Date of Award
5-2024
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical and Computer Engineering
Committee Chair/Advisor
Jon C. Calhoun
Committee Member
Melissa Smith
Committee Member
Tao Wei
Abstract
High-performance computing (HPC) has enabled advancements in computation speed and resource cost by utilizing all available server resources and using parallelization for speedup. This computation scheme encourages simulation model development, massive data collection, and AI computation models, all of which store and compute on massive amounts of data. Data compression has enhanced the performance of storing and transferring this HPC application data to enable acceleration, but the benefits of data compression can also be transferred to the active allocated memory used by the application. In-line compression is a compression method that keeps the application memory compressed in allocated memory, decompressing content as the data is needed by the algorithm. The actively decompressed data size in allocated memory can be limited by grouping and compressing the data into blocks informed by the application's computational kernel's data access patterns and a selected compressor. Several factors are considered to tune an in-line compression scheme for a kernel. This research explores factors such as block size and compressor choice on the runtime and memory usage of the Matrix Multiplication kernel (MM). Matrix multiplication is a fundamental algorithm in most HPC kernels that computes a linear transformation on a set of vectors. MM kernels provide a baseline for evaluating in-line compression due to MM's row-based data access patterns and the usage of several matrices to compute the resulting matrix. Like traditional data compression, trade-offs between memory size and the runtime necessary for compression necessitate tuned parameters for each kernel. The results of this research demonstrate essential parameter trends, trade-offs, and the importance of locality in the kernel's data access patterns.
Recommended Citation
Platt, Steven, "Analyzing an In-line Compression Management System for Improved Performance in a High-Performance Computing Environment" (2024). All Theses. 4241.
https://tigerprints.clemson.edu/all_theses/4241