HiPC 2025 will be the 32nd edition of the IEEE International Conference on High Performance Computing, Data, Analytics, and Data Science. HiPC serves as a forum to present current work by researchers in the areas of high performance computing and data science. The meeting focuses on all aspects of high performance computing systems, and data science and analytics, and their scientific, engineering, and commercial applications.

Authors are invited to submit original unpublished research manuscripts that demonstrate current research in all areas of high performance computing, and data science and analytics, covering all traditional areas and emerging topics including machine learning and big data analytics. Each submission should be submitted under the two broad themes of High Performance Computing and Data Science.

Up to two best paper awards will be given for outstanding contributed papers.

Important dates:*

Abstract Submission: June 18, 2025 (Wednesday)

Paper Submission (double-blind): June 25, 2025  (Wednesday) 

Reviews to Authors: August 21, 2025   (Thursday) 

Rebuttal Period: August 21-26, 2025  (Thursday to Tuesday)  

Author Notification: September 12, 2025 (Friday)

Shepherded Paper Submission: September 26, 2025  (Friday) 

Final Author Notification: October 3, 2025  (Friday) 

*All deadlines are Anywhere On Earth (AOE)

High Performance Computing:

Topics for papers include, but are not limited to the topics given under the categories below.

Algorithms. This track invites papers that describe original research on developing new parallel and distributed computing algorithms, and related advances. Examples of topics that are of interest include (but not limited to):

• New parallel and distributed algorithms and design techniques;
• Advances in enhancing algorithmic properties or providing guarantees (e.g., concurrency, data locality, communication-avoiding, asynchronous, hybrid CPU-GPU algorithms, fault tolerance, resilience,);

• Algorithmic techniques for resource allocation and optimization (e.g., scheduling, load balancing, resource management);
• Provably efficient parallel and distributed algorithms for advanced scientific computing and irregular applications (e.g., numerical linear algebra, graph algorithms, computational biology);
• Classical and emerging computation models (e.g., parallel/distributed models, quantum computing, neuromorphic and other bioinspired models).

Architecture. This track invites papers that describe original research on the design and evaluation of high performance computing architectures, and related advances. Examples of topics of interest include (but not limited to): 

• High performance processing architectures (e.g., reconfigurable, system-on-chip, many cores, vector processors);
• Networks for high performance computing platforms (e.g., interconnect topologies, network-on-chip);
• Memory, cache and storage architectures (e.g., 3D, photonic, Processing-In-Memory, NVRAM, burst buffers, parallel I/O);
• Approaches to improve architectural properties (e.g., energy/power efficiency, reconfigurable, resilience/fault tolerance, security/privacy);
• Emerging computational architectures (e.g., quantum computing, neuromorphic and other bioinspired architectures). 

Applications. This track invites papers that describe original research on the design and implementation of scalable and high performance applications for execution on parallel, distributed and accelerated platforms, and related advances. Examples of topics of interest include (but not limited to):

• Shared and distributed memory parallel applications (e.g., scientific computing, simulation and visualization applications, graph and irregular applications, data-intensive applications, science/engineering/industry applications, emerging applications in IoT and life sciences, etc.);
• Methods, algorithms, and optimizations for scaling applications on peta- and exa-scale platforms (e.g., co-design of hardware and software, heterogeneous and hybrid programming);
• Hardware acceleration of parallel applications (e.g., GPUs, FPGA, vector processors, manycore);
• Application benchmarks and workloads for parallel and distributed platforms.

Systems Software. This track invites papers that describe original research on the design, implementation, and evaluation of systems software for high performance computing platforms, and related advances. Examples of topics of interest include (but not limited to):

• Scalable systems and software architectures for high-performance computing (e.g., middleware, operating systems, I/O services); 
• Techniques to enhance parallel performance (e.g., compiler/runtime optimization, learning from application traces, profiling); 
• Techniques to enhance parallel application development and productivity (e.g., Domain-Specific Languages, programming environments, performance/correctness checking and debugging); 
• Techniques to deal with uncertainties, hardware/software resilience, and fault tolerance; 
• Software for cloud, data center, and exascale platforms (e.g., middleware tools, schedulers, resource allocation, data migration, load balancing); 
• Software and programming paradigms for heterogeneous platforms (e.g., libraries for CPU/GPU, multi-GPU clusters, and other accelerator platforms).

Data Science and AI:

Topics for papers include, but are not limited to the topics given under the categories below.

Scalable Data Science: This track invites papers that describe original research on developing scalable algorithms, systems, and software for data analysis at scale, and related advances. Examples of topics of interest include (but not limited to):

• New scalable algorithms, systems, and software for fundamental data analysis tasks. 
• Scalable algorithms, systems, and software that are designed to address the characteristics of different data sources and settings (e.g., graphs, social networks, sequences, data streams); 
• Scalable algorithms and techniques to reduce the complexity of large-scale data (e.g., streaming, sublinear data structures, summarization, compressive analytics); address requirements in different data-driven application domains (e.g., life sciences, business, agriculture), ensure the transparency and fairness of the analysis; 

• Design of scalable system software to support various data-centric applications (e.g., recommendation systems, web search, crowdsourcing applications, streaming applications) 
• Architectures and systems software to support various operations in large data frameworks (e.g., storage, retrieval, automated workflows, data organization, visualization, visual analytics, human-in-the-loop); 
• Systems software for distributed data frameworks (e.g., distributed file system, data deduplication, virtualization, cloud services, resource optimization, scheduling); 
• Case studies, experimental studies, and benchmarks for scalable algorithms and analytics;

• Standards and protocols for enhancing various aspects of data analytics (e.g., open data standards, privacy-preserving, and secure schemes). 

AI/ML for Systems and Systems for AI/ML. This track invites papers that describe original research on using AI/ML for systems design or  systems design for AI/ML application and related advances. Examples of topics of interest include (but not limited to):

• AI/ML methods for system design and optimization (e.g. efficient design space exploration, job scheduling, energy efficiency) in computing systems;

• AI/ML methods that benefit HPC applications or HPC system management;

• Scaling and accelerating machine learning, deep learning, natural language processing and computer vision applications;

• Efficient model training, inference, and serving (includes specialized hardware design and SW techniques);

• Fairness, interpretability, and explainability for AI/ML applications;

• End-to-end machine learning pipeline optimization (data prep and data cleaning);

• Compound AI systems and AI agent systems;
• Machine learning benchmarks and datasets.