ISCA‘22 文章挑选

[Graph Applications]

• TDGraph: A Topology-Driven Accelerator for High-Performance Streaming Graph Processing

[Processing in Memory]

• To PIM or Not for Emerging General Purpose Processing in DDR Memory Systems

[Industry Session]

• Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models
• Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training

[Persistent Memory]

• Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems using Online Reinforcement Learning

[Learning]

• Cascading Structured Pruning: Enabling High Data Reuse for Sparse DNN Accelerators
• Anticipating and Eliminating Redundant Computations in Accelerated Sparse Training

[Learning II and Security II]

• Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models

[Novel Architectures]

• BioHD: An Efficient Genome Sequence Search Platform Using HyperDimensional Memorization
• EDAM: Edit Distance tolerant Approximate Matching content addressable memory

[Learning III]

• Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwards
• Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models
• Accelerating Attention through Gradient-Based Learned Runtime Pruning

[Graph Applications and Algorithms]

• Graphite: Optimizing Graph Neural Networks on CPUs Through Cooperative Software-Hardware Techniques
• SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures
• Hyperscale FPGA-As-A-Service Architecture for Large-Scale Distributed Graph Neural Network
• Crescent: Taming Memory Irregularities for Accelerating Deep Point Cloud Analytics