HPC

The Joint Science Conference (GWK) of the German federal states has just announced that FAU will receive funds to establish a National Center for High Performance Computing (NHR@FAU). It will be part of a nationwide network with (initially) seven other centers. The federal and state governments will... Continue

We are happy to announce that our paper "Performance Modeling of Streaming Kernels and Sparse Matrix-Vector Multiplication on A64FX" has been awarded the "Best Short Paper Award" at PMBS20, the "11th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Com... Continue

The next HPC Café takes place VIRTUALLY on Tuesday, December 8, at 4 pm. The HPC Café is a new offering to complement our established contact channels and training events. Every second Tuesday of the month this is an opportunity to get to know each other. On demand we will offer short talks about... Continue

The HPC group is pleased to host the next webinar organized by the European Energy-Oriented Center of Excellence (EoCoE). The webinar will cover streaming kernels and sparse matrix-vector multiplication on the A64FX processor. It is free and open to everyone. If you are interested in attending, plea... Continue

We are proud to announce the HPC@RRZE Youtube channel. Lecture and tutorial videos, promotional clips, talks, and more will be published at: http://tiny.cc/YT-RRZE-HPC. We've set up some playlists to help you navigate the vast amount of content :-) LIKWID performance tools videos Parallel Pr... Continue

Our most popular tutorial was accepted again for the SC20 conference in Atlanta! SC is a 100% virtual event this year. The tutorial will be airing on November 9 and 10 as a number of pre-recorded presentations and live Q&A sessions. There’s still time to register: https://show.jspargo.com/sc20/ ... Continue

We are happy to announce a new bugfix release 5.0.2 of LIKWID. If you want to use LIKWID on AMD Zen/Zen2 systems, we highly recommend you updating your installation. Continue

Finally, our work on the Recursive Algebraic Coloring Engine (RACE) is officially published in the ACM Transactions on Parallel Computing: C. L. Alappat, G. Hager, O. Schenk, J. Thies, A. Basermann, A. R. Bishop, H. Fehske, and G. Wellein: A Recursive Algebraic Coloring Technique for Hardware-Eff... Continue

ISC 2020, conducted as a digital event, was a particular success for our group. Two papers were accepted for the conference: C. L. Alappat, J. Hofmann, G. Hager, H. Fehske, A. R. Bishop, and G. Wellein: Understanding HPC Benchmark Performance on Intel Broadwell and Cascade Lake Processors. DOI ... Continue

MachineState is a python3 module and CLI application for documenting and comparing settings known to affect application performance: e.g., CPU/Uncore frequencies, hardware prefetchers, memory capacity, but also OS and software settings like NUMA balancing, writeback workqueues, scheduling, or the ve... Continue