{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4323"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4323","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Neural Compression Inference Accelerator: a Cost and Energy-Effective Alternative to Conventional Machine Learning Inference Methods","abstract":"Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units (TPUs). However, these com- ponents are expensive for cloud services to purchase, costly for customers to rent, prone to price spikes, and energy-intensive. In this research we show that both cloud services and customers would benefit from utilizing field programmable gate arrays (FPGAs) to alleviate the aforementioned challenges. An FPGA can be configured as a machine learning accelerator, operating similarly to a GPU or TPU. We propose an FPGA-based architecture that utilizes compressed neural networks. This provides an alternative hardware option for those running machine learning inference, resulting in savings in server construction costs, power consumption, workload distribution, and providing a more affordable option for customers. We evaluate the system using architectural simulations and cloud-based deployment and demonstrate 76.2% cost and 26.5% energy savings on average from using the Neural Compression Inference Accelerator (NCIA).","abstract_html":"Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units (TPUs). However, these com- ponents are expensive for cloud services to purchase, costly for customers to rent, prone to price spikes, and energy-intensive. In this research we show that both cloud services and customers would benefit from utilizing field programmable gate arrays (FPGAs) to alleviate the aforementioned challenges. An FPGA can be configured as a machine learning accelerator, operating similarly to a GPU or TPU. We propose an FPGA-based architecture that utilizes compressed neural networks. This provides an alternative hardware option for those running machine learning inference, resulting in savings in server construction costs, power consumption, workload distribution, and providing a more affordable option for customers. We evaluate the system using architectural simulations and cloud-based deployment and demonstrate 76.2% cost and 26.5% energy savings on average from using the Neural Compression Inference Accelerator (NCIA).","abstract_has_math":false,"creators":["Wallace, Matthew"],"institution":null,"degree_name":"MS in Electrical Engineering","degree_level":null,"degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Joseph Callenes-Sloan","Electrical Engineering","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:29Z","subjects":["Machine Learning","FPGA","AI","AWS","ResNet50","Verilog","Computer Engineering","Electrical and Computer Engineering","VLSI and Circuits, Embedded and Hardware Systems"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2965","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2965","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://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4323","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Joseph Callenes-Sloan","Electrical Engineering","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Wallace, Matthew"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2023-06-16T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2023-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Electrical Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","FPGA","AI","AWS","ResNet50","Verilog","Computer Engineering","Electrical and Computer Engineering","VLSI and Circuits, Embedded and Hardware Systems"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2965"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units (TPUs). However, these com- ponents are expensive for cloud services to purchase, costly for customers to rent, prone to price spikes, and energy-intensive. In this research we show that both cloud services and customers would benefit from utilizing field programmable gate arrays (FPGAs) to alleviate the aforementioned challenges. An FPGA can be configured as a machine learning accelerator, operating similarly to a GPU or TPU. We propose an FPGA-based architecture that utilizes compressed neural networks. This provides an alternative hardware option for those running machine learning inference, resulting in savings in server construction costs, power consumption, workload distribution, and providing a more affordable option for customers. We evaluate the system using architectural simulations and cloud-based deployment and demonstrate 76.2% cost and 26.5% energy savings on average from using the Neural Compression Inference Accelerator (NCIA)."]},{"key":"dc:title","label":"Title","values":["Neural Compression Inference Accelerator: a Cost and Energy-Effective Alternative to Conventional Machine Learning Inference Methods"]}]}],"canonical_facts":{"dc:contributor":["Joseph Callenes-Sloan","Electrical Engineering","College of Engineering"],"dc:creator":["Wallace, Matthew"],"dc:date.available":["2023-06-16T07:00:00Z"],"dc:date.created":["2023-06-01T07:00:00Z"],"dc:description.abstract":["Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units (TPUs). However, these com- ponents are expensive for cloud services to purchase, costly for customers to rent, prone to price spikes, and energy-intensive. In this research we show that both cloud services and customers would benefit from utilizing field programmable gate arrays (FPGAs) to alleviate the aforementioned challenges. An FPGA can be configured as a machine learning accelerator, operating similarly to a GPU or TPU. We propose an FPGA-based architecture that utilizes compressed neural networks. This provides an alternative hardware option for those running machine learning inference, resulting in savings in server construction costs, power consumption, workload distribution, and providing a more affordable option for customers. We evaluate the system using architectural simulations and cloud-based deployment and demonstrate 76.2% cost and 26.5% energy savings on average from using the Neural Compression Inference Accelerator (NCIA)."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2965"],"dc:subject":["Machine Learning","FPGA","AI","AWS","ResNet50","Verilog","Computer Engineering","Electrical and Computer Engineering","VLSI and Circuits, Embedded and Hardware Systems"],"dc:title":["Neural Compression Inference Accelerator: a Cost and Energy-Effective Alternative to Conventional Machine Learning Inference Methods"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_name":["MS in Electrical Engineering"]},"updated_at":"2026-11-19T07:12:29Z"}