<?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>2026-11-22T23:02:18Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/21600" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/21600</identifier><datestamp>2025-05-20T07:03:46Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9908</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Bekmyrza, Marat</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-04-17T12:34:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-04-17T12:34:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-04-17</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2025-04-14</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/10012/21600</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Large Language Models (LLMs) are currently dominating the field of Artificial Intelligence (AI) applications, but their integration for edge computing purposes is rather limited due to computational complexity and power consumption. This thesis addresses this challenge by investigating the integer-only acceleration of transformer models on FPGAs, focusing on the BERT architecture. We demonstrate that by removing the floating-point operations from the inference pipeline, especially from non-linear functions like GELU, Softmax, and Layer Normalization, we can improve the performance without sacrificing accuracy.
Our pipelined, batched architecture processes multiple sequences in parallel and optimizes the FPGA resources. We achieve a 2.6x throughput improvement over a single-sequence inference and at least 10x speedup over the offloading to CPU approach. The results of the experiments show that our implementation has comparable accuracy to the floating-point models for the GLUE benchmark tasks with INT8 quantization. These findings reveal that integer-only transformer inference on FPGAs is a feasible way of implementing complex language models on resource-limited edge devices, with the potential for new privacy-conscious, low-latency AI applications.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject">Large Language Models</dim:field>
   <dim:field mdschema="dc" element="subject">Artificial Intelligence</dim:field>
   <dim:field mdschema="dc" element="subject">FPGA</dim:field>
   <dim:field mdschema="dc" element="subject">Inference Acceleration</dim:field>
   <dim:field mdschema="dc" element="title">Language Model Inference on FPGA with Integer-only Operations</dim:field>
   <dim:field mdschema="dc" element="type">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree">Master of Applied Science</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms">4 months</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Kapre, Nachiket</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Patel, Hiren</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1">Faculty of Engineering</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>