Cover Image

TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Size, Fang, Jin, Zheng, Xuegui, Hou, Qi, Bao, Wenlei, Zheng, Ningxin, Jiang, Ziheng, Wang, Dongyang, Ye, Jianxi, Lin, Haibin, Chang, Li-Wen, Liu, Xin
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler
by: Zheng, Size, et al.
Published: (2025)

UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
by: Zheng, Size, et al.
Published: (2026)

Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
by: Zhang, Shulai, et al.
Published: (2025)

FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion
by: Chang, Li-Wen, et al.
Published: (2024)

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
by: Zhang, Qiao, et al.
Published: (2025)

MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
by: Jin, Chao, et al.
Published: (2025)

Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap
by: Qiang, Xinwei, et al.
Published: (2026)

Optimizing Long-context LLM Serving via Fine-grained Sequence Parallelism
by: Li, Cong, et al.
Published: (2025)

Accelerating Sparse DNNs Based on Tiled GEMM
by: Guo, Cong, et al.
Published: (2024)

An Efficient and Adaptive Watermark Detection System with Tile-based Error Correction
by: Zhong, Xinrui, et al.
Published: (2025)

DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
by: Zeng, Zhichen, et al.
Published: (2026)

Xorbits: Automating Operator Tiling for Distributed Data Science
by: Lu, Weizheng, et al.
Published: (2023)

Design in Tiles: Automating GEMM Deployment on Tile-Based Many-PE Accelerators
by: Shen, Aofeng, et al.
Published: (2025)

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding
by: Zhang, Ziyi, et al.
Published: (2025)

TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators
by: Li, Wei, et al.
Published: (2025)

PALM: A Efficient Performance Simulator for Tiled Accelerators with Large-scale Model Training
by: Fang, Jiahao, et al.
Published: (2024)

Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping
by: Jiang, Chenyu, et al.
Published: (2024)

IsoSched: Preemptive Tile Cascaded Scheduling of Multi-DNN via Subgraph Isomorphism
by: Zhao, Boran, et al.
Published: (2025)

PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel
by: Yi, Jinjun, et al.
Published: (2025)

Can Asymmetric Tile Buffering Be Beneficial?
by: Wang, Chengyue, et al.
Published: (2025)

Lagom: Unleashing the Power of Communication and Computation Overlapping for Distributed LLM Training
by: Xu, Guanbin, et al.
Published: (2026)

Cross-region Model Training with Communication-Computation Overlapping and Delay Compensation
by: Zhu, Ying, et al.
Published: (2025)

PRISM: Dynamic Primitive-Based Forecasting for Large-Scale GPU Cluster Workloads
by: Wu, Xin, et al.
Published: (2026)

Fork, Explore, Commit: OS Primitives for Agentic Exploration
by: Wang, Cong, et al.
Published: (2026)

Characterizing Compute-Communication Overlap in GPU-Accelerated Distributed Deep Learning: Performance and Power Implications
by: Lee, Seonho, et al.
Published: (2025)

CCRSat: A Collaborative Computation Reuse Framework for Satellite Edge Computing Networks
by: Zhang, Ye, et al.
Published: (2025)

Collaborative Satellite Computing through Adaptive DNN Task Splitting and Offloading
by: Peng, Shifeng, et al.
Published: (2024)

MPI-Q: A Message Communication Library for Large-Scale Classical-Quantum Heterogeneous Hybrid Distributed Computing
by: Wang, Feng, et al.
Published: (2026)

More for Less: Integrating Capability-Predominant and Capacity-Predominant Computing
by: Zheng, Zhong, et al.
Published: (2025)

Semantic-aware Token Selection and Resource Optimization for Communication-efficient Split Federated Fine-tuning in Edge Intelligence
by: Qiang, Xianke, et al.
Published: (2026)

Exploring Uncore Frequency Scaling for Heterogeneous Computing
by: Zheng, Zhong, et al.
Published: (2025)

CO2: Efficient Distributed Training with Full Communication-Computation Overlap
by: Sun, Weigao, et al.
Published: (2024)

TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference
by: Gond, Raja, et al.
Published: (2025)

Modeling the Impact of Fiber Latency on Compute-Communication Overlap in Geo-Distributed Multi-Datacenter AI Training
by: Papavasileiou, Ioannis, et al.
Published: (2026)

On Similarity of Computational Kernels in our Codes and Proxies
by: McKinsey, Michael, et al.
Published: (2026)

MegaScale-Omni: A Hyper-Scale, Workload-Resilient System for MultiModal LLM Training in Production
by: Xue, Chunyu, et al.
Published: (2026)

Intelligent Task Management via Dynamic Multi-region Division in LEO Satellite Networks
by: Song, Zixuan, et al.
Published: (2025)

GPUOS: A GPU Operating System Primitive for Transparent Operation Fusion
by: Yang, Yiwei, et al.
Published: (2026)

Composing Distributed Computations Through Task and Kernel Fusion
by: Yadav, Rohan, et al.
Published: (2024)

NCCLbpf: Verified, Composable Policy Execution for GPU Collective Communication
by: Zheng, Yusheng
Published: (2026)