{"674339":{"#nid":"674339","#data":{"type":"event","title":"Ph.D. Dissertation Defense - Wantong Li","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E \u0026nbsp;\u003Cem\u003EEfficient and Robust Compute-in-Memory For Edge Intelligence\u003C\/em\u003E\u003Cbr \/\u003E\r\n\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nDr. Shimeng Yu, ECE, Chair, Advisor\u003Cbr \/\u003E\r\nDr. Shaolan Li, ECE\u003Cbr \/\u003E\r\nDr. Callie Hao, ECE\u003Cbr \/\u003E\r\nDr. Muhannad Bakir, ECE\u003Cbr \/\u003E\r\nDr. Celine Lin, CS\u003Cbr \/\u003E\r\n\u0026nbsp;\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThe increasingly more complex artificial intelligence (AI) models have attracted interdisciplinary efforts to speed up AI workloads. On the hardware front, the disruptive paradigm of compute-in-memory (CIM) aims to process data directly inside memory arrays, which is a promising approach to overcome the memory wall problem that conventional platforms face. Complex arithmetic operations can be performed using compute-capable CIM arrays to achieve massive parallelism and high energy efficiency. This dissertation focuses on the circuit design and hardware architecture aspects of CIM for executing AI inference. First, I will present a mixed-signal CIM engine that performs parallelized matrix multiplications inside resistive random-access memory (RRAM) arrays. The RRAM-based CIM chip, fabricated in TSMC 40-nm node, demonstrates circuit techniques that ensure PVT-robust and secure computing. Next, I will discuss the unique opportunities to transform computing inside heterogeneous 3D stacks. An 3D-stacked CIM accelerator targeting vision transformer models is shown to gain form factor and efficiency benefits. Finally, I will present a low-power portable ultrasound system to showcase how CIM can be applied to embedded electronics. Through data volume reduction of the ultrasound frontend and the on-device intelligence inserted by CIM, significant power savings can be achieved for the portable imaging system.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Efficient and Robust Compute-in-Memory For Edge Intelligence "}],"uid":"28475","created_gmt":"2024-04-23 17:55:12","changed_gmt":"2024-04-23 17:56:12","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-04-30T13:00:00-04:00","event_time_end":"2024-04-30T15:00:00-04:00","event_time_end_last":"2024-04-30T15:00:00-04:00","gmt_time_start":"2024-04-30 17:00:00","gmt_time_end":"2024-04-30 19:00:00","gmt_time_end_last":"2024-04-30 19:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Online","extras":[],"related_links":[{"url":"https:\/\/teams.microsoft.com\/l\/meetup-join\/19%3ameeting_OGVlMzdkMTEtNjc5NS00YTYyLThhODQtYTliMjg1NTg1OTNh%40thread.v2\/0?context=%7b%22Tid%22%3a%22482198bb-ae7b-4b25-8b7a-6d7f32faa083%22%2c%22Oid%22%3a%22bd6d4555-f571-4952-95e5-acd486eb4074%22%7d","title":"Microsoft Teams Meeting link"}],"groups":[{"id":"434381","name":"ECE Ph.D. Dissertation Defenses"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"},{"id":"1808","name":"graduate students"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}