="1" rowspan="1" |GPU semaphore access error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |31
| colspan="1" rowspan="1" |GPU memory page fault
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |32
| colspan="1" rowspan="1" |Invalid or corrupted push buffer stream
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |33
| colspan="1" rowspan="1" |Internal micro-controller error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |34
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |35
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |36
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |37
| colspan="1" rowspan="1" |Driver firmware error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |38
| colspan="1" rowspan="1" |Driver firmware error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |39
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |40
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |41
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |42
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |43
| colspan="1" rowspan="1" |GPU stopped processing
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |44
| colspan="1" rowspan="1" |Graphics Engine fault during context switch
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |45
| colspan="1" rowspan="1" |Preemptive cleanup, due to previous errors -- Most likely to see when running multiple [[CUDA|cuda]] applications and hitting a DBE
|Usually Kernel shows  following message before XID 45
sched: RT throttling activated
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |46
| colspan="1" rowspan="1" |GPU stopped processing
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |47
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |48
| colspan="1" rowspan="1" |Double Bit ECC Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |49
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |50
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |51
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |52
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |53
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |54
| colspan="1" rowspan="1" |Auxiliary power is not connected to the GPU board
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |55
| colspan="1" rowspan="1" |Unused
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |56
| colspan="1" rowspan="1" |Display Engine error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |57
| colspan="1" rowspan="1" |Error programming video memory interface
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |58
| colspan="1" rowspan="1" |Unstable video memory interface detected
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |EDC error – clarified in printout
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |59
| colspan="1" rowspan="1" |Internal micro-controller error


(older drivers)
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |60
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |61
| colspan="1" rowspan="1" |Internal micro-controller breakpoint/warning


(newer drivers)
== Best Practices ==
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |62
| colspan="1" rowspan="1" |Internal micro-controller halt


(newer drivers)
* 최신 버전 사용 권장
|
* 공식 문서 참고
| colspan="1" rowspan="1" |X
* 테스트 환경에서 먼저 검증
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |63
| colspan="1" rowspan="1" |ECC page retirement or row remapping recording event
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |64
| colspan="1" rowspan="1" |ECC page retirement or row remapper recording failure
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |65
| colspan="1" rowspan="1" |Video processor exception
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |66
| colspan="1" rowspan="1" |Illegal access by driver
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |67
| colspan="1" rowspan="1" |Illegal access by driver
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |68
| colspan="1" rowspan="1" |NVDEC0 Exception
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |69
| colspan="1" rowspan="1" |Graphics Engine class error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |70
| colspan="1" rowspan="1" |CE3: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |71
| colspan="1" rowspan="1" |CE4: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |72
| colspan="1" rowspan="1" |CE5: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |73
| colspan="1" rowspan="1" |NVENC2 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |74
| colspan="1" rowspan="1" |NVLINK Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |75
| colspan="1" rowspan="1" |CE6: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |76
| colspan="1" rowspan="1" |CE7: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |77
| colspan="1" rowspan="1" |CE8: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |78
| colspan="1" rowspan="1" |vGPU Start Error
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |79
| colspan="1" rowspan="1" |GPU has fallen off the bus
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |80
| colspan="1" rowspan="1" |Corrupted data sent to GPU
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |81
| colspan="1" rowspan="1" |VGA Subsystem Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |82
| colspan="1" rowspan="1" |NVJPG0 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |83
| colspan="1" rowspan="1" |NVDEC1 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |84
| colspan="1" rowspan="1" |NVDEC2 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |85
| colspan="1" rowspan="1" |CE9: Unknown Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |86
| colspan="1" rowspan="1" |OFA Exception
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |87
| colspan="1" rowspan="1" |Reserved
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |88
| colspan="1" rowspan="1" |NVDEC3 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |89
| colspan="1" rowspan="1" |NVDEC4 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |90
| colspan="1" rowspan="1" |Reserved
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |91
| colspan="1" rowspan="1" |Reserved
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |92
| colspan="1" rowspan="1" |High single-bit ECC error rate
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |93
| colspan="1" rowspan="1" |Non-fatal violation of provisioned InfoROM wear limit
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |94
| colspan="1" rowspan="1" |Contained ECC error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |95
| colspan="1" rowspan="1" |Uncontained ECC error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |96
| colspan="1" rowspan="1" |NVDEC5 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |97
| colspan="1" rowspan="1" |NVDEC6 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |98
| colspan="1" rowspan="1" |NVDEC7 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |99
| colspan="1" rowspan="1" |NVJPG1 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |100
| colspan="1" rowspan="1" |NVJPG2 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |101
| colspan="1" rowspan="1" |NVJPG3 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |102
| colspan="1" rowspan="1" |NVJPG4 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |103
| colspan="1" rowspan="1" |NVJPG5 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |104
| colspan="1" rowspan="1" |NVJPG6 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |105
| colspan="1" rowspan="1" |NVJPG7 Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |106
| colspan="1" rowspan="1" |SMBPBI [[Test]] Message
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |107
| colspan="1" rowspan="1" |SMBPBI Test Message Silent
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |108-


109
| colspan="1" rowspan="1" |Reserved
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |110
| colspan="1" rowspan="1" |Security Fault Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |111
| colspan="1" rowspan="1" |Display Bundle Error Event
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |112
| colspan="1" rowspan="1" |Display Supervisor Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |113
| colspan="1" rowspan="1" |DP Link Training Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |114
| colspan="1" rowspan="1" |Display Pipeline Underflow Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |115
| colspan="1" rowspan="1" |Display Core Channel Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |116
| colspan="1" rowspan="1" |Display Window Channel Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |117
| colspan="1" rowspan="1" |Display Cursor Channel Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |118
| colspan="1" rowspan="1" |Display Pixel Pipeline Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |119
| colspan="1" rowspan="1" |GSP RPC Timeout
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |120
| colspan="1" rowspan="1" |GSP Error
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
|-
| colspan="1" rowspan="1" |121
| colspan="1" rowspan="1" |Reserved
|
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |122
| colspan="1" rowspan="1" |SPI PMU RPC Read Failure
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |123
| colspan="1" rowspan="1" |SPI PMU RPC Write Failure
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |124
| colspan="1" rowspan="1" |SPI PMU RPC Erase Failure
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|-
| colspan="1" rowspan="1" |125
| colspan="1" rowspan="1" |Inforom FS Failure
|
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |X
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
| colspan="1" rowspan="1" |
|}


== References ==
== References ==
<references />
 
* [https://wiki.hpcmate.com Nvidia GPU Tips and Tricks]
 
 
== Related Pages ==
 
* [[Linux]]
* [[Server]]
* [[Hardware]]
* [[Network]]
 
 
[[Category:GPU]]
[[Category:GPU]]
== Knowledge Graph ==
Related
→ [[CUDA]]
→ [[GPU]]
→ [[NVIDIA GPU]]
→ [[H100]]
→ [[NVLink]]
→ [[AMD GPUs]]
→ [[A100]]
→ [[MIG]]


[[Category:Reference]]
[[Category:Guide]]

Latest revision as of 11:30, 17 July 2026

Template:Status

Template:TOC

Overview

Nvidia GPU Tips and Tricks에 대한 기술 문서입니다.

Summary

  • 무엇인가? - Nvidia GPU Tips and Tricks
  • 왜 필요한가? - HPC 및 서버 환경에서 필수 개념
  • 언제 사용하는가? - 서버 구성, 성능 튜닝, 문제 해결 시


Purpose

이 문서가 존재하는 이유

  • Goal: Nvidia GPU Tips and Tricks에 대한 기술 정보 제공
  • Scope: Nvidia GPU Tips and Tricks의 개념, 사용법, 설정
  • Non-goals: 다른 주제로의 확장


Key Concepts

Concept Description Related
Nvidia GPU Tips and Tricks HPC/서버 환경에서 중요한 기술 개념 Linux, Server


Detailed Explanation

Based on many cases, XID 62 and 119 error caused by incompatible driver version issues. it's recommended to install right version of GPU driver based on customer CUDA application version.

Remove Nvidia GPU driver on Ubuntu
$sudo apt-get remove --purge '^nvidia-.*'
apt search or get download GPU driver from nvidia then install and test
XID Nvidia GPU Failure Linux Kernel message Causes
HW Error Driver Error User App Error System Memory Corruption Bus Error


Best Practices

  • 최신 버전 사용 권장
  • 공식 문서 참고
  • 테스트 환경에서 먼저 검증


References


Related Pages

Knowledge Graph

Related

CUDAGPUNVIDIA GPUH100NVLinkAMD GPUsA100MIG