{"id":25,"date":"2021-07-11T23:49:57","date_gmt":"2021-07-11T15:49:57","guid":{"rendered":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/?page_id=25"},"modified":"2026-11-03T09:59:11","modified_gmt":"2026-11-03T01:59:11","slug":"research","status":"publish","type":"page","link":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/research\/","title":{"rendered":"Research"},"content":{"rendered":"\n<div style=\"max-width:100%;font-family:inherit\"><div style=\"font-size:12px;letter-spacing:2px;color:#367f89;font-weight:700;margin-bottom:12px\">RESEARCH AT iCAS<\/div><p style=\"font-size:21px;line-height:1.5;color:#12324b;margin:0 0 24px\">We design intelligent chips in intelligent ways.<\/p><div style=\"margin:36px 0 22px;padding:26px 28px;background:#12324b;border-radius:12px;border-top:4px solid #36a3ad\"><div style=\"font-size:11px;font-weight:700;letter-spacing:2px;text-transform:uppercase;color:#9ed9df;margin-bottom:10px\">RESEARCH THRUST 1<\/div><h2 style=\"margin:0 0 14px;color:#ffffff;font-size:25px;line-height:1.3;font-weight:650\">AI-Powered Chip Design<\/h2><p style=\"margin:0;color:#e2ecf3;font-size:15px;line-height:1.8;text-align:left\">We develop methods and tools that shorten the chip design cycle, from early design space exploration and logic synthesis to physical implementation and timing closure. Our research brings physical, timing, and thermal awareness into earlier design decisions, combining AI\/ML, large language models, and reusable design infrastructure.<\/p><\/div><article style=\"margin:0 0 20px;padding:26px;background:#ffffff;border:1px solid #dce5eb;border-radius:12px\"><div style=\"display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-bottom:18px\"><div style=\"flex:1;min-width:200px\"><div style=\"font-size:11px;font-weight:700;letter-spacing:1.5px;color:#367f89;margin-bottom:8px\">THEME 01<\/div><h3 style=\"font-size:21px;line-height:1.4;font-weight:650;color:#12324b;margin:0\">Early Exploration for 3D &amp; Chiplet Systems<\/h3><\/div><figure style=\"margin:0;width:110px;flex:0 0 110px;padding:8px;background:#ffffff\"><a href=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/image-5.png\" target=\"_blank\" rel=\"noopener\" title=\"Open full-size research figure\" aria-label=\"Open full-size research figure\" style=\"display:block;cursor:zoom-in\"><img decoding=\"async\" src=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/image-5.png\" alt=\"Early Exploration for 3D and Chiplet Systems research illustration\" style=\"display:block;width:100%;height:100px;object-fit:contain\" \/><\/a><figcaption style=\"font-size:10px;line-height:1.4;text-align:center;color:#367f89;margin-top:6px\">Click to enlarge \u2197<\/figcaption><\/figure><\/div><p style=\"margin:0;color:#415465;font-size:15px;line-height:1.85;text-align:left\">Good design decisions require fast feedback before expensive implementation. We explore architecture, partitioning, and packaging choices with models that expose their physical and system-level consequences early. Recent work includes <a href=\"https:\/\/ieeexplore.ieee.org\/document\/11083607\/\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: Cool-3D: An End-to-End Thermal-Aware Framework for Early-Phase Design Space Exploration of Microfluidic-Cooled 3DICs\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">Cool-3D<\/a> for thermal-aware exploration of microfluidic-cooled 3DICs and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=ChiPlanner%3A%20Physically-Aware%20and%20Timing-Driven%20Design%20Planner%20for%202.5D%20Multi-Chiplet%20Systems\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: ChiPlanner: Physically-Aware and Timing-Driven Design Planner for 2.5D Multi-Chiplet Systems\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">ChiPlanner<\/a> for physically aware, timing-driven planning of 2.5D multi-chiplet systems. Our exploration also examines <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Characterizing%20CPU-FPGA%20Boundary%20Cost%20Across%20Transformer%20Partitioning%20Strategies%20on%20Edge%20SoCs\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Characterizing CPU-FPGA Boundary Cost Across Transformer Partitioning Strategies on Edge SoCs\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">CPU\u2013FPGA partitioning costs<\/a> for transformer workloads. Current topics include:<\/p><ul style=\"margin:18px 0 0;padding:16px 16px 16px 32px;background:#f2f7fa;border-radius:8px;color:#415465;font-size:14px;line-height:1.8\">\n<li>Early thermal and physical modeling for 3DICs and multi-chiplet systems<\/li>\n<li>Hardware partitioning and architecture exploration for AI workloads<\/li>\n<li>Fast timing prediction and cross-corner design feedback<\/li>\n<\/ul><\/article><article style=\"margin:0 0 20px;padding:26px;background:#ffffff;border:1px solid #dce5eb;border-radius:12px\"><div style=\"display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-bottom:18px\"><div style=\"flex:1;min-width:200px\"><div style=\"font-size:11px;font-weight:700;letter-spacing:1.5px;color:#367f89;margin-bottom:8px\">THEME 02<\/div><h3 style=\"font-size:21px;line-height:1.4;font-weight:650;color:#12324b;margin:0\">Learning-Driven EDA: From Synthesis to Signoff<\/h3><\/div><figure style=\"margin:0;width:110px;flex:0 0 110px;padding:8px;background:#ffffff\"><a href=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/image-4.png\" target=\"_blank\" rel=\"noopener\" title=\"Open full-size research figure\" aria-label=\"Open full-size research figure\" style=\"display:block;cursor:zoom-in\"><img decoding=\"async\" src=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/image-4.png\" alt=\"Learning-Driven EDA: From Synthesis to Signoff research illustration\" style=\"display:block;width:100%;height:100px;object-fit:contain\" \/><\/a><figcaption style=\"font-size:10px;line-height:1.4;text-align:center;color:#367f89;margin-top:6px\">Click to enlarge \u2197<\/figcaption><\/figure><\/div><p style=\"margin:0;color:#415465;font-size:15px;line-height:1.85;text-align:left\">We combine learning-based methods with circuit structure and physical design knowledge to improve synthesis, placement, and timing closure. Recent work spans dataflow-aware macro placement with <a href=\"https:\/\/doi.org\/10.1145\/3795530\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: DARE: Enriching Physical Dataflow Awareness for Macro Placement Optimization\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">DARE<\/a> and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=IncreDFlip%3A%20Incremental%20Dataflow-Driven%20Macro%20Flipping%20for%20Efficient%20Macro%20Placement%20Refinement\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: IncreDFlip: Incremental Dataflow-Driven Macro Flipping for Efficient Macro Placement Refinement\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">IncreDFlip<\/a>, physically informed technology mapping with <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=PRISM%3A%20Beam-Search%20Technology%20Mapping%20via%20Learned%20Physical%20Timing\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: PRISM: Beam-Search Technology Mapping via Learned Physical Timing\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">PRISM<\/a>, <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Revisit%20MBFF%3A%20Efficient%20Early-Stage%20Multi-bit%20Flip-Flops%20Clustering%20with%20Physical%20and%20Timing%20Awareness\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Revisit MBFF: Efficient Early-Stage Multi-bit Flip-Flops Clustering with Physical and Timing Awareness\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">early multi-bit flip-flop clustering<\/a>, and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=One-for-All%3A%20An%20Unified%20Learning-based%20Framework%20for%20Efficient%20Cross-Corner%20Timing%20Signoff\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: One-for-All: An Unified Learning-based Framework for Efficient Cross-Corner Timing Signoff\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">cross-corner timing prediction<\/a>. We also investigate <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Beyond%20Iterative%20Search%3A%20Intelligent%20Generative%20GATv2%20Framework%20for%20Analog%20Sizing\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Beyond Iterative Search: Intelligent Generative GATv2 Framework for Analog Sizing\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">generative graph models for analog sizing<\/a> and LLM-assisted timing report analysis through <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=AutoTimer%3A%20An%20LLM-Powered%20Assistant%20for%20Timing%20Report%20Analysis%20and%20Physical%20Design%20Closure\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: AutoTimer: An LLM-Powered Assistant for Timing Report Analysis and Physical Design Closure\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">AutoTimer<\/a>. Our goal is to make design feedback available earlier and help designers navigate implementation tradeoffs with less manual iteration.<\/p><\/article><article style=\"margin:0 0 20px;padding:26px;background:#ffffff;border:1px solid #dce5eb;border-radius:12px\"><div style=\"display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-bottom:18px\"><div style=\"flex:1;min-width:200px\"><div style=\"font-size:11px;font-weight:700;letter-spacing:1.5px;color:#367f89;margin-bottom:8px\">THEME 03<\/div><h3 style=\"font-size:21px;line-height:1.4;font-weight:650;color:#12324b;margin:0\">Agile Design Ecosystems: Data, Tools &amp; Flows<\/h3><\/div><figure style=\"margin:0;width:110px;flex:0 0 110px;padding:8px;background:#ffffff\"><a href=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/Website-Figures-2.svg\" target=\"_blank\" rel=\"noopener\" title=\"Open full-size research figure\" aria-label=\"Open full-size research figure\" style=\"display:block;cursor:zoom-in\"><img decoding=\"async\" src=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/08\/Website-Figures-2.svg\" alt=\"Agile Design Ecosystems: Data, Tools and Flows research illustration\" style=\"display:block;width:100%;height:100px;object-fit:contain\" \/><\/a><figcaption style=\"font-size:10px;line-height:1.4;text-align:center;color:#367f89;margin-top:6px\">Click to enlarge \u2197<\/figcaption><\/figure><\/div><p style=\"margin:0;color:#415465;font-size:15px;line-height:1.85;text-align:left\">Agile hardware development depends on reusable tools, representative data, and efficient experimentation. Building on our work in configurable hardware and high-level design, we develop infrastructure that supports repeatable evaluation and faster iteration. Recent contributions include the <a href=\"https:\/\/doi.org\/10.1109\/ieeedata.2026.3678880\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: An EDA Physical Design Rectilinear Floorplan Benchmark Dataset (R-Zoo)\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">R-Zoo<\/a> rectilinear floorplan benchmark, the collaborative <a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/11199850\/\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: A Corpus Of Synthesizable Verilog RTL Modules Dataset for EDA Research (CORE)\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">CORE<\/a> synthesizable RTL dataset, and circuit data augmentation through <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=CircuitS2L%3A%20Circuit%20Dataset%20Augmentation%20via%20Generative%20Featuring%20and%20Supervised%20Labeling\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: CircuitS2L: Circuit Dataset Augmentation via Generative Featuring and Supervised Labeling\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">CircuitS2L<\/a> and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Sketch-to-Style%3A%20Augmenting%20AI4EDA%20Dataset%20with%20Automatic%20Image%20Generative%20Framework\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Sketch-to-Style: Augmenting AI4EDA Dataset with Automatic Image Generative Framework\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">Sketch-to-Style<\/a>. <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Elastic%20EDA%3A%20Auto-scaling%20Cloud%20Resources%20for%20EDA%20Tasks%20via%20Learning-based%20Approaches\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Elastic EDA: Auto-scaling Cloud Resources for EDA Tasks via Learning-based Approaches\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">Elastic EDA<\/a> explores learning-based cloud resource allocation for EDA workloads. Together, these efforts support the shift-left design approach examined in our <a href=\"https:\/\/doi.org\/10.1145\/3819588\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: Shift Left Techniques in Electronic Design Automation: A Survey\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">recent survey<\/a>, connecting early feedback with practical implementation flows.<\/p><\/article><div style=\"margin:36px 0 22px;padding:26px 28px;background:#12324b;border-radius:12px;border-top:4px solid #36a3ad\"><div style=\"font-size:11px;font-weight:700;letter-spacing:2px;text-transform:uppercase;color:#9ed9df;margin-bottom:10px\">RESEARCH THRUST 2<\/div><h2 style=\"margin:0 0 14px;color:#ffffff;font-size:25px;line-height:1.3;font-weight:650\">Energy-Efficient &amp; Resilient Computing<\/h2><p style=\"margin:0;color:#e2ecf3;font-size:15px;line-height:1.8;text-align:left\">We investigate how circuits, architectures, and software can work together to improve energy efficiency and reliability. Our research connects device aging and process variability with workload behavior, numerical precision, memory organization, and thermal design. We seek design choices that balance performance, energy, accuracy, and resilience across the system stack.<\/p><\/div><article style=\"margin:0 0 20px;padding:26px;background:#ffffff;border:1px solid #dce5eb;border-radius:12px\"><div style=\"display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-bottom:18px\"><div style=\"flex:1;min-width:200px\"><div style=\"font-size:11px;font-weight:700;letter-spacing:1.5px;color:#367f89;margin-bottom:8px\">THEME 04<\/div><h3 style=\"font-size:21px;line-height:1.4;font-weight:650;color:#12324b;margin:0\">Lifetime-Aware Circuits &amp; Self-Healing Systems<\/h3><\/div><figure style=\"margin:0;width:110px;flex:0 0 110px;padding:8px;background:#ffffff\"><a href=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/11\/Picture2.png\" target=\"_blank\" rel=\"noopener\" title=\"Open full-size research figure\" aria-label=\"Open full-size research figure\" style=\"display:block;cursor:zoom-in\"><img decoding=\"async\" src=\"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-content\/uploads\/sites\/30\/2021\/11\/Picture2.png\" alt=\"Lifetime-Aware Circuits and Self-Healing Systems research illustration\" style=\"display:block;width:100%;height:100px;object-fit:contain\" \/><\/a><figcaption style=\"font-size:10px;line-height:1.4;text-align:center;color:#367f89;margin-top:6px\">Click to enlarge \u2197<\/figcaption><\/figure><\/div><p style=\"margin:0;color:#415465;font-size:15px;line-height:1.85;text-align:left\">Device aging and process variability can change circuit behavior throughout a chip\u2019s operating life. We study how to model these effects and incorporate lifetime considerations into design and optimization. Recent work includes <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=RESIST%3A%20Residual%20Reinforcement%20Learning%20for%20Lifespan%20Clock%20Tree%20Reliability%20Optimization\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: RESIST: Residual Reinforcement Learning for Lifespan Clock Tree Reliability Optimization\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">RESIST<\/a>, which applies residual reinforcement learning to lifespan clock-tree reliability optimization, <a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/10493861\/\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: Impact of Aging and Process Variability on SRAM-based In-Memory Computing Architectures\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">aging and variability analysis of SRAM-based in-memory computing<\/a>, and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Aging%20Analysis%20of%20CMOS%20Synaptic%20Circuits%20with%20Simplified%20Leaky%20Integrate-and-Fire%20Neurons\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Aging Analysis of CMOS Synaptic Circuits with Simplified Leaky Integrate-and-Fire Neurons\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">aging analysis of CMOS synaptic circuits<\/a>. Our <a href=\"https:\/\/doi.org\/10.1145\/3829075\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: Extending Silicon Lifetime: A Review of Design Techniques for Reliable Integrated Circuits\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">review of reliable integrated-circuit design<\/a> brings together techniques for extending silicon lifetime. This direction builds on our work in active recovery and self-healing, with the aim of managing reliability alongside performance and power.<\/p><\/article><article style=\"margin:0 0 20px;padding:26px;background:#ffffff;border:1px solid #dce5eb;border-radius:12px\"><div style=\"display:flex;align-items:center;gap:18px;flex-wrap:wrap;margin-bottom:18px\"><div style=\"flex:1;min-width:200px\"><div style=\"font-size:11px;font-weight:700;letter-spacing:1.5px;color:#367f89;margin-bottom:8px\">THEME 05<\/div><h3 style=\"font-size:21px;line-height:1.4;font-weight:650;color:#12324b;margin:0\">Algorithm\u2013Hardware Co-Design for Efficient AI<\/h3><\/div><\/div><p style=\"margin:0;color:#415465;font-size:15px;line-height:1.85;text-align:left\">We co-design algorithms and hardware for efficient AI inference, with particular attention to edge platforms and memory-intensive workloads. Recent work includes <a href=\"https:\/\/ieeexplore.ieee.org\/document\/10633877\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: Edge-MPQ: Layer-Wise Mixed-Precision Quantization with Tightly Integrated Versatile Inference Units for Edge Computing\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">Edge-MPQ<\/a> and mixed-precision FPGA inference, <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=DDPA%3A%20Dynamic-Dimensional%20Piecewise%20Approximation%20for%20Unified%20Activation%20Function%20Acceleration\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: DDPA: Dynamic-Dimensional Piecewise Approximation for Unified Activation Function Acceleration\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">DDPA<\/a> activation-function acceleration, and <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=PIMScope%3A%20Augmenting%20Ramulator%202.0%20with%20Command-Level%20LPDDR-PIM%20for%20Transformer%20Inference\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: PIMScope: Augmenting Ramulator 2.0 with Command-Level LPDDR-PIM for Transformer Inference\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">PIMScope<\/a> modeling of LPDDR processing-in-memory for transformer inference. We also explore accuracy\u2013energy\u2013resilience tradeoffs through <a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/#:~:text=Tri-Balancing%20Act%3A%20Noise-Guided%20Mixed-Precision%20Search%20for%20Accuracy%E2%80%93Energy%E2%80%93Resilience%20Co-Optimization\" target=\"_blank\" rel=\"noopener\" title=\"View publication entry: Tri-Balancing Act: Noise-Guided Mixed-Precision Search for Accuracy\u2013Energy\u2013Resilience Co-Optimization\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">noise-guided mixed-precision search<\/a>. Collaborative work extends this direction to tunable numerical precision with <a href=\"https:\/\/arxiv.org\/abs\/2609.04724\" target=\"_blank\" rel=\"noopener\" title=\"Read paper: FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators\" style=\"color:#176c80;font-weight:600;text-decoration:underline\">FlexPosit<\/a> and efficient LLM execution. Across these projects, we examine how precision, data movement, computation, and hardware partitioning shape system efficiency.<\/p><\/article><div style=\"margin-top:28px;padding:20px 24px;background:#f2f7fa;border-radius:10px;color:#415465;font-size:14px;line-height:1.7\">Explore the papers behind these research directions.<br \/><a href=\"https:\/\/sites.gc.sjtu.edu.cn\/xinfei-guo\/publications\/\" style=\"display:inline-block;margin-top:8px;font-weight:700;color:#176c80;text-decoration:none\">View our publications &rarr;<\/a><\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>RESEARCH AT iCAS We design intelligent chips in intelligent ways. RESEARCH THRUST 1 AI-Powered Chip Design We develop methods and tools that shorten the chip design cycle, from early design space exploration and logic synthesis to physical implementation and timing closure. Our research brings physical, timing, and thermal awareness into earlier design decisions, combining AI\/ML, [&hellip;]<\/p>\n","protected":false},"author":31,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-25","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/pages\/25","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/users\/31"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/comments?post=25"}],"version-history":[{"count":71,"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/pages\/25\/revisions"}],"predecessor-version":[{"id":842,"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/pages\/25\/revisions\/842"}],"wp:attachment":[{"href":"https:\/\/sites.gc.sjtu.edu.cn\/icas\/wp-json\/wp\/v2\/media?parent=25"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}