MODAL-HPCLab
Optimization of Data-Driven Workflows on Next-Gen Computer Architectures
The HPCLab develops algorithmic and software solutions for the efficient implementation of data-driven optimization and decision workflows on near-future processor architectures and memory technologies. Our focus is on optimization methods and simulation workflows designed and developed in the MODAL Labs EnergyLab, MedLab, MobilityLab, NanoLab, and SynLab.
As heterogeneous compute platforms with manycore and vector CPUs, GPUs, and FPGAs become more significant, performance portability and the achievable productivity during the implementation cycle become important criteria for code designs. In close collaboration with technology vendors of future high-performance computing and data analytics platforms the newly developed methods are efficiently mapped onto the next-generation computer architectures. In particular, here we focus our work on compute and storage platforms which are powerful and energy efficient for the targeted use cases in the industrial environment.
Publications
2022 |
|||
Steffen Christgau, Marius Knaust, Thomas Steinke | A First Step towards Support for MPI Partitioned Communication on SYCL-programmed FPGAs | IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing, H2RC@SC 2022, Dallas, TX, USA, November 13-18, 2022, pp. 9-17, 2022 |
BibTeX
DOI |
Glenn Brook, Douglas Fuller, John Swinburne, Steffen Christgau, Matthias Läuter, Ronaldo Rodrigues Pelá, Stein Lewin, Tuma Christian, Thomas Steinke | An Early Scalability Study of Omni-Path Express | ISC High Performance, 2022 |
BibTeX
DOI |
Marius Knaust, Enrico Seiler, Knut Reinert, Thomas Steinke | Co-Design for Energy Efficient and Fast Genomic Search: Interleaved Bloom Filter on FPGA | FPGA '22: Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 180-189, 2022 |
BibTeX
DOI |