Awesome HPC

High Performance Computing tools and resources for engineers and administrators.

High Performance Computing (HPC) most generally refers to the practice of aggregating computing power in a way that delivers much higher performance than one could get out of a typical desktop computer or workstation in order to solve large problems in science, engineering, or business.

Contents

Provisioning

• Grendel - Bare Metal Provisioning system for HPC Linux clusters (Source Code) GPL-3.
• XCat - xCAT is a toolkit for deployment and administration of clusters of all sizes (Source Code) EPL-1.0.
• Warewulf - Warewulf is a stateless and diskless container operating system provisioning system for large clusters of bare metal and/or virtual systems (Source Code) BSD-3.
• Rocks - A Linux distribution for developing Linux clusters other.
• Cobbler - Cobbler is a Linux installation server that allows for rapid setup of network installation environments (Source Code) GPL-2.0.
• Base Command Manager - Base Command Manager allows administrator to quickly build and manage heterogeneous clusters Proprietary.
• Scyld - Scyld Clusterware Scyld ClusterWare is developed based on the continuing evolution of Beowulf clusters first developed at NASA in the 1990s Proprietary.
• BlueBanquise - BlueBanquise is an open source cluster deployment and management stack built on Python and Ansible (Source Code) MIT.

Workload Managers

• Slurm - A free and open source job scheduler (Source Code) OSS.
• LSF - A job scheduler and workload management software developed by IBM Proprietary.
• Moab - Moab is a workload management and job scheduler other.
• Torque - Torque is a workload management and job scheduler other.
• OpenLava - OpenLava is a workload management and job scheduler other.
• UGE/SGE - Univa Grid Engine is a workload management engine for HPC Proprietary.
• Volcano - Volcano is a batch system built on Kubernetes Apache-2.0.
• Maui - Maui is a workload management and job scheduler other.
• Kube Batch - A batch scheduler of kubernetes for high performance workload, e.g. AI/ML, BigData, HPC Apache-2.0.
• OpenPBS - OpenPBS® software optimizes job scheduling and workload management in high-performance computing (HPC) environments (Source Code) other.

Pipelines

• Nextflow - Data drive computational pipelines Apache-2.0.
• Cromwell - Scientific workflow engine designed for simplicity & scalability (Source Code) BSD-3.
• Pegasus - A configurable system for mapping and executing scientific workflows over a wide range of computational infrastructure (Source Code)Apache-2.0.

Applications

• Spack - A flexible package manager that supports multiple versions, configurations, platforms, and compilers (Source Code) other.
• EasyBuild - EasyBuild - building software with ease (Source Code) GPL-2.

Compilers

• Nvidia - NVIDIA HPC compiler suite for Fortran, C/C++ with OpenACC Proprietary.
• Portland Group - The Portland Group compilers were Fortran, C/C++ compilers now integrated into NVIDIA HPC SDK Proprietary.
• Intel - The Intel compiler suite offers many language compilers for use in the HPC space Proprietary.
• Cray - A suite of compilers designed and optimized to target the AMD interlagos instruction set Proprietary.
• GNU - The GNU Compiler Collection is a suite of compilers targeting many languages (Source Code) GPL-3.
• LLVM - The LLVM project is a collection of modular compilers and toolchains (Source Code) OSS.

MPI

• OpenMPI - OpenMPI is an open source implementation of the MPI-3.1 standard (Source Code) BSD.
• MPICH - MPICH is a high-performance and widely portable implementation of the MPI-3.1 standard (Source Code) other.
• MVAPICH - MVAPICH is an open source implementation of the MPI-3.1 standard developed by Ohio State University BSD.
• Intel-MPI - Intel-MPI is Intel’s MPI-3.1 implementation included in their compiler suite other.

Parallel Computing

• ArrayFire - A general purpose tensor library that simplifies the process of software development for parallel architectures other.
• OpenMP - OpenMP is an application programming interface that supports multi-platform shared-memory multiprocessing programming other.

Benchmarking

• OSU Benchmarks - A collection of benchmarking tools for MPI developed by Ohio State University other.
• Intel MPI Benchmarks - A set of benchmarks developed by Intel for use with their Intel MPI other.
• HPCC Systems - HPCC Systems (High Performance Computing Cluster) is an open source, massive parallel-processing computing platform for big data processing and analytics (Source Code) other.
• LINPACK - LINPACK is a set of efficient fortran subroutines for solving linear systems which benchmarks are useful for HPC other.
• IOzone - IOzone is a filesystem benchmark tool OSS.
• IOR - Interleaved or Random is a useful benchmarking tool for testing parallel filesystems other.
• MDtest - MDtest is an MPI-based application for evaluating the metadata performance of a file system other.
• FIO - Flexible I/O is an advanced disk benchmark that depends upon the kernel’s AIO access library (Source Code) GPL-2.
• elbencho - A distributed storage benchmark for files, objects & blocks with support for GPUs GPL-3.

Miscellaneous

• OpenOnDemand - Open OnDemand helps computational researchers and students efficiently utilize remote computing resources by making them easy to access from any device (Source Code) MIT.
• Open XDMod - Open XDMoD is an open source tool to facilitate the management of high performance computing resources (Source Code) LGPL-3.
• Coldfront - ColdFront is an open source resource allocation system designed to provide a central portal for administration, reporting, and measuring scientific impact of HPC resources (Source Code) GPL-3.
• Pavilion2 - Pavilion is a Python 3 (3.6+) based framework for running and analyzing tests targeting HPC systems (Source Code) other.
• Reframe - A powerful Python framework for writing and running portable regression tests and benchmarks for HPC systems. (Source Code) BSD-3.
• OLCF Test Harness - The OLCF Test Harness (OTH) helps automate the testing of applications, tools, and other system software (Source Code) other.
• GoSlmailer - Goslmailer is a drop-in notification delivery solution for slurm that can do slack, mattermost, teams, and more.

Performance

• TotalView - TotalView is a debugging tool for HPC applications Proprietary.
• Tau - TAU Performance System® is a portable profiling and tracing toolkit for performance analysis of parallel programs written in Fortran, C, C++, UPC, Java, Python other.
• Valgrind - Valgrind is a tool designed to profile programs to determine memory leaks (Source Code) GPL-2.
• Paraver - Paraver is a very flexible data browser that is part of the CEPBA-Tools toolkit other.
• PAPI - Performance Application Programming Interface (PAPI) is a performance analysis tool (Source Code) other.

Parallel Shells

• pdsh - pdsh runs terminal commands across multiple hosts in parallel (Source Code) GPL-2.
• ClusterShell - Scalable cluster administration Python framework (Source Code) LGPL-2.1 .

Containers

• Apptainer - Apptainer is an open source container system (Source Code) BSD.
• Charliecloud - Charliecloud provides user-defined software stacks (UDSS) for high-performance computing (HPC) centers (Source Code) Apache-2.0.
• Docker - Docker is a set of platform as a service products that use OS-level virtualization to deliver software in packages called containers other.
• uDocker - A basic user tool to execute simple docker containers in batch or interactive systems without root privileges (Source Code) Apache-2.0.
• Shifter - Shifter is Linux containers for HPC (Source Code) other.
• HPC Container Maker - HPC Container Maker is an open source tool to make it easier to generate container specification files. Apache-2.0.
• Scarus - An OCI-compatible container engine for HPC BSD.
• Singularity HPC - Singularity Registry HPC (shpc) allows you to install containers as modules (Source Code) MPL 2.0.

Environment Management

• Lmod - Lmod: An Environment Module System based on Lua, Reads TCL Modules, Supports a Software Hierarchy (Source Code) other.
• Environment Modules - Environment Modules: provides dynamic modification of a user’s environment (Source Code) GPL-2.
• Anaconda - Anaconda is a Python and R distribution for use in computational science other.
• Mamba - Mamba is a reimplementation of the conda package manager in C++ (Source Code) BSD.

Visualization

• Visit - VisIt - Visualization and Data Analysis for Mesh-based Scientific Data (Source Code) BSD-3.
• Paraview - ParaView is an open-source, multi-platform data analysis and visualization application based on Visualization Toolkit (VTK) (Source Code) BSD-3.

Parallel Filesystems

• GPFS - GPFS is a high-performance clustered file system software developed by IBM Proprietary.
• Quobyte - A high performance filesystem Proprietary.
• Ceph - Ceph is a distributed object, block, and file storage platform (Source Code) other.
• Weka - A file system designed for HPC Proprietary .
• Lustre/Exascaler - Lustre is an open-source, distributed parallel file system software platform designed for scalability, high-performance, and high-availability (Source Code) other.
• BeeGFS - BeeGFS is a hardware-independent POSIX parallel file system developed with a strong focus on performance and designed for ease of use, simple installation, and management Proprietary.
• OrangeFS - OrangeFS is a next generation parallel file system for Linux clusters (Source Code) other.
• MooseFS - Moose File System is an Open-source, POSIX-compliant distributed file system developed by Core Technology (Source Code) GPL-2.0.

Programming Languages

• Julia - Julia is a high-level, high-performance dynamic language for technical computing MIT.
• Futhark - Futhark is a purely functional data-parallel programming language in the ML family isc.
• Chapel - Chapel is a programming language designed for productive parallel computing at scale Apache-2.0.

Monitoring

Prometheus Based

• Slurm Exporter - Prometheus exporter for performance metrics from Slurm GPL-3.0.
• Slurm Exporter - Slurm Exporter for Prometheus using Rest API GPL-3.0.
• Infiniband Exporter - The InfiniBand exporter collects counters from InfiniBand switches and HCAs Apache-2.0.
• Cgroup Exporter - Produces metrics from cgroups Apache-2.0.
• Cgroup Exporter - A Prometheus exporter for cgroup-level metrics unknown.
• GPFS Exporter - The GPFS exporter collects metrics from the GPFS filesystem Apache-2.0.
• Lustre Exporter - Prometheus exporter for use with the Lustre parallel filesystem GPL-3.0.
• DCGM Exporter - NVIDIA GPU metrics exporter for Prometheus leveraging DCGM Apache-2.0.

Journals

• Journal of Super Computing - An International Journal of High-Performance Computer Design, Analysis, and Use.

Podcasts

• This week in HPC - Each week, Intersect360 Research CEO Addison Snell and HPCwire editor Tiffany Trader dissect the week’s top HPC stories.
• Exascaler Project - ECP’s Let’s Talk Exascale podcast goes behind the scenes to chat with some of the people who are bringing a capable and sustainable exascale computing ecosystem to fruition.
• @HPCpodcast - Join Shahin Khan and Doug Black as they discuss Supercomputing technologies and the applications, markets, and policies that shape them.

Blogs

• HPCWire - Since 1987 covering the fastest computers in the world and the people who run them.
• InsideHPC - insideHPC is a global publication recognized for its comprehensive and insightful coverage of the HPC-AI community, linking vendors, end-users and HPC strategists.
• The Next Platform - Offers in-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds.
• The Register HPC - The Register is a leading and trusted global online enterprise technology news publication, reaching roughly 40 million readers worldwide.
• HPC at Dell - High-Performance Computing knowledge base articles from Dell.

Conferences

• Pearc - Practice & Experience in Advanced Research Computing.
• Supercomputing (SC) - The International Conference for High Performance Computing, Networking, Storage, and Analysis.
• Supercomputing International (ISC) - The International Conference for High Performance Computing, Networking, Storage, and Analysis.
• CCGrid - IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing.
• IEEE-HPEC - IEEE High Performance Embedded Computing.
• Hot Chips - Semiconductor industry’s leading conference on high-performance microprocessors and related circuits.
• Hot Interconnects - IEEE conference on software architectures and implementations for interconnection networks of all scales.
• ESSA - Workshop on Extreme-Scale Storage and Analysis.
• IEEE-IPDPS - IEEE International Parallel & Distributed Processing Symposium.
• ESPM2 Workshop - International Workshop on Extreme Scale Programming Models and Middleware.
• LCI Workshops - The Linux Clusters Institute (LCI) is providing education and advanced technical training for the deployment and use of computing clusters to the high performance computing community worldwide.
• HPC Carpentry - Teaching basic skills for high-performance computing.

Websites

• Top500 - The TOP500 project ranks and details the 500 most powerful non-distributed computer systems in the world.

User Groups

• MVAPICH - The MUG conference provides an open forum for all attendees (users, system administrators, researchers, engineers, and students) to discuss and share their knowledge on using MVAPICH libraries.
• Slurm - The annual Slurm user group meeting.

Contributing

Contributing guidelines can be found in contributing.md.