可分离编译后如何将主机代码与静态 CUDA 库链接? [英] How to link host code with a static CUDA library after separable compilation?

问题描述

好的，关于如何正确链接事物，我有一个非常令人不安的 CUDA 5.0 问题.如果能提供任何帮助，我将不胜感激！

Alright, I have a really troubling CUDA 5.0 question about how to link things properly. I'd be really grateful for any assistance!

使用 CUDA 5.0 的可分离编译特性，我生成了一个静态库 (*.a).通过 nvcc 运行时，这很好地与其他 *.cu 文件链接，我已经这样做了很多次了.

Using the separable compilation features of CUDA 5.0, I generated a static library (*.a). This nicely links with other *.cu files when run through nvcc, I have done this many times.

我现在想获取一个 *.cpp 文件，并使用 g++ 或其他方式将其链接到此静态库中的主机代码，但不使用 nvcc.如果我尝试这样做，我会收到类似

I'd now like to take a *.cpp file and link it against the host code in this static library using g++ or whatever, but not nvcc. If I attempt this, I get compiler errors like

对 __cudaRegisterLinkedBinary 的未定义引用

undefined reference to __cudaRegisterLinkedBinary

我同时使用 -lcuda 和 -lcudart 并且据我所知，这些库的顺序正确(意思是 -lmylib -lcuda -lcudart).我不认为这是一个问题.也许我错了，但我觉得我错过了一步，我需要对我的静态库(设备链接?)做其他事情，然后才能将它与 g++ 一起使用.

I'm using both -lcuda and -lcudart and, to my knowledge, have the libraries in the correct order (meaning -lmylib -lcuda -lcudart). I don't think it is an issue with that. Maybe I'm wrong, but I feel I'm missing a step and that I need to do something else to my static library (device linking?) before I can use it with g++.

我错过了什么重要的事情吗?这甚至可能吗?

Have I missed something crucial? Is this even possible?

额外问题:我希望最终结果是一个动态库.我怎样才能做到这一点?

Bonus question: I want the end result to be a dynamic library. How can I achieve this?

推荐答案

当你与 nvcc 链接时，它会与主机链接一起进行隐式设备链接.如果您使用主机编译器进行链接(如使用 g++)，则需要添加显式步骤以使用 –dlink 选项进行设备链接，例如

When you link with nvcc, it does an implicit device link along with the host link. If you use the host compiler to link (like with g++), then you need to add an explicit step to do a device link with the –dlink option, e.g.

nvcc –arch=sm_35 –dc a.cu b.cu
nvcc –arch=sm_35 –dlink a.o b.o –o dlink.o
g++ a.o b.o dlink.o x.cpp –lcudart

在 使用 nvcc 文档的单独编译章节.

目前我们只支持可重定位设备代码的静态库.我们有兴趣了解您希望如何在动态库中使用此类代码.请随时在评论中回答.

Currently we only support static libraries for relocatable device code. We’d be interested in learning how you would want to use such code in a dynamic library. Please feel free to answer in the comments.

回答下面评论中的问题有没有办法使用nvcc将mylib.a变成可以放入g++的东西?"

To answer the question in the comment below " Is there any way to use nvcc to turn mylib.a into something that can be put into g++?"

只需像使用对象一样使用库，如下所示:

Just use the library like an object, like this:

nvcc –arch=sm_35 –dlink mylib.a –o dlink.o
g++ mylib.a dlink.o x.cpp –lcudart

这篇关于可分离编译后如何将主机代码与静态 CUDA 库链接?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！