Difference between revisions of "Nvidia CUDA Toolkit"

From UFRC
Jump to navigation Jump to search
Line 24: Line 24:
 
=== For single task, non MPI programs===  
 
=== For single task, non MPI programs===  
  
  module load cuda/9.1.85 intel/2017
+
  module load cuda/10.0.130 intel/2018.1.163
  
 
or  
 
or  
 
   
 
   
  module load cuda/9.1.85 gcc/7.3.0
+
  module load cuda/10.0.130  gcc/7.3.0
  
 
===For MPI programs ===
 
===For MPI programs ===

Revision as of 19:51, 10 September 2019

Description

cuda website  
CUDA™ is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU). With millions of CUDA-enabled GPUs sold to date, software developers, scientists and researchers are finding broad-ranging uses for GPU computing with CUDA.

Required Modules

For single task, non MPI programs

module load cuda/10.0.130 intel/2018.1.163

or

module load cuda/10.0.130  gcc/7.3.0

For MPI programs

module load cuda/9.1.85 intel/2017 openmpi/3.0.0

System Variables

  • HPC_{{#uppercase:cuda}}_DIR
  • HPC_{{#uppercase:cuda}}_BIN
  • HPC_{{#uppercase:cuda}}_INC
  • HPC_{{#uppercase:cuda}}_LIB

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. Currently cuda/8.0 and cuda/8.061 are the only versions supported on hipergator.

$ module spider cuda
-------------------------------------------------------------
cuda:
-------------------------------------------------------------
    Description:
      NVIDIA CUDA Toolkit

     Versions:
        cuda/8.0
        cuda/8.0.61
        cuda/9.0.176
        cuda/9.1.85

--------------------------------------------------------------------------------------------------------------------
  For detailed information about a specific "cuda" module (including how to load the modules) use the module full name.
  For example:

     $ module spider cuda/9.1.85
--------------------------------------------------------------------------------------------------------------------

$ module load cuda/9.1.85

$ which nvcc
/apps/compilers/cuda/9.1.85/bin/nvcc

$ printenv | grep CUDA
HPC_CUDA_DIR=/apps/compilers/cuda/9.1.85
HPC_CUDA_LIB=/apps/compilers/cuda/9.1.85/lib64
HPC_CUDA_BIN=/apps/compilers/cuda/9.1.85/bin
HPC_CUDA_INC=/apps/compilers/cuda/9.1.85/include
UFRC_FAMILY_CUDA=cuda
UFRC_FAMILY_CUDA_VERSION=9.1.85

Sample GPU Batch Job Scripts

SLURM Job Scripts

See the Example_SLURM-GPU-Job-Scripts page for an example.