Default host compiler used by nvcc for linux

gcc compiler-construction cuda nvcc
smilingbuddha picture smilingbuddha · Nov 29, 2011 · Viewed 13.2k times · Source

I am using CUDA 4.0 on Ubuntu 10.10 with GTX 570 (compute capcability 2.0), with the GCC compiler suite. As I understand it, during compilation the CUDA compiler driver nvcc splits the .cu files into host code and device code and calls the host compiler to compile the host code and compiles the device code separately. Finally it merges the generated host object code and the device PTX code into a single executable.

For Linux systems what is the default compiler that is invoked for compiling the host code? Is it the C compiler (gcc) or the C++ compiler (g++) of the GCC suite?

Answer

Kenneth Hoste picture Kenneth Hoste · Mar 20, 2013

You want the -ccbin option for nvcc, e.g. to use icpc (the Intel C++ compiler), use nvcc -ccbin=icpc (assuming the icpc is available in your $PATH).

Note that you should always pass a C++ compiler (g++, icpc, etc.), since nvcc treats the code as C++, even when it's C code.

Related questions

How to create a static library with g++?

Can someone please tell me how to create a static library from a .cpp and a .hpp file? Do I need to create the .o and the .a? I would also like to know how can I compile a static …

Read More
How do I compile the asm generated by GCC?

I'm playing around with some asm code, and something is bothering me. I compile this: #include <stdio.h> int main(int argc, char** argv){ printf("Hello World\n"); return 0; } with gcc file.c -S -o file.S this …

Read More
Clang vs GCC - which produces faster binaries?

I'm currently using GCC, but I discovered Clang recently and I'm pondering switching. There is one deciding factor though - quality (speed, memory footprint, reliability) of binaries it produces - if gcc -O3can produce a binary that runs 1% faster, …

Read More