Superpod Modules

Introduction

Modules in the context of High-Performance Computing (HPC) systems are packages that I can load and unload dynamically to configure my environment(s) with the necessary software. Below is a brief explanation of each module listed.

Compiler Modules

AMD AOCC

• Module: amd/aocc/4.1.0

  Description: AMD Optimizing C/C++ Compiler is a high-performance, production-quality code generation tool. It supports C, C++, and Fortran programming languages and is specifically optimized for AMD processors.

  module load amd/aocc/4.1.0

GNU Compiler Collection

• Modules: gcc/11.2.0 and gcc/13.2.0

• Description: These versions of GCC are widely-used compilers for C, C++, and Fortran. GCC 13.2.0 is the default version in this environment, known for its portability and a standard on many Linux distributions.

  module load gcc/11.2.0 and gcc/13.2.0

Intel OneAPI

• Module: intel/oneapi/2023.2

• Description: Intel OneAPI is a comprehensive, cross-architecture programming toolkit, which includes compilers and analysis tools optimized for Intel processors.

  module load intel/oneapi/2023.2

NVIDIA HPC SDK

• Module: nvidia/nvhpc/23.7

• Description: NVIDIA HPC SDK includes compilers and tools to develop applications for NVIDIA GPUs and CPUs, optimized for CUDA and GPU-accelerated applications.

• module load nvidia/nvhpc/23.7

Application Modules

AMBER

• Module: amber/22

• Description: AMBER is a suite of biomolecular simulation programs primarily used for molecular dynamics of proteins and nucleic acids.

• module load amber/22

Apptainer

• Module: apptainer/1.1.9

• Description: Formerly known as Singularity, Apptainer is a container platform designed for HPC environments, enabling portable and reproducible computational environments.

• module load apptainer/1.1.9

Conda

• Module: conda

• Description: Conda is an open-source package and environment management system, popular for managing Python environments and packages.

• module load conda

Gaussian

• Module: gaussian/g16c02

• Description: Gaussian is used for computational chemistry, performing electronic structure calculations, widely used for predicting molecular structures and properties.

• module load gaussian/g16c02

Using Modules

To use the NVIDIA NVHPC 23.7 compiler suite on an HPC system:

Step 1: Load the NVHPC Module

Load the NVIDIA NVHPC module to set up the environment with the necessary paths and environment variables.

module load nvidia/nvhpc/23.7

Verify that the module has been loaded correctly by checking the currently loaded modules:

module list

Step 2: Compile Code

Use the NVHPC compilers to compile code. NVHPC includes several compilers, such as nvc for C, nvc++ for C++, and nvfortran for Fortran. Here are examples of how to compile C, C++, and Fortran code:

Compile C Code

nvc -o my_program my_program.c

Compile C++ Code

nvc++ -o my_program my_program.cpp

Compile Fortran Code

nvfortran -o my_program my_program.f90

Step 3: Run Program

Run the compiled executable:

./my_program

Example Workflow

This workflow includes loading the NVHPC module, compiling a C program, and running the compiled program:

1. Load the NVHPC module:

module load nvidia/nvhpc/23.7

2. Compile the C program:

nvc -o hello_world hello_world.c

3. Run the compiled program:

./hello_world

This R Markdown setup will provide a clean and organized notebook in HTML format, detailing the use of superpod modules in an HPC environment. ```

This format keeps your document well-organized and easy to follow, making good use of sections and code blocks to separate and clearly describe each step.