ARCS 2025: 38th GI/ITG International Conference on Architecture of Computing Systems Christian-Albrechts-Universität zu Kiel Kiel, Germany, April 22-24, 2025 |
| Conference website | https://arcs-conference.org/home |
| Submission link | https://easychair.org/conferences/?conf=arcs2025 |
| Submission deadline | January 26, 2025 |
THIS YEAR'S FOCUS: *Mastering novel HPC chip architectures*
The ARCS conferences series has over 37 years of tradition reportingleading edge research in computer architecture and operating systems. leading edge research in computer architecture and operating systems.
New chips for high-performance computing (HPC) are being developed in and outside Europe (e.g. ARM processors for HPC, RISC-V chips, special purpose ASIC designs, etc.) and even disruptive technologies such as QPU accelerators are being connected to HPC systems.New chips are designed either as general purpose devices with a wide user portfolio in mind, or target the needs of specific applications (e.g. machine learning pipelines or deep learningworkloads, mobile or embedded systems). Accordingly, they might rely on well established architectural approaches (CPU-like, vector-extensions), or bring completely new disruptive ideas, always with the aim of limiting energy consumption. When these are integrated in HPC systems,the overall system design becomes more and more heterogeneous.
These increasingly complex architectures require optimizations in application code to exploit the full performance potential. There are standard optimization strategies that can be implemented specifically for certain architectures, and there may also be optimization rules that are totally specific to an accelerator or a hybrid processor-accelerator architecture. Porting HPC code to new architectures isan important challenge: it is desirable to achieve performance without having to redesign the whole code, or at least to be able to follow standard optimization rules.
The ARCS'25 conference welcomes all contributions on hardware architectures, as well as their programming models, software stacks (operating systems, compilers...), their insertioninto computing systems, and the challenges to port optimized code.
In addition to the main conference, ARCS will host:
- A special track on Organic Computing.
- A special track on Dependability and Fault Tolerance
- A PhD forum to present the work of young doctoral students (10 page papers)
- A Group forum for new professors, individual researchers, and consortia to present their research group's project (5 page papers)
List of Topics
Beside the conference main theme, the ARCS’25 conference welcomes all contributions on hardware architectures, as well as their programming models, software stacks (operating systems, compilers...), their insertion into computing systems, and the challenges to port optimized code:
- Hardware Architectures
- Reconfigurable architectures
- System‑on‑chip
- Distributed systems
- High performance systems
- Heterogeneous multi‑& many‑core architectures
- Hybrid CPU‑GPU and CPU‑QPU architectures
- HPC‑workload specific accelerator architectures
- Architectures for real‑time and mixed‑criticality systems
- Coarse‑/fine‑grained reconfigurable architecture
- Flexible I/O support
- Using new non‑volatile memory for energy‑efficient architectures
- New smart network technologies (e.g. Smart‑NICs, SmartSwitches)
- Advanced computing architectures
- Programming Models and Runtime Environments
- Programming on novel HPC chip architectures
- HPC programming models for heterogeneous computing
- Hybrid CPU‑QPU programming and experiments
- Tools to monitor and to optimize the power consumption of HPC architecture
- Operating systems, programming models, algorithms, and data structures for heterogeneous HPC architectures
- Operating systems, hypervisors and middleware for homogeneous and heterogeneous multi‑/many‑core computing platforms
- System management including but not limited to scheduling, memory management, power/thermal management, and RTOS
- Domain‑specific languages and programming models
- Architecture specific code generation/optimization
- Architectural simulation
- Cross-sectional Topics
- Near-memory and in-memory computing
- Memory and network compression technologies
- Organic computing
- Pervasive systems
- Autonomous systems
- Approximate Computing
- Mixed-criticality systems
- Support for safety and security
- Hardware in the loop simulations
- Optimization and performance analysis
Submission Guidelines
Submissions should be done through EasyChair. Papers must be submitted in PDF format.
They should be formatted according to Springer LNCS style and must not exceed 15 pages, including references and figures.
Publication
The proceedings of ARCS 2025 will be published in the Springer Lecture Notes on Computer Science (LNCS) series. A best paper will be elected by the Program Committee, and a publicum’s favourite presentation award will be chosen by the audience.Both awards will be given at the conference.
Organizers
General Co-Chairs:
- Sven Tomforde, University of Kiel, Germany
- Christian Krupitzer, University of Hohenheim in Stuttgart, Germany
PC Co-Chairs:
- Stephane Vialle, CentraleSupelec, Paris-Saclay University , LISN, France
- Estela Suarez, SiPEARL GmbH, Germany
Proceedings Chair:
Thilo Pionteck, Magdeburg University , Germany
Publicity Chair:
Mathias Pacher, DHBW Karlsruhe, German
Web Chair:
Lars Bauer
Contact
All questions about submissions should be emailed to Program Cho-Chairs