\documentclass[10pt,twocolumn]{article} \usepackage[margin=0.75in]{geometry} \usepackage{graphicx} \usepackage{booktabs} \usepackage{amsmath} \usepackage{amssymb} \usepackage{siunitx} \DeclareSIUnit\flop{FLOP} \DeclareSIUnit\cycle{cycle} \DeclareSIUnit\byte{B} \usepackage{xcolor} \usepackage{hyperref} \hypersetup{colorlinks=true,linkcolor=blue!50!black,citecolor=blue!50!black,urlcolor=blue!50!black} \usepackage{caption} \usepackage{subcaption} \captionsetup{font=small,labelfont=bf} \usepackage{lmodern} % scalable Latin Modern fonts (required by microtype expansion) \usepackage{microtype} \usepackage{tikz} \usetikzlibrary{arrows.meta,positioning,calc,fit} \graphicspath{{figures/}} \title{\textbf{Hardware--Software Co-Design for Grouped-Query Attention on AHBM}} \author{Mukesh Garg \and Jiyoon Lee \and Yangwook Kang} \date{ \small AGI Computing Lab, System Technology Group\\ 2026 Q1-Q3 Report } \begin{document} \maketitle \input{sections/00-exec-summary} \input{sections/01-introduction} \input{sections/02-platform} \input{sections/03-gemm} \input{sections/04-allreduce} \input{sections/05-gqa} % section header + intro \input{sections/05a-roofline} % 5.1 Roofline Analysis \input{sections/05b-capacity-planning} % 5.2 Capacity Planning \input{sections/05c-parallelism-selection} % 5.3 Parallelism Selection \input{sections/05x-fused-kernel} % 5.4-5.7 Placement + short/long ctx + composite \input{sections/05z-summary} % 5.8 Summary \input{sections/06-agentic} \input{sections/07-hw-spec-search} \input{sections/08-discussion} \input{sections/09-conclusion} \input{sections/10-future-work} \end{document}