PowerEdge XE8640 med H100: Problem med GPU-ydeevne – afmatning af HW-strømbremse – aktiv
Summary: Fald i GPU-ydeevne og "nvsmi-q"-loggen kan indikere, at HW-strømbremsens afmatning er aktiv.
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.
Instructions
I nogle hjørnetilfælde kan brugeren støde på en dårlig GPU-ydeevne, og nvsmi-q log kan indikere, at HW Power Brake Slowdown er aktiv.nvidia-smi & GPU_burn log output,
nvsmi-q Log output
Clocks Throttle Reasons Idle : Not Active Applications Clocks Setting : Not Active SW Power Cap : Not Active HW Slowdown : Active HW Thermal Slowdown : Not Active HW Power Brake Slowdown : Active Sync Boost : Not Active SW Thermal Slowdown : Not Active Display Clock Setting : Not Active
nvidia-smi --query-gpu=index,timestamp,power.draw,clocks.sm [clocks.sm],clocks.mem,clocks.gr [clocks.gr] --format=csv -l 1
Løsning: Opdater BIOS, CPLD og iDRAC til nyeste. Nylige feltsager har vist, at opdatering af CPLD til version 1.2.2 og iDRAC til version 7.10.30 har løst problemet
** Uddrag Post opdatering **gpu_burn opererer ved ~ 300k Gflops, og nvidia-smi viser hver GPU ~700 W ved 100 % udnyttelse.
nvsmi-q log output efter BIOS-opdatering.
Clocks Throttle Reasons Idle : Active Applications Clocks Setting : Not Active SW Power Cap : Not Active HW Slowdown : Not Active HW Thermal Slowdown : Not Active HW Power Brake Slowdown : Not Active Sync Boost : Not Active SW Thermal Slowdown : Not Active Display Clock Setting : Not Active
nvidia-smi & GPU_burn
Affected Products
PowerEdge XE8640Products
XE ServersArticle Properties
Article Number: 000220508
Article Type: How To
Last Modified: 10 Apr 2025
Version: 5
Find answers to your questions from other Dell users
Support Services
Check if your device is covered by Support Services.