PyCOMPSs/COMPSs

PyCOMPSs/COMPSs

Easy task-based parallelization and efficient execution in distributed infrastructures.

Last updated: 17 Jun 2025     |     Release: 3.3.3 Orchid Update

COMP Superscalar (COMPSs) is a task-based programming model which aims to ease the development of applications for distributed infrastructures, such as large High-Performance Clusters (HPC), Clouds and Container managed clusters. PyCOMPSs is the Python binding of COMPSs.
COMPSs provides a programming interface for the development of the applications in Python/Java/C/C++, a runtime system that exploits the inherent parallelism of applications at execution time, and a rich ecosystem for the operation monitoring, performance evaluation and integration with Jupyter/Jupyterlab.

22
Forks
55
Stargazers
Apache-2.0
License

Execution Environment

User Interfaces
  • Local
  • High Performance Cluster (HPC)
  • Clouds
  • Docker
  • Mesos
Resource Managers
  • SLURM
  • PBS
  • LSF
  • SGE
  • TCS
Transfer Protocols
  • NIO
  • SCP

Terminology
Terminology below follows the definitions established by the Workflows Community Terminology.

Characteristics
Flow
Task
Iterative
Granularity
Functions
Sub-workflows
Executables
Coupling
Loose
Dynamicity
Branches
Domain
Agnostic
Composition
Description
API
Abstraction
Intermediate
Modularity
Flat
Hierarchical
Orchestration
Planning
Dynamic
Execution
Resource Manager
Serverless
Data Management
Transport
Streaming
File-based
Storage
Local
Shared
Distributed
Metadata Capture
Anomaly Detection
Monitoring
Provenance
Extensions
Adaptive Resource Allocation
HPC Scalable
Replicated Storage