@article{RodriguesPelaDraxl2022, author = {Rodrigues Pel{\´a}, Ronaldo and Draxl, Claudia}, title = {Ehrenfest dynamics implemented in the all-electron package exciting}, volume = {4}, journal = {Electron. Struct.}, doi = {10.1088/2516-1075/ac7afc}, pages = {037001}, year = {2022}, abstract = {Ehrenfest dynamics combined with real-time time-dependent density functional theory has proven to be a reliable tool to study non-adiabatic molecular dynamics with a reasonable computational cost. Among other possibilities, it allows for assessing in real time electronic excitations generated by ultra-fast laser pulses, as e.g., in pump-probe spectroscopy, and their coupling to the nuclear vibrations even beyond the linear regime. In this work, we present its implementation in the all-electron full-potential package exciting. Three cases are presented as examples: diamond and cubic boron nitride (BN) relaxed after an initial lattice distortion, and cubic BN exposed to a laser pulse. Comparison with the Octopus code exhibits good agreement.}, language = {en} } @article{SalemSchintke2022, author = {Salem, Farouk and Schintke, Florian}, title = {Large-Scale Performance of the Data-Flow Scheduler (DFS) and FLESnet}, journal = {CBM Progress Report 2021}, doi = {10.15120/GSI-2022-00599}, pages = {170 -- 171}, year = {2022}, language = {en} } @inproceedings{KnaustSeilerReinertetal.2022, author = {Knaust, Marius and Seiler, Enrico and Reinert, Knut and Steinke, Thomas}, title = {Co-Design for Energy Efficient and Fast Genomic Search: Interleaved Bloom Filter on FPGA}, booktitle = {FPGA '22: Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays}, doi = {10.1145/3490422.3502366}, pages = {180 -- 189}, year = {2022}, abstract = {Next-Generation Sequencing technologies generate a vast and exponentially increasing amount of sequence data. The Interleaved Bloom Filter (IBF) is a novel indexing data structure which is state-of-the-art for distributing approximate queries with an in-memory data structure. With it, a main task of sequence analysis pipelines, (approximately) searching large reference data sets for sequencing reads or short sequence patterns like genes, can be significantly accelerated. To meet performance and energy-efficiency requirements, we chose a co-design approach of the IBF data structure on the FPGA platform. Further, our OpenCL-based implementation allows a seamless integration into the widely used SeqAn C++ library for biological sequence analysis. Our algorithmic design and optimization strategy takes advantage of FPGA-specific features like shift register and the parallelization potential of many bitwise operations. We designed a well-chosen schema to partition data across the different memory domains on the FPGA platform using the Shared Virtual Memory concept. We can demonstrate significant improvements in energy efficiency of up to 19x and in performance of up to 5.6x, respectively, compared to a well-tuned, multithreaded CPU reference.}, language = {en} } @article{GholamiSchintke2022, author = {Gholami, Masoud and Schintke, Florian}, title = {IOSIG: Declarative I/O-Stream Properties Using Pragmas}, volume = {22}, journal = {Datenbank-Spektrum}, number = {2}, publisher = {Springer Berlin Heidelberg}, doi = {10.1007/s13222-022-00419-w}, pages = {109 -- 119}, year = {2022}, language = {en} } @inproceedings{BaumannNoackSteinke2021, author = {Baumann, Tobias and Noack, Matthias and Steinke, Thomas}, title = {Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs}, booktitle = {IWOCL'21: International Workshop on OpenCL}, doi = {10.1145/3456669.3456698}, year = {2021}, abstract = {The Portable Computing Language (PoCL) is a vendor independent open-source OpenCL implementation that aims to support a variety of compute devices in a single platform. Evaluating PoCL versus the Intel OpenCL implementation reveals significant performance drawbacks of PoCL on Intel CPUs - which run 92 \% of the TOP500 list. Using a selection of benchmarks, we identify and analyse performance issues in PoCL with a focus on scheduling and vectorisation. We propose a new CPU device-driver based on Intel Threading Building Blocks (TBB), and evaluate LLVM with respect to automatic compiler vectorisation across work-items in PoCL. Using the TBB driver, it is possible to narrow the gap to Intel OpenCL and even outperform it by a factor of up to 1.3× in our proxy application benchmark with a manual vectorisation strategy.}, language = {en} } @inproceedings{ScheltenChristgauSchulteetal.2026, author = {Schelten, Niklas and Christgau, Steffen and Schulte, Anton and Schnor, Bettina and Signer, Hannes and Stabernack, Benno}, title = {A Flexible Open-Source Framework for FPGA-based Network-Attached Accelerators using SpinalHDL}, booktitle = {Architecture of Computing Systems - 39th International Conference, ARCS 2026, Mainz, Germany, March 24-26, 2026, Proceedings.}, year = {2026}, abstract = {Domain-specific accelerators are increasingly vital in heterogeneous computing systems, driven by the demand for higher computational capacity and especially energy efficiency. Network-attached FPGAs promise a scalable and flexible alternative to closely coupled FPGAs for integrating accelerators into computing environments. While the advantages of specialized hardware implementations are apparent, traditional hardware development and integration remain time-consuming and complex. We present an open-source framework which combines a hardware shell with supporting software libraries, which enables fast development and deployment of FPGA-based network-attached accelerators. In contrast to traditional approaches using VHDL or Verilog, we leverage generative programming with SpinalHDL, providing a flexible hardware description with multi-level abstractions. This work eases the integration of accelerators into existing network infrastructures and simplifies adaptation to different FPGAs, eliminating complex and lengthy top-level hardware descriptions.}, language = {en} } @article{JiAnitaFournier2025, author = {Ji, Hongchen and Anita, Ragyanszki and Fournier, Rene}, title = {Computational Study of the Reactions of CH2 with HCNO and HNCO}, volume = {103}, journal = {Canadian Journal of Chemistry}, number = {7}, doi = {10.1139/cjc-2024-0203}, pages = {386 -- 395}, year = {2025}, abstract = {We present a computational approach for screening reaction mechanisms with machine learning estimates of energy barriers. A comprehensive screening of thousands of reactions identified the CH2 reactions with HCNO and HNCO as possible sources of relatively complex organic molecules in space. We report detailed reaction mechanisms, including TS, intermediate, and product energies, calculated with density functional theory and coupled cluster theory. Singlet CH2, located 9 kcal/mol above the triplet ground state, reacts with HCNO or HNCO without a barrier, producing four prod11 ucts: CH2NCHO, N-methyleneformamide, the thermodynamically favored product; NHCHCHO, imine acetaldehyde; NHCHOCH; and (CH2OC)NH, oxiran-2-ylazanide. The lowest energy pathway for CH2 + HCNO, involving a triplet-to-singlet crossing, has a barrier of 8 kcal/mol and leads to N -methyleneformamide, imine acetaldehyde, and NHCHOCH. The reaction of triplet CH2 with HNCO has a lowest energy pathway with a barrier of 11 kcal/mol, yielding CH2(CO)NH.}, language = {en} } @article{RayaMorenoDaschFarahanietal.2026, author = {Raya-Moreno, Mart{\´i} and Dasch, Noah Alexy and Farahani, Nasrin and Gonzalez Oliva, Ignacio and Gulans, Andris and Hossain, Manoar and Kleine, Hannah and Kuban, Martin and Lubeck, Sven and Maurer, Benedikt and Pavone, Pasquale and Peschel, Fabian and Popova-Gorelova, Daria and Qiao, Lu and Richter, Elias and Rigamonti, Santiago and Rodrigues Pel{\´a}, Ronaldo and Sinha, Kshitij and Speckhard, Daniel T. and Tillack, Sebastian and Tumakov, Dmitry and Hong, Seokhyun and Uzulis, Janis and Voiculescu, Mara and Vona, Cecilia and Yang, Mao and Draxl, Claudia}, title = {An exciting approach to theoretical spectroscopy}, arxiv = {http://arxiv.org/abs/2601.11388}, year = {2026}, language = {en} } @article{QiaoRodriguesPelaDraxl2026, author = {Qiao, Lu and Rodrigues Pel{\´a}, Ronaldo and Draxl, Claudia}, title = {First-principles approach to ultrafast pump-probe spectroscopy in solids}, arxiv = {http://arxiv.org/abs/2509.07612}, year = {2026}, language = {en} } @inproceedings{ScheltenChristgauHutzleretal.2026, author = {Schelten, Niklas and Christgau, Steffen and Hutzler, Merit and Kreowsky, Philipp and De Lucia, Marco and Schnor, Bettina and Signer, Hannes and Spazier, Johannes and Stabernack, Benno and Yahdzhyiev, Serhii}, title = {Using FPGA-based Network-Attached Accelerators for Energy-Efficient AI Training in HPC Datacenters}, booktitle = {2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)}, year = {2026}, abstract = {FPGA-based Network-Attached Accelerators offer a disaggregated alternative to closely-coupled FPGAs or GPUs, but their adoption is very limited due to missing hardware/software frameworks. However, the usability and energy-efficiency of FPGAs for HPC use-cases has been demonstrated previously. Yet, the support by HPC infrastructure for those devices is lacking behind other accelerators. This paper addresses this shortcoming and demonstrates a full-stack approach that seamlessly integrates Network-Attached Accelerators in HPC datacenters and allows flexible and scalable usage of FPGAs. The presented work includes the according framework, integration steps and a show-case application from the geoscience domain. We evaluate our approach by comparing the training of a Physics-Informed Neural Network on the NAA against two GPU implementations. The NAA reduces total energy consumption by about 50\% and 17\% compared to the Keras and CUDA implementation, respectively. These results demonstrate that FPGA-based NAAs can be successfully integrated into HPC environments and are a viable path toward more energy-efficient AI training.}, language = {en} } @misc{RamakiSchintke2025, author = {Ramaki, Niaz Mohammad and Schintke, Florian}, title = {Ensuring Reproducibility in Stream Processing with Blockchain Technologies}, journal = {2025 11th International Conference on Computer and Communications (ICCC)}, publisher = {IEEE}, doi = {10.1109/ICCC68654.2025.11437772}, pages = {1383 -- 1391}, year = {2025}, language = {en} } @misc{KharmaWiesSchintke2026, author = {Kharma, Sami and Wies, Tobias and Schintke, Florian}, title = {Comprehensive Plugin-Based Monitoring of Nexflow Workflow Executions}, journal = {SCA/HPC Asia 2026}, arxiv = {http://arxiv.org/abs/2603.28783}, year = {2026}, language = {en} }