ASPLOS 2024 PROCEEDINGS
Volume 1: https://dl.acm.org/doi/proceedings/10.1145/3617232
Volume 2: https://dl.acm.org/doi/proceedings/10.1145/3620665
Volume 3: https://dl.acm.org/doi/proceedings/10.1145/3620666
Sunday, 18:00 PDT – 21:00 PDT: Welcome Reception and Poster Session (Location: Grande C)
Floor Plan
Day 1: Monday, April 29
7:30 PDT – 8:30 PDT: Breakfast
8:30 PDT – 9:00 PDT: Opening Remarks (Location: Grande)
9:00 PDT – 10:00 PDT: Keynote 1 by Amin Vahdat (Google)
| Societal infrastructure in the age of Artificial General Intelligence |
| Abstract Today, we are at an inflection point in computing where emerging Generative AI services are placing unprecedented demand for compute while the existing architectural patterns for improving efficiency have stalled. In this talk, we will discuss the likely needs of the next generation of computing infrastructure and use recent examples at Google from networks to accelerators to servers to illustrate the challenges and opportunities ahead. Taken together, we chart a course where computing must be increasingly specialized and co-optimized with algorithms and software, all while fundamentally focusing on security and sustainability. |
| Bio Amin Vahdat (Vice President Google — ML, Systems, and Cloud AI) is a Fellow and vice president of Engineering at Google, where his team is responsible for delivering industry-leading Machine Learning software and hardware that serves Alphabet, Google and the world, and Artificial Intelligence technologies that empower ML developers and solve customers’ most pressing business challenges. In the past, he was General Manager for Google’s compute, storage, and network hardware and software infrastructure. Until 2019, he was the Technical Lead for the Networking organization at Google. Before joining Google, Amin was the Science Applications International Corporation (SAIC) Professor of Computer Science and Engineering at UC San Diego (UCSD). He received his doctorate from the University of California Berkeley in computer science. He is a member of the National Academy of Engineering (NAE) and an ACM Fellow. Amin has been recognized with a number of awards, including the National Science Foundation (NSF) CAREER award, the UC Berkeley Distinguished EECS Alumni Award, the Alfred P. Sloan Fellowship, the ACM SIGCOMM Networking Systems Award, and the Duke University David and Janet Vaughn Teaching Award. Most recently, Amin was awarded the SIGCOMM lifetime achievement award for his contributions to data center and wide area networks. Lastly, he was inducted into the National Academy of Engineering in September 2023 for his contributions to the design and implementation of datacenter and planet-scale networks that power cloud computer systems. |
10:00 PDT – 10:30 PDT: Break
10:30 PDT – 11:45 PDT: Lightning Talk Session
| Lightning A (Location: Grande A/B) Session Chair: Soroush Ghodrati (University of California, San Diego) |
|---|
| Papers from all A sessions. |
| Lightning B (Location: Grande C) Session Chair: Moumita Dey (AMD Research and Advanced Development) |
|---|
| Papers from all B sessions. |
| Lightning C (Location: Grande: D/E) Session Chair: Nader Sehatbakhsh (University of California, Los Angeles) |
|---|
| Papers from all C sessions. |
| Lightning D (Location: Scripps I/II) Session Chair: Kazem Taram (Purdue University) |
|---|
| Papers from all D sessions. |
11:45 PDT – 12:00 PDT: Break
12:00 PDT – 13:00 PDT: Session 1
| 1A: Synthesis for Architectures (Location: Grande A/B) Session Chair: Adrian Sampson (Cornell University) |
|---|
| Explainable Port Mapping Inference with Sparse Performance Counters for AMD’s Zen Architectures Fabian Ritter and Sebastian Hack (Saarland University) Paper . Abstract . Lightning Talk |
| Longnail: High-Level Synthesis of Portable Custom Instruction Set Extensions for RISC-V Processors from Descriptions in the Open-Source CoreDSL Language Julian Oppermann, Brindusa Mihaela Damian-Kosterhon, Florian Meisel, and Tammo Mürmann (Technical University of Darmstadt);Eyck Jentzsch (MINRES Technologies GmbH);Andreas Koch (Technical University of Darmstadt) Paper . Abstract . Lightning Talk |
| SEER: Super-Optimization Explorer for High-Level Synthesis using E-graph Rewriting Jianyi Cheng (University of Cambridge and Intel); Samuel Coward (Imperial College London and Intel); Lorenzo Chelini, Rafael Barbalho, and Theo Drane (Intel) Paper . Abstract . Lightning Talk |
| HIDA: A Hierarchical Dataflow Compiler for High-Level Synthesis Hanchen Ye, Hyegang Jun, and Deming Chen (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| 1B: Optimizing ML Communication (Location: Grande C) Session Chair: Roshan Dathathri (Microsoft Research) |
|---|
| TCCL: Discovering Better Communication Paths for PCIe GPU Clusters Heehoon Kim, Junyeol Ryu, and Jaejin Lee (Seoul National University) Paper . Abstract . Lightning Talk |
| [Best Paper] Centauri: Enabling Efficient Scheduling for Communication-Computation Overlap in Large Model Training via Communication Partitioning Chang Chen, Xiuhong Li, and Qianchao Zhu (Peking University); Jiangfei Duan (Chinese University of Hong Kong); Peng Sun and Xingcheng Zhang (Shanghai AI Lab); Chao Yang (Peking University) Paper . Abstract . Lightning Talk |
| T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives Suchita Pati (University of Wisconsin-Madison and AMD); Shaizeen Aga, Mahzabeen Islam, and Nuwan Jayasena (AMD); Matthew D. Sinclair (University of Wisconsin-Madison and AMD) Paper . Abstract . Lightning Talk |
| Two-Face: Combining Collective and One-Sided Communication for Efficient Distributed SpMM Charles Block, Gerasimos Gerogiannis, and Charith Mendis (University of Illinois at Urbana-Champaign); Ariful Azad (Indiana University); Josep Torrellas (University of Illinois at Urbana-Champaign) Paper . Abstract . Lightning Talk |
| 1C: Case Studies and Experience (Location: Grande D/E) Session Chair: Akanksha Jain (Google) |
|---|
| A Quantitative Analysis and Guidelines of Data Streaming Accelerator in Modern Intel Xeon Scalable Processors Reese Kuper (University of Illinois at Urbana Champaign); Ipoom Jeong (University of Illinois Urbana-Champaign); Yifan Yuan, Ren Wang, Narayan Ranganathan, and Nikhil Rao (Intel Labs); Jiayu Hu (Tencent); Sanjay Kumar and Philip Lantz (Intel Labs); Nam Sung Kim (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| Thesios: Synthesizing Accurate Counterfactual I/O Traces from I/O Samples Phitchaya Mangpo Phothilimthana (Google DeepMind);Saurabh Kadekodi (Google);Soroush Ghodrati (University of California San Diego);Selene Moon (Google);Martin Maas (Google DeepMind) Paper . Abstract . Lightning Talk |
| A Journey of a 1,000 Kernels Begins with a Single Step: A Retrospective of Deep Learning on GPUs Michael Davies, Ian McDougall, Selvaraj Anandaraj, Deep Machchhar, Rithik Jain, and Karthikeyan Sankaralingam (University of Wisconsin-Madison) Paper . Abstract . Lightning Talk |
| Expanding Datacenter Capacity with DVFS Boosting: A safe and scalable deployment experience Leonardo Piga, Iyswarya Narayanan, Aditya Sundarrajan, Matt Skach, and Qingyuan Deng (Meta); Biswadip Maity (University of California Irvine); Manoj Chakkaravarthy, Alison Huang, Abhishek Dhanotia, and Parth Malani (Meta) Paper . Abstract . Lightning Talk |
| 1D: Attacks and Mitigations (Location: Scripps I/II) Session Chair: Moumita Dey (AMD Research and Advanced Development) |
|---|
| Rubix: Reducing the Overhead of Secure Rowhammer Mitigations via Randomized Line-to-Row Mapping Anish Saxena, Saurav Mathur, and Moinuddin Qureshi (Georgia Tech) Paper . Abstract . Lightning Talk |
| TAROT: A CXL SmartNIC-Based Defense Against Multi-bit Errors by Row-Hammer Attacks Chihun Song (University of Illinois Urbana-Champaign); Michael Jaemin Kim (Seoul National University); Tianchen Wang, Houxiang Ji, Jinghan Huang, and Ipoom Jeong (University of Illinois Urbana-Champaign); Jaehyun Park, Hwayong Nam, Minbok Wi, and Jung Ho Ahn (Seoul National University); Nam Sung Kim (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| Pythia: Compiler-Guided Defense Against Non-Control Data Attacks Sharjeel Khan, Bodhisatwa Chatterjee, and Santosh Pande (Georgia Tech) Paper . Abstract . Lightning Talk |
| Everywhere All at Once: Co-Location Attacks on Public Cloud FaaS Zirui Neil Zhao (University of Illinois Urbana-Champaign); Adam Morrison (Tel Aviv University); Christopher W. Fletcher and Josep Torrellas (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
13:00 PDT – 14:30 PDT: Lunch
14:30 PDT – 15:30 PDT: Session 2
| 2A: Binary Analysis (Location: Grande A/B) Session Chair: Tapti Palit (Purdue University) |
|---|
| Plankton: Reconciling Binary Code and Debug Information Anshunkang Zhou and Chengfeng Ye (The Hong Kong University of Science and Technology); Heqing Huang (City University of Hong Kong); Yuandao Cai and Charles Zhang (The Hong Kong University of Science and Technology) Paper . Abstract . Lightning Talk |
| What You Trace is What You Get: Dynamic Stack-Layout Recovery for Binary Recompilation Fabian Parzefall, Chinmay Deshpande, Felicitas Hetzelt, and Michael Franz (University of California Irvine) Paper . Abstract . Lightning Talk |
| Accurate Disassembly of Complex Binaries Without Use of Compiler Metadata Soumyakant Priyadarshan, Huan Nguyen, and R. Sekar (Stony Brook University) Paper . Abstract . Lightning Talk |
| FITS: Inferring Intermediate Taint Sources for Effective Vulnerability Analysis of IoT Device Firmware Puzhuo Liu (Chinese Academy of Sciences); Yaowen Zheng (Nanyang Technological University); Chengnian Sun (University of Waterloo); Chuan Qin, Dongliang Fang, Mingdong Liu, and Limin Sun (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |
| 2B: Side Channels (Location: Grande C) Session Chair: Sadullah Canakci (Advanced Micro Devices) |
|---|
| Avoiding Instruction-Centric Microarchitectural Timing Channels Via Binary-Code Transformations Michael Flanders, Reshabh K Sharma, Alexandra E. Michael, Dan Grossman, and David Kohlbrenner (University of Washington) Paper . Abstract . Lightning Talk |
| Last-Level Cache Side-Channel Attacks Are Feasible in the Modern Public Cloud Zirui Neil Zhao (University of Illinois Urbana-Champaign); Adam Morrison (Tel Aviv University); Christopher W. Fletcher and Josep Torrellas (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| Pathfinder: High-Resolution Control-Flow Attacks Exploiting the Conditional Branch Predictor Hosein Yavarzadeh and Archit Agarwal (University of California San Diego); Max Christman (University of North Carolina at Chapel Hill); Christina Garman (Purdue University); Daniel Genkin (Georgia Tech); Andrew Kwong (University of North Carolina at Chapel Hill); Daniel Moghimi (Google); Deian Stefan (University of California San Diego); Kazem Taram (Purdue University); Dean Tullsen (University of California San Diego) Paper . Abstract . Lightning Talk |
| Pentimento: Data Remanence in Cloud FPGAs Colin Drewes (Stanford University); Olivia Weng and Andres Meza (University of California San Diego); Alric Althoff (ARM); David Kohlbrenner (University of Washington); Ryan Kastner (University of California San Diego); Dustin Richmond (University of California Santa Cruz) Paper . Abstract . Lightning Talk |
| 2C: Memory Optimizations (Location: Grande D/E) Session Chair: Christian Pinto (IBM Research Europe) |
|---|
| Kimbap: A Node-Property Map System for Distributed Graph Analytics Hochan Lee (University of Texas at Austin); Roshan Dathathri (Microsoft Research); Keshav Pingali (University of Texas at Austin) Paper . Abstract . Lightning Talk |
| TrackFM: Far-out Compiler Support for a Far Memory World Brian R. Tauro (Illinois Institute of Technology); Brian Suchy, Simone Campanoni, and Peter Dinda (Northwestern University); Kyle C. Hale (Illinois Institute of Technology) Paper . Abstract . Lightning Talk |
| Scaling Up Memory Disaggregated Applications with SMART (Recorded Talk) Feng Ren, Mingxing Zhang, and Kang Chen (Tsinghua University); Huaxia Xia (Meituan); Zuoning Chen (Chinese Academy of Engineering); Yongwei Wu (Tsinghua University) Paper . Abstract . Lightning Talk |
| CC-NIC: a Cache-Coherent Interface to the NIC Henry N. Schuh and Arvind Krishnamurthy (Google and University of Washington); David Culler (Google); Henry M. Levy (Google and University of Washington); Luigi Rizzo (Google); Samira Khan (Google and University of Virginia); Brent E. Stephens (Google and University of Utah) Paper . Abstract . Lightning Talk |
| 2D: ML Inference Systems (Location: Scripps I/II) Session Chair: Charith Mendis (University of Illinois at Urbana-Champaign) |
|---|
| SpecInfer: Accelerating Large Language Model Serving with Tree-based Speculative Inference and Verification Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, and Zeyu Wang (Carnegie Mellon University); Zhengxin Zhang (Tsinghua University); Rae Ying Yee Wong (Stanford University); Alan Zhu and Lijie Yang (Carnegie Mellon University); Xiaoxiang Shi (Shanghai Jiao Tong University); Chunan Shi (Peking University); Zhuoming Chen and Daiyaan Arfeen (Carnegie Mellon University); Reyna Abhyankar (University of California San Diego); Zhihao Jia (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
| ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference Hyungjun Oh, Kihong Kim, Jaemin Kim, Sungkyun Kim, and Junyeol Lee (Hanyang University); Du-seong Chang (KT Corporation); Jiwon Seo (Hanyang University) Paper . Abstract . Lightning Talk |
| Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling Sohaib Ahmad and Hui Guan (University of Massachusetts Amherst); Brian D. Friedman and Thomas Williams (Nokia Bell Labs); Ramesh K. Sitaraman (University of Massachusetts Amherst); Thomas Woo (Nokia Bell Labs) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] SpotServe: Serving Generative Large Language Models on Preemptible Instances Xupeng Miao (Carnegie Mellon University); Chunan Shi (Peking University); Jiangfei Duan (The Chinese University of Hong Kong); Xiaoli Xi (Carnegie Mellon University); Dahua Lin (Chinese University of Hong Kong and Sensetime Research); Bin Cui (Peking University);Zhihao Jia (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
15:30 PDT – 16:00 PDT: Break
16:00 PDT – 17:00 PDT: Session 3
| 3A: Dynamic Analysis and Instrumentation (Location: Grande A/B) Session Chair: Sangeeta Chowdhary (AMD Research) |
|---|
| Flexible Non-intrusive Dynamic Instrumentation for WebAssembly Ben L. Titzer, Elizabeth Gilbert, Bradley Wei Jie Teo, Yash Anand, Kazuyuki Takayama, and Heather Miller (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
| ShapleyIQ: Influence Quantification by Shapley Values for Performance Debugging of Microservices Ye Li, Jian Tan, Bin Wu, Xiao He, and Feifei Li (Alibaba) Paper . Abstract . Lightning Talk |
| Loupe: Driving the Development of OS Compatibility Layers Hugo Lefeuvre (University of Manchester); Gaulthier Gain (University of Liege); Vlad-Andrei Bădoiu and Daniel Dinca (University Politehnica of Bucharest); Vlad-Radu Schiller (University of Manchester); Costin Raiciu (University Politehnica of Bucharest); Felipe Huici (Unikraft.io); Pierre Olivier (University of Manchester) Paper . Abstract . Lightning Talk |
| Amanda: Unified Instrumentation Framework for Deep Neural Networks Yue Guan, Yuxian Qiu, and Jingwen Leng (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute);Fan Yang (Microsoft Research);Shuo Yu (Shanghai Jiao Tong University);Yunxin Liu (Tsinghua University);Yu Feng and Yuhao Zhu (University of Rochester);Lidong Zhou (Microsoft Research);Yun Liang (Peking University);Chen Zhang, Chao Li, and Minyi Guo (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| 3B: Security (Location: Grande C) Session Chair: Tal Garfinkel (UC San Deigo) |
|---|
| [Best Paper] GIANTSAN: Efficient Memory Sanitization with Segment Folding Hao Ling (The Hong Kong University of Science and Technology); Heqing Huang (City University of Hong Kong); Chengpeng Wang, Yuandao Cai, and Charles Zhang (The Hong Kong University of Science and Technology) Paper . Abstract . Lightning Talk |
| Enforcing C/C++ Type and Scope at Runtime for Control-Flow and Data-Flow Integrity Mohannad Ismail and Christopher Jelesnianski (Virginia Tech);Yeongjin Jang (Samsung Research America);Changwoo Min (Igalia);Wenjie Xiong (Virginia Tech) Paper . Abstract . Lightning Talk |
| Lightweight Fault Isolation: Practical, Efficient, and Secure Software Sandboxing Zachary Yedidia (Stanford University) Paper . Abstract . Lightning Talk |
| FreePart: Hardening Data Processing Software via Framework-based Partitioning and Isolation Ali Ahad (University of Virginia);Gang Wang (University of Illinois at Urbana-Champaign);Chung Hwan Kim (University of Texas at Dallas);Suman Jana (Columbia University);Zhiqiang Lin (Ohio State University);Yonghwi Kwon (University of Virginia) Paper . Abstract . Lightning Talk |
| 3C: ML Cluster Scheduling (Location: Grande D/E) Session Chair: Jingweng Leng (Shanghai Jiao Tong University) |
|---|
| DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads Seah Kim (University of California Berkeley); Hyoukjun Kwon (University of California Irvine); Jinook Song, Jihyuck Jo, Yu-Hsin Chen, Liangzhen Lai, and Vikas Chandra (Meta) Paper . Abstract . Lightning Talk |
| SoCFlow: Efficient and Scalable DNN Training on SoC-Clustered Edge Servers Daliang Xu (Peking University); Mengwei Xu (State Key Laboratory of Networking and Switching Technology); Chiheng Lou (Peking University); Li Zhang (State Key Laboratory of Networking and Switching Technology); Gang Huang, Xin Jin, and Xuanzhe Liu (Peking University) Paper . Abstract . Lightning Talk |
| Training Job Placement in Clusters with Statistical In-Network Aggregation Bohan Zhao and Wei Xu (Tsinghua University); Shuo Liu, Yang Tian, and Qiaoling Wang (Huawei); Wenfei Wu (Peking University) Paper . Abstract . Lightning Talk |
| RAP: Resource-aware Automated GPU Sharing for Multi-GPU Recommendation Model Training and Input Preprocessing Zheng Wang (University of California San Diego); Yuke Wang and Jiaqi Deng (University of California Santa Barbara); Da Zheng (Amazon); Ang Li (Pacific Northwest National Laboratory); Yufei Ding (University of California San Diego) Paper . Abstract . Lightning Talk |
| 3D: ML Quantization and Memory Optimizations (Location: Scripps I/II) Session Chair: Kiwan Maeng (Pennsylvania State University) |
|---|
| MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN Renze Chen (Peking University); Zijian Ding (University of California Los Angeles); Size Zheng and Chengrui Zhang (Peking University); Jingwen Leng (Shanghai Jiao Tong University); Xuanzhe Liu and Yun Liang (Peking University) Paper . Abstract . Lightning Talk |
| 8-bit Transformer Inference and Fine-tuning for Edge Accelerators Jeffrey Yu, Kartik Prabhu, Yonatan Urman, Robert M. Radway, Eric Han, and Priyanka Raina (Stanford University) Paper . Abstract . Lightning Talk |
| Cocco: Hardware-Mapping Co-Exploration towards Memory Capacity-Communication Optimization Zhanhong Tan, Zijian Zhu, and Kaisheng Ma (Tsinghua University) Paper . Abstract . Lightning Talk |
| Atalanta: A Bit is Worth a “Thousand” Tensor Values Alberto Delmas Lascorz and Mostafa Mahmoud (University of Toronto); Ali Hadi Zadeh (University of Toronto and 1QBit); Milos Nikolic, Kareem Ibrahim, and Christina Giannoula (University of Toronto); Ameer Abdelhadi (McMaster University); Andreas Moshovos (University of Toronto and Vector Institute) Paper . Abstract . Lightning Talk |
17:00 PDT – 18:00 PDT: Break
18:00 PDT – 18:50 PDT: Debate (Location: Grande)
Topic: Should everyone work on machine learning/AI?
AI has made incredible strides of late, thanks to foundational advances in both ML algorithms and hardware. As AI continues to revolutionize more of our lives, should everyone in the ASPLOS community switch to working on topics in AI? Why should we look at other problems when we could help AI improve so it can solve them instead?
| Speakers | Team |
|---|---|
| Amir Yazdanbaksh (Google DeepMind), Vijay Janapa Reddi (Harvard) and Charith Mendis (UIUC) | Yes |
| Tamar Eilam (IBM), Moin Qureshi (Georgia Tech) and Josep Torrellas (UIUC) | No |
18:50 PDT – 19:00 PDT: Break
19:00 PDT – 19:50 PDT: WACI (Location: Grande)
| Title | Speaker(s) |
|---|---|
| Computing Foundations: Knitting Together a WACI Purl | Zachary Tatlock (University of Washington) |
| BoltBleed – Security from an Aerial Perspective | Guy Wilks (UC Santa Barbara) |
| Apparate?: Evading Memory Hierarchy with GodSpeed Wireless on Chip | Nitesh Narayana Gondlyala Sathya and Abhijit Das (Universitat Politècnica de Catalunya Barcelona) |
| Bureaucracy in Systems | Michael Roitzsch (Barkhausen Institut) |
| BRAINSTORM: Supercharging Innovation with AI-Driven Ideation | Deniz Altınbüken, Martin Maas, Phitchaya Mangpo Phothilimthana (Google DeepMind) |
19:50 PDT – 20:00 PDT: Break
20:00 PDT – 21:00 PDT: Business Meeting (Location: Grande)
- ASPLOS’24 Budget and Stats (Nael Abu-Ghazaleh & Rajiv Gupta)
- ASPLOS’24 Program Recap and Stats (Madan Musuvathi & Dan Tsafrir)
- CARES (Shan Lu)
- Revival of TOCS (Shan Lu)
- ASPLOS’25 Plans
- Plans for the program (PC Chairs: Martha Kim, Chris Rossbach, Adrian Sampson)
- Plans for the venue (GC Chair: Lieven Eeckhout)
- ASPLOS’26 Looking for bids (Shan Lu)
- ISCA’26 Looking for bids (Natalie Enright Jerger & Daniel Jiménez)
Day 2: Tuesday, April 30
7:30 PDT – 8:30 PDT: Breakfast
8:30 PDT – 9:30 PDT: Keynote 2 by Emmett Witchel (University of Texas at Austin) (Location: Grande)
| Challenges and Opportunities for Systems Using CXL Memory |
| Abstract We are at the start of the technology cycle for compute express link (CXL) memory, which is a significant opportunity and challenge for architecture, operating systems, and programming languages. The 3.0 CXL specification allows multiple, physically attached hosts to dynamically share memory. We call such a configuration a CXL pod. Pods provide an intermediate hardware configuration between a network of machines, each with their private memory, and a shared memory multiprocessor with a unified memory, accessible to all machines. This talk will discuss system support for single-node applications to attain scalable performance and high availability across a CXL pod as well as pointing out likely technical challenges for future systems. Along with the technical content, the talk categorizes computer systems research using the model of storytelling with a beginning, a middle and an end. We also examine the fascination popular culture has with personal aha moments and weigh their importance for a group working on an impending submission deadline. |
| Bio Emmett Witchel is Professor of Computer Science at the University of Texas at Austin, where he has been on the faculty since 2004, after receiving his PhD at MIT. His thesis won honorable mention for the ACM doctoral dissertation award. Witchel’s research interests include operating systems, security, architecture, and concurrency. His recent work has been on system support for CXL memory, serverless computing, persistent memory, and trusted execution environments. He co-chaired ASPLOS in 2019. His publishing recognition includes best paper awards at both SOSP and OSDI, as well as IEEE Micro top picks and research highlights in Communications of the ACM (CACM). He is a fellow of the ACM. |
9:30 PDT – 10:00 PDT: Break
10:00 PDT – 11:15 PDT: Session 4
| 4A: Accelerators (Location: Grande C) Session Chair: Minsoo Rhu (KAIST) |
|---|
| Harp: Leveraging Quasi-Sequential Characteristics to Accelerate Sequence-to-Graph Mapping of Long Reads Yichi Zhang, Dibei Chen, Gang Zeng, and Jianfeng Zhu (Tsinghua University); Zhaoshi Li (MetaX Integrated Circuits); Longlong Chen, Shaojun Wei, and Leibo Liu (Tsinghua University) Paper . Abstract . Lightning Talk |
| GSCore: Efficient Radiance Field Rendering via Architectural Support for 3D Gaussian Splatting Junseo Lee, Seokwon Lee, Jungi Lee, Junyong Park, and Jaewoong Sim (Seoul National University) Paper . Abstract . Lightning Talk |
| BeeZip: Towards An Organized and Scalable Architecture for Data Compression Ruihao Gao, Zhichun Li, Guangming Tan, and Xueqi Li (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |
| ACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations Xiaoyang Lu (Illinois Institute of Technology); Boyu Long, Xiaoming Chen, and Yinhe Han (Chinese Academy of Sciences); Xian-He Sun (Illinois Institute of Technology) Paper . Abstract . Lightning Talk |
| Explainable-DSE: An Agile and Explainable Exploration of Efficient HW/SW Codesigns of Deep Learning Accelerators Using Bottleneck Analysis Shail Dave (Arizona State University); Tony Nowatzki (University of California Los Angeles); Aviral Shrivastava (Arizona State University) Paper . Abstract . Lightning Talk |
| 4B: Serverless Computing 1 (Location: Grande D/E) Session Chair: Chris Rossbach (University of Texas at Austin and Katana Graph) |
|---|
| λFS:: A Scalable and Elastic Distributed File System Metadata Service using Serverless Functions Benjamin Carver (George Mason University); Runzhou Han (Iowa State University); Jingyuan Zhang (George Mason University); Mai Zheng (Iowa State University); Yue Cheng (University of Virginia) Paper . Abstract . Lightning Talk |
| FaaSMem: Improving Memory Efficiency of Serverless Computing with Memory Pool Architecture Chuhao Xu, Yiyu Liu, Zijun Li, Quan Chen, and Han Zhao (Shanghai Jiao Tong University); Deze Zeng (China University of Geosciences); Qian Peng, Xueqi Wu, Haifeng Zhao, and Senbo Fu (Huawei);Minyi Guo (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| CodeCrunch: Improving Serverless Performance via Function Compression and Cost-Aware Warmup Location Optimization Rohan Basu Roy (Northeastern University); Tirthak Patel (Rice University); Rohan Garg (Nutanix); Devesh Tiwari (Northeastern University) Paper . Abstract . Lightning Talk |
| RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing Hanfei Yu (Louisiana State University); Rohan Basu Roy (Northeastern University); Christian Fontenot (Louisiana State University); Devesh Tiwari (Northeastern University); Jian Li (Stony Brook University); Hong Zhang (University of Waterloo); Hao Wang (Louisiana State University); Seung-Jong Park (Missouri University of Science and Technology) Paper . Abstract . Lightning Talk |
| Flame: A Centralized Cache Controller for Serverless Computing (Recorded Talk) Yanan Yang, Laiping Zhao, Yiming Li, and Shihao Wu (Tianjin University); Yuechan Hao and Yuchi Ma (Huawei); Keqiu Li (Tianjin University) Paper . Abstract . Lightning Talk |
| 4C: Power and Energy (Location: Scripps I) Session Chair: Christina Delimitrou (MIT) |
|---|
| Characterizing Power Management Opportunities for LLMs in the Cloud Pratyush Patel (Microsoft Azure and University of Washington); Esha Choukse, Chaojie Zhang, Íñigo Goiri, Brijesh Warrier, Nithish Mahalingam, and Ricardo Bianchini (Microsoft Azure) Paper . Abstract . Lightning Talk |
| Going Green for Less Green: Optimizing the Cost of Reducing Cloud Carbon Emissions Walid A. Hanafy and Qianlin Liang (University of Massachusetts Amherst); Noman Bashir (MIT); Abel Souza, David Irwin, and Prashant Shenoy (University of Massachusetts Amherst) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] FOCAL: A First-Order Carbon Model to Assess Processor Sustainability (Recorded Talk) Lieven Eeckhout (Ghent University) Paper . Abstract . Lightning Talk |
| Predict; Don’t React for Enabling Efficient Fine-Grain DVFS in GPUs Srikant Bharadwaj (Microsoft); Shomit Das (Qualcomm); Kaushik Mazumdar and Bradford M. Beckmann (AMD); Stephen Kosonocky (Uhnder) Paper . Abstract . Lightning Talk |
| SUIT: Secure Undervolting with Instruction Traps Jonas Juffinger (Graz University of Technology); Stepan Kalinin (North Carolina State University); Daniel Gruss (Graz University of Technology); Frank Mueller (North Carolina State University) Paper . Abstract . Lightning Talk |
| 4D: Static Analysis and Verification (Location: Scripps II) Session Chair: Shan Lu (Microsoft Research) |
|---|
| Kaleidoscope: Precise Invariant-Guided Pointer Analysis Tapti Palit and Pedro Fonseca (Purdue University) Paper . Abstract . Lightning Talk |
| Lifting Micro-Update Models from RTL for Formal Security Analysis Adwait Godbole and Kevin Cheang (University of California Berkeley); Yatin A. Manerkar (University of Michigan); Sanjit A. Seshia (University of California Berkeley) Paper . Abstract . Lightning Talk |
| Formal Mechanised Semantics of CHERI C: Capabilities, Undefined Behaviour, and Provenance Vadim Zaliva and Kayvan Memarian (University of Cambridge); Ricardo Almeida (University of Edinburgh); Jessica Clarke (University of Cambridge); Brooks Davis (SRI International); Alexander Richardson (University of Cambridge); David Chisnall (Microsoft); Brian Campbell and Ian Stark (University of Edinburgh); Robert N. M. Watson and Peter Sewell (University of Cambridge) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] Lightweight, Modular Verification for WebAssembly-to-Native Instruction Selection Alexa VanHattum (Wellesley College); Monica Pardeshi (Carnegie Mellon University); Chris Fallin (Fastly); Adrian Sampson (Cornell University); Fraser Brown (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
| Verifying Rust Implementation of Page Tables in a Software Enclave Hypervisor Zhenyang Dai (Tsinghua University and Ant Group); Shuang Liu (Ant Group); Vilhelm Sjoberg (CertiK); Xupeng Li (Columbia University); Yu Chen (Tsinghua University); Wenhao Wang (Chinese Academy of Sciences); Yuekai Jia (Tsinghua University and Ant Group); Sean Noble Anderson (Portland State University); Laila Elbeheiry (Max Planck Institute for Software Systems); Shubham Sondhi (CertiK); Yu Zhang (Yale University); Zhaozhong Ni (CertiK); Shoumeng Yan (Ant Group); Ronghui Gu (Columbia University); Zhengyu He (Ant Group) Paper . Abstract . Lightning Talk |
11:15 PDT – 11:45 PDT: Break
11:45 PDT – 13:00 PDT: Session 5
| 5A: Compiler and Optimization Techniques (Location: Grande C) Session Chair: Gilbert Bernstein (University of Washington) |
|---|
| C4CAM: A Compiler for CAM-based In-memory Accelerators Hamid Farzaneh and Joao Paulo Cardoso De Lima (TU Dresden); Mengyuan Li (University of Notre Dame); Asif Ali Khan (TU Dresden); Xiaobo Sharon Hu (University of Notre Dame); Jeronimo Castrillon (TU Dresden) Paper . Abstract . Lightning Talk |
| BaCO: A Fast and Portable Bayesian Compiler Optimization Framework Erik Orm Hellsten (Lund University);Artur Souza (Federal University of Minas Gerais); Johannes Lenfers (University of Münster); Rubens Lacouture and Olivia Hsu (Stanford University);Adel Ejjeh (University of Illinois at Urbana-Champaign); Fredrik Kjolstad (Stanford University); Michel Steuwer (University of Edinburgh); Kunle Olukotun (Stanford University); Luigi Nardi (Lund University and Stanford University) Paper . Abstract . Lightning Talk |
| Merlin: Multi-tier Optimization of eBPF Code for Performance and Compactness Jinsong Mao (University of Massachusetts Amherst); Hailun Ding (Rutgers University); Juan Zhai and Shiqing Ma (University of Massachusetts Amherst) Paper . Abstract . Lightning Talk |
| [Best Paper] Automatic Generation of Vectorizing Compilers for Customizable Digital Signal Processors Samuel Thomas and James Bornholt (University of Texas at Austin) Paper . Abstract . Lightning Talk |
| Fast Instruction Selection for Fast Digital Signal Processing Alexander J Root (Stanford University); Maaz Bin Safeer Ahmad (Adobe); Dillon Sharlet (Independent Researcher); Andrew Adams and Shoaib Kamil (Adobe); Jonathan Ragan-Kelley (MIT CSAIL) Paper . Abstract . Lightning Talk |
| 5B: Emerging and Non-Traditional Technologies (Location: Grande D/E) Session Chair: Sara Achour (Stanford University) |
|---|
| An Encoding Scheme to Enlarge Practical DNA Storage Capacity by Reducing Primer-Payload Collisions Yixun Wei (University of Minnesota Twin Cities); Bingzhe Li (University of Texas at Dallas); David H.C. Du (University of Minnesota Twin Cities) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] Design of Novel Analog Compute Paradigms with Ark Yu-Neng Wang (Stanford University); Glenn Cowan (Concordia University); Ulrich Rührmair (TU Berlin and University of Connecticut); Sara Achour (Stanford University) Paper . Abstract . Lightning Talk |
| LightRidge: An End-to-end Agile Design Framework for Diffractive Optical Neural Networks Yingjie Li (University of Utah and University of Maryland); Ruiyang Chen, Minhan Lou, Berardi Sensale-Rodriguez, and Weilu Gao (University of Utah); Cunxi Yu (University of Utah and University of Maryland) Paper . Abstract . Lightning Talk |
| EagleEye: Nanosatellite constellation design for high-coverage, high-resolution sensing Zhuo Cheng, Bradley Denby, Kyle McCleary, and Brandon Lucia (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
| Energy Efficient Convolutions with Temporal Arithmetic Rhys Gretsch and Peiyang Song (University of California Santa Barbara); Advait Madhavan (University of Maryland College Park); Jeremy Lau and Timothy Sherwood (University of California Santa Barbara) Paper . Abstract . Lightning Talk |
| 5C: Memory: Allocation and Management (Location: Scripps I) Session Chair: Martin Maas (Google) |
|---|
| Getting a Handle on Unmanaged Memory Nick Wanninger, Tommy McMichen, Simone Campanoni, and Peter Dinda (Northwestern University) Paper . Abstract . Lightning Talk |
| Cornucopia Reloaded: Load Barriers for CHERI Heap Temporal Safety Nathaniel Wesley Filardo (University of Cambridge and Microsoft); Brett F. Gutstein, Jonathan Woodruff, Jessica Clarke, and Peter Rugg (University of Cambridge);Brooks Davis (SRI International);Mark Johnston (University of Cambridge);Robert Norton (Microsoft);David Chisnall (SCI Semiconductor); Simon W. Moore (University of Cambridge); Peter G. Neumann (SRI International); Robert N. M. Watson (University of Cambridge) Paper . Abstract . Lightning Talk |
| Characterizing a Memory Allocator at Warehouse Scale Zhuangzhuang Zhou (Cornell University); Vaibhav Gogte, Nilay Vaish, Chris Kennelly, Patrick Xia, Svilen Kanev, and Tipp Moseley (Google); Christina Delimitrou (MIT); Parthasarathy Ranganathan (Google) Paper . Abstract . Lightning Talk |
| More Apps, Faster Hot-Launch on Mobile Devices via Fore/Background-aware GC-Swap Co-design Jiacheng Huang (City University of Hong Kong and Wuhan University); Yunmo Zhang and Junqiao Qiu (City University of Hong Kong); Yu Liang (ETH Zürich); Rachata Ausavarungnirun (King Mongkut’s University of Technology North Bangkok); Qingan Li (Wuhan University); Chun Jason Xue (Mohamed bin Zayed University of Artificial Intelligence) Paper . Abstract . Lightning Talk |
| MiniMalloc: A Lightweight Memory Allocator for Hardware-Accelerated Machine Learning Michael D. Moffitt (Google) Paper . Abstract . Lightning Talk |
| 5D: Quantum Architecture (Location: Scripps II) Session Chair: Gokul Ravi (University of Michigan, Ann Arbor) |
|---|
| Codesign of quantum error-correcting codes and modular chiplets in the presence of defects Sophia Fuhui Lin and Joshua Viszlai (University of Chicago); Kaitlin N. Smith (Infleqtion); Gokul Subramanian Ravi (University of Chicago); Charles Yuan (MIT CSAIL); Frederic T. Chong (University of Chicago); Benjamin J. Brown (IBM T. J. Watson Research Center) Paper . Abstract . Lightning Talk |
| MECH: Multi-Entry Communication Highway for Superconducting Quantum Chiplets Hezi Zhang and Keyi Yin (University of California San Diego); Anbang Wu (University of California Santa Barbara); Hassan Shapourian and Alireza Shabani (Cisco Quantum Lab); Yufei Ding (University of California San Diego) Paper . Abstract . Lightning Talk |
| QuFEM: Fast and Accurate Quantum Readout Calibration Using the Finite Element Method Siwei Tan, Liqiang Lu, Hanyu Zhang, Jia Yu, Congliang Lang, Yongheng Shang, Xinkui Zhao, and Mingshuai Chen (Zhejiang University); Yun Liang (Peking University); Jianwei Yin (Zhejiang University) Paper . Abstract . Lightning Talk |
| A Fault-Tolerant Million Qubit-Scale Distributed Quantum Computer Junpyo Kim, Dongmoon Min, Jungmin Cho, Hyeonseong Jeong, Ilkwon Byun, Junhyuk Choi, Juwon Hong, and Jangwoo Kim (Seoul National University) Paper . Abstract . Lightning Talk |
| Promatch: Extending the Reach of Real-Time Quantum Error Correction with Adaptive Predecoding Narges Alavisamani, Suhas Vittal, and Ramin Ayanzadeh (Georgia Tech); Poulami Das (University of Texas at Austin); Moinuddin Qureshi (Georgia Tech) Paper . Abstract . Lightning Talk |
13:00 PDT – 14:30 PDT: Lunch
14:30 PDT – 15:30 PDT: Session 6
| 6A: Bug Finding and Testing (Location: Grande C) Session Chair: Sangeeta Chowdhary (AMD Research) |
|---|
| Greybox Fuzzing for Concurrency Testing Dylan Wolff, Shi Zheng, Gregory J. Duck, Umang Mathur, and Abhik Roychoudhury (National University of Singapore) Paper . Abstract . Lightning Talk |
| Multi-Dimensional and Message-Guided Fuzzing for Robotic Programs in Robot Operating System (Speaker Zhenyang Dai) Jia-Ju Bai (Beihang University); Hao-Xuan Song and Shi-Min Hu (Tsinghua University) Paper . Abstract . Lightning Talk |
| [Best Paper] CSSTs: A Dynamic Data Structure for Partial Orders in Concurrent Execution Analysis Hünkar Can Tunç (Aarhus University);Ameya Prashant Deshmukh (Indian Institute of Technology Bombay); Berk Cirisci (Amazon Web Services); Constantin Enea (Ecole Polytechnique); Andreas Pavlogiannis (Aarhus University) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] UBFuzz: Finding Bugs in Sanitizer Implementations Shaohua Li and Zhendong Su (ETH Zurich) Paper . Abstract . Lightning Talk |
| 6B: Processing-In-Memory (PIM) for ML (Location: Grande D/E) Session Chair: Christina Giannoula (University of Toronto) |
|---|
| AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference Jaehyun Park, Jaewan Choi, Kwanhee Kyung, Michael Jaemin Kim, and Yongsuk Kwon (Seoul National University); Nam Sung Kim (University of Illinois Urbana-Champaign); Jung Ho Ahn (Seoul National University) Paper . Abstract . Lightning Talk |
| SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration Cong Li, Zhe Zhou, Size Zheng, Jiaxi Zhang, Yun Liang, and Guangyu Sun (Peking University) Paper . Abstract . Lightning Talk |
| PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization Cong Li and Zhe Zhou (Peking University); Yang Wang (Microsoft Research Asia); Fan Yang (Nankai University); Ting Cao and Mao Yang (Microsoft Research); Yun Liang and Guangyu Sun (Peking University) Paper . Abstract . Lightning Talk |
| NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing Guseul Heo, Sangyeop Lee, Jaehong Cho, Hyunmin Choi, and Sanghyeon Lee (KAIST); Hyungkyu Ham and Gwangsun Kim (POSTECH); Divya Mahajan (Georgia Tech); Jongse Park (KAIST) Paper . Abstract . Lightning Talk |
| 6C: Optimization of Tensor Programs (Location: Scripps I) Session Chair: Mangpo Phothilimthana (Google DeepMind) |
|---|
| Felix: Optimizing Tensor Programs with Gradient Descent Yifan Zhao, Hashim Sharif, Vikram Adve, and Sasa Misailovic (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| Optimizing Deep Learning Inference via Global Analysis and Tensor Expressions Chunwei Xia, Jiacheng Zhao, and Qianqi Sun (Chinese Academy of Sciences); Zheng Wang (University of Leeds); Yuan Wen (University of Aberdeen); Teng Yu (Thewake Systems); Xiaobing Feng and Huimin Cui (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |
| PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation Jason Ansel, Edward Yang, and Horace He (Meta); Natalia Gimelshein (OpenAI); Animesh Jain, Michael Voznesensky, Bin Bao, David Berard, Geeta Chauhan, Anjali Chourdia, Will Constable, Alban Desmaison, Zachary DeVito, Elias Ellison, and Will Feng (Meta); Jiong Gong (Intel); Michael Gschwind, Brian Hirsh, Sherlock Huang, Laurent Kirsch, Michael Lazos, Yanbo Liang, Jason Liang, Yinghai Lu, CK Luk, and Bert Maher (Meta); Yunjie Pan (University of Michigan); Christian Puhrsch, Matthias Reso, Mark Saroufim, Helen Suk, and Michael Suo (Meta); Phil Tillet (OpenAI); Eikan Wang (Intel); Xiaodong Wang, William Wen, Shunting Zhang, and Xu Zhao (Meta); Keren Zhou (OpenAI); Richard Zou, Ajit Mathews, Gregory Chanan, Peng Wu, and Soumith Chintala (Meta) Paper . Abstract . Lightning Talk |
| Optimal Kernel Orchestration for Tensor Programs with Korch Muyan Hu (University of Illinois at Urbana-Champaign); Ashwin Venkatram (AMD); Shreyashri Biswas (Carnegie Mellon University); Balamurugan Marimuthu (Sambanova Systems); Bohan Hou and Gabriele Oliaro (Carnegie Mellon University); Haojie Wang and Liyan Zheng (Tsinghua University); Xupeng Miao (Carnegie Mellon University); Jidong Zhai (Tsinghua University); Zhihao Jia (Carnegie Mellon University) Paper . Abstract . Lightning Talk |
| 6D: Variational Quantum Computing (Location: Scripps II) Session Chair: Gushu Li (University of Pennsylvania) |
|---|
| Elivagar: Efficient Quantum Circuit Search for Classification Sashwat Anagolum (Pennsylvania State University); Narges Alavisamani (Georgia Tech); Poulami Das (The University of Texas at Austin); Moinuddin Qureshi (Georgia Tech); Yunong Shi (Amazon Quantum Technologies) Paper . Abstract . Lightning Talk |
| Red-QAOA: Efficient Variational Optimization through Circuit Reduction Meng Wang (University of British Columbia and Pacific Northwest National Laboratory); Bo Fang and Ang Li (Pacific Northwest National Laboratory); Prashant J. Nair (University of British Columbia) Paper . Abstract . Lightning Talk |
| VarSaw: Application-tailored Measurement Error Mitigation for Variational Quantum Algorithms Siddharth Dangwal (University of Chicago); Gokul Subramanian Ravi (University of Michigan); Poulami Das (University of Texas at Austin); Kaitlin N. Smith (Infleqtion); Jonathan Mark Baker (University of Texas at Austin); Frederic T. Chong (University of Chicago) Paper . Abstract . Lightning Talk |
| ProxiML: Building Machine Learning Classifiers for Photonic Quantum Computing Aditya Ranjan (Northeastern University); Tirthak Patel (Rice University); Daniel Silver, Harshitta Gandhi, and Devesh Tiwari (Northeastern University) Paper . Abstract . Lightning Talk |
15:30 PDT – 16:00 PDT: Break
16:00 PDT – 17:00 PDT: Session 7
| 7A: Architecture Support for ML (Location: Grande C) Session Chair: Hyoukjun Kwon (University of California, Irvine) |
|---|
| FEASTA: A Flexible and Efficient Accelerator for Sparse Tensor Algebra in Machine Learning Kai Zhong and Zhenhua Zhu (Tsinghua University); Guohao Dai (Shanghai Jiao Tong University and Infinigence-AI); Hongyi Wang, Xinhao Yang, and Haoyu Zhang (Tsinghua University); Jin Si (Beijing University of Posts and Telecommunications);Qiuli Mao (Tsinghua University); Shulin Zeng (Tsinghua University and Infinigence-AI); Ke Hong (Tsinghua University); Genghan Zhang (Stanford University); Huazhong Yang and Yu Wang (Tsinghua University) Paper . Abstract . Lightning Talk |
| CMC: Video Transformer Acceleration via CODEC Assisted Matrix Condensing (Speaker Qingyuan Liu) Zhuoran Song, Chunyu Qi, Fangxin Liu, Naifeng Jing, and Xiaoyao Liang (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| Tandem Processor: Grappling with Emerging Operators in Neural Networks Soroush Ghodrati, Sean Kinzer, Hanyang Xu, and Rohan Mahapatra (University of California San Diego); Yoonsung Kim (KAIST); Byung Hoon Ahn (University of California San Diego); Dong Kai Wang (University of Illinois Urbana-Champaign); Lavanya Karthikeyan (University of California San Diego); Amir Yazdanbakhsh (Google DeepMind); Jongse Park (KAIST); Nam Sung Kim (University of Illinois Urbana-Champaign); Hadi Esmaeilzadeh (University of California San Diego) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] Carat: Unlocking Value-Level Parallelism for Multiplier-Free GEMMs Zhewen Pan and Joshua San Miguel (University of Wisconsin-Madison);Di Wu (University of Central Florida) Paper . Abstract . Lightning Talk |
| 7B: Program and Configuration Synthesis (Location: Grande D/E) Session Chair: Tamara Lehman (University of Colorado, Boulder) |
|---|
| NetRen: Service Migration-Driven Network Renascence with Synthesizing Updated Configuration (Recorded Talk) Rongxin Han, Jingyu Wang, Qi Qi, Haifeng Sun, Chaowei Xu, Zhaoyang Wan, and Zirui Zhuang (Beijing University of Posts and Telecommunications);Yichuan Yu (Huawei); Jianxin Liao (Beijing University of Posts and Telecommunications) Paper . Abstract . Lightning Talk |
| Hydride: A Retargetable and Extensible Synthesis-based Compiler for Modern Hardware Architectures Akash Kothari, Abdul Rafae Noor, Muchen Xu, Hassam Uddin, Dhruv Baronia, Stefanos Baziotis, Vikram Adve, and Charith Mendis (University of Illinois at Urbana-Champaign);Sudipta Sengupta (Amazon Web Services) Paper . Abstract . Lightning Talk |
| RTL-Repair: Fast Symbolic Repair of Hardware Design Code Kevin Laeufer, Brandon Fajardo, Abhik Ahuja, Vighnesh Iyer, Borivoje Nikolić, and Koushik Sen (University of California Berkeley) Paper . Abstract . Lightning Talk |
| SIRO: Empowering Version Compatibility in Intermediate Representations via Program Synthesis Bowen Zhang and Wei Chen (The Hong Kong University of Science and Technology); Peisen Yao (Zhejiang University); Chengpeng Wang, Wensheng Tang, and Charles Zhang (The Hong Kong University of Science and Technology) Paper . Abstract . Lightning Talk |
| 7C: Storage Optimizations in Software (Location: Scripps I) Session Chair: Joseph Devietti (University of Pennsylvania) |
|---|
| MemSnap μCheckpoints: A Data Single Level Store for Fearless Persistence Emil Tsalapatis, Ryan Hancock, Rakeeb Hossain, and Ali José Mashtizadeh (University of Waterloo) Paper . Abstract . Lightning Talk |
| Grafu: Unleashing the Full Potential of Future Value Computation for Out-of-core Synchronous Graph Processing Tsun-Yu Yang (The Chinese University of Hong Kong); Cale England (Oklahoma State University); Yi Li and Bingzhe Li (University of Texas at Dallas); Ming-Chang Yang (The Chinese University of Hong Kong) Paper . Abstract . Lightning Talk |
| CrossPrefetch: Accelerating I/O Prefetching for Modern Storage Shaleen Garg and Jian Zhang (Rutgers University);Rekha Pitchumani (Samsung);Manish Parashar (University of Utah);Bing Xie (Microsoft);Sudarsun Kannan (Rutgers University) Paper . Abstract . Lightning Talk |
| Palantir: Hierarchical Similarity Detection for Post-Deduplication Delta Compression Hongming Huang (City University of Hong Kong and Huawei); Peng Wang (Huawei); Qiang Su (City University of Hong Kong); Hong Xu (The Chinese University of Hong Kong); Chun Jason Xue (City University of Hong Kong and Mohamed bin Zayed University of Artificial Intelligence); André Brinkmann (Johannes Gutenberg University Mainz) Paper . Abstract . Lightning Talk |
| 7D: Graph Neural Networks (Location: Scripps II) Session Chair: Xulong Tang (University of Pittsburgh) |
|---|
| TGLite: A Lightweight Programming Framework for Continuous-Time Temporal Graph Neural Networks Yufeng Wang and Charith Mendis (University of Illinois at Urbana-Champaign) Paper . Abstract . Lightning Talk |
| MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training Hongwu Peng and Xi Xie (University of Connecticut); Kaustubh Shivdikar (Northeastern University); Md Amit Hasan, Jiahui Zhao, Shaoyi Huang, and Omer Khan (University of Connecticut); David Kaeli (Northeastern University); Caiwen Ding (University of Connecticut) Paper . Abstract . Lightning Talk |
| Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures Kun Wu (University of Illinois at Urbana-Champaign); Mert Hidayetoğlu (Stanford University); Xiang Song (AWS AI); Sitao Huang (University of California Irvine); Da Zheng and Israt Nisa (AWS AI); Wen-Mei Hwu (Nvidia and University of Illinois at Urbana-Champaign) Paper . Abstract . Lightning Talk |
| Sleuth: A Trace-Based Root Cause Analysis System for Large-Scale Microservices with Graph Neural Networks Yu Gan, Guiyang Liu, Xin Zhang, Qi Zhou, Jiesheng Wu, and Jiangwei Jiang (Alibaba) Paper . Abstract . Lightning Talk |
17:00 PDT – 22:00 PDT: Excursion and Banquet at USS Midway Museum
The buses to the USS Midway Museum start departing from the entrance of the hotel at 5:15 pm and return from the banquet at 9:15 pm. The temperature will be 55oF, please dress accordingly.
Day 3: Wednesday, May 1
7:30 PDT – 8:30 PDT: Breakfast
8:30 PDT – 9:30 PDT: Keynote 3 by Tamar Eilam (IBM T. J. Watson Research Center) (Location: Grande)
| Harnessing the Power of Specialization for Sustainable Computing |
| Abstract Computing is critical to address some of the most pressing needs of humanity today, including climate change mitigation and adaptation. However, it is also the source of a significant and steadily increasing carbon toll, attributed in part to the exponential growth in energy-demanding workloads, such as artificial intelligence (AI). Due to the demise of Dennard scaling, we can no longer count on exponentially-improve energy efficiency of general-purpose processors. Therefore, today’s operational efficiency gains rely on specialized hardware. In this talk I will discuss the promise and the perils of harnessing specialization on the road to sustainable computing. |
| Bio Dr. Tamar Eilam is an IBM Fellow and Chief Scientist for Sustainable Computing in the IBM T. J. Watson Research Center, New York. Tamar is leading research aiming at drastically reducing the carbon footprint associated with computing across infrastructure, systems, and software, data and AI. Tamar complete a Ph.D. degree in Computer Science in the Technion, Israel, in 2000. She joined the IBM T.J. Watson Research Center in New York as a Research Staff Member that same year. She was recognized as an IBM Fellow in 2014. |
9:30 PDT – 10:00 PDT: Break
10:00 PDT – 11:15 PDT: Session 8
| 8A: Caching and Prefetching (Location: Grande C) Session Chair: Akanksha Jain (Google) |
|---|
| [Best Paper] PDIP: Priority Directed Instruction Prefetching Bhargav Reddy Godala (Princeton University);Sankara Prasad Ramesh (University of California San Diego); Gilles A. Pokam, Jared Stark, and Andre Seznec (Intel); Dean Tullsen (University of California San Diego); David I. August (Princeton University) Paper . Abstract . Lightning Talk |
| Limoncello: Prefetchers for Scale Akanksha Jain (Google); Hannah Lin (Google and University of Washington); Carlos Villavieja (Google);Baris Kasikci (Google and University of Washington); Chris Kennelly, Milad Hashemi, and Parthasarathy Ranganathan (Google) Paper . Abstract . Lightning Talk |
| PATHFINDER: Practical Real-Time Learning for Data Prefetching Lin Jia, James Patrick Mcmahon, Sumanth Gudaparthi, Shreyas Singh, and Rajeev Balasubramonian (University of Utah) Paper . Abstract . Lightning Talk |
| Skip It: Take Control of Your Cache! Shashank Anand and Michal Friedman (ETH Zurich);Michael Giardino (Huawei);Gustavo Alonso (ETH Zurich) Paper . Abstract . Lightning Talk |
| RPG^2: Robust Profile-Guided Runtime Prefetch Generation Yuxuan Zhang, Nathan Sobotka, and Soyoon Park (University of Pennsylvania);Saba Jamilan (University of California Santa Cruz);Tanvir Ahmed Khan (Columbia University);Baris Kasikci (University of Washington and Google);Gilles A Pokam (Intel);Heiner Litz (University of California Santa Cruz);Joseph Devietti (University of Pennsylvania) Paper . Abstract . Lightning Talk |
| 8B: Memory: Address Translation and Tiering (Location: Grande D/E) Session Chair: Jayneel Gandhi (Meta) |
|---|
| METAL: Caching Multi-level Indexes in Domain-Specific Architectures Anagha Molakalmur Anil Kumar and Aditya Prasanna (Simon Fraser University); Jonathan Balkind (University of California Santa Barbara); Arrvindh Shriraman (Simon Fraser University) Paper . Abstract . Lightning Talk |
| GMT: GPU Orchestrated Memory Tiering for the Big Data Era Chia-Hao Chang, Jihoon Han, and Anand Sivasubramaniam (Pennsylvania State University);Vikram Sharma Mailthody, Zaid Qureshi, and Wen-Mei Hwu (NVIDIA Research) Paper . Abstract . Lightning Talk |
| GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching Cong Guo (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Rui Zhang (Ant Group); Jiale Xu, Jingwen Leng, Zihan Liu, Ziyu Huang, and Minyi Guo (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Hao Wu, Shouren Zhao, Junping Zhao, and Ke Zhang (Ant Group) Paper . Abstract . Lightning Talk |
| Direct Memory Translation for Virtualized Clouds Jiyuan Zhang (University of Illinois Urbana-Champaign);Weiwei Jia (University of Rhode Island);Siyuan Chai, Peizhe Liu, Jongyul Kim, and Tianyin Xu (University of Illinois Urbana-Champaign) Paper . Abstract . Lightning Talk |
| WASP: Workload-Aware Self-Replicating Page-Tables for NUMA Servers Hongliang Qu and Zhibin Yu (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |
| 8C: High Performance Systems (Location: Scripps I/II) Session Chair: Dongyoon Lee (Stony Brook University) |
|---|
| Supporting Descendants in SIMD-Accelerated JSONPath Mateusz Gienieczko and Filip Murlak (University of Warsaw); Charles Paperman (CRIStAL, Université de Lille, INRIA) Paper . Abstract . Lightning Talk |
| Boost Linear Algebra Computation Performance via Efficient VNNI Utilization (Recorded Talk) Hao Zhou and Qiukun Han (Enflame Tech); Heng Shi (Enflame Tech and Shanghai Jiao Tong University); Yalin Zhang (Enflame Tech Inc.); Jianguo Yao (Enflame Tech and Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| A shared compilation stack for distributed-memory parallelism in stencil DSLs George Bisbas (Imperial College London); Anton Lydike, Emilien Bauer, Nick Brown, and Mathieu Fehr (University of Edinburgh); Lawrence Mitchell (Unaffiliated); Gabriel Rodriguez-Canal and Maurice Jamieson (University of Edinburgh); Paul H J Kelly (Imperial College London); Michel Steuwer (Technische Universität Berlin); Tobias Grosser (University of Cambridge) Paper . Abstract . Lightning Talk |
| SlimSLAM: An Adaptive Runtime for Visual-Inertial Simultaneous Localization and Mapping Armand Behroozi and Yuxiang Chen (University of Michigan);Vlad Fruchter, Lavanya Subramanian, and Sriseshan Srikanth (Meta);Scott Mahlke (University of Michigan) Paper . Abstract . Lightning Talk |
| Compiling Loop-Based Nested Parallelism for Irregular Workloads Yian Su (Northwestern University); Mike Rainey (Carnegie Mellon University); Nick Wanninger, Nadharm Dhiantravan, and Jasper Liang (Northwestern University); Umut A. Acar (Carnegie Mellon University); Peter Dinda and Simone Campanoni (Northwestern University) Paper . Abstract . Lightning Talk |
| 8D: IoT and Embedded (Location: Fairway I/IV) Session Chair: Don Porter (University of North Carolina at Chapel Hill) |
|---|
| TinyForge: A Design Space Exploration to Advance Energy and Silicon Area Trade-offs in tinyML Compute Architectures with Custom Latch Arrays Massimo Giordano, Rohan Doshi, and Qianyun Lu (Stanford University);Boris Murmann (University of Hawaii) Paper . Abstract . Lightning Talk |
| MulBERRY: Enabling Bit-Error Robustness for Energy-Efficient Multi-Agent Autonomous Systems Zishen Wan (Georgia Tech);Nandhini Chandramoorthy, Karthik Swaminathan, and Pin-Yu Chen (IBM Research);Kshitij Bhardwaj (Lawrence Livermore National Lab);Vijay Janapa Reddi (Harvard University);Arijit Raychowdhury (Georgia Tech) Paper . Abstract . Lightning Talk |
| Exploiting Human Color Discrimination for Memory- and Energy-Efficient Image Encoding in Virtual Reality Nisarg Ujjainkar and Ethan Shahan (University of Rochester);Kenneth Chen, Budmonde Duinkharjav, and Qi Sun (New York University);Yuhao Zhu (University of Rochester) Paper . Abstract . Lightning Talk |
| MicroVSA: An Ultra-Lightweight Vector Symbolic Architecture-based Classifier Library for Always-On Inference on Tiny Microcontrollers Nuntipat Narkthong and Shijin Duan (Northeastern University);Shaolei Ren (University of California Riverside);Xiaolin Xu (Northeastern University) Paper . Abstract . Lightning Talk |
| Energy-Adaptive Buffering for Efficient, Responsive, and Persistent Batteryless Systems Harrison Williams and Matthew Hicks (Virginia Tech) Paper . Abstract . Lightning Talk |
11:15 PDT – 11:45 PDT: Break
11:45 PDT – 13:00 PDT: Session 9
| 9A: Accelerated Applications (Location: Grande C) Session Chair: Arrvindh Shriraman (Simon-Fraser University) |
|---|
| JUNO: Optimizing High-Dimensional Approximate Nearest Neighbour Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping Zihan Liu (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Wentao Ni (Shanghai Jiao Tong University); Jingwen Leng (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Yu Feng (University of Rochester); Cong Guo (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Quan Chen (Shanghai Jiao Tong University); Chao Li and Minyi Guo (Shanghai Jiao Tong University and Shanghai Qi Zhi Institute); Yuhao Zhu (University of Rochester) Paper . Abstract . Lightning Talk |
| [Best Paper] ngAP: Non-blocking Large-scale Automata Processing on GPUs Tianao Ge (Hong Kong University of Science and Technology Guangzhou); Tong Zhang (Samsung); Hongyuan Liu (Hong Kong University of Science and Technology Guangzhou) Paper . Abstract . Lightning Talk |
| Marple: Scalable Spike Sorting for Untethered Brain-Machine Interfacing Eugene Sha, Andy Liu, Kareem Ibrahim, Mostafa Mahmoud, and Christina Giannoula (University of Toronto); Ameer Abdelhadi (McMaster University); Andreas Moshovos (University of Toronto and Vector Institute) Paper . Abstract . Lightning Talk |
| Manticore: Hardware-Accelerated RTL Simulation with Static Bulk-Synchronous Parallelism Mahyar Emami and Sahand Kashani (EPFL); Keisuke Kamahori (University of Tokyo); Mohammad Sepehr Pourghannad (Sharif University); Ritik Raj (Indian Institute of Technology Roorkee); James R. Larus (EPFL) Paper . Abstract . Lightning Talk |
| ORIANNA: An Accelerator Generation Framework for Optimization-based Robotic Applications Yuhui Hao (Tianjin University); Yiming Gan (Chinese Academy of Sciences); Bo Yu (Shenzhen Institute of Artificial Intelligence and Robotics for Society); Qiang Liu (Tianjin University); Yinhe Han (Chinese Academy of Sciences); Zishen Wan (Georgia Tech); Shaoshan Liu (Shenzhen Institute of Artificial Intelligence and Robotics for Society) Paper . Abstract . Lightning Talk |
| 9B: SSDs (Location: Grande D/E) Session Chair: Anand Sivasubramaniam (Penn State) |
|---|
| AERO: Adaptive Erase Operation for Improving Lifetime and Performance of Modern NAND Flash-Based SSDs Sungjun Cho (POSTECH);Beomjun Kim (Kyungpook National University);Hyunuk Cho (POSTECH);Gyeongseob Seo (Kyungpook National University);Onur Mutlu (ETH Zürich);Myungsuk Kim (Kyungpook National University);Jisung Park (POSTECH) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] BypassD: Enabling fast userspace access to shared SSDs Sujay Yadalam (University of Wisconsin-Madison);Chloe Alverti (National Technical University of Athens);Vasileios Karakostas (University of Athens);Jayneel Gandhi (Meta);Michael Swift (University of Wisconsin-Madison) Paper . Abstract . Lightning Talk |
| Eliminating Storage Management Overhead of Deduplication over SSD Arrays Through a Hardware/Software Co-Design Yuhong Wen, Xiaogang Zhao, and You Zhou (Huazhong University of Science and Technology); Tong Zhang (Rensselaer Polytechnic Institute and ScaleFlux); Shangjun Yang, Changsheng Xie, and Fei Wu (Huazhong University of Science and Technology) Paper . Abstract . Lightning Talk |
| LazyBarrier: Reconstructing Android IO Stack for Barrier-Enabled Flash Storage (Recorded Talk) Yuanyi Zhang, Heng Zhang, Wenbin Cao, Xing He, Daejun Park, Jinyoung Choi, and SungJun Park (Samsung Electronics) Paper . Abstract . Lightning Talk |
| Achieving Near-Zero Read Retry for 3D NAND Flash Memory Min Ye (City University of Hong Kong);Qiao Li (Xiamen University); Yina Lv (City University of Hong Kong);Jie Zhang (Peking University);Tianyu Ren (City University of Hong Kong);Daniel Wen (YEESTOR Microelectronics);Tei-Wei Kuo (National Taiwan University);Chun Jason Xue (City University of Hong Kong and Mohamed bin Zayed University of Artificial Intelligence) Paper . Abstract . Lightning Talk |
| 9C: ML Systems and Optimizations (Location: Scripps I/II) Session Chair: Sangeeta Chowdhary (AMD Research) |
|---|
| SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile Wei Niu, Md Musfiqur Rahman Sanim, and Zhihao Shu (University of Georgia);Jiexiong Guan (William & Mary);Xipeng Shen (North Carolina State University);Miao Yin (University of Texas at Arlington);Gagan Agrawal (University of Georgia);Bin Ren (William & Mary) Paper . Abstract . Lightning Talk |
| Dr. DNA: Combating Silent Data Corruptions in Deep Learning using Distribution of Neuron Activations Dongning Ma (Villanova University);Fred Lin, Alban Desmaison, Joel Coburn, Daniel Moore, and Sriram Sankar (Meta); Xun Jiao (Villanova University and Meta) Paper . Abstract . Lightning Talk |
| GPU-based Private Information Retrieval for On-Device Machine Learning Inference Maximilian Lam (Harvard University); Jeff Johnson (Meta); Wenjie Xiong (Virginia Tech); Kiwan Maeng (Pennsylvania State University); Udit Gupta (Harvard University); Yang Li, Liangzhen Lai, and Ilias Leontiadis (Meta); Minsoo Rhu (KAIST and Meta); Hsien-Hsin S. Lee (Intel); Vijay Janapa Reddi, Gu-Yeon Wei, and David Brooks (Harvard University); Edward Suh (Meta and Cornell University) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] RECom: A Compiler Approach to Accelerate Recommendation Model Inference with Massive Embedding Columns Zaifeng Pan (Renmin University of China);Zhen Zheng (Alibaba);Feng Zhang and Ruofan Wu (Renmin University of China);Hao Liang (Alibaba);Dalin Wang (Renmin University of China);Xiafei Qiu, Junjie Bai, and Wei Lin (Alibaba);Xiaoyong Du (Renmin University of China) Paper . Abstract . Lightning Talk |
| NDPipe: Exploiting Near-data Processing for Scalable Inference and Continuous Training in Photo Storage Jungwoo Kim and Seonggyun Oh (DGIST);Jaeha Kung (Korea University);Yeseong Kim and Sungjin Lee (DGIST) Paper . Abstract . Lightning Talk |
| 9D: Quantum Software (Location: Fairway I/IV) Session Chair: Yufei Ding (University of California San Diego) |
|---|
| Exploiting the Regular Structure of Modern Quantum Architectures for Compiling and Optimizing Programs with Permutable Operators Yuwei Jin, Fei Hua, Yanhao Chen, and Ari Hayes (Rutgers University);Chi Zhang (University of Pittsburgh);Eddy Z. Zhang (Rutgers University) Paper . Abstract . Lightning Talk |
| One Gate Scheme to Rule Them All: Introducing a Complex Yet Reduced Instruction Set for Quantum Computing Jianxin Chen and Dawei Ding (DAMO Academy);Weiyuan Gong (Harvard University);Cupjin Huang (DAMO Academy);Qi Ye (DAMO Academy and Tsinghua University) Paper . Abstract . Lightning Talk |
| MorphQPV: Exploiting Isomorphism in Quantum Programs to Facilitate Confident Verification Siwei Tan, Debin Xiang, and Liqiang Lu (Zhejiang University); Junlin Lu (Peking University); Qiuping Jiang (Ningbo University); Mingshuai Chen and Jianwei Yin (Zhejiang University) Paper . Abstract . Lightning Talk |
| Fermihedral: On the Optimal Compilation for Fermion-to-Qubit Encoding Yuhao Liu, Shize Che, and Junyu Zhou (University of Pennsylvania); Yunong Shi (AWS Quantum Technologies); Gushu Li (University of Pennsylvania) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] OnePerc: A Randomness-aware Compiler for Photonic Quantum Computing Hezi Zhang and Jixuan Ruan (University of California San Diego); Hassan Shapourian and Ramana Rao Kompella (Cisco Systems); Yufei Ding (University of California San Diego) Paper . Abstract . Lightning Talk |
13:00 PDT – 14:30 PDT: Lunch
14:30 PDT – 15:30 PDT: Keynote 4 by Nafea Bshara (Amazon) (Location: Grande)
| AWS Trainium: The Journey for Designing and Optimization Full Stack ML Hardware |
| Abstract Machine learning accelerators present a unique set of design challenges across chip architecture, instruction set, server design, compiler, and both inter- and intra-chip connectivity. With AWS Trainium, we’ve utilized AWS’s end-to-end ownership from chip to server, network, compilers, and runtime tools to collaboratively design and optimize across all layers, emphasizing simplicity and ease of use. This talk will illustrate the design principles, tradeoffs, and lessons learned during the development of three generations of AWS ML products, from conceptualization to placing systems in the hands of AWS customers. |
| Bio Machine learning accelerators present a unique set of design challenges across chip architecture, instruction set, server design, compiler, and both inter- and intra-chip connectivity. With AWS Trainium, we’ve utilized AWS’s end-to-end ownership from chip to Nafea Bshara, Vice President and Distinguished Engineer at Amazon Web Services (AWS), leads the strategy and architecture for AWS custom hardware, including Nitro, Nitro SSD, SRD, Graviton, Inferentia, Trainium, and Neuron AI SDK. Nafea began his career at Galileo Technology, where he held various leading roles in software and chip design for network, storage, and compute infrastructure, culminating in his position as Chief Architect. Following Galileo’s acquisition by Marvell Semiconductor in 2001, Nafea joined Marvell and served in several product definition roles. In 2011, he co-founded Annapurna Labs, a startup focused on designing cloud-optimized infrastructure chips and associated software. Amazon acquired Annapurna Labs in February 2015, after which Nafea and his team have led AWS’s custom silicon and hardware efforts. Nafea holds an M.Sc. degree in Electrical and Computer Engineering from the Technion – Israel Institute of Technology and has been granted over 350 US patents. |
15:30 PDT – 16:00 PDT: Break
16:00 PDT – 17:00 PDT: Session 10
| 10A: FPGAs and Reconfigurable Hardware (Location: Grande C) Session Chair: Jonathan Balkind (UC Santa Barbara) |
|---|
| FPGA Technology Mapping Using Sketch-Guided Program Synthesis Gus Henry Smith, Benjamin Kushigian, Vishal Canumalla, and Andrew Cheung (University of Washington); Steven Lyubomirsky (OctoAI); Sorawee Porncharoenwase, René Just, Gilbert Louis Bernstein, and Zachary Tatlock (University of Washington) Paper . Abstract . Lightning Talk |
| TAPA-CS: Enabling Scalable Accelerator Design on Distributed HBM-FPGAs Neha Prakriya, Yuze Chi, Suhail Basalama, Linghao Song, and Jason Cong (University of California Los Angeles) Paper . Abstract . Lightning Talk |
| Zoomie: A Software-like Debugging Tool for FPGAs Tianrui Wei and Kevin Laeufer (University of California Berkeley);Katie Lim (University of Washington);Jerry Zhao and Koushik Sen (UC Berkeley);Jonathan Balkind (University of California Santa Barbara);Krste Asanovic (University of California Berkeley) Paper . Abstract . Lightning Talk |
| HIR: An MLIR-based Intermediate Representation for Hardware Accelerator Description Kingshuk Majumder and Uday Bondhugula (Indian Institute of Science) Paper . Abstract . Lightning Talk |
| 10B: Serverless Computing 2 (Location: Grande D/E) Session Chair: Jian Huang (University of Illinois Urbana-Champaign) |
|---|
| FaaSGraph: Enabling Scalable, Efficient, and Cost-Effective Graph Processing with Serverless Computing Yushi Liu, Shixuan Sun, Zijun Li, and Quan Chen (Shanghai Jiao Tong University);Sen Gao and Bingsheng He (National University of Singapore);Chao Li and Minyi Guo (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| In-Storage Domain-Specific Acceleration for Serverless Computing Rohan Mahapatra, Soroush Ghodrati, Byung Hoon Ahn, Sean Kinzer, Shu-Ting Wang, Hanyang Xu, and Lavanya Karthikeyan (University of California San Diego);Hardik Sharma (Google);Amir Yazdanbakhsh (Google DeepMind);Mohammad Alian (University of Kansas);Hadi Esmaeilzadeh (University of California San Diego) Paper . Abstract . Lightning Talk |
| FUYAO: DPU-enabled Direct Data Transfer for Serverless Computing (Recorded Talk) Guowei Liu, Laiping Zhao, Yiming Li, Zhaolin Duan, Sheng Chen, and Yitao Hu (Tianjin University);Zhiyuan Su (Inspur Electronic Information Industry);Wenyu Qu (Tianjin University) Paper . Abstract . Lightning Talk |
| DataFlower: Exploiting the Data-flow Paradigm for Serverless Workflow Orchestration Zijun Li, Chuhao Xu, Quan Chen, Jieru Zhao, Chen Chen, and Minyi Guo (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| 10C: ML Sparsity and Dynamic Shapes (Location: Scripps I/II) Session Chair: Roshan Dathathri (Microsoft Research) |
|---|
| Fractal: Joint Multi-Level Sparse Pattern Tuning of Accuracy and Performance for DNN Pruning Yue Guan, Changming Yu, Yangjie Zhou, Jingwen Leng, Chao Li, and Minyi Guo (Shanghai Jiao Tong University and Shanghai Qizhi Institute) Paper . Abstract . Lightning Talk |
| Optimizing Dynamic-Shape Neural Networks on Accelerators via On-the-Fly Micro-Kernel Polymerization (Recorded Talk) Feng Yu, Guangli Li, Jiacheng Zhao, Huimin Cui, and Xiaobing Feng (Chinese Academy of Sciences);Jingling Xue (University of New South Wales) Paper . Abstract . Lightning Talk |
| DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores (Recorded Talk) Ruibo Fan, Wei Wang, and Xiaowen Chu (Hong Kong University of Science and Technology) Paper . Abstract . Lightning Talk |
| SoD2: Statically Optimizing Dynamic Deep Neural Network Execution Wei Niu and Gagan Agrawal (University of Georgia);Bin Ren (William & Mary) Paper . Abstract . Lightning Talk |
| 10D: Trusted Computing (Location: Fairway I/IV) Session Chair: Dan Williams (Virginia Tech) |
|---|
| SEVeriFast: Minimizing the root of trust for fast startup of SEV microVMs Benjamin Holmes (MIT and Vassar College); Jason Waterman (Vassar College); Dan Williams (Virginia Tech) Paper . Abstract . Lightning Talk |
| sIOPMP: Scalable and Efficient I/O Protection for TEEs Erhu Feng (Shanghai Jiao Tong University);Dahu Feng (Tsinghua University);Dong Du and Yubin Xia (Shanghai Jiao Tong University);Wenbin Zheng and Siqi Zhao (Alibaba DAMO Academy);Haibo Chen (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| A Midsummer Night’s Tree: Efficient and High Performance Secure SCM Samuel Thomas (Brown University); Kidus Workneh (University of Colorado Boulder); Jac McCarty (Bryn Mawr College); Joseph Izraelevitz and Tamara Lehman (University of Colorado Boulder); R. Iris Bahar (Colorado School of Mines) Paper . Abstract . Lightning Talk |
| Veil: A Protected Services Framework for Confidential Virtual Machines Adil Ahmad (Arizona State University); Botong Ou and Congyu Liu (Purdue University); Xiaokuan Zhang (George Mason University); Pedro Fonseca (Purdue University) Paper . Abstract . Lightning Talk |
17:00 PDT – 17:30 PDT: Break
17:30 PDT – 18:30 PDT: Session 11
| 11A: Cryptography and Privacy (Location: Grande C; Ends 18:45 PDT) Session Chair: Moumita Dey (AMD Research and Advanced Development) |
|---|
| Accelerating Multi-Scalar Multiplication for Efficient Zero Knowledge Proofs with Multi-GPU Systems Zhuoran Ji and Zhiyuan Zhang (Shandong University);Jiming Xu (Ant Group);Lei Ju (Shandong University) Paper . Abstract . Lightning Talk |
| LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models Juntaek Lim, Youngeun Kwon, and Ranggi Hwang (KAIST);Kiwan Maeng (Pennsylvania State University);Edward Suh (FAIR at Meta and Cornell University);Minsoo Rhu (KAIST) Paper . Abstract . Lightning Talk |
| BitPacker: Enabling High Arithmetic Efficiency in Fully Homomorphic Encryption Accelerators Nikola Samardzic and Daniel Sanchez (MIT) Paper . Abstract . Lightning Talk |
| ZENO: A Type-based Optimization Framework for Zero Knowledge Neural Network Inference Boyuan Feng, Zheng Wang, Yuke Wang, Shu Yang, and Yufei Ding (University of California Santa Barbara) Paper . Abstract . Lightning Talk |
| Performance-aware Scale Analysis with Reserve for Homomorphic Encryption Yongwoo Lee, Seonyoung Cheon, and Dongkwan Kim (Yonsei University); Dongyoon Lee (Stony Brook University); Hanjun Kim (Yonsei University) Paper . Abstract . Lightning Talk |
| 11B: Scheduling (Location: Grande D/E) Session Chair: Martin Maas (Google) |
|---|
| Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters Zizhao Mo, Huanle Xu, and Chengzhong Xu (University of Macau) Paper . Abstract . Lightning Talk |
| Efficient Microsecond-scale Blind Scheduling with Tiny Quanta Zhihong Luo, Sam Son, and Dev Bali (University of California Berkeley);Emmanuel Amaro (VMware Research);Amy Ousterhout (University of California San Diego);Sylvia Ratnasamy (University of California Berkeley);Scott Shenker (ICSI and University of California Berkeley) Paper . Abstract . Lightning Talk |
| AUDIBLE: A Convolution-Based Resource Allocator for Oversubscribing Burstable Virtual Machines (Recorded Talk) Seyedali Jokar Jandaghi and Kaveh Mahdaviani (University of Toronto); Amirhossein Mirhosseini (University of Michigan); Sameh Elnikety (Microsoft Research); Cristiana Amza and Bianca Schroeder (University of Toronto) Paper . Abstract . Lightning Talk |
| CPS: A Cooperative Para-virtualized Scheduling Framework for Manycore Machines (Recorded Talk) Yuxuan Liu, Tianqiang Xu, Zeyu Mi, Zhichao Hua, Binyu Zang, and Haibo Chen (Shanghai Jiao Tong University) Paper . Abstract . Lightning Talk |
| 11C: ML Training Optimizations (Location: Scripps I/II) Session Chair: Roshan Dathathri (Microsoft Research) |
|---|
| PrimePar: Efficient Spatial-temporal Tensor Partitioning for Large Transformer Model Training (Speaker Shixin Zhao) Haoran Wang, Lei Wang, Haobo Xu, Ying Wang, Yuming Li, and Yinhe Han (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |
| AdaPipe: Optimizing Pipeline Parallelism with Adaptive Recomputation and Partitioning Zhenbo Sun, Huanqi Cao, Yuanwei Wang, Guanyu Feng, Shengqi Chen, Haojie Wang, and Wenguang Chen (Tsinghua University) Paper . Abstract . Lightning Talk |
| [Distinguished Artifact Evaluation Award] EVT: Accelerating Deep Learning Training with Epilogue Visitor Tree Zhaodong Chen (University of California Santa Barbara);Andrew Kerr, Richard Cai, Jack Kosaian, and Haicheng Wu (NVIDIA); Yufei Ding (University of California San Diego); Yuan Xie (The Hong Kong University of Science and Technology) Paper . Abstract . Lightning Talk |
| Slapo: A Schedule Language for Progressive Optimization of Large Deep Learning Model Training Hongzheng Chen (Cornell University); Cody Hao Yu and Shuai Zheng (Boson AI); Zhen Zhang (Amazon Web Services); Zhiru Zhang (Cornell University); Yida Wang (Amazon Web Services) Paper . Abstract . Lightning Talk |
| 11D: More Processing-In-Memory (Location: Fairway I/IV) Session Chair: Sara Achour (Stanford) |
|---|
| BVAP: Energy and Memory Efficient Automata Processing for Regular Expressions with Bounded Repetitions Ziyuan Wen, Lingkun Kong, Alexis Le Glaunec, Konstantinos Mamouras, and Kaiyuan Yang (Rice University) Paper . Abstract . Lightning Talk |
| IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System Minseok Seo and Xuan Truong Nguyen (Seoul National University and Inter-university Semiconductor Research Center); Seok Joong Hwang (SAPEON); Yongkee Kwon, Guhyun Kim, Chanwook Park, Ilkon Kim, Jaehan Park, Jeongbin Kim, Woojae Shin, Jongsoon Won, Haerang Choi, Kyuyoung Kim, Daehan Kwon, and Chunseok Jeong (SK hynix);Sangheon Lee, Yongseok Choi, Wooseok Byun, and Seungcheol Baek (SAPEON);Hyuk-Jae Lee (Seoul National University and Inter-university Semiconductor Research Center);John Kim (KAIST) Paper . Abstract . Lightning Talk |
| PIM-STM: Software Transactional Memory for Processing-In-Memory Systems André Lopes, Daniel Castro, and Paolo Romano (IST/INESC-ID) Paper . Abstract . Lightning Talk |
| CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators Songyun Qu and Shixin Zhao (Chinese Academy of Sciences); Bing Li (Capital Normal University); Yintao He, Xuyi Cai, Lei Zhang, and Ying Wang (Chinese Academy of Sciences) Paper . Abstract . Lightning Talk |