{"total":33,"rows":[{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2306.10209","title":"ZeRO++: Extremely Efficient Collective Communication for Giant Model Training","created":"2023-06-16","cited_by_count":52,"area":null},{"id":"2111.04867","title":"TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches","created":"2021-11-08","cited_by_count":38,"area":null},{"id":"2308.00852","title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters","created":"2023-08-01","cited_by_count":26,"area":null},{"id":"2211.05322","title":"On Optimizing the Communication of Model Parallelism","created":"2022-11-10","cited_by_count":19,"area":null},{"id":"2110.04478","title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models","created":"2021-10-09","cited_by_count":16,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2409.15241","title":"Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping","created":"2024-09-23","cited_by_count":9,"area":null},{"id":"2207.10898","title":"Impact of RoCE Congestion Control Policies on Distributed Training of DNNs","created":"2022-07-22","cited_by_count":6,"area":null},{"id":"2202.03356","title":"Efficient Direct-Connect Topologies for Collective Communications","created":"2022-02-07","cited_by_count":5,"area":null},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2509.10371","title":"Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2110.10548","title":"Synthesizing Optimal Parallelism Placement and Reduction Strategies on Hierarchical Systems for Deep Learning","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2304.05301","title":"TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2109.11762","title":"LIBRA: Enabling Workload-aware Multi-dimensional Network Topology Optimization for Distributed Training of Large AI Models","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2302.12445","title":"DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2403.07585","title":"Communication Optimization for Distributed Training: Architecture, Advances, and Opportunities","created":"2024-03-12","cited_by_count":3,"area":null},{"id":"2402.06787","title":"ForestColl: Throughput-Optimal Collective Communications on Heterogeneous Network Fabrics","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2103.15195","title":"MergeComp: A Compression Scheduler for Scalable Communication-Efficient Distributed Training","created":"2021-03-28","cited_by_count":1,"area":null},{"id":"2110.09132","title":"EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2205.14465","title":"ByteComp: Revisiting Gradient Compression in Distributed Training","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2207.10982","title":"Efficient All-reduce for Distributed DNN Training in Optical Interconnect System","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2305.18461","title":"Bandwidth Optimal Pipeline Schedule for Collective Communication","created":"2023-05-29","cited_by_count":1,"area":null},{"id":"2505.23523","title":"Efficient AllReduce with Stragglers","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.27844","title":"ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2210.08376","title":"Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2503.05324","title":"Routing for Large ML Models","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2510.19322","title":"Enabling Reconfiguration-Communication Overlap for Collective Communication in Optical Networks","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2606.01680","title":"Don't Let a Few Network Failures Slow the Entire AllReduce","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.10440","title":"ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.25759","title":"NEURON-Fabric: Architecture-Runtime Co-Design for Controlled Low-Bit Gradient Communication","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}