A5017676165- Distributed and Parallel Computing Systems
- Advanced Data Storage Technologies
- Parallel Computing and Optimization Techniques
- Computer Graphics and Visualization Techniques
- Scientific Computing and Data Management
- Advanced Data Compression Techniques
- 3D Shape Modeling and Analysis
- Algorithms and Data Compression
- Digital Radiography and Breast Imaging
- Advanced Neural Network Applications
- Machine Learning and Algorithms
- Network Packet Processing and Optimization
- Image Retrieval and Classification Techniques
Indiana University Bloomington
2023-2025
Indiana University
2023
Washington State University
2022
Lossy compression and asynchronous I/O are two of the most effective solutions for reducing storage overhead enhancing performance in large-scale high-performance computing (HPC) applications. However, current approaches have limitations that prevent them from fully leveraging lossy compression, they may also result task collisions, which restrict overall HPC To address these issues, we propose an optimization approach scheduling problem encompasses computation, I/O. Our algorithm adaptively...
Error-bounded lossy compression has been effective in significantly reducing the data storage/transfer burden while preserving reconstructed fidelity very well. Many error-bounded compressors have developed for a wide range of parallel and distributed use cases years. These are designed with distinct models design principles, such that each them features particular pros cons. In this paper we provide comprehensive survey emerging techniques different involving big to process. The key...
As supercomputers advance towards exascale capabilities, computational intensity increases significantly, and the volume of data requiring storage transmission experiences exponential growth. Adaptive Mesh Refinement (AMR) has emerged as an effective solution to address these two challenges. Concurrently, error-bounded lossy compression is recognized one most efficient approaches tackle latter issue. Despite their respective advantages, few attempts have been made investigate how AMR can...
Today's scientific simulations require a significant reduction of data volume because extremely large amounts they produce and the limited I/O bandwidth storage space. Error-bounded lossy compression has been considered one most effective solutions to above problem. However, little work done improve error-bounded for Adaptive Mesh Refinement (AMR) simulation data. Unlike previous that only leverages 1D compression, in this work, we propose leverage high-dimensional (e.g., 3D) each refinement...
Today's scientific simulations generate exceptionally large volumes of data, challenging the capacities available I/O bandwidth and storage space. This necessitates a substantial reduction in data volume, for which error-bounded lossy compression has emerged as highly effective strategy. A crucial metric assessing efficacy is visualization. Despite extensive research on impact visualization, there notable gap literature concerning effects visualization Adaptive Mesh Refinement (AMR) data....
Recent years have witnessed a clear trend towards language models with an ever-increasing number of parameters, as well the growing training overhead and memory usage. Distributed training, particularly through Sharded Data Parallelism (ShardedDP) which partitions optimizer states among workers, has emerged crucial technique to mitigate time Yet, major challenge in scalability ShardedDP is intensive communication weights gradients. While compression techniques can alleviate this issue, they...
Multi-resolution methods such as Adaptive Mesh Refinement (AMR) can enhance storage efficiency for HPC applications generating vast volumes of data. However, their applicability is limited and cannot be universally deployed across all applications. Furthermore, integrating lossy compression with multi-resolution techniques to further boost encounters significant barriers. To this end, we introduce an innovative workflow that facilitates high-quality data both uniform AMR simulations....
Today's scientific simulations require significant data volume reduction because of the enormous amounts produced and limited I/O bandwidth storage space. Error-bounded lossy compression has been considered one most effective solutions to above problem. However, little work done improve error-bounded for Adaptive Mesh Refinement (AMR) simulation data. Unlike previous that only leverages 1D compression, in this work, we propose an approach (TAC) leverage high-dimensional SZ each refinement...
As supercomputers advance towards exascale capabilities, computational intensity increases significantly, and the volume of data requiring storage transmission experiences exponential growth. Adaptive Mesh Refinement (AMR) has emerged as an effective solution to address these two challenges. Concurrently, error-bounded lossy compression is recognized one most efficient approaches tackle latter issue. Despite their respective advantages, few attempts have been made investigate how AMR can...
Today's scientific simulations generate exceptionally large volumes of data, challenging the capacities available I/O bandwidth and storage space. This necessitates a substantial reduction in data volume, for which error-bounded lossy compression has emerged as highly effective strategy. A crucial metric assessing efficacy is visualization. Despite extensive research on impact visualization, there notable gap literature concerning effects visualization Adaptive Mesh Refinement (AMR) data....