Add to your calendar by clicking the + button above or download for iCal.
đź”—Conference Site
Note: All times below are in Pacific Time (GMT -07:00).
Monday, April 19th
| 7:00 – 7:30 AM | Opening and Award Announcements | |
|---|---|---|
| 7:30 – 7:45 AM | Session 1: Packet Up |
|
| 7:45 – 8:00 AM | Session 1: Q&A Panel | |
| 8:00 – 9:15 AM | Keynote: Chris Lattner (SiFive) | |
| 9:15 AM | Introduction to CARES | |
| 4:00 – 4:15 PM | Session 2: Memory Systems | |
| 4:15 – 4:30 PM | Session 2: Q&A Panel | Session 3: Flow |
| 4:30 – 4:45 PM | Session 4: Microservices | Session 3: Q&A Panel |
| 4:45 – 5:00 PM | Session 4: Q&A Panel | |
| 5:00 – 6:15 PM | An Interview with Timothy Pinkston (USC) | |
| 6:15 PM | Introduction to CARES | |
Tuesday, April 20th
| 7:00 – 7:15 AM | Session 5: Pages and Machine Architecture | |
|---|---|---|
| 7:15 – 7:30 AM | Session 5: Q&A Panel | Session 6: Languages and Systems 1 |
| 7:30 – 7:45 AM | Session 7: Towards Improved Throughput | Session 6: Q&A Panel |
| 7:45 – 8:00 AM | Session 7: Q&A Panel | |
| 8:00 – 9:15 AM | Influential Paper Awards + Ask a Program Chair – Emery Berger (UMass Amherst), Christos Kozyrakis (Stanford) | |
| 4:00 – 4:15 PM | Session 8: Tools and Frameworks | |
| 4:15 – 4:30 PM | Session 8: Q&A Panel | Session 9: Mapping and Management of Quantum and Cloud |
| 4:30 – 4:45 PM | Session 10: Persistence 1 | Session 9: Q&A Panel |
| 4:45 – 5:00 PM | Session 10: Q&A Panel | |
| 5:00 – 6:15 PM | Keynote: Dongmei Zhang (Microsoft) | |
Wednesday, April 21st
| 7:00 – 7:15 AM | Session 11: Quantum Abstractions | |
|---|---|---|
| 7:15 – 7:30 AM | Session 11: Q&A Panel | Session 12: Persistence 2 |
| 7:30 – 7:45 AM | Session 13: Systems Software | Session 12: Q&A Panel |
| 7:45 – 8:00 AM | Session 13: Q&A Panel | |
| 8:00 – 9:15 AM | Excursion (21st) | |
| 4:00 – 4:15 PM | Session 14: Beyond the Pixels | |
| 4:15 – 4:30 PM | Session 14: Q&A Panel | Session 15: Races and Concurrency |
| 4:30 – 4:45 PM | Session 16: Robots, Optimization, and Robo-optimization | Session 15: Q&A Panel |
| 4:45 – 5:00 PM | Session 16: Q&A Panel | |
| 5:00 – 6:15 PM | An Interview with Kathryn McKinley (Google) | |
Thursday, April 22nd
| 7:00 – 7:15 AM | Session 17: Solid State Drives | |
|---|---|---|
| 7:15 – 7:30 AM | Session 17: Q&A Panel | Session 18: Security 1 |
| 7:30 – 7:45 AM | Session 19: Better Hardware through Compilers | Session 18: Q&A Panel |
| 7:45 – 8:00 AM | Session 19: Q&A Panel | |
| 8:00 – 9:15 AM | Keynote: Nuria Oliver (ELLIS, DataPop Alliance) | |
| 4:00 – 4:15 PM | Session 20: Data Driven Optimization | |
| 4:15 – 4:30 PM | Session 20: Q&A Panel | Session 21: Supporting Hardware Parallelism |
| 4:30 – 4:45 PM | Session 22: Neural Net Optimization | Session 21: Q&A Panel |
| 4:45 – 5:00 PM | Session 22: Q&A Panel | |
| 5:00 – 6:15 PM | Excursion (22nd) | |
Friday, April 23rd
| 7:00 – 7:15 AM | Session 23: Beyond Neural Nets | |
|---|---|---|
| 7:15 – 7:30 AM | Session 23: Q&A Panel | Session 24: Language and Systems 2 |
| 7:30 – 7:45 AM | Session 25: Security 2 | Session 24: Q&A Panel |
| 7:45 – 8:00 AM | Session 25: Q&A Panel | |
| 8:00 – 9:15 AM | Panel: Industrial research in 2021 – Ricardo Bianchini (Microsoft) | |
Session Details
| Session 1: Packet Up Session Chair: Dan Tsafrir (Technion & VMware Research) | |
| #393 | PacketMill: Toward Per-Core 100-Gbps Networking |
| #499 | Autonomous NIC Offloads |
| #59 | Dagger: Efficient and Fast RPCs in Cloud Microservices with Near-Memory Reconfigurable NICs |
| Session 2: Memory Systems Session Chair: Sasha Fedorova (UBC) | |
| #379 | BCD Deduplication: Effective Memory Compression using Partial Cache-Line Deduplication |
| #844 | KLOCs: Kernel-Level Object Contexts for Heterogeneous Memory Systems |
| #210 | Rethinking Software Runtimes for Disaggregated Memory |
| Session 3: Flow Session Chair: Chris Fletcher (UIUC) | |
| #101 | DiAG: A Dataflow-Inspired Architecture for General-Purpose Processors |
| #402 | LifeStream: A High-Performance Stream Processing Engine for Periodic Streams |
| #79 | When Application-Specific ISA Meets FPGAs: A Multi-layer Virtualization Framework for Heterogeneous Cloud FPGAs |
| Session 4: Microservices Session Chair: Mike Marty (Google) | |
| #85 | Sage: Practical and Scalable ML-Driven Performance Debugging in Microservices |
| #89 | Nightcore: Efficient and Scalable Serverless Computing for Latency-Sensitive, Interactive Microservices |
| #43 | Sinan: ML-Based and QoS-Aware Resource Management for Cloud Microservices |
| Session 5: Pages and Machine Architecture Session Chair: Dimitrios Nikolopoulos (VT) | |
| #415 | NOREBA: A Compiler-Informed Non-speculative Out-of-Order Commit Processor |
| #158 | Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis |
| #111 | PTEMagnet: Fine-Grained Physical Memory Reservation for Faster Page Walks in Public Clouds |
| Session 6: Language and Systems 1 Session Chair: Daniel Sanchez (MIT) | |
| #1439 | In-Fat Pointer: Hardware-Assisted Tagged-Pointer Spatial Memory Safety Defense with Subobject Granularity Protection |
| #515 | Judging a Type by Its Pointer: Optimizing GPU Virtual Functions |
| #459 | Enclosure: Language-Based Restriction of Untrusted Libraries |
| Session 7: Towards Improved Throughputs Session Chair: Marco Serafini (UMass Amherst) | |
| #1375 | Switches for HIRE: Resource Scheduling for Data Center In-Network Computing |
| #1594 | Probabilistic Profiling of Stateful Data Planes for Adversarial Testing |
| #265 | MERCI: Efficient Embedding Reduction on Commodity Hardware via Sub-query Memoization |
| Session 8: Tools and Frameworks Session Chair: Yungang Bao (ICT, CAS) | |
| #974 | SherLock: Unsupervised Synchronization-Operation Inference |
| #926 | SIMDRAM: A Framework for Bit-Serial SIMD Processing using DRAM |
| #476 | Clobber-NVM: Log Less, Re-execute More |
| Session 9: Mapping and Management of Quantum and Cloud Session Chair: Jason Cong, (UCLA) | |
| #129 | Time-Optimal Qubit Mapping |
| #276 | Orchestrated Trios: Compiling for Efficient Communication in Quantum Programs with 3-Qubit Gates |
| #1225 | FaasCache: Keeping Serverless Computing Alive with Greedy-Dual Caching |
| Session 10: Persistence 1 Session Chair: Vijay Chidambaram (UT Austin & VMware Research) | |
| #44 | Hippocrates: Healing Persistent Memory Bugs without Doing Any Harm |
| #544 | Jaaru: Efficiently Model Checking Persistent Memory Programs |
| #171 | Corundum: Statically-Enforced Persistent Memory Safety |
| Session 11: Quantum Abstractions Session Chair: Marco Pistoia, JPMorgan Chase | |
| #772 | Qraft: Reverse Your Quantum Circuit and Know the Correct Program Output |
| #936 | Logical Abstractions for Noisy Variational Quantum Algorithm Simulation |
| #1241 | CutQC: Using Small Quantum Computers for Large Quantum Circuit Evaluations |
| Session 12: Persistence 2 Session Chair: Mike Swift (UW-Madison) | |
| #8 | PMFuzz: Test Case Generation for Persistent Memory Programs |
| #827 | Fast, Flexible, and Comprehensive Bug Detection for Persistent Memory Programs |
| #75 | PMEM-Spec: Persistent Memory Speculation (Strict Persistency Can Trump Relaxed Persistency) |
| Session 13: Systems Software Session Chair: Chris Rossbach (UT Austin) | |
| #922 | VSync: Push-Button Verification and Optimization for Synchronization Primitives on Weak Memory Models |
| #486 | CubicleOS: A Library OS with Software Componentisation for Practical Isolation |
| #212 | Benchmarking, Analysis, and Optimization of Serverless Function Snapshots |
| Session 14: Beyond the Pixels Session Chair: Adrian Sampson (Cornell) | |
| #588 | Rhythmic Pixel Regions: Multi-resolution Visual Sensing System towards High-Precision Visual Computing at Low Power |
| #228 | Q-VR: System-Level Design for Future Mobile Collaborative Virtual Reality |
| #388 | Warehouse-Scale Video Acceleration: Co-design and Deployment in the Wild |
| Session 15: Races and Concurrency Session Chair: Dan Lustig (NVIDIA) | |
| #1170 | Automatically Detecting and Fixing Concurrency Bugs in Go Software Systems |
| #172 | C11Tester: A Race Detector for C/C++ Atomics |
| #442 | Kard: Lightweight Data Race Detection with Per-Thread Memory Protection |
| Session 16: Robots, Optimization, and Robo-optimization Session Chair: Christina Delimitrou (Cornell) | |
| #321 | Quantifying the Design-Space Tradeoffs in Autonomous Drones |
| #857 | Robomorphic Computing: A Design Methodology for Domain-Specific Accelerators Parameterized by Robot Morphology |
| #95 | Gamma: Leveraging Gustavson’s Algorithm to Accelerate Sparse Matrix Multiplication |
| Session 17: Solid State Drives Session Chair: Steve Swanson (UC San Diego) | |
| #278 | Reducing Solid-State Drive Read Latency by Optimizing Read-Retry |
| #1455 | RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference |
| #500 | Prolonging 3D NAND SSD Lifetime via Read Latency Relaxation |
| Session 18: Security 1 Session Chair: Jakub Szefer (Yale University) | |
| #701 | PIBE: Practical Kernel Control-Flow Hardening with Profile-Guided Indirect Branch Elimination |
| #460 | Computing with Time: Microarchitectural Weird Machines |
| #548 | HerQules: Securing Programs via Hardware-Enforced Message Queues |
| Session 19: Better Hardware through Compilers Session Chair: Karu Sankaralingam (UW-Madison) | |
| #315 | Effective Simulation and Debugging for a High-Level Hardware Language using Software Compilers |
| #206 | A Compiler Infrastructure for Accelerator Generators |
| #990 | Compiler-Driven FPGA Virtualization with SYNERGY |
| Session 20: Data Driven Optimization Session Chair: Alexandre Passos (Google) | |
| #648 | BayesPerf: Minimizing Performance Monitoring Errors using Bayesian Statistics |
| #731 | Training for Multi-resolution Inference using Reusable Quantization Terms |
| #963 | A Hierarchical Neural Model of Data Prefetching |
| Session 21: Supporting Hardware Parallelism Session Chair: Lizy K. John (UT Austin) | |
| #142 | Vectorization for Digital Signal Processors via Equality Saturation |
| #113 | Scalable FSM Parallelization via Path Fusion and Higher-Order Speculation |
| #28 | VeGen: A Vectorizer Generator for SIMD and Beyond |
| Session 22: Neural Net Optimization Session Chair: Amir Yazdanbakhsh (Google Research) | |
| #969 | Neural Architecture Search as Program Transformation Exploration |
| #1367 | Analytical Characterization and Design Space Exploration for Optimization of CNNs |
| #1450 | Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search |
| Session 23: Beyond Neural Nets Session Chair: Sara Achour (Stanford) | |
| #62 | Statistical Robustness of Markov Chain Monte Carlo Accelerators |
| #593 | NeuroEngine: A Hardware-Based Event-Driven Simulation System for Advanced Brain-Inspired Computing |
| #898 | Defensive Approximation: Securing CNNs using Approximate Computing |
| Session 24: Language and Systems 2 Session Chair: James Bornholt (UT Austin) | #949 | Language-Parametric Compiler Validation with Application to LLVM |
| #1687 | Incremental CFG Patching for Binary Rewriting |
| #58 | Who’s Debugging the Debuggers? Exposing Debug Information Bugs in Optimized Binaries |
| Session 25: Security 2 Session Chair: Mengjia Yan (MIT) | |
| #148 | Speculative Interference Attacks: Breaking Invisible Speculation Schemes |
| #255 | Jamais Vu: Thwarting Microarchitectural Replay Attacks |
| #744 | Streamline: A Fast, Flushless Cache Covert-Channel Attack by Enabling Asynchronous Collusion |