CUDA编译和链接 [英] CUDA compilation and Linking

问题描述

我有主机编译器（ g ++ ），设备文件（例如d_A.cu等）编译的主机文件（比如h_A.cpp等）由设备编译器编译（ nvcc ）和主机设备文件（例如主机函数，内核调用等）（例如h_d_A.cu） nvcc ）。

I have host files (say h_A.cpp, etc) which can be compiled by host compiler (g++), device files (say d_A.cu, etc) to be compiled by device compiler (nvcc) and host-device files i.e., host functions, kernel call, etc (say h_d_A.cu) to be compiled by device compiler (nvcc).

设备端编译

nvcc -arch=sm_20 -dc d_A.cu -o d_A.o $(INCLUDES)

/ ，因为该文件可能调用/具有可重定位设备功能* /

/* -dc since the file may call / have relocatable device functions */

主机端编译

g++ -c h_A.cpp -o h_A.o $(INCLUDES, FLAGS)

设备链接建议此处

nvcc -arch=sm_20 -dlink d_A.o -o link.o

/ *链接由于可重定位设备函数* /

/* Linkage due to relocatable device functions */

我正在为项目使用Makefile。现在，我的查询是，我如何形成最终的可执行？
我试过了，

I am using Makefile for the project. Now, the query i have is, how do i form the final executable? I have tried,

1. g++ h_A.o link.o –L<path> -lcudart
Error: relocation 0 has invalid symbol index 10
2. g++ h_A.o link.o –lcudadevrt –L<path> –lcudart
Error: undefined reference to phase2(int*, int) //where phase2 is my __global__ kernel.

推荐答案

抱歉，找到我错过的对象，同时形成最终的可执行文件。

Sorry, Found out the problem i missed to include device objects while forming the final executable.

更正了语法。

g++ h_A.o d_A.o link.o –L<path> -lcudart

这篇关于CUDA编译和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！