HCW 2025 Program
The thirty-fourth Heterogeneity in Computing Workshop (HCW) will be held at the Politecnico di Milano, Milan, Italy, on June 4, 2025. This is an in-person workshop requiring prior registration. All times indicated on this page are in the Central European Summer Time (UTC+2) time zone.
Session 1: Introductions and Keynote Presentation (9:15-10:30 am)
Session Chairs: Ali Akoglu (University of Arizona, US) and Kamesh Madduri (Pennsylvania State University, US)
9:15 am
Welcome and Introductions, HCW’25 overview
9:30 am
Jeffrey Vetter, Section Head - Advanced Computing Systems Research at Oak Ridge National Laboratory, will deliver the HCW 2025 keynote.
Break (10:30-11 am)
Session 2: Research Papers (11 am-12:30 pm)
11 am
Improving energy efficiency of HPC applications using unbalanced GPU power capping
Albert d’Aviau de Piolant (University of Bordeaux, FR), Hayfa Tayeb (University of Bordeaux and University of Strasbourg, FR), Berenger Bramas (University of Strasbourg, FR), Mathieu Faverge (University of Bordeaux, FR), Abdou Guermouche (University of Bordeaux, FR), Amina Guermouche (University of Bordeaux, FR)
11:20 am
Methodology for GPU Frequency Switching Latency Measurement
Daniel Velicka (Technical University of Ostrava, CZ), Ondrej Vysocky (Technical University of Ostrava, CZ), Lubomir Riha (Technical University of Ostrava, CZ)
11:40 am
LM-Offload: Performance Model-Guided Generative Inference of Large Language Models with Parallelism Control
Jianbo Wu (University of California, Merced, US), Jie Ren (William & Mary, US), Shuangyan Yang (University of California, Merced, US), Konstantinos Parasyris (Lawrence Livermore National Laboratory, US), Giorgis Georgakoudis (Lawrence Livermore National Laboratory, US), Ignacio Laguna (Lawrence Livermore National Laboratory, US), Dong Li (University of California, Merced, US)
12 pm
Millions of Matrix-Multiplications: GEMM Variations on Aurora
Colleen Bertoni (Argonne National Laboratory, US), Thomas Applencourt (Argonne National Laboratory, US), Longfei Gao (Argonne National Laboratory, US), Ti Leggett (Argonne National Laboratory, US)
12:10 pm
Leveraging Interaction Between Memory Footprint and Parallelism Degree for efficient GPU Portings
Michael Boichot (Institut Polytechnique de Paris, FR), Adrien Rouseel (CEA, FR), Elisabeth Brunet (Institut Polytechnique de Paris, FR), Patrick Carribault (CEA, FR)
12:20 pm
HaaS - A Platform for Password Cracking in Distributed Heterogeneous Systems
Carlos Lima (Polytechnic Institute of Bragança, PT), Rui Alves (Polytechnic Institute of Bragança, PT), José Rufino (Polytechnic Institute of Bragança, PT)
Lunch break (12:30-2 pm)
Session 3: Research Papers (2-3:30 pm)
2 pm
Static task mapping for heterogeneous systems based on series-parallel decompositions
Martin Wilhelm (Otto-von-Guericke University, DE), Thilo Pionteck (Otto-von-Guericke University, DE)
2:20 pm
On the Usability and Energy Efficiency of High-Level Synthesis for FPGA-based Network-Attached Accelerators
Steffen Christgau (Zuse Institute Berlin, DE), Dylan Everingham (Zuse Institute Berlin, DE), Max Lubke (University of Potsdam, DE), Marco De Lucia (GFZ Helmholtz Centre for Geosciences, DE), Danny Puhan (PERFACCT GmbH, DE), Niklas Schelten (Fraunhofer Heinrich Hertz Institute, DE), Bettina Schnor (University of Potsdam, DE), Hannes Signer (University of Potsdam, DE), Johannes Spazier (PERFACCT GmbH, DE), Benno Stabernack (Fraunhofer Heinrich Hertz Institute and University of Potsdam, DE), Fritjof Steinert (Fraunhofer Heinrich Hertz Institute and University of Potsdam, DE), Serhii Yahdzhyiev (PERFACCT GmbH, DE)
2:40 pm
Scheduling Strategies for Partially-Replicable Task Chains on Two Types of Resources
Diane Orhan (University of Bordeaux, FR), Yacine Idouar (Sorbonne University, FR), Laércio Lima Pilla (University of Bordeaux, FR), Adrien Cassagne (Sorbonne University, FR), Denis Barthou (Bordeaux INP, FR), Christophe Jego (University of Bordeaux, FR)
3 pm
Heterogeneous Memory Pool Tuning
Filip Vaverka (Technical University of Ostrava, CZ), Ondrej Vysocky (Technical University of Ostrava, CZ), Lubomir Riha (Technical University of Ostrava, CZ)
3:10 pm
On the Singularity of SYCL
Ami Marowka (Parallel Research Labs, IL)
3:20 pm
Proactive Endpoint Congestion Avoidance in UCC
Ferrol Aderholdt (NVIDIA, US), Aamir Shafi (NVIDIA, US), Manjunath Gorentla Venkata (NVIDIA, US)
Break (3:30-3:40 pm)
Session 4: Best Paper Award (3:40-4 pm)
Session Chair: Ali Akoglu (University of Arizona, US)
Best Paper Award
To Be Announced at HCW 2025.
Author Discussions and Closing Remarks
Based on their outstanding and insightful reviews, we are pleased to acknowledge Abdou Guermouche (University of Bordeaux, FR), Sahil Hassan (University of Arizona, US), Joshua Mack (Praetorian, US), and José Rufino (Polytechnic Institute of Bragança, PT) as recipients of the Top Reviewer Recognition for HCW 2025. Their thoughtful and constructive reviews not only upheld the workshop’s high standards but also provided authors with valuable feedback to improve their work. We truly appreciate their dedication and commitment to HCW.