Kokkos Kernels: Portable Math Kernels

C++ Performance Portable Math Library

Kokkos Kernels provides math kernels for dense, batched and sparse linear algebra as well as graph computations. Our interfaces and implementations are portable to major HPC architectures and based on the Kokkos programming model. The library supports vendor implementation when available and more performant than our native algorithms.

The Kokkos Ecosystem includes:

Name	Info
kokkos	(this library) Programming Model - Parallel Execution and Memory Abstraction	GitHub link
kokkos-kernels	Sparse, dense, batched math kernels	GitHub link
kokkos-tools	Profiling and debugging tools	GitHub link
pykokkos	Provides Python bindings to the Kokkos performance portable parallel programming.	GitHub link
kokkos-remote-spaces	Shared memory semantics across multiple processes	GitHub link
kokkos-resilience	Resilience and Checkpointing Extensions for Kokkos	GitHub link

Questions?

Find us on Slack: https://kokkosteam.slack.com #kokkos-kernels or open an issue on github.

Website Content

• Quick Start
• Requirements
• Building
• CMake Options
• API: Common
• API: BLAS
• API: Batched
• API: LAPACK
• API: Sparse
• API: Graph
• Known issues
• Deprecations
• Tutorials
• GitHub Repo
• Contributing
• Publications
• License