ACE Presentations

ACE Liaison Meetings and Quarterly e-Workshops 
Theme 1
April 7, 2023 Wei Tang and Junkang Zhu, University of Michigan, Composable Accelerator Design for Evolvable ML and Communication Workloads
May 2, 2023 Yixiao Du, Cornell University, Building Evolvable Accelerators for Sparse Data Processing
June 2, 2023 Yufeng Wang and Damitha Lenadora, Illinois, Optimizing Graph Neural Network Computations
July 4, 2023  HOLIDAY No Liaison Meeting
August 4, 2023 Gerasimos Gerogiannis, Illinois, Domain-Specific hardware and Software for Mixed sparse-Dense Algebra at Scale
September 5, 2023 Jovan Stojkovic, Illinois, uManyCore 
October 6, 2023 No Theme Meeting - SRC Annual Review at Illinois
November 7, 2023 Prof. Charith Mendis, Illinois, Making Compilers More Evolvable with Learned Cost Models
December 1, 2023 Garasimo (Makis) Gerogiannis, Illinois, Micro-Armed Bandit: Lightweight & Reusable Reinforcement Learning for Microarchitecture Decision-Making
January 9, 2024 Raveesh Garg, Georgia Tech, Scheduling and HW-Support for Extracting Inter-Operation Reuse in Diverse Tensor Algebra Applications 
February 2, 2024 Chenhui Deng, Cornell, Accurate and Scalable Representation Learning on Computational Graphs 
March 5, 2024 Hongzheng Chen, Cornell, A Schedule Language for Distributed ML Model Training 
April 5, 2024 Junkang (Jerry) Zhu & Minsik Kim, Univ of Michigan, EVA: Evolavable Accelerator for ML and DSP Workloads
May 7, 2024 Huwan Peng & Scott Davison, Chiplet Cloud 3D for Future Large Language Models
Theme 2
April 14, 2023 Narangerelt (Nara) Batsoyol, UCSD, P-MASSIVE: A Real-Time Search Engine for a Multi-Terabyte Mass Spectrometry Database
May 9, 2023 Neel Patel, University of Kansas, Near-Memory Acceleration of Software-Defined Far Memory
June 9, 2023 Socrates Wong, Cornell University, PUMICE: Processing-using-memory integration with a scalar pipeline for symbiotic execution
July 11, 2023   GUEST LECTURE: Prof. Puneet Gupta, UCSL, Challenges in Disaggregation/Reaggregation to/from Chiplets
August  11, 2023 Suyash Mahar, University of  California San Diego, Puddles: Application-Independent Recovery and Location-Independent Data for Persistent Memory
September 12, 2023 Kailin Yang, Cornell University, VersaTile: Flexible Tiled architectures via Processing-Using-Memory Cores
October  13, 2023 Ruijie Wang, Illinois, Online Inference Acceleration by Learning to Sample and Refresh on Streaming Temporal Graphs
November 14, 2023 Henry Schuh, University of Washington, CC-NIC: a Cache-Coherent Interface to the NIC
December 8, 2023 Niansong Zhang, Cornell, Evaluating a Commercial Compute-in-SRAM Accelerator with Binarized ML Operators
January 12, 2024 Gohar Chaudhry, MIT, Unleashing Datacenter Flash with Adaptive I/O Steering 
February 9, 2024 Cecilio Tamarit, Cornell, The Road to GENIAL: An Associative Processing Approach to High-Throughput Plant Phenogenomics
March 12, 2024 Narangeralt (Nara) Batsoyol, UCSD , Using DPUs to Transparently Accelerate Large-Scale Data Processing
April 12, 2024 Lequn Chen, Univ Washington, Multi-tenant ML model serving systems for DNNs and LLMs
May 14, 2024 No Liaison Meeting
Theme 3
April 21, 2023  Yang Zhou, Harvard University, Electrode: Accelerating Distributed Protocols with eBPF
May 16, 2023 Mark Zhao, Stanford University, Understanding and Optimizing ML Data Storage and Ingestion Systems
June 16, 2023 Jaehong Min, University of Washington, eZNS: An Elastic Zoned Namespace for Commodity ZNS SSDs 
July 18, 2023 Annus Zulfiqar, Purdue University, Homunculus: Auto-Generating Efficient Data-Plane ML Pipelines for Datacenter Networks 
August 18, 2023 Jovan Stojkovic, Illinois, MXFaaS: Resource Sharing in Serverless Environments for Parallelism and Efficiency 
September 19, 2023 Taekyoung Heo & William Won, Georgia Tech, Chakra and ASTRA-sim: An open-source ecosystem for advancing co-design for future AI systems
October 21, 2023 No Liaison Meeting
November 21, 2023 Amin Mamandipoor and Neel Patel, Kansas, SmartDIMM: In-Memory Acceleration of Upper Layer I/O Protocols
December 15, 2023 Sudarsanan Rajasekaran, MIT, CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters
January 23, 2024 Gohar Chaudhry, MIT, Unleashing Datacenter Flash with Adaptive I/O Steering 
February 16, 2024 Antonis Psistakis, Illinois, MINOS: Distributed Consistency and Persistency Implementation and Offloading to SmartNICs 
March 19, 2024 Minghao Li, Harvard, THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression 
May 21, 2024 Yang Zhou, Harvard, DINT: Fast In-Kernel Distributed Transactions with eBPF
April 19, 2024  Bilal Saleem (Purdue), Tegra, A Fast, Flexible, and Scalable Cloud-Native 5G Core
May 21, 2024 Yang Zhou (Harvard), DINT: Fas In-Kernal Distributed Transactions with eBPF
June 21, 2024 Athinagoras Skiadopoulos (Stanford), High-throughput and Flexible Host Networking via Control and Data Path Physical Separation
Theme 4
April 28, 2023 Drew Zagieboylo, Cornell University, Hardware Design Languages to Prevent Bugs and Security Vulnerabilities
May 23, 2023 Moein Ghaniyoun, The Ohio State University, TEESec: Pre-Silicon Vulnerability Discovery for Trusted Execution Environments
June 23, 2023 Neil Zhao, Illinois, Untangle: A Principled Framework to Design Low-Leakage, High Performance Dynamic Partitioning Schemes
July 25, 2023 Mulong Luo, Cornell,  AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks 
August 25, 2023 Zirui Neil Zhao, Illinois, Untangle: A Principled Framework to Design Low-Leakage, High-Performance Dynamic Partitioning Schemes
September 26, 2023 Saikat Majumdar, Voltage Noise-Based Adversarial Attacks on Machine Learning Inference in Multi-Tenant FPGA Accelerators
October 27, 2023 Shijia Wei, UT Austin, Understanding Security Domains and Their Implications for Architects
November 28, 2023 Saranyu Chatophadhyay, Stanford, G-QED-Enhanced Abstraction for Formally Verifying Very Large Digital Designs
January 30, 2024 Neil Zhao, Illinois, Everywhere All at Once: Co-Location Attacks on Public Cloud FaaS 
February 23, 2024 Yuheng Yang, MIT, Pensieve: Microarchitectural Modeling for Security Evaluation 
March, 26, 2024 Yang Hu, UTA, Fixing Privilege Escalations in Cloud Access Control with MaxSAT and Graph Neural Networks 
April 26, 2024 Moein Ghaniyoun , OSU, MicroSampler: A Framework for Microarchitecture-Level Security Verification of Constant Time Execution 
June 28, 2024 Prof. Mengjia Yan, MIT, SecureLoop: Design Space Exploration of Secure DNN Accelerators 


Quarterly e-Workshops (Recordings are available in Pillar to center members)
February 14, 2023 Josep Torrellas, Illinois, ACE Plan Vision
May 23, 2023 Minlan Yu, Harvard University, Fine-grained Communication and Coordination for Millions of Accelerators 
September 5, 2023 Zhengya Zhang, University of Michigan, Ann Arbor, Composing Evolvable Accelerators Using Chiplets
November 28, 2023 Mohit Tiwari, University of Texas, Austin, Data-centric Security
March 26, 2023 Mohammad Alian, University of Kansas, Data-Delivery Acceleration for Cross-Domain Multi-Acceleration at Scale


Liaison Meetings are not recorded, but the presentation file may be in Pillar for SRC Members to see.
Quarterly e-workshops recordings are in Pillar for a limited time.