* All times in Singapore time (SGT). Eastern Time (ET) is 12 hours behind and Centra European Time (CET) is 6 hours behind.

StartEnd Sunday, May 22, 2022
09:00 13:00
Tutorial: Multi-threading Simulation
LoopPoint and ELFies: Tools and Techniques to Accelerate Architecture Simulations of Complex Multi-threaded Applications using Checkpointing
Alen Sabu (National University of Singapore), Changxi Liu (National University of Singapore), Harish Patil (Intel), Wim Heirman (Intel), Trevor E. Carlson (National University of Singapore)
13:00 14:00
Break
14:00 16:55
Tutorial: Hardware Security Tutorial on Efficient security protocols, Fault injection and Side-channel attacks
The Laser Attack Benchmark Suite (LABS)
Burin Amornpaisannon (National University of Singapore), Andreas Diavastos (National University of Singapore), Li-Shiuan Peh (National University of Singapore), Trevor E. Carlson (National University of Singapore)
A multi-level evaluation framework for side-channel evaluations on embedded devices
Shivam Bhasin (Nanyang Technological University)
Efficient Security Protocol Realization for Secure Processors
Naina Gupta (Nanyang Technological University), Anupam Chattopadhyay (Nanyang Technological University)
18:00 -
Welcome Session
StartEnd Monday, May 23, 2022
08:00 08:15
Registration Opens
08:15 08:30
Welcome
08:30 09:30
Keynote I: Building Quantum Computers with Superconducting Circuits
Speaker: Yvonne Gao
(National University of Singapore)
09:30 10:00
Break
10:00 11:20
Paper Session I: Best Paper Nominations
Session Chair: Trevor E. Carlson
(National University of Singapore)
Profiling Intel Graphics Architecture with Long Instruction Traces
Konstantin Levit-Gurevich (Intel Corporation), Alex Skaletsky (Intel Corporation), Michael Berezalsky (Intel Corporation), Yulia Kuznotcova (Intel Corporation), Hila Yakov (Intel Corporation)
Performance Analysis and Optimization with Little's Law
Sanyam Mehta (HPE)
The Indigo Program-Verification MicrobenchmarkSuite of Irregular Parallel Code Patterns
Yiqian Liu (Texas State University), Noushin Azami (Texas State University), Corbin K. Walters (Texas State University), Martin Burtscher (Texas State University)
gpuFI-4: A Microarchitecture-Level Framework for Assessing the Cross-Layer Resilience of Nvidia GPUs
Dimitris Sartzetakis (University of Athens), George Papadimitriou (University of Athens), Dimitris Gizopoulos (University of Athens)
11:20 12:50
Lunch
12:50 14:30
Paper Session II: Simulation Technologies and Performance Analysis
Session Chair: Jialin Li
(National University of Singapore)
Distilling the Real Cost of Production Garbage Collectors
Zixian Cai (Australian National University), Stephen M. Blackburn (Australian National University), Michael D. Bond (Ohio State University), Martin Maas (Google)
Scale-Model Architectural Simulation
Wenjie Liu (Ghent University), Wim Heirman (Intel), Stijn Eyerman (Intel), Shoaib Akram (Australian National University), Lieven Eeckhout (Ghent University)
MEGsim: A Novel Methodology for Efficient Simulation of Graphics Workloads in GPUs
Jorge Ortiz-Escribano (University of Murcia), David Corbalan-Navarro (University of Murcia), Juan Luis Aragon (University of Murcia), Antonio Gonzalez (Polytechnic University of Catalonia)
MARTA: Multi-configuration Assembly pRofiler and Toolkit for performance Analysis
Marcos Horro (Universidade da Coruna), Louis-Noel Pouchet (Colorado State University), Gabriel Rodriguez (Universidade da Coruna), Juan Tourino (Universidade da Coruna)
Left-shifter : A pre-silicon framework for usage model based performance verification of the PCIe interface in server processor system on chips.
Tessil Thomas (Arm Limited), Bharath Venkatasubramanian (Arm Limited), Dinesh Sthapit (Arm Limited), Christopher Gray (Arm Limited), Atresh Gummadavelly (Arm Limited), Prabu Thangamuthu (Synopsys Inc), Pankaj Mehta (Synopsys Inc), Janick Bergeron (Synopsys Inc)
14:30 15:00
Break
15:00 16:00
Paper Session III: Code Generation and Optimization
Session Chair: Gregory J. Duck
(National University of Singapore)
Fourst: A code generator for FFT-based fast stencil computations
Zafar Ahmad (Stony Brook University), Mohammad Mahdi Javanmard (Meta Platforms, Inc.), Gregory Croisdale (The University of Tennessee, Knoxville), Aaron Gregory (Stony Brook University), Pramod Ganapathi (Stony Brook University), Louis-Noel Pouchet (Colorado State University), Rezaul Chowdhury (Stony Brook University)
Flexible Binary Instrumentation Framework to Profile Code Running on Intel GPUs
Konstantin Levit-Gurevich (Intel Corporation), Alex Skaletsky (Intel Corporation), Michael Berezalsky (Intel Corporation), Yulia Kuznetcova (Intel Corporation), Hila Yakov (Intel Corporation)
POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning
Shalini Jain (IIT Hyderabad), Yashas Andaluri (IIT Hyderabad), S. VenkataKeerthy (IIT Hyderabad), Ramakrishna Upadrasta (IIT Hyderabad)
16:00 16:45
Break and Poster Session I
*Poster sessions will consist of lightning talks, followed by Q&A in Zoom breakout sessions. After the lightning talks, join a room to ask questions with the poster authors.
XFeatur: Hardware Feature Extraction for DNN Auto-tuning
Jorge Sierra Acosta (Universitat Politecnica de Catalunya (UPC)), Andreas Diavastos (Universitat Politecnica de Catalunya (UPC)), Antonio Gonzalez (Universitat Politecnica de Catalunya (UPC))
SGXGauge: A Comprehensive Benchmark Suite for Intel SGX
Sandeep Kumar (IIT Delhi), Abhisek Panda (IIT Delhi), Smruti R. Sarangi (IIT Delhi)
SAPCo Sort: Optimizing Degree-Ordering for Power-Law Graphs
Mohsen Koohi Esfahani (Queen's University Belfast), Peter Kilpatrick (Queen's University Belfast), Hans Vandierendonck (Queen's University Belfast)
TILE-SIM: A Systematic Approach to Systolic Array-based Accelerator Evaluation
Yuhang Li (National University of Defense Technology), Mei Wen (National University of Defense Technology), Jiawei Fei (National University of Defense Technology), Junzhong Shen (National University of Defense Technology), Yasong Cao (National University of Defense Technology)
FASE: A Fast, Accurate and Seamless Emulator for Custom Numerical Formats
John Osorio (Barcelona Supercomputing Center, Universidad Politecnica de Catalunya), Adria Armejach (Barcelona Supercomputing Center, Universidad Politecnica de Catalunya), Eric Petit (Intel), Greg Henry (Intel), Marc Casas (Barcelona Supercomputing Center, Universidad Politecnica de Catalunya)
Meterstick: Benchmarking Performance Variability in Cloud and Self-Hosted Minecraft-like Games
Jerrit Eickhoff (TUDelft), Jesse Donkervliet (Vrije Universitiet Amsterdam), Alexandru Iosup (Vrije Universitiet Amsterdam)
Simulating Noisy Channels in DNA Storage
Mayank Keoliya (National University of Singapore), Puru Sharma (National University of Singapore), Djordje Jevdjic (National University of Singapore), Mayank Keoliya (National University of Singapore)
OS-level Implications of using DRAM caches in Memory Disaggregation
Bin Gao (National University of Singapore), Hao-Wei Tee (National University of Singapore), Alireza Sanaee (Queen Mary University of London), Soh Boon Jun (National University of Singapore), Djordje Jevdjic (National University of Singapore)
VIPP: Validation-Included Precision-Parametric N-Body Benchmark Suite
Shigeyuki Sato (The University of Tokyo), Kota Iizuka (Fixstars Corp.), Naoki Yoshifuji (Fixstars Corp.), Masaki Natsume (Fixstars Corp.)
High-Performance Deployment of Text Detection Model: Compression and Hardware Platform considerations
Nupur Sumeet (TCS Research), Manoj Nambiar (TCS Research), Karan Rawat (TCS Research)
StartEnd Tuesday, May 24, 2022
08:30 09:30
Keynote II: Silicon Cityscapes
Speaker: Gabriel Loh
(AMD Research)
09:30 10:00
Break
10:00 11:40
Paper Session IV: Benchmarks and Characterization of Emerging Workloads, Scheduling and Reliability
Session Chair: Roland Yap
(National University of Singapore)
Roofline Model for UAVs:A Bottleneck Analysis Tool for Designing Compute Systems for Autonomous Drones
Srivatsan Krishnan (Harvard University), Zishen Wan (Georgia tech), Kshitij Bhardwaj (LLNL), Ninad Jadhav (Harvard University), Aleksandra Faust (Google Brain Research), Vijay Janapa Reddi (Harvard University)
RTRBench: A Benchmark Suite for Real-Time Robotics
Mohammad Bakhshalipour (Carnegie Mellon University), Maxim Likhachev (Carnegie Mellon University), Phillip B. Gibbons (Carnegie Mellon University)
Characterization of MPC-based Private Inferences for Transformer-based Models
Yongqin Wang (University of Southern California), Edward Suh (Meta AI), Wenjie Xiong (Meta AI), Benjamin Lefaudeux (Meta AI), Brian Knott (Meta AI), Murali Annavaram (University of Southern California), Hsien-Hsin S. Lee (Meta AI)
Spatiotemporal Strategies for Long-Term FPGA Resource Management
Atefeh Mehrabi (Duke University), Daniel J. Sorin (Duke University), Benjamin C. Lee (University of Pennsylvania)
Eris: Fault Injection and Tracking Framework for Reliability Analysis of Open-Source Hardware
Shubham Nema (North Carolina State University), Justin Kirschner (North Carolina State University), Debpratim Adak (North Carolina State University), Sapan Agarwal (Sandia National Laboratories), Ben Feinberg (Sandia National Laboratories), Arun F. Rodrigues (Sandia National Laboratories), Matthew Marinella (Sandia National Laboratories), Amro Awad (North Carolina State University)
11:40 12:40
Break and Poster Session II
*Poster sessions will consist of lightning talks, followed by Q&A in Zoom breakout sessions. After the lightning talks, join a room to ask questions with the poster authors.
Understanding Data Compression in Warehouse-Scale Datacenter Services
Geonhwa Jeong (Georgia Institute of Technology), Bikash Sharma (Meta), Nick Terrell (Meta), Abhishek Dhanotia (Meta), Zhiwei Zhao (Meta), Niket Agarwal (Meta), Arun Kejariwal (Meta), Tushar Krishna (Georgia Institute of Technology)
LoopIn: A Loop-Based Simulation Sampling Mechanism with Efficient Warm-up Strategy
Uday Kumar Reddy Vengalam (University of Rochester), Anshujit Sharma (University of Rochester), Michael Huang (University of Rochester)
Building a Performance Model for Deep Learning Recommendation Model Training on GPUs
Zhongyi Lin (UC Davis), Louis Feng (Meta), Ehsan K. Ardestani (Meta), Jaewon Lee (Meta), John Lundell (Meta), Changkyu Kim (Meta), Arun Kejariwal (Meta), John D. Owens (UC Davis)
Advancing Near-Data Processing with Precise Exceptions and Efficient Data Fetching
Sairo Santos (UFPR), Tiago R. Kepe (UFPR), Francis B. Moreira (UFPR), Paulo C. Santos (UFRGS), Marco A. Z. Alves (UFPR)
Profiling an Architectural Simulator
Nedasadat Taheri (University of Kansas), Alexander Manley (University of Kansas), Ahmni R Pang-Johnson (University of Kansas), Mohammad Alian (University of Kansas)
Benchmarking Test-Time Unsupervised Deep Neural Network Adaptation on Edge Devices
Kshitij Bhardwaj (Lawrence Livermore National Laboratory), James Diffenderfer (Lawrence Livermore National Laboratory), Bhavya Kailkhura (Lawrence Livermore National Laboratory), Maya Gokhale (Lawrence Livermore National Laboratory)
GPUCalorie: Floorplan Estimation for GPU Thermal Evaluation
Marcus Chow (University of California Riverside), Ali Jahanshahi (University of California Riverside), Ana Cardenas Beltran (University of California Riverside), Sheldon Tan (University of California Riverside), Daniel Wong (University of California Riverside)
ARBench: Augmented Reality Benchmark For Mobile Devices
Sofiane Chetoui (Brown University), Rahul Shahi (Brown University), Seif Abdelaziz (Cupertino High School), Abhinav Golas (Meta Platforms), Farrukh Hijaz (Meta Platforms), Sherief Reda (Brown University)
Cross-Level Characterization of Program Behavior
Li Tang (Los Alamos National Laboratory), Scott Pakin (Los Alamos National Laboratory)
A SIMT Analyzer for Multi-Threaded CPU Applications
Ahmad Alawneh (Purdue University), Mahmoud Khairy (Purdue University), Timothy G. Rogers (Purdue University), Mahmoud Khairy (Purdue University)
Microarchitectural Performance Evaluation of AV1 Video Encoding Workloads
Steffen Jensen (UT Austin), Jaekyu Lee (Arm), Dam Sunwoo (Arm), Matt Horsnell (Arm), Lizy John (UT Austin)
12:40 14:10
Lunch
14:10 15:30
Paper Session V: Machine Learning Systems, Acceleration and Applications
Session Chair: Weng-Fai Wong
(National University of Singapore)
Ruby: Improving Hardware Efficiency for Tensor Algebra Accelerators Through Imperfect Factorization
Mark Horeni (University of Notre Dame), Pooria Taheri (University of Notre Dame), Po-An Tsai (NVIDIA), Angshuman Parashar (NVIDIA), Joel Emer (Massachusetts Institute of Technology (MIT), NVIDIA), Siddharth Joshi (University of Notre Dame)
Pareto Rank Surrogate Model for Hardware-aware Neural Architecture Search
Hadjer Benmeziane (Université Polytechnique Hauts-de-France, LAMIH/CNRS), Smail Niar (Université Polytechnique Hauts-de-France, LAMIH/CNRS, INSA), Hamza Ouarnoughi (Université Polytechnique Hauts-de-France, LAMIH/CNRS, INSA), Kaoutar El Maghraoui (IBM T. J. Watson Research Center)
Learning A Continuous and Reconstructible Latent Space for Hardware Accelerator Design
Qijing Huang (NVIDIA), Charles Hong (UC Berkeley), John Wawrzynek (UC Berkeley), Mahesh Subedar (Intel), Sophia Shao (UC Berkeley)
Bifrost: End-to-End Evaluation and Optimization of Reconfigurable DNN Accelerators
Axel Stjerngren (University of Glasgow), Perry Gibson (University of Glasgow), Jose Cano (University of Glasgow)
15:30 16:00
Break
16:00 17:00
Paper Session VI: Memory Technologies and Architectures
Session Chair: Magnus Själander
(Norwegian University of Science and Technology)
PCMCsim: An Accurate Phase-Change Memory Controller Simulator and its Performance Analysis
Hyokeun Lee (Seoul National University), Hyungsuk Kim (DEEPX), Seokbo Shim (SK Hynix), Seungyong Lee (Seoul National University), Dosun Hong (SK Hynix), Hyuk-Jae Lee (Seoul National University), Hyun Kim (Seoul National University of Science and Technology)
Address Translation Conscious Caching and Prefetching for High Performance Cache Hierarchy
Vasudha (IIT Kanpur (Qualcomm)), Biswabandan Panda (IIT Bombay)
DRAM Bandwidth and Latency Stacks: Visualizing DRAM Bottlenecks
Stijn Eyerman (Intel), Wim Heirman (Intel), Ibrahim Hur (Intel)
17:00 17:20
Concluding Remarks and Best Paper Announcement


This website is maintained by the ISPASS-2022 Committee.

Contact Andreas Diavastos if you have any questions or comments on this website.