Kokkos 3: Programming Model Extensions for the Exascale Era

2021/08/24 by Christian Robert Trott, Christian R. Trott, Damien Lebrun-Grandie +21 · 22 citations
Computer Science · #Advanced Data Storage Technologies #Distributed and Parallel Computing Systems #Parallel Computing and Optimization Techniques

paper · pdf · doi:10.1109/tpds.2021.3097283

openalex publication_date 2021/08/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

As the push towards exascale hardware has increased the diversity of system architectures, performance portability has become a critical aspect for scientific software. We describe the Kokkos Performance Portable Programming Model that allows developers to write single source applications for diverse high-performance computing architectures. Kokkos provides key abstractions for both the compute and memory hierarchy of modern hardware. We describe the novel abstractions that have been added to Kokkos version 3 such as hierarchical parallelism, containers, task graphs, and arbitrary-sized atomic operations to prepare for exascale era architectures. We demonstrate the performance of these new features with reproducible benchmarks on CPUs and GPUs.

Citations

• OCCA: A unified approach to multi-threading languages

Cited by

• HORSES3D-GPU: A high-order discontinuous Galerkin solver for multi-GPU systems
• Unified sparse framework for large-scale simulations using the material point method
• Layout-Agnostic MPI Abstraction for Distributed Computing in Modern C++
• A Performance Portable Matrix Free Dense MTTKRP in GenTen
• Comparing Cross-Platform Performance via Node-to-Node Scaling Studies
• ChemGen: Code Generation for Multispecies Chemically Reacting Flow Simulations
• LAPIS: A Performance Portable, High Productivity Compiler Framework
• ChromRec: Self-Assembly of Nucleosomes Driven by Directional Recognition
• Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem
• Characterizing Adaptive Mesh Refinement on Heterogeneous Platforms with Parthenon-VIBE
• A CPU+DCU Heterogeneous Parallel Framework for Post-Processing Reconstruction in Quantum Circuit Cutting
• A foundation model for atomistic materials chemistry
• Accelerating Garfield++ with CUDA
• Suspending OpenMP Tasks on Asynchronous Events: Extending the Taskwait Construct
• LAMMPS-KOKKOS: Performance Portable Molecular Dynamics Across Exascale Architectures
• SYCL for Energy-Efficient Numerical Astrophysics: the case of DPEcho
• Decoupling of a supermassive black hole binary from its magnetically arrested circumbinary accretion disk
• Mixed-Precision Performance Portability of FFT-Based GPU-Accelerated Algorithms for Block-Triangular Toeplitz Matrices
• Horizon tracking for asynchronous parallel black hole simulations
• A Study of Mixed Precision Strategies for GMRES on GPUs
• More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation
• Efficient Numerical Strategies for Entropy-Regularized Semi-Discrete Optimal Transport

Related

• Programming at Exascale: Challenges and Innovations
• A Performance-Portable SYCL Implementation of CRK-HACC for Exascale
• Implementing Multi-GPU Scientific Computing Miniapps Across Performance Portable Frameworks
• Evaluating Portable Parallelization Strategies for Heterogeneous Architectures in High Energy Physics
• Enhancing Programmability, Portability, and Performance with Rich Cross-Layer Abstractions