会议日程
| 2021-05-22 (Day 1): | ||
| Time | Sessions | Talks |
| 8:30 - 8:35 | 开幕 | |
| 8:35 - 9:05 | Session: Keynote I | 开源芯片与敏捷设计：现状与趋势，包云岗（中科院计算所）[演讲视频] |
| 9:05 - 9:35 | 高性能安全持久内存系统组织模式，华宇（华中科技大学） | |
| 9:35 - 10:05 | 百度量子平台：迈向量子人工智能，段润尧（百度）[演讲视频] | |
| 10:05 - 10:35 | ZZ年度忽悠，张峥（上海纽约大学） | |
| 10:35 - 10:45 | 茶歇 | |
| 10:45 - 11:00 | Session: Cloud & Data Center |
When Cloud Storage Meets RDMA，高翼枭（南京大学）[演讲视频] |
| 11:00 - 11:15 | PolarDB Serverless: A Cloud Native Database for Disaggregated Data Centers，章颖强（阿里巴巴） | |
| 11:15 - 11:30 | Bringing Decentralized Search to Decentralized Services，李明煜（上海交通大学）[演讲视频] | |
| 11:30 - 11:45 | Confidential Serverless Made Efficient with Plug-In Enclaves，李明煜（上海交通大学）[演讲视频] | |
| 11:45 - 12:00 | An In-Depth Study of Correlated Failures in Production SSD-Based Data Centers，[线上参会] 韩淑捷（香港中文大学）[演讲视频] | |
| 12:00 - 13:30 | 午餐 | |
| 13:30 - 13:45 | Session: FAST I - Traditional Storage |
The Dilemma between Deduplication and Locality: Can Both be Achieved?，邹翔宇（哈尔滨工业大学（深圳））[演讲视频] |
| 13:45 - 14:00 | Concordia: Distributed Shared Memory with In-Network Cache Coherence，汪庆（清华大学）[演讲视频] | |
| 14:00 - 14:15 | Pattern-Guided File Compression with User-Experience Enhancement for Log-Structured File System on Mobile Devices，薛春（香港城市大学）[演讲视频] | |
| 14:15 - 14:30 | Exploiting Combined Locality for Wide-Stripe Erasure Coding in Distributed Storage，胡燏翀（华中科技大学）[演讲视频] | |
| 14:30 - 14:45 | ROART: Range-query Optimized Persistent ART，马少楠（清华大学） | |
| 14:45 - 15:00 | 茶歇 | |
| 15:00 - 15:15 | Session: ISCA I - NN |
NN-Baton: DNN Workload Orchestration and Chiplet Granularity Exploration for Multichip Accelerators，谭展宏（清华大学）[演讲视频] |
| 15:15 - 15:30 | NASA: Accelerating Neural Network Design with a NAS Processor，马晓晗（中科院计算所） | |
| 15:30 - 15:45 | NASGuard: A Novel Accelerator Architecture forRobust NAS Networks，王兴宾（中科院信工所）[演讲视频] | |
| 15:45 - 16:00 | Cambricon-Q: a hybrid architecture for efficient training，[线上参会] 赵永威（中科院计算所）[演讲视频] | |
| 16:00 - 16:15 | Session: NVM and Memory I |
Bridging the Performance Gap for Copy-based Garbage Collectors atop Non-Volatile Memory，吴明瑜（上海交通大学）[演讲视频] |
| 16:15 - 16:30 | A Write-Friendly NVM Scheme for Security Metadata with High Availability，黄建明（华中科技大学）[演讲视频] | |
| 16:30 - 16:45 | Fast, Flexible and Comprehensive Bug Detection for Persistent Memory Programs，[线上参会] 狄棒（湖南大学）[演讲视频] | |
| 16:45 - 17:00 | Streamline Ring ORAM Accesses through Spatial and Temporal Optimization，张明喆（中科院信工所） | |
| 17:00 - 18:00 | Session: Poster | |
| 18:00 | 晚宴（越风楼酒店，位于会场对面的湘湖路681号） | |
| 2021-05-23 (Day 2): | ||
| Time | Sessions | Talks |
| 8:30 - 9:00 | Session: Keynote II | 从分布式系统的共识到社会选择，周礼栋（微软亚洲研究院）[演讲视频] |
| 9:00 - 9:30 | 图计算和图数据库在金融中的应用和挑战，陈文光（清华大学）[演讲视频] | |
| 9:30 - 10:00 | AI x Database: Search and Analytics in Embedding Spaces, 郭人通（ZILLIZ）[演讲视频] | |
| 10:00 - 10:30 | 应用驱动的体系结构，喻之斌（中国科学院深圳先进技术研究院）[演讲视频] | |
| 10:30 - 10:45 | 茶歇 | |
| 10:45 - 11:00 | Session: GNN & Graph |
稀疏算子优化与图神经网络系统加速，戴国浩（清华大学）[演讲视频] |
| 11:00 - 11:15 | Understanding and Bridging the Gaps in Current GNN Performance Optimizations，黄可钊（清华大学）[演讲视频] | |
| 11:15 - 11:30 | DepGraph: A Dependency-Driven Accelerator for Efficient Iterative Graph Processing，彭达（华中科技大学）[演讲视频] | |
| 11:30 - 11:45 | Session: FAST II - SSD | FusionRAID: Achieving Consistent Low Latency for Commodity SSD Arrays，姜天洋（清华大学）[演讲视频] |
| 11:45 - 12:00 | Remap-SSD: Safely and Efficiently Exploiting SSD Address Remapping to Eliminate Duplicate Writes，周游（华中科技大学）[演讲视频] | |
| 12:00 - 12:15 | SpanDB: A Fast, Cost-Effective LSM-tree Based KV Store on Hybrid Storage，陈浩（中国科学技术大学）[演讲视频] | |
| 12:15 - 13:30 | 午餐 | |
| 13:30 - 13:45 | Session: Edge Device |
面向智能持续感知的感算共融架构和芯片，刘哲宇（清华大学）[演讲视频] |
| 13:45 - 14:00 | A Systematic View of Leakage Risks in Deep Neural Network Systems，陈小兵（中科院计算所）[演讲视频] | |
| 14:00 - 14:15 | Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices，李广力（中科院计算所）[演讲视频] | |
| 14:15 - 14:30 | Achieving Low Tail-latency and High Scalability for Serializable Transactions in Edge Computing，[线上参会] 陈旭升（香港大学） | |
| 14:30 - 14:45 | Session: ISCA II - Tensor | PipeZK: Accelerating Zero-Knowledge Proof with a Pipelined Architecture，张烨（纽约大学）[演讲视频] |
| 14:45 - 15:00 | Dual-side Sparse Tensor Core，张宸（阿里巴巴）[演讲视频] | |
| 15:00 - 15:15 | TENET: A Framework for Modeling Tensor Dataflow Based on Relation-centric Notation，卢丽强（北京大学） | |
| 15:15 - 15:30 | HASCO: Towards Agile HArdware and Software CO-design for Tensor Computation，肖倾城（北京大学）[演讲视频] | |
| 15:30 - 15:45 | 茶歇 | |
| 15:45 - 16:00 | Session: NVM and Memory II |
MobiLego: 用户体验感知的移动设备内存融合，石亮（华东师范大学）[演讲视频] |
| 16:00 - 16:15 | TADOC: Text analytics directly on compression，张峰（中国人民大学）[演讲视频] | |
| 16:15 - 16:30 | Scalable Memory Protection in PENGLAI Enclave，冯二虎（上海交通大学）[演讲视频] | |
| 16:30 - 16:45 | 闭幕 | |