NVIDIA H100 GPU nvidia-SMI 输出报告不正确的聚合 SRAM 可纠正值

Summary: NVIDIA H100 图形处理单元 (GPU) 的 nvidia-SMI 输出可能会报告聚合静态随机存取存储器 (SRAM) 可纠正计数器的值不正确。

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.

Symptoms

输出示例来自”nvidia-smi -q -d ECC" 命令配合使用的常见选项:

 

NVSMI 日志输出,带有聚合 SRAM 可纠正值 18446744073709551615

在上面的例子中,18446744073709551615的总SRAM可纠正值异常高且不正确。

 

Cause

SRAM计数器计算错误。

Resolution

更新到 NVIDIA H100 驱动程序包版本 570.124.06 或更高版本。

Affected Products

PowerEdge XE8640, PowerEdge XE9640, PowerEdge XE9680
Article Properties
Article Number: 000317812
Article Type: Solution
Last Modified: 12 May 2025
Version:  1
Find answers to your questions from other Dell users
Support Services
Check if your device is covered by Support Services.