ACE Presentations
ACE Liaison Meetings and Quarterly e-Workshops
Theme 1
September 3, 2024 Jie Liu, Cornell, UniSparse: An Intermediate Language for General Sparse Format Customization
August 2, 2024 Jianming Tong, Georgia Tech, FEATHER: A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching
June 7, 2024 Jiayun Zhang & Keerthivasan Vijayakumar, UCSD, Accelerating Distributed ML Applications: Convolutional LSTM Networks for Human Activity Recognition
May 7, 2024 Huwan Peng & Scott Davison, Chiplet Cloud 3D for Future Large Language Models
April 5, 2024 Junkang (Jerry) Zhu & Minsik Kim, Univ of Michigan, EVA: Evolvable Accelerator for ML and DSP Workloads
March 5, 2024 Hongzheng Chen, Cornell, A Schedule Language for Distributed ML Model Training
February 2, 2024 Chenhui Deng, Cornell, Accurate and Scalable Representation Learning on Computational Graphs
January 9, 2024 Raveesh Garg, Georgia Tech, Scheduling and HW-Support for Extracting Inter-Operation Reuse in Diverse Tensor Algebra Applications
December 1, 2023 Garasimo (Makis) Gerogiannis, Illinois, Micro-Armed Bandit: Lightweight & Reusable Reinforcement Learning for Microarchitecture Decision-Making
November 7, 2023 Prof. Charith Mendis, Illinois, Making Compilers More Evolvable with Learned Cost Models
October 6, 2023 No Theme Meeting - SRC Annual Review at Illinois
September 5, 2023 Jovan Stojkovic, Illinois, uManyCore
August 4, 2023 Gerasimos Gerogiannis, Illinois, Domain-Specific hardware and Software for Mixed sparse-Dense Algebra at Scale
July 4, 2023 HOLIDAY No Liaison Meeting
June 2, 2023 Yufeng Wang and Damitha Lenadora, Illinois, Optimizing Graph Neural Network Computations
May 2, 2023 Yixiao Du, Cornell University, Building Evolvable Accelerators for Sparse Data Processing
April 7, 2023 Wei Tang and Junkang Zhu, University of Michigan, Composable Accelerator Design for Evolvable ML and Communication Workloads
Theme 2
Sept 10, 2024 Neel Patel, Cornell, Unlocking the Potential of Accelerated Chip Multi-Processors
August 9, 2024 Ehsan Hajyasini, UCSD, Telepathic Datacenters: Fast RPCs using Shared CXL Memory
July 9, 2024 Akhil Shekhar, Guest from UVA, Membrane: Accelerating Database Analytics with Bank-Level DRAM-PIM Filtering
April 12, 2024 Lequn Chen, Univ Washington, Multi-tenant ML model serving systems for DNNs and LLMs
March 12, 2024 Narangeralt (Nara) Batsoyol, UCSD , Using DPUs to Transparently Accelerate Large-Scale Data Processing
February 9, 2024 Cecilio Tamarit, Cornell, The Road to GENIAL: An Associative Processing Approach to High-Throughput Plant Phenogenomics
January 12, 2024 Gohar Chaudhry, MIT, Unleashing Datacenter Flash with Adaptive I/O Steering
December 8, 2023 Niansong Zhang, Cornell, Evaluating a Commercial Compute-in-SRAM Accelerator with Binarized ML Operators
November 14, 2023 Henry Schuh, University of Washington, CC-NIC: a Cache-Coherent Interface to the NIC
October 13, 2023 Ruijie Wang, Illinois, Online Inference Acceleration by Learning to Sample and Refresh on Streaming Temporal Graphs
September 12, 2023 Kailin Yang, Cornell University, VersaTile: Flexible Tiled architectures via Processing-Using-Memory Cores
August 11, 2023 Suyash Mahar, University of California San Diego, Puddles: Application-Independent Recovery and Location-Independent Data for Persistent Memory
July 11, 2023 GUEST LECTURE: Prof. Puneet Gupta, UCSL, Challenges in Disaggregation/Reaggregation to/from Chiplets
June 9, 2023 Socrates Wong, Cornell University, PUMICE: Processing-using-memory integration with a scalar pipeline for symbiotic execution
May 9, 2023 Neel Patel, University of Kansas, Near-Memory Acceleration of Software-Defined Far Memory
April 14, 2023 Narangerelt (Nara) Batsoyol, UCSD, P-MASSIVE: A Real-Time Search Engine for a Multi-Terabyte Mass Spectrometry Database
Theme 3
October 18, 2024 Ali Imran, Purdue, Caravan: Practical Online Learning of In-Network ML Models with Labeling Agents
September 17, 2024 Swapnil Gandhi, Stanford, Adapting Pipelines for Distributed Training of Large DNNs Amid Failures
August 16, 2024 William Won, Georgia Tech, TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning
July 16, 2024 Ajay Brahmakshatriya , MIT, NetBlocks: Staging Layouts for High-Performance Custom Host Network Stacks
June 21, 2024 Athinagoras Skiadopoulos, Stanford, High-throughput and Flexible Host Networking via Control and Data Path Physical Separation
May 21, 2024 Yang Zhou, Harvard, DINT: Fast In-Kernal 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: Fast In-Kernel Distributed Transactions with eBPF
March 19, 2024 Minghao Li, Harvard, THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression
February 16, 2024 Antonis Psistakis, Illinois, MINOS: Distributed Consistency and Persistency Implementation and Offloading to SmartNICs
January 23, 2024 Gohar Chaudhry, MIT, Unleashing Datacenter Flash with Adaptive I/O Steering
December 15, 2023 Sudarsanan Rajasekaran, MIT, CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters
November 21, 2023 Amin Mamandipoor and Neel Patel, Kansas, SmartDIMM: In-Memory Acceleration of Upper Layer I/O Protocols
October 21, 2023 No Liaison Meeting
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
August 18, 2023 Jovan Stojkovic, Illinois, MXFaaS: Resource Sharing in Serverless Environments for Parallelism and Efficiency
July 18, 2023 Annus Zulfiqar, Purdue University, Homunculus: Auto-Generating Efficient Data-Plane ML Pipelines for Datacenter Networks
June 16, 2023 Jaehong Min, University of Washington, eZNS: An Elastic Zoned Namespace for Commodity ZNS SSDs
May 16, 2023 Mark Zhao, Stanford University, Understanding and Optimizing ML Data Storage and Ingestion Systems
April 21, 2023 Yang Zhou, Harvard University, Electrode: Accelerating Distributed Protocols with eBPF
Theme 4
September 24, 2024 Vincent Ulitzsch, Guest from Technical University Berlin & Peter Deutsch, MIT, DelayAVF: Calculating Architectural Vulnerability Factors for Delay Faults
August 23, 2024 Hyoungwook Nam, Illinois, FriendlyFoe: Adversarial Machine Learning as a Practical Architectural Defense for Side Channels
June 28, 2024 Prof. Mengjia Yan, MIT, SecureLoop: Design Space Exploration of Secure DNN Accelerators
April 26, 2024 Moein Ghaniyoun , OSU, MicroSampler: A Framework for Microarchitecture-Level Security Verification of Constant Time Execution
March, 26, 2024 Yang Hu, UTA, Fixing Privilege Escalations in Cloud Access Control with MaxSAT and Graph Neural Networks
February 23, 2024 Yuheng Yang, MIT, Pensieve: Microarchitectural Modeling for Security Evaluation
January 30, 2024 Neil Zhao, Illinois, Everywhere All at Once: Co-Location Attacks on Public Cloud FaaS
November 28, 2023 Saranyu Chatophadhyay, Stanford, G-QED-Enhanced Abstraction for Formally Verifying Very Large Digital Designs
October 27, 2023 Shijia Wei, UT Austin, Understanding Security Domains and Their Implications for Architects
September 26, 2023 Saikat Majumdar, Voltage Noise-Based Adversarial Attacks on Machine Learning Inference in Multi-Tenant FPGA Accelerators
August 25, 2023 Zirui 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
June 23, 2023 Neil Zhao, Illinois, Untangle: A Principled Framework to Design Low-Leakage, High Performance Dynamic Partitioning Schemes
May 23, 2023 Moein Ghaniyoun, The Ohio State University, TEESec: Pre-Silicon Vulnerability Discovery for Trusted Execution Environmentts
April 28, 2023 Drew Zagieboylo, Cornell University, Hardware Design Languages to Prevent Bugs and Security Vulnerabilities
Quarterly e-Workshops (Recordings are available in Pillar to center members)
October 8, 2024 Tushar Krishna, Georgia Tech, Design and Optimization of Network Fabrics for Distributed AI/ML Platforms
July 2, 2024 Charith Mendis, Illinois, Optimizations and Compilation Techniques for Sparse Machine Learning Models
March 26, 2024 Mohammad Alian, University of Kansas, Data-Delivery Acceleration for Cross-Domain Multi-Acceleration at Scale
November 28, 2023 Mohit Tiwari, University of Texas, Austin, Data-centric Security
September 5, 2023 Zhengya Zhang, University of Michigan, Ann Arbor, Composing Evolvable Accelerators Using Chiplets
May 23, 2023 Minlan Yu, Harvard University, Fine-grained Communication and Coordination for Millions of Accelerators
February 14, 2023 Josep Torrellas, Illinois, ACE Plan Vision