如何分析cuda内核的全局内存事务数

如何分析cuda内核的全局内存事务数

本文介绍了如何分析cuda内核的全局内存事务数?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

如何在cuda命令行探查器中为 uncached_global_load_transaction计数器启用分析?

How to enable profiling for "uncached_global_load_transaction" counter in cuda command-line profiler?

推荐答案

命令行探查器受到控制使用以下环境变量-

The command line profiler is controlled using the following environment variables -

COMPUTE_PROFILE: is set to either 1 or 0 (or unset) to enable or disable profiling.
COMPUTE_PROFILE_CONFIG: is used to specify a config file for enabling performance counters in the GPU and various other options.
COMPUTE_PROFILE_LOG: is set to the desired file path for profiling output.

您可以将上述环境变量设置为-

In your case you can set above environment variables as -

COMPUTE_PROFILE=1
COMPUTE_PROFILE_CONFIG=config.txt
COMPUTE_PROFILE_LOG=profiler_output.txt

config.txt 必须包含条目 uncached_global_load_transaction

这篇关于如何分析cuda内核的全局内存事务数?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!

08-04 22:09