{"id":3602,"date":"2023-02-03T15:28:19","date_gmt":"2023-02-03T20:28:19","guid":{"rendered":"https:\/\/asplos-conference.org\/?page_id=3602"},"modified":"2023-03-30T04:26:41","modified_gmt":"2023-03-30T08:26:41","slug":"program","status":"publish","type":"page","link":"https:\/\/asplos-conference.org\/program\/","title":{"rendered":"Program"},"content":{"rendered":"\n

Remote attendees: Please access the live stream of the program and asynchronous Q&A for individual papers via Whova at this URL<\/a>.  For the best remote experience we recommend using a laptop or desktop computer. Register for remote attendance here<\/a>. Here is a guide<\/a> for remote attendees.<\/p>\n\n\n\n

In-person attendees: Please download the Whova app to your mobile device here<\/a>.  The app gives you access to the conference agenda (with links to floor maps), online networking, asynchronous Q&A for individual papers, and important announcements. Here is a guide<\/a> for in-person attendees. <\/p>\n\n\n\n

Links to lightning talks can be found under each paper in the program below. The conference proceedings will be freely accessible without membership on the ACM Digital Library, not behind a paywall for 1 month starting on the first day of the conference.<\/p>\n\n\n\n

ASPLOS 2023 Proceedings<\/em>
Volume 1: https:\/\/doi.org\/10.1145\/3567955<\/a>
Volume 2: https:\/\/doi.org\/10.1145\/3575693<\/a>
Volume 3: https:\/\/doi.org\/10.1145\/3582016<\/a><\/p>\n\n\n\n<\/a>\n

\n
\n

Saturday, March 25 \/ Sunday, March 26: Workshops & Tutorials<\/a><\/h2>\n <\/div>\n\n
\n

Sunday, 6:00 PM PDT<\/span> – 9:00 PM PDT<\/span>: Welcome Reception<\/h3>\n
\n Location: Pavillion Ballroom\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n<\/div>\n\n
\n\n
\n
\n Jump to\n Sat\/Sun<\/a> |\n Monday<\/a> |\n Tuesday<\/a> |\n Wednesday<\/a> \n Expand All<\/a> \/ \n Collapse All<\/a> Sessions\n <\/div>\n<\/div>\n\n
\n\n<\/a>\n
\n
\n

Day 1: Monday, March 27<\/h2>\n <\/div>\n\n
\n

8:00 AM PDT<\/span> – 8:40 AM PDT<\/span>: Breakfast<\/h3>\n
\n Location: Junior Ballroom & Pavillion Ballroom\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

8:40 AM PDT<\/span> – 9:00 AM PDT<\/span>: Opening Remarks<\/h3>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

\n 9:00 AM PDT<\/span> – 10:00 AM PDT<\/span>:\n Keynote 1 by Azalia Mirhoseini\n (Anthropic \/ Stanford Univ.)<\/span>\n <\/h3>\n <\/div>\n
\n
\n
\n

\n \n Pushing the Limits of Scaling Laws in the Age of Generative Models\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n

\n \"Azalia\n Abstract<\/b>\n The emergence of powerful generative AI (e.g. large language \/ vision models) would not have been possible without recent advances in computing systems and accelerators. This talk sheds light on the important role that generative AI itself can play in designing the next generation of computing systems and hardware that in turn would fuel the next generation of AI breakthroughs. Concretely, I will discuss our work on learned optimization for hardware resource allocation and model mapping, which inspired a new and ongoing trend of policy gradient methods for solving combinatorial optimization in computer systems, a generalizable deep reinforcement learning method for chip floorplanning that saved several weeks of design cycle for Google TPUs, and an automated framework for full-stack HW\/SW co-design that resulted in drastic Perf\/TCO improvements in custom accelerator design. Finally, I will discuss the opportunities and challenges for future computing systems in the era of large generative models.\n <\/p>\n

\n

\n Bio<\/b>\n Azalia Mirhoseini is a Member of Technical Staff at Anthropic, and an incoming Assistant Professor of Computer Science at Stanford University. Previously, she was a Staff Research Scientist and Team Lead at Google Brain, where she co-founded the Machine Learning for Systems Team. Azalia has published more than 40 peer-reviewed papers at scientific venues such as Nature, ICML, ICLR, NeurIPS, UAI, ASPLOS, SIGMETRICS, DAC, DATE, and ICCAD. She has received a number of awards, including the MIT Technology Review 35 under 35 award, the Best Ph.D. Thesis Award at Rice, and a Gold Medal in the National Math Olympiad in Iran. Her work has been covered in various media outlets, including WIRED, CNBC, ABC News, MIT Technology Review, and IEEE Spectrum.\n <\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n

\n

10:00 AM PDT<\/span> – 10:20 AM PDT<\/span>: Coffee Break<\/h3>\n
\n Location: Grand Foyer\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

10:20 AM PDT<\/span> – 12:00 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 1A: Systems for ML\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Tushar Krishna (Georgia Inst. of Technology)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Overlap Communication with Dependent Computation via Decomposition in Large Deep Learning Models\n <\/div>\n
\n Shibo Wang, Amit Sabne, Andy Davis, Berkin Ilbeyi, Blake Hechtman (Google); Dehao Chen (Waymo); Jinliang Wei, Karthik Srinivasa Murthy, Marcello Maggioni, Qiao Zhang, Sameer Kumar, Tongfei Guo, Yuanzhong Xu, Zongwei Zhou (Google)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Heron: Automatically Constrained High-performance Library Generation for Deep Learning Accelerators\n <\/div>\n
\n Jun Bi (Univ. of Science and Technology of China); Qi Guo, Xiaqing Li, Yongwei Zhao (Inst. of Computing Tech., Chinese Academy of Sciences); Yuanbo Wen, Yuxuan Guo, Enshuai Zhou (Univ. of Science and Technology of China); Xing Hu, Zidong Du (Inst. of Computing Tech., Chinese Academy of Sciences); Ling Li (Inst. of Software, Chinese Academy of Sciences); Huaping Chen (Univ. of Science and Technology of China); Tianshi Chen (Cambricon Technologies)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n TelaMalloc: Efficient On-Chip Memory Allocation for Production Machine Learning Accelerators\n <\/div>\n
\n Martin Maas, Ulysse Beaugnon, Arun Chauhan, Berkin Ilbeyi (Google)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n EVStore: Storage and Caching Capabilities for Scaling Embedding Tables in Deep Recommendation Systems\n <\/div>\n
\n Daniar H. Kurniawan (Univ. of Chicago); Ruipu Wang (Beijing Univ. of Technology); Kahfi S. Zulkifli, Fandi A. Wiranata (Bandung Inst. of Technology); John Bent (Seagate Technology); Ymir Vigfusson (Emory Univ.); Haryadi S. Gunawi (Univ. of Chicago)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n WACO: Learning Workload-Aware Co-optimization of the Format and Schedule of a Sparse Tensor Program\n <\/div>\n
\n Jaeyeon Won (Massachusetts Inst. of Technology); Charith Mendis (Univ. of Illinois Urbana-Champaign); Joel Emer (Massachusetts Inst. of Technology \/ NVIDIA); Saman Amarasinghe (Massachusetts Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n GRACE: A Scalable Graph-Based Approach To Accelerating Recommendation Model Inference\n <\/div>\n
\n Haojie Ye (Univ. of Michigan); Sanketh Vedula (Technion); Yuhan Chen, Yichen Yang (Univ. of Michigan); Alex Bronstein (Technion); Ronald Dreslinski, Trevor Mudge, Nishil Talati (Univ. of Michigan)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 1B: Shared Memory\/Mem Consistency\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Nadav Amit (VMware Research Group)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Cohort: Software-Oriented Acceleration for Heterogeneous SoCs\n <\/div>\n
\n Tianrui Wei (Univ. of California, Berkeley); Nazerke Turtayeva (Univ. of California, Santa Barbara); Marcelo Orenes-Vera (Princeton Univ.); Omkar Lonkar, Jonathan Balkind (Univ. of California, Santa Barbara)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n PipeSynth: Automated Synthesis of Microarchitectural Axioms for Memory Consistency\n <\/div>\n
\n Chase Norman, Adwait Godbole (Univ. of California, Berkeley); Yatin A. Manerkar (Univ. of Michigan)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Probabilistic Concurrency Testing for Weak Memory Programs\n <\/div>\n
\n Mingyu Gao, Soham Chakraborty, Burcu Kulahcioglu Ozkan (Technische Univ. Delft)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n MC Mutants: Evaluating and Improving Testing for Memory Consistency Specifications\n <\/div>\n
\n Reese Levine, Tianhao Guo, Mingun Cho (Univ. of California, Santa Cruz); Alan Baker, Raph Levien, David Neto (Google); Andrew Quinn, Tyler Sorensen (Univ. of California, Santa Cruz)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n AtoMig: Automatically Migrating Millions Lines of Code from TSO to WMM\n <\/div>\n
\n Martin Beck, Koustubha Bhat, Lazar Striçević (Huawei Dresden Research Center, Huawei Central Software Inst.); Geng Chen (Huawei Fundamental Software Innovation Lab, Huawei Central Software Inst.); Diogo Behrens, Ming Fu (Huawei Dresden Research Center, Huawei Central Software Inst.); Viktor Vafeiadis (Max Planck Inst. for Software Syst.); Haibo Chen (Huawei Central Software Inst., Shanghai Jiao Tong Univ.); Hermann Härtig (Technische Univ. Dresden)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Risotto: A Dynamic Binary Translator for Weak Memory Model Architectures\n <\/div>\n
\n Redha Gouicem (Technische Univ. München); Dennis Sprokholt (Technische Univ. Delft); Jasper Ruehl (Technische Univ. München); Rodrigo C. O. Rocha (Univ. of Edinburgh); Tom Spink (Univ. of St Andrews); Soham Chakraborty (Technische Univ. Delft); Pramod Bhatotia (Technische Univ. München)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 1C: IoT\/Embedded\/Mobile\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Trevor Carlson (National Univ. of Singapore)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Kodan: Addressing the Computational Bottleneck in Space\n <\/div>\n
\n Bradley Denby (Carnegie Mellon Univ.); Shadi Noghabi, Krishna Chintalapudi (Microsoft Research); Ranveer Chandra (Microsoft); Brandon Lucia (Carnegie Mellon Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Space-Efficient TREC for Enabling Deep Learning on Microcontrollers\n <\/div>\n
\n Jiesong Liu, Feng Zhang, Jiawei Guan (Renmin Univ. of China); Hsin-Hsuan Sung (North Carolina State Univ.); Xiaoguang Guo, Xiaoyong Du (Renmin Univ. of China); Xipeng Shen (North Carolina State Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining\n <\/div>\n
\n Liwei Guo, Wonkyo Choe, Felix Xiaozhu Lin (Univ. of Virginia)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n LEGO: Empowering Chip-level functionality plug-and-play for next-generation IoT devices\n <\/div>\n
\n Chong Zhang, Songfan Li, Yihang Song, Qianhe Meng, Minghua Chen, YanXu Bai, Li Lu (Univ. of Electronic Science and Technology of China); Hongzi Zhu (Shanghai Jiao Tong Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Transparent Runtime Change Handling for Android Apps\n <\/div>\n
\n Zizhan Chen, Zili Shao (The Chinese Univ. of Hong Kong)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

12:00 PM PDT<\/span> – 1:00 PM PDT<\/span>: Lunch<\/h3>\n
\n Location: Junior Ballroom & Pavillion Ballroom\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

1:00 PM PDT<\/span> – 2:40 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 2A: Compiler Techniques & Optimization\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Xipeng Shen (North Carolina State Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n SPLENDID: Supporting Parallel LLVM-IR Enhanced Natural Decompilation for Interactive Development\n <\/div>\n
\n Zujun Tan, Yebin Chon (Princeton Univ.); Michael Kruse, Johannes Doerfert (Argonne National Laboratory); Ziyang Xu (Princeton Univ.); Brian Homerding, Simone Campanoni (Northwestern Univ.); David I. August (Princeton Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Beyond Static Parallel Loops: Supporting Dynamic Task Parallelism on Manycore Architectures with Software-Managed Scratchpad Memories\n <\/div>\n
\n Lin Cheng (Cornell Univ.); Max Ruttenberg, Dai Cheol Jung (Univ. of Washington); Dustin Richmond (Univ. of California, Santa Cruz); Michael Taylor, Mark Oskin (Univ. of Washington); Christopher Batten (Cornell Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Graphene: An IR for Optimized Tensor Computations on GPUs\n <\/div>\n
\n Bastian Hagedorn, Bin Fan, Hanfeng Chen, Cris Cecka, Michael Garland, Vinod Grover (NVIDIA)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Coyote: A Compiler for Vectorizing Encrypted Arithmetic Circuits\n <\/div>\n
\n Raghav Malik, Kabir Sheth, Milind Kulkarni (Purdue Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers\n <\/div>\n
\n Jiawei Liu (Univ. of Illinois Urbana-Champaign); Jinkun Lin, Fabian Ruffy (New York Univ.); Cheng Tan (Northeastern Univ.); Jinyang Li, Aurojit Panda (New York Univ.); Lingming Zhang (Univ. of Illinois Urbana-Champaign)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n TiLT: A Time-Centric Approach for Stream Query Optimization and Parallelization\n <\/div>\n
\n Anand Jayarajan (Univ. of Toronto \/ Vector Inst.); Wei Zhao, Yudi Sun (Univ. of Toronto); Gennady Pekhimenko (Univ. of Toronto \/ Vector Inst.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 2B: GPUs\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Mark Silberstein (Technion)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n NUBA: Non-Uniform Bandwidth GPUs\n <\/div>\n
\n Xia Zhao (Artificial Intelligence Research Center); Magnus Jahre (Norwegian Univ. of Science and Technology); Yuhua Tang (National Univ. of Defense Technology); Guangda Zhang (Artificial Intelligence Research Center); Lieven Eeckhout (Ghent Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Scoped Buffered Persistency Model for GPUs\n <\/div>\n
\n Shweta Pandey (Indian Inst. of Science); Aditya K Kamath (Univ. of Washington); Arkaprava Basu (Indian Inst. of Science)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Skybox: Open-source Graphic Rendering on Programmable RISC-V GPUs\n <\/div>\n
\n Blaise Tine, Varun Saxena (Georgia Inst. of Technology); Santosh Raghav Srivatsan (Georgia Inst. of Technology \/ North Carolina State Univ.); Joshua R. Simpson, Fadi Alzammar (California Polytechnic State Univ.); Liam Cooper, Hyesoon Kim (Georgia Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n DefT: Boosting Scalability of Deformable Convolution Operations on GPUs\n <\/div>\n
\n Edward Hanson, Mark Horton, Hai "Helen" Li, Yiran Chen (Duke Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n MSCCLang: Microsoft Collective Communication Language\n <\/div>\n
\n Meghan Cowan, Saeed Maleki, Madanlal Musuvathi, Olli Saarikivi, Yifan Xiong (Microsoft Research)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture\n <\/div>\n
\n Zaid Qureshi, Vikram Sharma Mailthody (Univ. of Illinois Urbana-Champaign); Isaac Gelado (NVIDIA); Seungwon Min, Amna Masood, Jeongmin Park (Univ. of Illinois Urbana-Champaign); Jinjun Xiong (Univ. at Buffalo); CJ Newburn, Dmitri Vainbrand (NVIDIA); IHsin Chung (IBM Research); Michael Garland (NVIDIA); William Dally (NVIDIA \/ Stanford Univ.); Wen-mei Hwu (Univ. of Illinois Urbana-Champaign)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 2C: Clouds\/Datacenters\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Mohammad Shahrad (Univ. of British Columbia)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-demand VMs\n <\/div>\n
\n Fangkai Yang, Lu Wang, Zhenyu Xu, Jue Zhang, Liqun Li, Bo Qiao (Microsoft Research); Camille Couturier, Chetan Bansal (Microsoft 365); Soumya Ram (Microsoft Azure); Si Qin (Microsoft Research); Zhen Ma (Microsoft 365); Íñigo Goiri, Eli Cortez (Microsoft Azure); Terry Yang, Victor Rühle, Saravan Rajmohan (Microsoft 365); Qingwei Lin, Dongmei Zhang (Microsoft Research)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Erms: Efficient Resource Management for Shared Microservices with SLA Guarantees\n <\/div>\n
\n Shutian Luo (Shenzhen Inst. of Advanced Tech., Chinese Academy of Sciences \/ Univ. of Macau); Huanle Xu (Univ. of Macau); Kejiang Ye (Shenzhen Inst. of Advanced Tech., Chinese Academy of Sciences); Guoyao Xu, Liping Zhang, Jian He, Guodong Yang (Alibaba Group); Chengzhong Xu (Univ. of Macau, Macau SAR, China)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Ditto: End-to-End Application Cloning for Networked Cloud Services\n <\/div>\n
\n Mingyu Liang, Yu Gan, Yueying Li (Cornell Univ.); Carlos Torres, Abhishek Dhanotia (Meta); Mahesh Ketkar (Intel); Christina Delimitrou (Massachusetts Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n BeeHive: Sub-second Elasticity for Web Services with Semi-FaaS Execution\n <\/div>\n
\n Ziming Zhao, Mingyu Wu, Jiawei Tang, Binyu Zang, Zhaoguo Wang, Haibo Chen (Shanghai Jiao Tong Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n AQUATOPE: QoS-and-Uncertainty-Aware Resource Management for Multi-stage Serverless Workflows\n <\/div>\n
\n Zhuangzhuang Zhou, Yanqi Zhang, Christina Delimitrou (Cornell Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n A Generic Service to Provide In-network Aggregation for Key-value Streams\n <\/div>\n
\n Yongchao He (Tsinghua Univ.); Wenfei Wu (Peking Univ.); Yanfang Le (Intel, Barefoot Switch Division); Ming Liu (Univ. of Wisconsin-Madison); ChonLam Lao (Harvard Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

2:40 PM PDT<\/span> – 3:00 PM PDT<\/span>: Coffee Break<\/h3>\n
\n Location: Grand Foyer\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

3:00 PM PDT<\/span> – 3:50 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 3A: Sustainability\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Lieven Eeckhout (Ghent Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Junkyard Computing: Repurposing Discarded Smartphones to Minimize Carbon\n <\/div>\n
\n Jennifer Switzer, Gabriel Marcano, Ryan Kastner, Pat Pannuto (Univ. of California, San Diego)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Carbon Explorer: A Holistic Framework for Designing Carbon Aware Datacenters\n <\/div>\n
\n Bilge Acun (Meta); Benjamin Lee (Univ. of Pennsylvania \/ Meta); Fiodar Kazhamiaka (Stanford Univ.); Kiwan Maeng (Meta); Udit Gupta (Harvard Univ.); Manoj Chakkaravarthy (Meta); David Brooks (Harvard Univ.); Carole-Jean Wu (Meta)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Ecovisor: A Virtual Energy System for Carbon-Efficient Applications\n <\/div>\n
\n Abel Souza, Noman Bashir, Jorge Murillo, Walid Hanafy, Qianlin Liang, David Irwin, Prashant Shenoy (Univ. of Massachusetts Amherst)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 3B: Accelerators A\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Adrian Sampson (Cornell Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Mapping Very Large Scale Spiking Neuron Network to Neuromorphic Hardware\n <\/div>\n
\n Ouwen Jin, Qinghui Xing, Ying Li, Shuiguang Deng, Shuibing He, Gang Pan (Zhejiang Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n HuffDuff: Stealing Pruned DNNs from Sparse Accelerators\n <\/div>\n
\n Dingqing Yang, Prashant J. Nair, Mieszko Lis (Univ. of British Columbia)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n OCCAMY: Elastically Sharing a SIMD Co-Processor Across Multiple CPU Cores\n <\/div>\n
\n Zhongcheng Zhang (Inst. of Computing Technology, Chinese Academy of Sciences); Yan Ou (Turing Business Department, HiSilicon Technologies Company, Ltd); Ying Liu, Chenxi Wang (Inst. of Computing Technology, Chinese Academy of Sciences); Yongbin Zhou, Xiaoyu Wang (Turing Business Department, HiSilicon Technologies Company, Ltd); Yuyang Zhang, Yucheng Ouyang (Inst. of Computing Technology, Chinese Academy of Sciences); Jiahao Shan (unaffiliated); Ying Wang (Inst. of Computing Technology, Chinese Academy of Sciences); Jingling Xue (Univ. of New South Wales, Sydney); Huimin Cui, Xiaobing Feng (Inst. of Computing Technology, Chinese Academy of Sciences)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 3C: Persistence\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Mike Bond (Ohio State Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Efficient Compactions Between Storage Tiers with PrismDB\n <\/div>\n
\n Ashwini Raina, Jianan Lu (Princeton Univ.); Asaf Cidon (Columbia Univ.); Michael J. Freedman (Princeton Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Persistent Memory Disaggregation for Cloud-Native Relational Databases\n <\/div>\n
\n Chaoyi Ruan (Univ. of Science and Technology of China \/ Alibaba Cloud); Yingqiang Zhang (Alibaba Cloud); Chao Bi (Univ. of Science and Technology of China \/ Alibaba Cloud); Xiaosong Ma (Qatar Computing Research Inst., Hamad Bin Khalifa Univ.); Hao Chen, Feifei Li, Xinjun Yang (Alibaba Cloud); Cheng Li (Univ. of Science and Technology of China); Ashraf Aboulnaga (Qatar Computing Research Inst., Hamad Bin Khalifa Univ.); Yinlong Xu (Univ. of Science and Technology of China)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n SpecPMT: Speculative Logging for Resolving Crash Consistency Overhead of Persistent Memory\n <\/div>\n
\n Chencheng Ye (Huazhong Univ. of Science and Technology); Yuanchao Xu, Xipeng Shen (North Carolina State Univ.); Yan Sha, Xiaofei Liao, Hai Jin (Huazhong Univ. of Science and Technology); Yan Solihin (Univ. of Central Florida)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

3:50 PM PDT<\/span> – 5:10 PM PDT<\/span>: Poster Session 1<\/h3>\n
\n Location: Junior Ballroom & Junior Foyer\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

5:10 PM PDT<\/span> – 6:10 PM PDT<\/span>: WACI: Wild and Crazy Ideas<\/a><\/h3>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

6:10 PM PDT<\/span> – 7:10 PM PDT<\/span>: Business Meeting<\/h3>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n<\/div>\n\n
\n\n
\n
\n Jump to\n Sat\/Sun<\/a> |\n Monday<\/a> |\n Tuesday<\/a> |\n Wednesday<\/a> \n Expand All<\/a> \/ \n Collapse All<\/a> Sessions\n <\/div>\n<\/div>\n\n
\n\n<\/a>\n
\n
\n

Day 2: Tuesday, March 28<\/h2>\n <\/div>\n\n
\n

8:00 AM PDT<\/span> – 9:00 AM PDT<\/span>: Breakfast<\/h3>\n
\n Location: Junior Ballroom & Pavillion Ballroom\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

\n 9:00 AM PDT<\/span> – 10:00 AM PDT<\/span>:\n Keynote 2 by Abhishek Bhattacharjee\n (Yale Univ.)<\/span>\n <\/h3>\n <\/div>\n
\n
\n
\n

\n \n Direct Mind-Machine Teaming\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n

\n \"Abhishek\n Abstract<\/b>\n Direct mind-machine teaming will help us treat brain disorders, augment the healthy brain, and shed light on how the brain as an organ gives rise to the mind. Delivering on this promise requires the design of computer systems that delicately balance the tight power, latency, and bandwidth trade-offs needed to decode brain activity, stimulate biological neurons, and control assistive devices most effectively.This talk presents my group's design of a standardized and general computer architecture for future brain interfacing. Our design enables the treatment of several neurological disorders (most notably, epilepsy and movement disorders) and lays the groundwork for brain interfacing techniques that can help augment cognitive control and decision-making in the healthy brain. Central to our design is end-to-end hardware acceleration, from the microarchitectural to the distributed system level. Key insights are undergirded via detailed physical synthesis models and chip tape-outs in a 12nm CMOS process.\n <\/p>\n

\n

\n Bio<\/b>\n Abhishek Bhattacharjee is an Associate Professor of Computer Science at Yale University. His work on hardware optimizations for memory translation has influenced the design of TLBs in AMD CPUs, starting with the Zen 1 architecture, and in NVIDIA's GPUs, starting with the Ampere architecture. His work on software optimizations for memory translation has been shipped in the Linux OS since the 4.14 kernel. More recently, Abhishek has been building flexible and low-power architectures for brain-computer interfacing — the topic of this talk.\n <\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n

\n

10:00 AM PDT<\/span> – 10:20 AM PDT<\/span>: Coffee Break<\/h3>\n
\n Location: Grand Foyer\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

10:20 AM PDT<\/span> – 12:00 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 4A: Design Tools\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Brandon Lucia (Carnegie Mellon Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Simulator Independent Coverage for RTL Hardware Languages\n <\/div>\n
\n Kevin Laeufer, Vighnesh Iyer, David Biancolin, Jonathan Bachrach, Borivoje Nikolic, Koushik Sen (Univ. of California, Berkeley)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n RepCut: Superlinear Parallel RTL Simulation with Replication-Aided Partitioning\n <\/div>\n
\n Haoyuan Wang, Scott Beamer (Univ. of California, Santa Cruz)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n SMAPPIC: Scalable Multi-FPGA Architecture Prototype Platform in the Cloud\n <\/div>\n
\n Grigory Chirkov, David Wentzlaff (Princeton Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n ShakeFlow: Functional Hardware Description with Latency-Insensitive Interface Combinators\n <\/div>\n
\n Sungsoo Han, Minseong Jang, Jeehoon Kang (KAIST)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n eHDL: Turning eBPF\/XDP Programs into Hardware Designs for the NIC\n <\/div>\n
\n Alessandro Rivitti (Axbryd \/ Tor Vergata Univ. of Rome); Roberto Bifulco (NEC Laboratories Europe); Angelo Tulumello (Axbryd \/ Tor Vergata Univ. of Rome); Marco Bonola (Axbryd); Salvatore Pontarelli (Sapienza Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n CaT: A Solver-Aided Compiler for Packet-Processing Pipelines\n <\/div>\n
\n Xiangyu Gao (New York Univ.); Divya Raghunathan, Ruijie Fang (Princeton Univ.); Tao Wang, Xiaotong Zhu, Anirudh Sivaraman (New York Univ.); Srinivas Narayana (Rutgers Univ.); Aarti Gupta (Princeton Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 4B: Memory Mgmt. \/ Near Data Processing\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Jayneel Gandhi (Meta)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n TeraHeap: Reducing Memory Pressure in Managed Big Data Frameworks\n <\/div>\n
\n Iacovos G. Kolokasis, Giannos Evdorou (Univ. of Crete \/ ICS-FORTH); Shoaib Akram (Australian National Univ.); Christos Kozanitis (ICS-FORTH); Anastasios Papagiannis (Isovalent); Foivos Zakkak (Red Hat, Inc.); Polyvios Pratikakis, Angelos Bilas (Univ. of Crete \/ ICS-FORTH)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Copy-on-Pin: The Missing Piece for Correct Copy-on-Write\n <\/div>\n
\n David Hildenbrand, Martin Schulz (Technical Univ. of Munich); Nadav Amit (VMware Research Group)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Mosaic Pages: Big TLB Reach with Small Pages\n <\/div>\n
\n Krishnan Gosakan (Rutgers Univ.); Jaehyun Han (Univ. of North Carolina at Chapel Hill); William Kuszmaul (Massachusetts Inst. of Technology); Ibrahim Nael Mubarek, Nirjhar Mukherjee (Carnegie Mellon Univ.); Karthik Sriram (Yale Univ.); Guido Tagliavini (Rutgers Univ.); Evan West, Michael Bender (Stony Brook Univ.); Abhishek Bhattacharjee (Yale Univ.); Alex Conway (VMware Research); Martin Farach-Colton (Rutgers Univ.); Jayneel Gandhi (Meta); Rob Johnson (VMware Research); Sudarsun Kannan (Rutgers Univ.); Donald Porter (Univ. of North Carolina at Chapel Hill)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Revisiting Log-structured Merging for KV Stores in Hybrid Memory Systems\n <\/div>\n
\n Zhuohui Duan, Jiabo Yao, Haikun Liu, Xiaofei Liao, Hai Jin, Yu Zhang (Huazhong Univ. of Science and Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n ABNDP: Co-Optimizing Data Access and Load Balance in Near-Data Processing\n <\/div>\n
\n Boyu Tian, Qihang Chen, Mingyu Gao (Tsinghua Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Infinity Stream: Portable and Programmer-Friendly In-\/Near-Memory Fusion\n <\/div>\n
\n Zhengrong Wang, Christopher Liu (Univ. of California, Los Angeles); Aman Arora, Lizy John (Univ. of Texas at Austin); Tony Nowatzki (Univ. of California, Los Angeles)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 4C: Tensor Computation\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Dimitrios Skarlatos (Carnegie Mellon Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Flexagon: A Multi-Dataflow Sparse-Sparse Matrix Multiplication Accelerator for Efficient DNN Processing\n <\/div>\n
\n Francisco Munoz-Martinez (Universidad de Murcia); Raveesh Garg (Georgia Inst. of Technology); Michael Pellauer (NVIDIA); José L. Abellan, Manuel E. Acacio (Universidad de Murcia); Tushar Krishna (Georgia Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Accelerating Sparse Data Orchestration via Dynamic Reflexive Tiling\n <\/div>\n
\n Toluwanimi O. Odemuyiwa (Univ. of California, Davis); Hadi Asghari-Moghaddam (Univ. of Illinois Urbana-Champaign \/ Meta); Michael Pellauer (NVIDIA); Kartik Hegde (Univ. of Illinois Urbana-Champaign); Po-An Tsai, Neal Crago, Aamer Jaleel (NVIDIA); John D. Owens (Univ. of California, Davis); Edgar Solomonik (Univ. of Illinois Urbana-Champaign); Joel Emer (Massachusetts Inst. of Technology \/ NVIDIA); Christopher Fletcher (Univ. of Illinois Urbana-Champaign)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n SPADA: Accelerating Sparse Matrix Multiplication with Adaptive Dataflow\n <\/div>\n
\n Zhiyao Li (Tsinghua Univ.); Jiaxiang Li (Northwestern Univ.); Taijie Chen (Tsinghua Univ.); Dimin Niu, Hongzhong Zheng, Yuan Xie (Alibaba DAMO Academy); Mingyu Gao (Tsinghua Univ. \/ Shanghai Qi Zhi Inst.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning\n <\/div>\n
\n Zihao Ye (Univ. of Washington); Ruihang Lai (Carnegie Mellon Univ.); Junru Shao (OctoML); Tianqi Chen (Carnegie Mellon Univ.); Luis Ceze (Univ. of Washington)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Hidet: Task Mapping Programming Paradigm for Deep Learning Tensor Programs\n <\/div>\n
\n Yaoyao Ding (Univ. of Toronto \/ Vector Inst.); Cody Hao Yu (Amazon Web Services); Bojian Zheng (Univ. of Toronto \/ Vector Inst.); Yizhi Liu, Yida Wang (Amazon Web Services); Gennady Pekhimenko (Univ. of Toronto \/ Vector Inst.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n The Sparse Abstract Machine\n <\/div>\n
\n Olivia Hsu, Maxwell Strange, Ritvik Sharma (Stanford Univ.); Jaeyeon Won (Massachusetts Inst. of Technology); Kunle Olukotun (Stanford Univ.); Joel Emer (Massachusetts Inst. of Technology \/ NVIDIA); Mark A Horowitz, Fredrik Kjolstad (Stanford Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

12:00 PM PDT<\/span> – 1:40 PM PDT<\/span>: Lunch<\/h3>\n
\n Location: Junior Ballroom & Pavillion Ballroom\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

1:40 PM PDT<\/span> – 3:20 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 5A: Debugging\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Pedro Fonseca (Purdue Univ.)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Compilation Consistency Modulo Debug Information\n <\/div>\n
\n Theodore Luo Wang, Yongqiang Tian, Yiwen Dong, Zhenyang Xu, Chengnian Sun (Univ. of Waterloo)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Where Did My Variable Go? Poking Holes in Incomplete Debug Information\n <\/div>\n
\n Cristian Assaiante, Daniele Cono D'Elia, Giuseppe Antonio Di Luna, Leonardo Querzoni (Sapienza Univ. of Rome)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Protecting Data Integrity of Web Applications With Database Constraints Inferred From Application Code\n <\/div>\n
\n Haochen Huang, Bingyu Shen, Li Zhong, Yuanyuan Zhou (Univ. of California, San Diego)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n VClinic: A Portable and Efficient Framework for Fine-grained Value Profilers\n <\/div>\n
\n Xin You, Hailong Yang, Kelun Lei, Zhongzhi Luan, Depei Qian (Beihang Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Vidi: Record Replay for Reconfigurable Hardware\n <\/div>\n
\n Gefei Zuo, Jiacheng Ma (Univ. of Michigan); Andrew Quinn (Univ. of California, Santa Cruz); Baris Kasikci (Univ. of Michigan \/ Google)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n DrGPUM: Guiding Memory Optimization for GPU-accelerated Applications\n <\/div>\n
\n Mao Lin (Univ. of California, Merced); Keren Zhou (Rice Univ.); Pengfei Su (Univ. of California, Merced)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 5B: Storage\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Huaicheng Li (Virginia Tech)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Disaggregated RAID Storage in Modern Datacenters\n <\/div>\n
\n Junyi Shu, Ruidong Zhu, Yun Ma, Gang Huang, Hong Mei, Xuanzhe Liu, Xin Jin (Peking Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Reconfigurable Virtual Memory for FPGA-Driven I\/O\n <\/div>\n
\n Joshua Landgraf, Matthew Giordano, Esther Yoon (Univ. of Texas at Austin); Christopher J. Rossbach (Univ. of Texas at Austin \/ Katana Graph)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n LeaFTL: A Learning-based Flash Translation Layer for Solid-State Drives\n <\/div>\n
\n Jinghan Sun, Shaobo Li (Univ. of Illinois Urbana-Champaign); Yunxin Sun (ETH Zürich); Chao Sun, Dejan Vucinic (Western Digital Research); Jian Huang (Univ. of Illinois Urbana-Champaign)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n RAIZN: Redundant Array of Independent Zoned Namespaces\n <\/div>\n
\n Thomas Kim, Jekyeom Jeon, Nikhil Arora, Huaicheng Li (Carnegie Mellon Univ.); Michael Kaminsky (BrdgAI \/ Carnegie Mellon Univ.); David Andersen, Gregory R. Ganger, George Amvrosiadis (Carnegie Mellon Univ.); Matias Bjørling (Western Digital)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Re-architecting I\/O Caches for Emerging Fast Storage Devices\n <\/div>\n
\n Mohammadamin Ajdari (HPDS Research \/ Sharif Univ. of Technology); Pouria Peykani Sani, Amirhossein Moradi, Masoud Khanalizadeh Imani (Sharif Univ. of Technology); Amir Hossein Bazkhanei (HPDS Research \/ Sharif Univ. of Technology); Hossein Asadi (Sharif Univ. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Prism: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices\n <\/div>\n
\n Yongju Song (Sungkyunkwan Univ.); Wook-Hee Kim (Konkuk Univ.); Sumit Kumar Monga, Changwoo Min (Virginia Tech); Young Ik Eom (Sungkyunkwan Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 5C: Machine Learning\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Alexandros Daglis (Georgia Inst. of Technology)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Homunculus: Auto-Generating Efficient Data-Plane ML Pipelines for Datacenter Networks\n <\/div>\n
\n Tushar Swamy (Stanford Univ.); Annus Zulfiqar (Purdue Univ.); Luigi Nardi (Lund Univ. \/ Stanford Univ.); Muhammad Shahbaz (Purdue Univ.); Kunle Olukotun (Stanford Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n TensorIR: An Abstraction for Automatic Tensorized Program Optimization\n <\/div>\n
\n Siyuan Feng (Shanghai Jiao Tong Univ.); Bohan Hou, Hongyi Jin (Carnegie Mellon Univ.); Wuwei Lin, Junru Shao (OctoML); Ruihang Lai (Carnegie Mellon Univ.); Zihao Ye (Univ. of Washington); Lianmin Zheng (Univ. of California, Berkeley); Cody Hao Yu (Amazon Web Services); Yong Yu (Shanghai Jiao Tong Univ.); Tianqi Chen (Carnegie Mellon Univ. \/ OctoML)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks\n <\/div>\n
\n Sheng-Chun Kao (Georgia Inst. of Technology); Suvinay Subramanian (Google); Gaurav Agrawal (Microsoft); Amir Yazdanbakhsh (Google Research, Brain Team); Tushar Krishna (Georgia Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n TLP: A Deep Learning-based Cost Model for Tensor Program Tuning\n <\/div>\n
\n Yi Zhai, Yu Zhang, Shuo Liu, Xiaomeng Chu, Jie Peng, Jianmin Ji, Yanyong Zhang (Univ. of Science and Technology of China)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Mobius: Fine Tuning Large-scale Models on Commodity GPU Servers\n <\/div>\n
\n Yangyang Feng, Minhui Xie, Zijie Tian, Shuo Wang, Youyou Lu, Jiwu Shu (Tsinghua Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Betty: Enabling Large-Scale GNN Training with Batch-Level Graph Partitioning\n <\/div>\n
\n Shuangyan Yang (Univ. of California, Merced); Minjia Zhang (Microsoft Research); Wenqian Dong, Dong Li (Univ. of California, Merced)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

3:20 PM PDT<\/span> – 3:40 PM PDT<\/span>: Coffee Break<\/h3>\n
\n Location: Grand Foyer\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

3:40 PM PDT<\/span> – 4:30 PM PDT<\/span><\/h3>\n <\/div>\n \n
\n
\n
\n

\n \n Session 6A: Quantum A\n <\/a>\n <\/h4>\n
\n Location: Grand AB\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Brandon Reagen (New York Univ. \/ Meta)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Qompress: Efficient Compilation for Ququarts Exploiting Partial and Mixed Radix Operations for Communication Reduction\n <\/div>\n
\n Andrew Litteken, Lennart Maximilian Seifert, Jason Chadwick, Natalia Nottingham, Frederick T Chong, Jonathan Baker (Univ. of Chicago)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Verification of nondeterministic quantum programs\n <\/div>\n
\n Yuan Feng, Yingte Xu (Univ. of Technology Sydney)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n CAFQA: A classical simulation bootstrap for variational quantum algorithms\n <\/div>\n
\n Gokul Subramanian Ravi (Univ. of Chicago); Pranav Gokhale (Super.tech); Yi Ding (Massachusetts Inst. of Technology); William Kirby (Tufts Univ.); Kaitlin Smith, Jonathan Baker (Univ. of Chicago); Peter J. Love (Tufts Univ.); Henry Hoffmann (Univ. of Chicago); Kenneth R. Brown (Duke Univ.); Frederic Chong (Univ. of Chicago)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 6B: Networking\n <\/a>\n <\/h4>\n
\n Location: Grand C\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Sergey Blagodurov (AMD)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n In-Network Aggregation with Transport Transparency for Distributed Training\n <\/div>\n
\n Shuo Liu, Qiaoling Wang, Junyi Zhang (Huawei Technologies Co., Ltd.); Wenfei Wu (Peking Univ.); Qinliang Lin (Huawei Technologies Co., Ltd.); Yao Liu (Sun Yat-sen Univ.); Meng Xu (Huawei Technologies Co., Ltd.); Marco Canini (King Abdullah Univ. of Science and Technology); Ray C. C. Cheung, Jianfei He (City Univ. of Hong Kong)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Rosebud: Making FPGA-accelerated Middlebox Development More Pleasant\n <\/div>\n
\n Moein Khazraee (Massachusetts Inst. of Technology); Alex Forencich, George C. Papen (Univ. of California, San Diego); Alex C. Snoeren (UC San Diego \/ Google); Aaron Schulman (Univ. of California, San Diego)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n Cooperative Concurrency Control for Write-Intensive Key-Value Workloads\n <\/div>\n
\n Mark Sutherland, Babak Falsafi (EcoCloud \/ EPFL); Alexandros Daglis (Georgia Inst. of Technology)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n \n
\n
\n
\n

\n \n Session 6C: Graphs A\n <\/a>\n <\/h4>\n
\n Location: Grand D\n (GB level, below ground<\/a>)<\/span>\n <\/h5>\n <\/div>\n \n
\n
\n
\n Session Chair: Chris Rossbach (Univ. of Texas at Austin \/ Katana Graph)<\/span>\n <\/div>\n
\n <\/span> Session Lightning Talks<\/a>\n <\/div>\n
\n
\n Glign: Taming Misaligned Graph Traversals in Concurrent Graph Processing\n <\/div>\n
\n Xizhe Yin, Zhijia Zhao, Rajiv Gupta (Univ. of California, Riverside)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n NosWalker: A Decoupled Architecture for Out-of-Core Random Walk Processing\n <\/div>\n
\n Shuke Wang, MingXing Zhang (Tsinghua Univ.); Ke Yang (Tsinghua Univ. \/ Beijing HaiZhi XingTu Technology Co., Ltd.); Kang Chen, Shaonan Ma, Jinlei Jiang, Yongwei Wu (Tsinghua Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n
\n
\n
\n DecoMine: A Compilation-based Graph Pattern Mining System with Pattern Decomposition\n <\/div>\n
\n Jingji Chen, Xuehai Qian (Purdue Univ.)\n <\/div>\n
\n <\/span> Paper<\/a>\n •\n <\/span> Lightning Talk<\/a>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n <\/div>\n\n
\n

4:30 PM PDT<\/span> – 6:00 PM PDT<\/span>: Poster Session 2<\/h3>\n
\n Location: Junior Ballroom & Junior Foyer\n (3rd floor<\/a>)<\/span>\n <\/h5>\n <\/div>\n\n
\n

6:30 PM PDT<\/span> – 11:00 PM PDT<\/span>: Excursion, Banquet, and Awards: Vancouver Aquarium<\/a><\/h3>\n