List of Accepted Papers

Session: High Performance Computing – Algorithms and Applications

 

• “Fast Parallel Tensor Times Same Vector for Hypergraphs” 

 

• “Reduce, Reuse and Adapt — Accelerating Graph Processing on GPUs” 

 

• “Reduce Computational Complexity for Convolutional Layers by Skipping Zeros” 

 

• “A Lossless Compression Pipeline for Petabyte-scale Whole Genome Sequencing Data” 

 

• “SpikeNC: An Accurate and Scalable Simulator for Spiking Neural Network on Multi-Core Neuromorphic Hardware”

 

• “DAGit : A Platform For Enabling Serverless Applications”

 

• “Efficient GPU Implementation of Automatic Differentiation for Computational Fluid Dynamics” 

 

Session: High Performance Computing – Architecture

 

• “DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference” 

 

• “A 118 GOPS/mm^2 3D eDRAM TensorCore Architecture for Large-scale Matrix Multiplication” 

 

• “PARAG: PIM Architecture for Real-time Acceleration of GCNs”

 

• “Hybrid CUDA Unified Memory Management in Fully Homomorphic Encryption Workloads”

 

• “Mobile Gaming Experience: An Approach based on Thread Scheduler & Thread Priority Manager”

 

• “Optimized All-to-all Connection Establishment for High-Performance MPI Libraries over InifiniBand” 

 

• “Data Locality Aware Computation Offloading in Near Memory Processing Architecture for Big Data Applications” 

 

 

 

Session: High Performance Computing – Systems

 

• “Towards Efficient I/O Pipelines using Accumulated Compression” 

 

• “Quartermaster: A Reinforcement-Learning, Resource-Recommendation System for Cloud HPC” 

 

• “TOOL – Programming Model and Parallel Runtime for Optimization Problems” 

 

• “Towards Enhanced I/O Performance of NVM File Systems” 

 

• “MOSAIC : A Multi-Objective Optimization Framework for Sustainable Datacenter Management”

 

• “Benesh: Choreographic Coordination for In-situ Workflows” 

 

• “Profit Maximization using Colloborative Storage Management in Multi-tier Cloud System” 

Session: Data Science – Scalable Algorithms and Analytics

 

• “Contour Algorithm for Connected Components” 

 

• “CAPTURE: Memory-Centric Partitioning for Distributed DNN Training with Hybrid Parallelism” 

 

• “MiCRO: Near-Zero Cost Gradient Sparsification for Scaling and Accelerating Distributed DNN Training” 

 

• “Patterns of Model Evolution in Network Architecture Search”   

     

• “Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference” 

 

• “Performance Characterization of Containerized DNN Training and Inference on Edge Accelerators” 

 

Session: Data Science – Scalable Systems and Software

 

• “SECRE: Surrogate-based Error-controlled Lossy Compression Ratio Estimation Framework” 

 

• “Fast Algorithms  for Scientific Data  Compression”  

 

• “CAPIO: a Middleware for Transparent I/O  Streaming in Data-Intensive Workflows” 

 

• “Multi-Streamed Metadata-Integrity Verification For Cloud Migration In Deduplication Systems” 

 

• “CPU-GPU Tuning to Improve Scientific Applications run on Heterogeneous Nodes” 

 

• “JASS: A Tunable Checkpointing System for NVM-based Systems”

 

• “DDIOSim: A Microarchitecture Simulator for Data Direct I/O Technology”

 

• “FPGA Accelerated Bi-Cubic Convolution for Image Interpolation”

 

Session: Best Paper Nominees

 

• “DeltaSPARSE: High-Performance Sparse General Matrix-Matrix Multiplication on Multi-GPU Systems” 

 

• “Strategies for Fast I/O Throughput in Large-scale Climate Modeling Applications” 

 

• “ME-ViT: A Single-Load Memory-Efficient FPGA Accelerator for Vision Transformers” 

 

• “Graph Pattern Mining Paradigms: Consolidation and Renewed Bearing” 

 

• “Accelerating Time to Science using CRADLE: A Framework for Materials Data Science”

 

• “Optimizing the Training of Co-Located Deep Learning Models Using Cache-Aware Staggering”