Greetings Jim, Welcome to the IAP Newsletter with research publications, conferences and news regarding applications and infrastructure for AI and machine learning, hardware acceleration, operating systems, networking, security, and storage. | |
AI and CLOUD WORKSHOPS - 2023 and 2024 | |
|
Speakers Joel Emer and Carole-Jean Wu (center) pose with attendees during the Poster Session at lunch.
Speakers included:
Dr. Carole-Jean Wu, Meta, "Scaling AI Computing Sustainably"
Prof. Joel Emer, MIT and Nvidia, “Einsums, Fibertrees and Dataflow: Architecture for the Post-Moore Era”
Prof. Vijay Janapa Reddi, Harvard, “Architecture 2.0: Why Architects Need a Data-centric AI Gymnasium”
Dr. Richard Kessler, Marvell, “AI, Cloud, and Marvell Semiconductor”
Prof. Song Han, MIT, "TinyChat for On-device LLM"
Prof. Manya Ghobadi, MIT, “Next-Generation Optical Networks for Machine Learning Jobs”
Prof. Daniel Sanchez, MIT, "A Hardware and Software Architecture to Accelerate Computation on Encrypted Data"
Sundar Dev, Google, “AI-powered infrastructure for the AI-driven future”
Prof. Christina Delimitrou, MIT, “Designing the Next Generation Cloud Systems: To ML or not to ML”
Dr. Jiaqi Gao, Alibaba, “Towards a 100,000-GPU Machine Learning Infrastructure"
This was the fourth AI and Cloud Workshop hosted by MIT. Please see the MIT WORKSHOP WEB PAGE for the speaker bios, abstracts and videos of the presentations.
| |
UCSD WORKSHOP ON THE FUTURE OF AI and CLOUD COMPUTING
Friday, April 21, 2023
UCSD, CSE Building, La Jolla, CA
| |
Dr. Doug Terry, Distinguished Scientist and VP at AWS, kicks off the morning session with “Replicating Cloud Data Across Regions for Business Continuity."
Other Speakers on April 21 included:
Prof. Salman Avestimehr, USC, “Collaborative Machine Learning at the Edge”
Dr. Yunfei Ma, Alibaba, “Overcome the "Last-mile" Challenge through Wireless and Video Collaboration"
Prof. Amy Ousterhout, UCSD, "Optimizing CPU Efficiency and Tail Latency in Datacenters"
Prof. Yiying Zhang, UCSD, “An End-to-End Implementation of A “Server-less” Data Center”
Dr. Amir Yazdanbakhsh, Google, "From Data to Success: Leveraging Machine Learning for Full Stack Optimization"
Prof. Hung-Wei Tseng, UCR, “The upcoming revolution of general-purpose computing”
Prof. Hyoukjun Kwon, UCI, “XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse”
Prof. Hadi Esmaeilzadeh, UCSD, “Towards Architecting Machines for Empathic Conscious Intelligence”
This was the first AI and Cloud Workshop hosted by UCSD. Please see the UCSD WORKSHOP WEB PAGE for the speaker bios, abstracts and videos of the presentations.
| |
|
COMING in SPRING 2024
UW AI and CLOUD WORKSHOP
University of Washington
Seattle, WA
Organized by Prof. Arvind Krishnamurthy and the IAP.
Please watch for IAP Newsletters and our website for further updates on the date and agenda.
At right, Prof. Arvind Krishnamurthy presents at a previous IAP Workshop at UW.
| |
|
SELECT CONFERENCES and PUBLICATIONS in JUNE-DECEMBER 2023
MLSys 2023, Miami, FL, June 4-8, 2023
RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure Storage, Scheduling, and Networking
Mark Zhao (Stanford) · Dhruv Choudhary (Meta) · Devashish Tyagi (Meta) · Ajay Somani (Meta) · Max Kaplan (Meta) · Sung-Han Lin (Meta) · Sarunya Pumma (Meta) · Jongsoo Park (Meta) · Aarti Basant (Meta) · Niket Agarwal (NVIDIA) · Carole-Jean Wu (Meta) · Christos Kozyrakis (Stanford)
MegaBlocks: Efficient Sparse Training with Mixture-of-Experts Sparsity 1: Models and Algorithms
Trevor Gale (Stanford), Deepak Narayanan (Microsoft Research), Cliff Young (Google), Matei Zaharia (Stanford and Databricks)
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse Emerging Models and Domains
Hyoukjun Kwon (UC Irvine), Krishnakumar Nair (Meta) · Jamin Seo (Georgia Tech) · Jason Yik (Harvard) · Debabrata Mohapatra (Meta) · Dongyuan Zhan (Meta) · JINOOK SONG (META) · Peter Capak (Meta) · Peizhao Zhang (Meta) · Peter Vajda (Meta) · Colby Banbury (Harvard) · Mark Mazumder (Harvard) · Liangzhen Lai (Facebook Inc) · Ashish Sirasao (Meta inc) · Tushar Krishna (Georgia Tech) · Harshit Khaitan (Meta) · Vikas Chandra (Meta) · Vijay Janapa Reddi (Harvard)
On Optimizing the Communication of Model Parallelism Parallel and Distributed Systems 2: Communication
Yonghao Zhuang (Carnegie Mellon University) · Hexu Zhao (Tsinghua University) · Lianmin Zheng (UC Berkeley) · Zhuohan Li (UC Berkeley) · Eric Xing (MBZUAI, CMU, and Petuum Inc.) · Qirong Ho (MBZUAI) · Joseph Gonzalez (UC Berkeley) · Ion Stoica (UC Berkeley) · Hao Zhang (UC Berkeley) · Hexu Zhao (Tsinghua University)
| |
ISCA 2023, Orlando, Florida, June 17-22, 2023
Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks
Mingyu Liang, Wenyin Fu, Louis Feng, Zhongyi Lin, Pavani Panakanti, Shengbao Zheng, Srinivas Sridharan, Christina Delimitrou
μManycore: A Cloud-Native CPU for Tail at Scale
Jovan Stojkovic, Chunao Liu, Muhammad Shahbaz, Josep Torrella
Metior: A Comprehensive Model to Evaluate Obfuscating Side-Channel Defense Schemes
Peter W. Deutsch, Weon Taek Na, Thomas Bourgeat, Joel S. Emer, Mengjia Yan
RoboShape: Using Topology Patterns to Scalably and Flexibly Deploy Accelerators Across Robots
Sabrina M. Neuman, Radhika Ghosal, Thomas Bourgeat, Brian Plancher, Vijay Janapa Reddi
CDPU: Co-designing Compression and Decompression Processing Units for Hyperscale Systems
Sagar Karandikar, Aniruddha N. Udipi, Junsun Choi, Joonho Whangbo, Jerry Zhao, Svilen Kanev, Edwin Lim, Jyrki Alakuijala, Vrishab Madduri, Yakun Sophia Shao, Borivoje Nikolic, Krste Asanovic, Parthasarathy Ranganathan
ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design
Srivatsan Krishnan, Amir Yazdanbakhsh, Shvetank Prakash, Jason Jabbour, Ikechukwu Uchendu, Susobhan Ghosh, Behzad Boroujerdian, Daniel Richins, Devashree Tripathy, Aleksandra Faust, Vijay Janapa Redd
Profiling Hyperscale Data Processing
Abraham Gonzalez, Aasheesh Kolli, Samira Khan, Sihang Liu, Vidushi Dadu, Sagar Karandikar, Jichuan Chang, Krste Asanović, Parthasarathy Ranganathan
TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embedding
Norm Jouppi, George Kurian, Sheng Li, Peter Ma, Rahul Nagarajan, Lifeng Nai, Nishant Patil, Suvinay Subramanian, Andy Swin, Brian Towles, Clifford Young, Xiang Zhou, Zongwei Zhou, David A Patterson
A Research Retrospective on AMD’s Exascale Computing Journey
Gabriel H. Loh, Michael J. Schulte, Mike Ignatowski, V. Adhinarayanan, et. al.
| |
|
USENIX ATC, Boston, MA, July 10-12, 2023
Sky Computing
Ion Stoica, University of California, Berkeley
Comosum: An Extensible, Reconfigurable, and Fault-Tolerant IoT Platform for Digital Agriculture
Gloire Rubambiza, Shiang-Wan Chin, Mueed Rehman, Sachille Atapattu, José F. Martínez, and Hakim Weatherspoon, Cornell University
Tectonic-Shift: A Composite Storage Fabric for Large-Scale ML Training
Mark Zhao, Stanford University and Meta; Satadru Pan, Niket Agarwal, Zhaoduo Wen, David Xu, Anand Natarajan, Pavan Kumar, Shiva Shankar P, Ritesh Tijoriwala, Karan Asher, Hao Wu, Aarti Basant, Daniel Ford, Delia David, Nezih Yigitbasi, Pratap Singh, and Carole-Jean Wu, Meta; Christos Kozyrakis, Stanford University
SAGE: Software-based Attestation for GPU Execution
Andrei Ivanov and Benjamin Rothenberger, ETH Zürich; Arnaud Dethise and Marco Canini, KAUST; Torsten Hoefler and Adrian Perrig, ETH Zürich
Distributed Transactions at Scale in Amazon DynamoDB
Joseph Idziorek, Alex Keyes, Colin Lazier, Somu Perianayagam, Prithvi Ramanathan, James Christopher Sorenson III, Doug Terry, and Akshat Vig, Amazon Web Services
| |
|
SIGCOMM 2023, New York City, September 10-14, 2023
P4Testgen: An Extensible Test Oracle For P4-16
Fabian Ruffy (NYU), Jed Liu (Postman), Prathima Kotikalapudi, Vojtech Havel, Hanneli Tavante (Intel), Rob Sherwood (NetDebug.com), Vladyslav Dubina, Volodymyr Peschanenko (Litsoft), Anirudh Sivaraman (NYU), Nate Foster (Cornell)
Host Congestion Control
Saksham Agarwal (Cornell), Arvind Krishnamurthy (Google/University of Washington), Rachit Agarwal (Cornell)
Murphy: Performance Diagnosis of Distributed Cloud Applications
Vipul Harsh (University of Illinois Urbana-Champaign), Wenxuan Zhou (VMware), Sachin Ashok (UIUC), Radhika Niranjan Mysore (VMware Research), Brighten Godfrey (UIUC and VMware), Sujata Banerjee (VMware Research)
Exoshuffle: An Extensible Shuffle Architecture
Frank Sifei Luan, Stephanie Wang, Samyukta Yagati, Sean Kim, Kenneth Lien, Isaac Ong, Tony Hong (UC Berkeley), SangBin Cho, Eric Liang (Anyscale), Ion Stoica (UC Berkeley)
Destination Unreachable: Characterizing Internet Outages and Shutdowns
Zachary S. Bischof (Georgia Tech), Kennedy Pitcher (UC San Diego), Esteban Carisimo (Northwestern), Amanda Meng (Georgia Tech), Rafael Bezerra Nunes (Yale), Ramakrishna Padmanabhan (Amazon), Margaret E. Roberts (UC San Diego), Alex C. Snoeren (UC San Diego), Alberto Dainotti (Georgia Tech)
Resilient Baseband Processing in Virtualized RANs with Slingshot
Nikita Lazarev (MIT), Tao Ji (UT Austin), Anuj Kalia (Microsoft), Daehyeok Kim (UT Austin and Microsoft), Ilias Marinos, Francis Y. Yan (Microsoft), Christina Delimitrou (MIT), Zhiru Zhang (Cornell), Aditya Akella (The University of Texas at Austin)
CellFusion: Multipath Vehicle-to-Cloud Video Streaming with Network Coding in the Wild
Yunzhe Ni (Alibaba Cloud & Peking Univ.), Zhilong Zheng, Xianshang Lin, Fengyu Gao, Xuan Zeng, Yirui Liu, Tao Xu, Hua Wang, Zhidong Zhang, Senlang Du, Guang Yang, Yuanchao Su, Dennis Cai (Alibaba Cloud), Hongqiang Harry Liu (Uber Technology), Chenren Xu (Peking Univ.), Ennan Zhai, Yunfei Ma (Alibaba Cloud)
| |
|
ARCHITECTURE 2.0 - Virtual - September 15, 2023
Keynote: Partha Ranganathan
The goal of this virtual event is to identify the next generation of machine learning algorithms, datasets, tools, infrastructure, best practices, education and workforce training required to drive progress in our community.
| |
|
ACM SIGPLAN Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH) with Object-Oriented Programming, Systems, Languages & Applications (OOPSLA), Cascais, Portugal, October 22-27, 2023
Hydroflow: A Compiler Target for Fast, Correct Distributed Programs
Keynote
Joseph M. Hellerstein, UC Berkeley
A Full Employment Theorem for PL Researchers: Domain-Specific Languages
Nate Foster, Cornell
Degrees of Separation: A Flexible Type System for Data Race Prevention
Yichen Xu, EPFL, Aleksander Boruch-Gruszecki, EPFL, Martin Odersky, EPFL
Hardware-Aware Static Optimization of Hyperdimensional Computations
Pu (Luke) Yi, Stanford, Sara Achour, Stanford
Formal Abstractions for Packet Scheduling (Distinguished Paper Award)
Anshuman Mohan, Cornell, Yunhe Liu, Cornell University, Nate Foster, Cornell University, Tobias Kappé, Open University of the Netherlands; University of Amsterdam, Dexter Kozen, Cornell
| |
|
IEEE/ACM International Symposium on Microarchitecture (MICRO-56), Toronto, Canada, October 28-November 1, 2023
Social Infrastructure in the Age of Artificial General Intelligence
Amin Vahdat (Google)
Keynote
AuRORA: Virtualized Accelerator Orchestration for Multi-Tenant Workloads
Seah Kim, Jerry Zhao, Krste Asanovic, Borivoje Nikolic, Yakun Sophia Shao (UC Berkeley)
Accelerating RTL Simulation with Hardware-Software Co-Design
Fares Elsabbagh, Shabnam Sheikhha, Victor A. Ying, Quan M. Nguyen (MIT); Joel Emer (MIT/NVIDIA); Daniel
Sanchez (MIT)
Simultaneous and Heterogenous Multithreading
Kuan-Chieh Hsu, Hung-Wei Tseng (UC Riverside)
Spatula: A Hardware Accelerator for Sparse Matrix Factorization
Axel Feldmann, Daniel Sanchez (MIT)
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
Haotian Tang, Shang Yang, Zhijian Liu (MIT); Ke Hong (Tsinghua); Zhongming Yu (UC San Diego); Xiuyu Li
(UC Berkeley); Guohao Dai (Shanghai Jiao Tong University); Yu Wang (Tsinghua); Song Han (MIT)
SecureLoop: Design Space Exploration of Secure DNN Accelerators
Kyungmi Lee, Mengjia Yan (MIT); Joel Emer (MIT, NVIDIA); Anantha Chandrakasan (MIT)
HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity
Yannan Nellie Wu (MIT); Po-An Tsai, Saurav Muralidharan, Angshuman Parashar (NVIDIA); Vivienne Sze (MIT); Joel Emer (MIT/NVIDIA)
Victima: Drastically Increasing Address Translation Reach by Leveraging Underutilized Cache Resources
Konstantinos Kanellopoulos, Hong Chul Nam, Nisa Bostanci, Rahul Bera, Mohammad Sadrosadati (ETH Zürich); Rakesh Kumar (Norwegian University of Science and Technology (NTNU)); Davide Basilio Bartolini (Huawei); Onur Mutlu (ETH Zürich)
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
Ligeng Zhu (MIT); Lanxiang Hu (Columbia); Ji Lin, Wei-Ming Chen, Wei-Chen Wang, Chuang Gan, Song Han (MIT)
Pipestitch: An energy-minimal dataflow architecture with lightweight threads
Nathan Serafin, Souradip Ghosh, Harsh Desai, Nathan Beckmann, Brandon Lucia (Carnegie Mellon University)
| |
|
ACM Symposium on Cloud Computing 2023 (SoCC '23), Santa Cruz, CA, October 30-November 1, 2023
Dissecting Overheads of Service Mesh Sidecars
Xiangfeng Zhu (U of Washington); Guozhen She (Duke); Bowen Xue (U of Washington); Yu Zhang, Yongsu Zhang, Xuan Kelvin Zou, Xiong Chun Duan, Peng He (ByteDance Inc.); Arvind Krishnamurthy (U of Washington); Matthew Lentz (Duke University and VMware Research); Danyang Zhuo (Duke); Ratul Mahajan (U of Washington, Amazon)
Enabling Multi-tenancy on SSDs with Accurate IO Interference Modeling
Lokesh N. Jaliminche (UC Santa Cruz); Chandranil (Nil)
Chakraborttii (Trinity College, Hartford, USA); Changho Choi (Samsung
Semiconductor, Inc, USA); Heiner Litz (UC Santa Cruz)
TMC: Near-Optimal Resource Allocation for Tiered-Memory Systems
Yuanjiang Ni (Alibaba Group); Pankaj Mehra (Elephance Memory; Ethan Miller (Pure Storage / UC Santa Cruz); Heiner Litz (UC Santa Cruz)
Anticipatory Resource Allocation for ML Training Clusters
Tapan Chugh (U of Washington); Srikanth Kandula (Microsoft); Arvind Krishnamurthy (U of Washington); Ratul Mahajan (U of Washington, Amazon); Ishai Menache (Microsoft)
Disaggregating ML Input Data Processing at Scale
Andrew Audibert, Yang Chen (Google); Dan-Ovidiu Graur, Ana Klimovic (ETH Zurich); Jiri Simsa, Chandramohan A. Thekkath (Google)
Yama: Providing Performance Isolation for Black-Box Offloads
Tao Ji, Divyanshu Saxena (UT Austin); Brent Stephens (U of Utah); Aditya Akella (UT Austin and Google)
| |
|
AWARDS
2023 ACM-IEEE CS Eckert-Mauchly Award: The ACM and IEEE Computer Society named Kunle Olukotun, Professor at Stanford University, as the recipient of the ACM-IEEE CS Eckert-Mauchly Award for contributions and leadership in the development of parallel systems, especially multicore and multithreaded processors.
2023 ACM-IEEE CS Ken Kennedy Award: ACM has named Keshav Pingali, the W.A. "Tex" Moncrief Chair of Grid and Distributed Computing at the University of Texas at Austin, as the recipient of the 2023 ACM-IEEE CS Ken Kennedy Award. The Ken Kennedy Award recognizes groundbreaking achievements in parallel and high-performance computing. Pingali is cited for contributions to high-performance parallel computing for irregular algorithms such as graph algorithms.
BEST PAPER AWARDS
ASPLOS 2023 Distinguished Papers:
MC Mutants: Evaluating and Improving Testing for Memory Consistency Specifications
Reese Levine, Tianhao Guo, Mingun Cho, Alan Baker, Raph Levien, David Neto, Andrew Quinn, Tyler Sorensen
Pond: CXL-Based Memory Pooling Systems for Cloud Platforms
Huaicheng Li, Daniel S. Berger, Lisa Hsu, Daniel Ernst, Pantea Zardoshti, Stanko Novakovic, Monish Shah, Samir Rajadnya, Scott Lee, Ishwar Agarwal, Mark D. Hill, Marcus Fontoura, Ricardo Bianchini
RepCut: Superlinear Parallel RTL Simulation with Replication-Aided Partitioning
Haoyuan Wang and Scott Beamer
GRANTS and FUND RAISING
Hakim Weatherspoon and Robbert van Renesse (Cornell)
BOOKS
MACHINE LEARNING SYSTEMS with TINYML
Machine Learning Systems with TinyML” offers an accessible entry into the fascinating world of computing that enables machine learning, with a special focus on its implementation in resource-constrained environments using TinyML. This is an open source project on GitHub; contributors are welcome!
BLOGS
September 25, 2023
Remembering Luiz Barroso
by Partha Ranganathan
August 3, 2023
by Daniel S. Berger, David Brooks, Fiodar Kazhamiaka, Mark D. Hill, Ricardo Bianchini, Carole-Jean Wu, Karin Strauss, Kali Frost, Jaylen Wang, Kevin Martins, Sharon Gillett, Esha Choukse, Dan Ernst, Rodrigo Fonseca, Kari Lio, Bhargavi Narayanasetty, Pratyush Patel, Celine Irvene, Akshitha Sriraman, George Porter, Alex Jones, Udit Gupta, Bilge Acun-Uyan, Kim Hazelwood, and Doug Carmean
July 3, 2023
by José Martínez
June 14, 2023
Architecture 2.0: Why Computer Architects Need a Data-Centric AI Gymnasium
by Vijay Janapa Reddi and Amir Yazdanbakhsh
NEWS ITEMS
December 6, 2023
AMD Takes On Nvidia with New GPU for AI
September 13, 2023
Cornell Start-up Exostellar raises $15M to help companies optimize their cloud spend
August 9, 2023
Baidu, Bytedance, Tencent and Alibaba Order $5B of Nvidia Chips to Power AI Ambitions
June 20, 2023
AMD hopes to catch up on AI with Instinct MI300 AI supercomputing hybrid processor
June 14, 2023
OctoML launches OctoAI, a self-optimizing compute service for AI
May 26, 2023
Marvell Follows Nvidia as the Next Hot AI Stock. The Sector Is on Fire.
IAP Workshop Testimonials
Professor Christos Kozyrakis, Stanford - “As a starting point, I think of these IAP workshops as ‘Hot Chips meets ISCA’, i.e., an intersection of industry’s newest solutions in hardware (Hot Chips) with academic research in computer architecture (ISCA); but more so, these workshops additionally cover new subsystems and applications, and in a smaller venue where it is easy to discuss ideas and cross-cutting approaches with colleagues.”
Professor Heiner Litz, UC Santa Cruz - "The IAP workshops represent extremely valuable events for all attendees including industry members, students and faculty. On my side, multiple project collaborations and student internships have evolved from these meetings leading to a win-win-win situation for all participants.”
Prof. Ana Klimovic, ETH Zurich - “I have attended three IAP workshops as a PhD student at Stanford and was consistently impressed by the quality of the talks and the breadth of the topics covered. These workshops bring top-tier industry and academia together to discuss cutting-edge research challenges. It is a great opportunity to exchange ideas and get inspiration for new research opportunities."
Dr. Nathan Pemberton, Scientist, Amazon Web Services - "IAP workshops provide a valuable chance to explore emerging research topics with a focused group of participants, and without all the time/effort of a full-scale conference. Instead of rushing from talk to talk, you can slow down and dive deep into a few topics with experts in the field."
Support a unique tech forum that brings together academia and industry under your company's banner?
Please feel free to contact us regarding sponsorship opportunities, and for more info about any of the items above.
Best,
Jim Ballingall
Executive Director
Industry-Academia Partnership (IAP)
www.industry-academia.org
jim.ballingall@gmail.com
cel: 408-212-1035
| |
Copyright © 2013-2024 Industry-Academia Partnership | | | | |
