使用Nvidia Nsight生成可重定位设备代码 [英] Generating Relocatable Device Code using Nvidia Nsight

问题描述

我正在尝试在CUDA上编译一个动态并行性示例，当我尝试对其进行编译时，会给出错误提示，

I'm trying to compile a dynamic parallelism example on CUDA and when i try to compile it gives and error saying,

内核需要单独的编译模式

后来发现我必须将-relocabletable-device-code 标志设置为 true .但是，在Nsight Eclipse中是否要设置一个标志，以使将 relocabletable-device-code 设置为 true ?

Later found that I have to set the --relocatable-device-code flag to true. But, is there a flag to set in order to make the set relocatable-device-code to true in Nsight Eclipse?

推荐答案

如果您不使用makefile项目，您可以从菜单开始，在以下位置更改传递给Nsight项目的 nvcc 的选项.

If you are not using makefile project, you could change the options passed to nvcc of a Nsight project at the following position, starting from the menu.

项目-属性-生成-设置-工具设置-NVCC编译器

Project - Properties - Build - Settings - Tool Settings - NVCC Compiler

由于Nsight不提供rdc选项供您检查，因此您可以直接将"Commnad"更改为

As Nsight does not provide a rdc option for you to check, you could directly change 'Commnad' from

nvcc

到

nvcc -rdc=true

或从以下位置更改命令行模式"

or change 'Command line pattern' from

${COMMAND} ${FLAGS} ${OUTPUT_FLAG} ${OUTPUT_PREFIX} ${OUTPUT} ${INPUTS}

到

${COMMAND} ${FLAGS} -rdc=true ${OUTPUT_FLAG} ${OUTPUT_PREFIX} ${OUTPUT} ${INPUTS}

第二个更好.

您可能还希望仅针对所有配置"而不是调试"或发布"进行更改.

You may also want to change this for 'All configurations' rather than 'Debug' or 'Release' only.

您应该按照评论中@RobertCrovella的说明进行操作.这是官方的方式.

You should follow @RobertCrovella's instructions in the comment. It is the official way.

这篇关于使用Nvidia Nsight生成可重定位设备代码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IT屋！