Abstract is missing.
- A Dedicated CPU Core for MPI Progress: Towards Improved Overlap in Non-Blocking Two-Sided CommunicationEhab Saleh, Amir Raoofy, Robert Mijakovic, Ahmad Moh'd Saleh A. Belbeisi, Josef Weidendorfer. 1-10 [doi]
- Tuning for the Code: Exploring Optimizations of an MPI Library for a Community ApplicationXu Huang 0010, Carsten Clauss, Simon Pickartz. 11-19 [doi]
- Pooling HPC Resources Across Organizations and Reducing Carbon Emissions with Transparent, User-Centric Meta-SchedulingRuben Horn, Marco Plaß, Philipp Neumann. 20-29 [doi]
- Enabling Efficient Vectorization in Particle-In-Cell Monte Carlo Simulations on X86 and RISC-VKallia Chronaki, Evangelos Gkolantas, Jeremy J. Williams, Stefan Costea, David Tskhakaya, Leon Kos, Stefano Markidis, Vassilis Papaefstathiou. 30-38 [doi]
- SIMD Vectorization of the Three-Body Axilrod-Teller-Muto PotentialJose Alfonso Pinzon Escobar, Amartya Das Sharma, Philipp Neumann. 39-47 [doi]
- Do We Need Reinforcement Learning for Serverless Scheduling at the Edge? a Comparative EvaluationCherif Latreche, Nikos Parlavantzas, Hector A. Duran-Limon. 48-56 [doi]
- A Concurrent Queue System for Multi-GPU Platforms: Application to Bellman-Ford SSSPBeyza Çavusoglu. 57-64 [doi]
- Transparent Checkpointing in Parallel Applications Using AD-HOC File SystemsDario Muñoz-Muñoz, Félix García Carballeira, Alejandro Calderón Mateos, Diego Camarmas-Alonso, Jesús Carretero 0002. 65-73 [doi]
- Flatterscatter in mallocMC - Performant and Portable Many-Core Memory AllocationJulian Lenz, René Widera, Michael Bussmann. 74-83 [doi]
- Low-Level I/O Monitoring for Scientific WorkflowsJoel Witzke, Ansgar Lößer, Vasilis Bountris, Tobias Wies, Florian Schintke, Björn Scheuermann 0001. 84-92 [doi]
- Distributed Maximal Independent Set Computation in Hundred Billion-Edge GraphsYisheng Liu, Roger Pearce, Tahsin Reza. 93-102 [doi]
- A Tabular Schedule Abstraction for Communication-Aware Evaluation of Pipeline-Parallel LLM TrainingDaniel Barley, Jonathan Leis, Benjamin Klenk, Holger Fröning. 103-111 [doi]
- ONACADI: An Online Autotuner for Compiled Applications Based on Debugger InterfacesFabian Mikula, Matthias Korch. 112-120 [doi]
- From Microbenchmarks to LLM Inference an End-To-End Analysis on the Energy Efficiency of the Grace Hopper SuperchipMarkus Velten, Christian von Elm, Lena Jurkschat, Gülçin Gedik, Sebastian Döbel, Daniel Hackenberg. 121-129 [doi]
- Can Microbenchmark-Derived Insights Guide Energy-Efficient Execution of Real Applications on Asymmetric Multicore Processors?Hana Shatri Ahmeti, Matthias Korch, Tim Werner, Thomas Rauber. 130-138 [doi]