kokkos/kokkos

What it solves

Kokkos solves the problem of performance portability in High-Performance Computing (HPC). It allows developers to write C++ code once and run it efficiently across different major HPC platforms without having to rewrite the application for every specific hardware architecture.

How it works

It provides a C++ programming model that abstracts both parallel execution and data management. By targeting complex node architectures with N-level memory hierarchies and multiple execution resources, it can utilize various backend programming models including CUDA, HIP, SYCL, HPX, OpenMP, and C++ threads.

Who it’s for

It is designed for developers of performance-critical applications targeting major HPC platforms who need their code to remain efficient across diverse hardware.

Highlights

• Core libraries for parallel execution and data management.
• Support for multiple backends: CUDA, HIP, SYCL, HPX, OpenMP, and C++ threads.
• Designed for N-level memory hierarchies and complex node architectures.
• Part of the Linux Foundation and the Kokkos C++ Performance Portability Programming Ecosystem.