CUDA¶

Description¶

The NVIDIA CUDA Toolkit provides a development environment for creating high performance GPU-accelerated applications. The toolkit includes GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler and a runtime library to deploy your application.

Environment Modules¶

Run module spider cuda to find out what environment modules are available for this application.

Environment Variables¶

HPC_CUDA_DIR - installation directory
HPC_CUDA_BIN - executable directory
HPC_CUDA_INC - includes directory
HPC_CUDA_LIB - library directory

Additional Usage Information¶

Environment¶

For CUDA development please load the "cuda" module. Doing so will ensure that your environment is set up correctly for the use of the CUDA compiler, header files, and libraries. The cuda versions below are currently supported on hipergator.

Expand to view example of loading/using cuda.

``` bash $ module spider cuda

cuda:¶

Description:
  NVIDIA CUDA Toolkit

 Versions:
    cuda/12.4.1
    cuda/12.8.1
    cuda/12.9.1
 Other possible modules matches:
    pycuda

To find other possible module matches execute:

  $ module -r spider '.*cuda.*'

For detailed information about a specific "cuda" package (including how to load the modules) use the module's full name. Note that names that have a trailing (E) are extensions provided by other modules. For example:

 $ module spider cuda/12.9.1

$ module load cuda/12.9

$ which nvcc
/apps/compilers/cuda/12.9.1/bin/nvcc

$ env | grep _CUDA
LMOD_FAMILY_CUDA_VERSION=12.9.1
HPC_CUDA_DIR=/apps/compilers/cuda/12.9.1
HPC_CUDA_LIB=/apps/compilers/cuda/12.9.1/lib64
HPC_CUDA_BIN=/apps/compilers/cuda/12.9.1/bin
HPC_CUDA_INC=/apps/compilers/cuda/12.9.1/include
LMOD_FAMILY_CUDA=cuda
```

Selecting CUDA Arch Flags¶

When compiling with NVCC, you need to specify the Nvidia architecture that the CUDA files will be compiled for. Please refer to GPU Feature List for CUDA naming scheme sm_xy where x denotes the GPU generation and y denotes the version. The table below lists the SM flags for the three types of GPUs on HiPerGator.

SM	Nvidia Cards
SM_89	L4
SM_100	B200

Sample GPU Batch Job Scripts¶

See the Sample Job Scripts page for an example.

Categories¶

programming, library, graphics