NEKO

Events

Events Search and Views Navigation

Event Views Navigation

Today

  • Promotional graphic for a webinar titled “Extreme-Scale High-Fidelity Computational Fluid Dynamics with Neko.” The title is written in large bold black letters across the top left on a white background. In the top right corner is the CEEC logo in black, with three curved lines above the first “E” suggesting airflow. Below the title, inside a rounded white rectangular panel with a thin black outline, is the event description in black text: “Join CEEC and Niclas Jansson for a hands-on webinar introducing Neko! We’ll explore Neko's capabilities, focusing on major updates to its features, functionalities, and user interaction. This interactive session will teach participants how to run the code and fine-tune configuration settings for peak performance.” Near the bottom left of the panel, small black icons show a calendar, a clock, and a location pin, followed by the event details: “June 17, 2026 13:00 – 15:00 CEST Online” On the right side of the image, outside the text panel, is the Neko logo: a stylized black-and-white cartoon cat wearing goggles, with a curved, wave-like flourish beneath it, followed by the word “NEKO” in bold, italicized, horizontal-striped letters that give a sense of motion. Along the very bottom edge of the image, thin gray wavy lines suggest flowing fluid or waves.

    Extreme-Scale High-Fidelity Computational Fluid Dynamics with Neko

    Neko is a portable framework for high-order spectral element-based simulations, focusing primarily on incompressible and compressible fluid flows. Written using a modern object-oriented approach, the framework supports a wide range of hardware backends, including general-purpose processors, accelerators, and vector processors. Neko has demonstrated excellent performance and scalability across various hardware architectures and was nominated as […]

  • Mixed-Precision and Energy-Efficiency in SEM Codes

    Congress Center Hamburg Congressplatz 1, Hamburg, Germany

    Mixed-precision computing has emerged as a key strategy to improve performance and energy efficiency on current and future high-performance computing (HPC) systems. However, integrating mixed-precision into large, production-level scientific applications remains challenging due to concerns about numerical stability, accuracy, and the complexity of identifying which computations can safely tolerate reduced precision. Our results confirm that mixed-precision approaches, when carefully designed and guided by arithmetic and performance analysis, can yield significant improvements on HPC platforms for real-world scientific applications.