<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T01:43:27Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/30640" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/30640</identifier><datestamp>2026-09-24T01:10:45Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Nicolici, Nicola</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Pogue, Trevor E.</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-12-16T15:22:48Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-12-16T15:22:48Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-06</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/30640</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/14834</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">The field of deep learning has seen increasing breakthroughs and commercial adoption in recent years for enabling a wide range of applications including image and speech recognition, multimedia generation, information summarization, and human-like chatbots. This has led to a growing need for hardware that can quickly and efficiently perform deep learning inference, which increasingly requires massive amounts of computational power.&#xd;
&#xd;
To address this need, recent years have seen many works for optimizing deep learning inference in hardware. Systolic arrays are an efficient class of hardware designs to use as a starting point for this application. However, after hardware-oriented deep learning model optimizations reach their limits, after the known parallelism for executing their compute patterns in hardware is exhausted, and after technology scaling slows to a halt, there is an accelerator wall that limits further improvement on the implementation side.&#xd;
&#xd;
In this thesis, we contribute to this field through an under-explored direction by presenting new efficient matrix multiplication algorithms and/or their systolic-array hardware architectures that increase performance-per-area by reducing the workload at the algebraic level, and thus by computing the same result from a re-arranged compute pattern requiring fewer or cheaper operations to be performed in hardware. We evaluate our architectures in an end-to-end deep learning accelerator, demonstrating their ability to increase the performance-per-area of hardware accelerators beyond their normal theoretical limits.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">hardware</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">acceleration</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">architecture</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">performance</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">algorithms</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">matrix multiplication</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">artificial intelligence</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Algebraic Enhancements for Systolic Arrays</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>