[Colloquium] Reminder - Yuanjian Liu MS Presentation/March 15, 2022

[Megan Woodward]

This is an announcement of Yuanjian Liu’s MS Presentation
===============================================
Candidate: Yuanjian Liu

Date: Tuesday, March 15, 2022

Time: 3 pm CST

Remote Location:  https://uchicago.zoom.us/j/6019256463?pwd=SENUMzJEZEJDMVhMaHZiVDI2V09qdz09<https://urldefense.com/v3/__https://uchicago.zoom.us/j/6019256463?pwd=SENUMzJEZEJDMVhMaHZiVDI2V09qdz09__;!!BpyFHLRN4TMTrA!vmWi4rH4FAUjJ1JaQaxc8thYl0-Xhiey1v5XI0AvMOar6IEgD4C1Qiwdh34M-B2d16qZZy0h$>

M.S. Paper Title: Optimizing Error-Bounded Lossy Compression for Scientific Data with Diverse Constraints

Abstract: Vast volumes of data are produced by today’s scientific simulations and advanced instruments. These data cannot be stored and transferred efficiently because of limited I/O bandwidth, network speed, and storage capacity. Error-bounded lossy compression can be an effective method for addressing these issues: not only can it significantly reduce data size, but it can also control the data distortion based on user-defined error bounds. In practice, many scientific applications have specific requirements or constraints for lossy compression, in order to guarantee that the reconstructed data are valid for post hoc analysis. For example, some datasets contain irrelevant data that will not be used and users often have intuition regarding value ranges, geospatial regions, and other data subsets that are crucial for subsequent analysis. Existing state-of-the-art error-bounded lossy compressors, however, do not consider these constraints, particularly during compression, resulting in reduced overall compression ratios due to data that provide little or no value for post hoc analysis. This thesis addresses this issue by proposing an optimized solution based on the state-of-the-art SZ lossy compression framework. Specifically, the solution can automatically clean the irrelevant data, efficiently preserve different precisions for multiple value intervals, and allow users to set diverse precisions over both regular and irregular regions. Evaluations are performed on a supercomputer with up to 3,500 cores. Experiments with six real-world applications show that the proposed diverse constraints-based error-bounded lossy compressor can obtain a higher visual quality or data fidelity on reconstructed data with the same or even higher compression ratios compared with the traditional state-of-the-art compressor SZ. The experiments also demonstrate very good scalability in compression performance compared with the I/O throughput of the parallel file system.

Advisors: Ian Foster, Kyle Chard

Committee Members: Ian Foster, Kyle Chard, Sheng Di



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220315/eba84060/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Yuanjian_MS_Thesis.pdf
Type: application/pdf
Size: 5814558 bytes
Desc: Yuanjian_MS_Thesis.pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220315/eba84060/attachment-0001.pdf>