Discover High Performance ParalleX (HPX), the first runtime system implementation of the ParalleX execution model.
With its ability to hide latency and deliver variable-grained parallelism within a hierarchical namespace environment, HPX makes programming efficient, scalable, and surprisingly straightforward.
Powered by C++ and aligned with the C standard library, HPX offers standardization and a gentle learning curve.
It's built on a solid foundation of experience gained from years of crafting highly parallel applications for HPC systems.

What’s so Special About HPX?

standards-oriented API
HPX exposes a uniform, standards-oriented API for ease of programming parallel and distributed applications.
syntax and semantics
HPX provides unified syntax and semantics for local and remote operations.
runtime services
It implements a rich set of runtime services supporting a broad range of use cases.
solve problems
It is designed to solve problems conventionally considered to be scaling-impaired.
It is the first fully functional implementation of the ParalleX execution model.
asynchronous code
It enables programmers to write fully asynchronous code using hundreds of millions of threads.
HPX makes concurrency manageable with dataflow and future based synchronization.
runtime adaptivity
HPX exposes a uniform, flexible, and extendable performance counter framework which can enable runtime adaptivity.
HPX has been designed and developed for systems of any scale, from hand-held devices to very large scale systems.
open source license
HPX is published under a liberal open-source license and has an open, active, and thriving developer community.

Explore Real-World HPX Applications

Browse our curated collection of HPX users and applications. Gain insights into the organizations and individuals utilizing HPX, understand their purposes, and access relevant links.

  • YewPar

    Developed by
    Archibald Maier

    A generic framework for exact combinatorial search.

  • Hytrac

    Developed by
    First Light Fusion Ltd

    A hydrodynamic front-tracking cose for the study of high energy density multi-material flows.

  • Phylanx

    Developed by
    Louisiana State University, University of Oregon, University of Arizona

    An asyncronous distributed C++ array processing toolkit.

Become a HPX Contributor

Delve into our comprehensive resource section, where we share our Governance Models and Code of Conduct. This valuable information is especially tailored for contributors, and anyone interested in our work processes, decision-making, roles, and future plans.