Nvidia and CUDA programming - Let's try some CUDA programming

• Fedora 42 - my notes on installing the CUDA toolkit

Hello world

• CUDA tutorial -- hello world

__global__ void cuda_hello(){
    printf("Hello World from GPU!\n");
}

int main() {
    cuda_hello<<<1,1>>>();
    return 0;
}

#NOPTS = -allow-unsupported-compiler -Wno-deprecated-gpu-targets
NOPTS = -Wno-deprecated-gpu-targets

NVCC = /usr/local/cuda-12.9/bin/nvcc $(NOPTS)

all: hello

hello: hello.cu
	$(NVCC) hello.cu -o hello

#!/bin/bash

# You could put all this into some bash script ...
export CUDAHOSTCXX=/usr/bin/g++-14
export CC=/usr/bin/gcc-14
export CXX=/usr/bin/g++-14
export NVCC_CCBIN=/usr/bin/g++-14

# And perhaps this also.
export LD_LIBRARY_PATH=/usr/local/cuda-12.9/targets/x86_64-linux/lib:$LD_LIBRARY_PATH
export CPATH=/usr/local/cuda-12.9/targets/x86_64-linux/include:$CPATH
export PATH=/usr/local/cuda-12.9/bin:$PATH

make

/usr/local/cuda-12.9/bin/nvcc -Wno-deprecated-gpu-targets hello.cu -o hello
/usr/include/bits/mathcalls.h(79): error: exception specification is incompatible with that of previous function "cospi" (declared at line 2601 of /usr/local/cuda-12.9/bin/../targets/x86_64-linux/include/crt/math_functions.h)
   extern double cospi (double __x) noexcept (true); extern double __cospi (double __x) noexcept (true);

hello.cu(2): error: identifier "printf" is undefined
      printf("Hello World from GPU!\n");
      ^

5 errors detected in the compilation of "hello.cu".
make: *** [Makefile:24: hello] Error 2

These apparently reference things in /usr/include/bits/mathcalls.h (which is a regular part of linux) but in an "old" way. The fix is something like this. Replace the first line with the second:

extern __DEVICE_FUNCTIONS_DECL__ __device_builtin__ double                 sinpi(double x);
extern __DEVICE_FUNCTIONS_DECL__ __device_builtin__ double                 sinpi(double x) noexcept (true);

cd /usr/local/cuda-12.9/targets/x86_64-linux/include/crt
vi math_functions.h

#include 

We get the file "hello" and running it does nothing. No output. Just like the tutorial said. So what is the point? It did help us to grind out way through compiling something with nvcc. Nonetheless, a printf() that doesn't produce output is pretty disappointing.

As an experiment, I changed my file to this, compiled it, and ran it. No output. And it returns to the command line in about a second. It should be in an infinite loop. There are clearly strange things going on.

#include 

__global__ void cuda_hello(){
    for ( ;; )
        printf("Hello World from GPU!\n");
}

int main() {
    cuda_hello<<<1,1>>>();
    return 0;
}

#include 

__global__ void cuda_hello(){
	for ( ;; )
		printf("Hello World from GPU!\n");
}

int main() {
    cuda_hello<<<1,1>>>();
	printf ( "Goodbye\n" );
    return 0;
}

I found the solution!

#include 

__global__ void cuda_hello(){
	int i;

	for ( i=0 ; i<4; i++ )
		printf("Hello World %d from GPU!\n", i+1 );
}

int main() {
    cuda_hello<<<1,1>>>();
	cudaDeviceSynchronize();
	printf ( "Goodbye\n" );
    return 0;
}

Hello World 1 from GPU!
Hello World 2 from GPU!
Hello World 3 from GPU!
Hello World 4 from GPU!
Goodbye

MUCH better tutorials

• An even easier intro to CUDA
• An easy into to CUDA

A better Makefile

# Build a cuda hello world
# Tom Trebisky  6-19-2025
# Hot! these days. over 110 yesterday.

# We could do this:
## .EXPORT_ALL_VARIABLES:

export CUDAHOSTCXX=/usr/bin/g++-14
export CC=/usr/bin/gcc-14
export CXX=/usr/bin/g++-14
export NVCC_CCBIN=/usr/bin/g++-14

# These won't work (and don't seem to be needed).
# They fail because of how the previous values are referenced.
# In lieu of CPATH we could use a -I line on gcc (but not nvcc)

#export LD_LIBRARY_PATH=/usr/local/cuda-12.9/targets/x86_64-linux/lib:$LD_LIBRARY_PATH
##export CPATH=/usr/local/cuda-12.9/targets/x86_64-linux/include:$CPATH
#export PATH=/usr/local/cuda-12.9/bin:$PATH

#NOPTS = -allow-unsupported-compiler -Wno-deprecated-gpu-targets
NOPTS = -Wno-deprecated-gpu-targets

# This nice options doesn't seem to work for us
#NVCC = /usr/local/cuda-12.9/bin/nvcc --std=c++14 $(NOPTS)
NVCC = /usr/local/cuda-12.9/bin/nvcc $(NOPTS)

all: hello

hello: hello.cu
	$(NVCC) hello.cu -o hello

clean:
	rm -f hello

# THE END

Time to do my homework

• CUDA C programming guide