{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-5348"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-5348","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Analyzing an In-line Compression Management System for Improved Performance in a High-Performance Computing Environment","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.","abstract_html":"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&#x27;s computational kernel&#x27;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&#x27;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&#x27;s data access patterns.","abstract_has_math":false,"creators":["Platt, Steven"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Jon C. Calhoun","Melissa Smith","Tao Wei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:31:26Z","subjects":["HPC","Lossy Compression","Matrix Multiplication","In-line Compression","Computer Engineering","Data Storage Systems"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/4241","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/4241","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-5348","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jon C. Calhoun","Melissa Smith","Tao Wei"]},{"key":"dc:creator","label":"Author","values":["Platt, Steven"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2024-04-22T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-05-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["HPC","Lossy Compression","Matrix Multiplication","In-line Compression","Computer Engineering","Data Storage Systems"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/4241"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:title","label":"Title","values":["Analyzing an In-line Compression Management System for Improved Performance in a High-Performance Computing Environment"]}]}],"canonical_facts":{"dc:contributor":["Jon C. Calhoun","Melissa Smith","Tao Wei"],"dc:creator":["Platt, Steven"],"dc:date.available":["2024-04-22T07:00:00Z"],"dc:date.created":["2024-05-01T07:00:00Z"],"dc:description.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."],"dc:identifier":["https://open.clemson.edu/all_theses/4241"],"dc:subject":["HPC","Lossy Compression","Matrix Multiplication","In-line Compression","Computer Engineering","Data Storage Systems"],"dc:title":["Analyzing an In-line Compression Management System for Improved Performance in a High-Performance Computing Environment"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:31:26Z"}