Technology-Driven, Highly-Scalable Dragonfly Topology

No abstract is available for this paper.

• Publication year

  2008

• Venue

  International Symposium on Computer Architecture

• Publication date

  2008-06-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1145/1394608.1382129
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Cray BlackWidow: a highly scalable vector multiprocessor

  2007cited by this paper
• Flattened butterfly: a cost-efficient topology for high-radix networks

  2007influential reference
• On-Chip Interconnection Architecture of the Tile Processor

  2007cited by this paper
• Building Ultralow-Latency Interconnection Networks Using Photonic Integration

  2007cited by this paper
• A 14mW 6.25Gb/s Transceiver in 90nm CMOS for Serial Chip-to-Chip Communications

  2007cited by this paper
• Adaptive Routing in High-Radix Clos Network

  2006cited by this paper
• The BlackWidow High-Radix Clos Network

  2006cited by this paper
• Topology optimization of interconnection networks

  2006cited by this paper
• Niagara: a 32-way multithreaded Sparc processor

  2005cited by this paper
• Microarchitecture of a high radix router

  2005cited by this paper
• Adaptive channel queue routing on k-ary n-cubes

  2004cited by this paper
• Design of a high-speed optical interconnect for scalable shared memory multiprocessors

  2004cited by this paper
• Principles and Practices of Interconnection Networks

  2004influential reference
• GOAL: a load-balanced adaptive routing algorithm for torus networks

  2003cited by this paper
• Scalable opto-electronic network (SOENet)

  2002cited by this paper
• Gemini: An Optical Interconnection Network for Parallel Processing

  2002cited by this paper
• Digital systems engineering

  1998cited by this paper
• The Cray T3E Network: Adaptive Routing in a High Performance 3D Torus

  1996cited by this paper
• Design considerations for optical interconnects in parallel computers

  1994cited by this paper
• Extended Hypercube: A Hierarchical Interconnection Network of Hypercubes

  1992cited by this paper
• Virtual-channel flow control

  1990cited by this paper
• Hierarchical Interconnection Networks for Multicomputer Systems

  1990cited by this paper
• Mappable peripheral memory for high speed applications

  1989cited by this paper
• Deadlock-Free Message Routing in Multiprocessor Interconnection Networks

  1987cited by this paper
• Polymorphic Arrays: A Novel VLSI Layout for Systolic Computers

  1984cited by this paper
• A Scheme for Fast Parallel Communication

  1982cited by this paper
• The cube-connected-cycles: A versatile network for parallel computation

  1979cited by this paper
• A study of non-blocking switching networks

  1953cited by this paper

• AFCC: ACK-Based Fast Congestion Control in Lossless Networks

  2026cites this paper
• Benchmarking Quantum Data Center Architectures: A Performance and Scalability Perspective

  2026cites this paper
• Constructing edge-disjoint spanning trees in dragonfly networks

  2026cites this paper
• Network Design for Wafer-Scale Systems with Wafer-on-Wafer Hybrid Bonding

  2026cites this paper
• To Reconfigure or Not to Reconfigure: Optimizing All-to-All Collectives in Circuit-Switched Photonic Interconnects

  2026cites this paper
• The 3-Path Connectivity of Dragonfly Networks

  2026cites this paper
• Spritz: Path-Aware Load Balancing in Low-Diameter Networks

  2026influential citation
• Designing Optimal Compact Oblivious Routing for Datacenter Networks in Polynomial Time

  2026cites this paper
• A new switch buffer architecture for dragonfly networks

  2025cites this paper
• Octopus: Scalable Low-Cost CXL Memory Pooling

  2025influential citation
• LIA: Latency-Improved Adaptive routing for Dragonfly networks

  2025influential citation
• Orderlock: A New Type of Deadlock and its Implications on High Performance Network Protocol Design

  2025cites this paper
• Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery

  2025cites this paper
• Path congestion detection and disjoint path for improving communication efficiency in dragonfly interconnection networks

  2025cites this paper
• PAARD: Proximity-aware all-reduce communication for dragonfly networks

  2025cites this paper
• PIMnet: A Domain-Specific Network for Efficient Collective Communication in Scalable PIM

  2025cites this paper
• Exploring DeepSeek: A Survey on Advances, Applications, Challenges and Future Directions

  2025cites this paper
• FoldedHexaTorus: An Inter-Chiplet Interconnect Topology for Chiplet-based Systems using Organic and Glass Substrates

  2025cites this paper
• Ultra Ethernet's Design Principles and Architectural Innovations

  2025cites this paper
• Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures

  2025cites this paper
• Topology-Aware Interleaved All-Reduce Communication for Dragonfly Network

  2025influential citation
• FORS: fault-adaptive optimized routing and scheduling for DAQ networks

  2025cites this paper
• PIAR: Path-Improved Adaptive Routing for Dragonfly Networks

  2025influential citation
• 2-edge-Hamilton-connected dragonfly network

  2025cites this paper
• PICO: Performance Insights for Collective Operations

  2025cites this paper
• From ATOP to ZCube: Automated Topology Optimization Pipeline and A Highly Cost-Effective Network Topology for Large Model Training

  2025cites this paper
• Resilience-Driven Task-Cluster Co-Management: Proactive Mitigation of Co-Resident Threats in AI Clusters

  2025cites this paper
• LAPS: Joint Load Balancing and Congestion Control on Unequal-cost Multi-path Data Center Networks

  2025cites this paper
• Non-Shortest Path Routing in Lossy Data Center Networks

  2025cites this paper
• Scaling MPI Applications on Aurora

  2025influential citation
• Fault tolerance assessment of the data center network DPCell based on g-good-neighbor conditions

  2025cites this paper
• Towards performance analysis of GPU-aware MPI over Angara interconnect

  2025cites this paper
• NetJIT: Bridging the Gap from Traffic Prediction to Preknowledge for Distributed Machine Learning

  2025cites this paper
• HPC Workload Analysis Using Distributed Cross-ISA Binary Instrumentation

  2025cites this paper
• Two-Disjoint-Cycle-Cover Pancyclicity of Dragonfly Networks

  2025cites this paper
• The Needle in the One-Billion Event-Haystack: A Deep-Copy Approach for Checking Reverse Handlers in Parallel Discrete Event Simulation

  2025cites this paper
• SINA: Accelerating Time Synchronization in Large-Scale Network Simulation Using In-Network Allreduce

  2025cites this paper
• Reliable Communication Scheme Based on Completely Independent Spanning Trees in Data Center Networks

  2025cites this paper
• Exploiting Software-Defined Networking Technology for Improving Ugal Routing in Dragonfly Networks

  2025influential citation
• RailX: A Flexible, Scalable, and Low-Cost Network Architecture for Hyper-Scale LLM Training Systems

  2025cites this paper
• 基于级联多模干涉耦合器的模式选择开关

  2025cites this paper
• Closed-Form Formulas for Cluster Sizing for Two-Level Hierarchical Networks with Source Routing

  2025cites this paper
• Accelerating Design Space Exploration for LLM Training Systems with Multi-experiment Parallel Simulation

  2025cites this paper
• Reliability Analysis Toward a Family of Interconnection Networks and Data Center Networks

  2025cites this paper
• RECCL: optimizing collective algorithms for reconfigurable optical networks

  2025cites this paper
• Advancing Healthcare with GPGPU and Energy Efficient NoC Architectures: A Comprehensive Survey

  2025cites this paper
• Routing optimization strategies in data center networks: A survey

  2025cites this paper
• Flowcut Switching: High-Performance Adaptive Routing With In-Order Delivery Guarantees

  2025cites this paper
• PD Constraint-aware Physical/Logical Topology Co-Design for Network on Wafer

  2025cites this paper
• CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training

  2025cites this paper
• Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference

  2025cites this paper
• X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms

  2025influential citation
• Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality

  2025cites this paper
• Evaluating AMD Instinct™ MI300A APU: Performance Insights on LLM Training via Knowledge Distillation

  2025cites this paper
• Deadlock-Free Routing for Full-Mesh Networks Without Using Virtual Channels

  2025cites this paper
• Server Chiplet Networking

  2025cites this paper
• Parameterized Algorithms and Parameter Selection for Fast GPU-GPU Collective Communication

  2025cites this paper
• Quantifying the Impact of Job Placement and Routing on Network Efficiency in AI Clusters

  2025cites this paper
• NetSparse: In-Network Acceleration of Distributed Sparse Kernels

  2025cites this paper
• Toward a Metal Usage Effectiveness metric in Data Centers: A Study

  2025cites this paper
• Locality Aware Process Remapping for Distributed-Memory Graph Workloads

  2025cites this paper
• The CAMINOS interconnection networks simulator

  2025cites this paper
• UB-Mesh: A Hierarchically Localized nD-FullMesh Data Center Network Architecture

  2025cites this paper
• Zettafly: A Network Topology with Flexible Non-blocking Regions for Large-scale AI and HPC Systems

  2025influential citation
• S-Lop: An accuracy-improved performance model of MPI communication based on network contention

  2025cites this paper
• Scalable, High-Fidelity Monitoring of Application Communication Patterns in Vernier

  2025cites this paper
• Defining the Boundaries for Endpoint Congestion Management in Networks for High-Performance Computing

  2024cites this paper
• Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning

  2024cites this paper
• A low‐latency memory‐cube network with dual diagonal mesh topology and bypassed pipelines

  2024cites this paper
• An in‐depth study of dimension‐extended dragonfly interconnection network

  2024cites this paper
• On the Performance Investigation of a Recursive Fast Optical Switch-Based High Performance Computing Network Architecture

  2024cites this paper
• Comprehensive Performance and Robustness Analysis of Expander-Based Data Centers

  2024cites this paper
• Exploring GPU-to-GPU Communication: Insights into Supercomputer Interconnects

  2024cites this paper
• Alarm: An Adaptive Routing Algorithm Based on One-Way Delay for Infiniband

  2024cites this paper
• A Bandwidth-Optimal All-to-All Communication in Two-Dimensional Fully Connected Network

  2024cites this paper
• Analysis and prediction of performance variability in large-scale computing systems

  2024cites this paper
• REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation

  2024cites this paper
• Understanding Data Movement in Tightly Coupled Heterogeneous Systems: A Case Study with the Grace Hopper Superchip

  2024cites this paper
• RD-Probe: Scalable Monitoring With Sufficient Coverage In Complex Datacenter Networks

  2024cites this paper
• A Topology- and Load-Aware Design for Neighborhood Allgather

  2024cites this paper
• FlowStar: Fast Convergence Per-Flow State Accurate Congestion Control for InfiniBand

  2024cites this paper
• Demystifying Chains, Trees, and Graphs of Thoughts

  2024cites this paper
• GraphCube: Interconnection Hierarchy-aware Graph Processing

  2024cites this paper
• Accurate and Scalable Many-Node Simulation

  2024cites this paper
• HPC Systems with Reconfigurable Optical Networks: Performance and Energy Consumption Exploration

  2024cites this paper
• Network states-aware collective communication optimization

  2024cites this paper
• Hybrid PDES Simulation of HPC Networks Using Zombie Packets

  2024cites this paper
• Understanding the Impact of Arbitration in MZI-Based Beneš Switching Fabrics

  2024cites this paper
• Network-Centered Resource Management for HPC Networks

  2024cites this paper
• LEFT: LightwEight and FasT packet Reordering for RDMA

  2024cites this paper
• MUSE: A Runtime Incrementally Reconfigurable Network Adapting to HPC Real-Time Traffic

  2024influential citation
• Switch-Less Dragonfly on Wafers: A Scalable Interconnection Architecture based on Wafer-Scale Integration

  2024influential citation
• Edge-Disjoint Tree Allocation for Multi-Tenant Cloud Security in Datacenter Topologies

  2024influential citation
• ForestColl: Efficient Collective Communications on Heterogeneous Network Fabrics

  2024cites this paper
• Enabling Artificial Intelligence Supercomputers With Domain-Specific Networks

  2024cites this paper
• Graph Analytics on Jellyfish topology

  2024cites this paper
• Rina: Enhancing Ring-Allreduce with in-Network Aggregation in Distributed Model Training

  2024cites this paper
• DFModel: Design Space Optimization of Large-Scale Systems Exploiting Dataflow Mappings

  2024cites this paper
• Surrogate Modeling for HPC Application Iteration Times Forecasting with Network Features

  2024cites this paper
• The Case for Coherence Directories in Memory Cubes

  2024cites this paper