Image de couverture de livre

Fast Cross-Operator Optimization of Attention Dataflow

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chang, Haodong, Hu, Hailiang, Wang, Zhenrui, Gong, Yu, Liang, Rongjian, Tang, Zhexiang, Yuan, Bo, Hu, Jiang
Format:	Preprint
Publié:	2026
Sujets:	Hardware Architecture
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Implementing and Optimizing the Scaled Dot-Product Attention on Streaming Dataflow
par: Sohn, Gina, et autres
Publié: (2024)

CODO: An Automated Compiler for Comprehensive Dataflow Optimization
par: Zhang, Weichuang, et autres
Publié: (2026)

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
par: Chang, Kaiyan, et autres
Publié: (2025)

FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Large Attention-Based Model Inference on Tile-Based Accelerators
par: Zhang, Chi, et autres
Publié: (2026)

Multilayer Dataflow: Orchestrate Butterfly Sparsity to Accelerate Attention Computation
par: Wu, Haibin, et autres
Publié: (2024)

FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
par: Zhang, Chi, et autres
Publié: (2025)

A Sparsity-Aware Autonomous Path Planning Accelerator with HW/SW Co-Design and Multi-Level Dataflow Optimization
par: Zhang, Yifan, et autres
Publié: (2025)

NEURAL: An Elastic Neuromorphic Architecture with Hybrid Data-Event Execution and On-the-fly Attention Dataflow
par: Chen, Yuehai, et autres
Publié: (2025)

FlexMem: High-Parallel Near-Memory Architecture for Flexible Dataflow in Fully Homomorphic Encryption
par: Shi, Shangyi, et autres
Publié: (2025)

Hermes: A Unified High-Performance NTT Architecture with Hybrid Dataflow
par: Gu, Hang, et autres
Publié: (2026)

MIREDO: MIP-Driven Resource-Efficient Dataflow Optimization for Computing-in-Memory Accelerator
par: He, Xiaolin, et autres
Publié: (2025)

DFModel: Design Space Optimization of Large-Scale Systems Exploiting Dataflow Mappings
par: Ko, Sho, et autres
Publié: (2024)

PIMfused: Near-Bank DRAM-PIM with Fused-layer Dataflow for CNN Data Transfer Optimization
par: Yang, Simei, et autres
Publié: (2025)

Low Power Vision Transformer Accelerator with Hardware-Aware Pruning and Optimized Dataflow
par: Hsiung, Ching-Lin, et autres
Publié: (2025)

SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators
par: Umuroglu, Yaman, et autres
Publié: (2025)

ReDas: A Lightweight Architecture for Supporting Fine-Grained Reshaping and Multiple Dataflows on Systolic Array
par: Han, Meng, et autres
Publié: (2023)

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
par: Wu, Junyi, et autres
Publié: (2025)

Revet: A Language and Compiler for Dataflow Threads
par: Rucker, Alexander, et autres
Publié: (2023)

Stream-HLS: Towards Automatic Dataflow Acceleration
par: Basalama, Suhail, et autres
Publié: (2025)

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator
par: Wang, Zhican, et autres
Publié: (2025)

DORA: Dataflow-Instruction Orchestration Architecture for DNN Acceleration
par: Chen, Xingzhen, et autres
Publié: (2026)

A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling Formats
par: Cheng, Jianyi, et autres
Publié: (2023)

A Persistent-State Dataflow Accelerator for Memory-Bound Linear Attention Decode on FPGA
par: Gupta, Neelesh, et autres
Publié: (2026)

LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization
par: He, Siyuan, et autres
Publié: (2025)

AccelCIM: Systematic Dataflow Exploration for SRAM Compute-in-Memory Accelerator
par: Xue, Chenhao, et autres
Publié: (2026)

StreamDCIM: A Tile-based Streaming Digital CIM Accelerator with Mixed-stationary Cross-forwarding Dataflow for Multimodal Transformer
par: Qin, Shantian, et autres
Publié: (2025)

DAS-MP: Enabling High-Quality Macro Placement with Enhanced Dataflow Awareness
par: Zhao, Xiaotian, et autres
Publié: (2025)

StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs
par: Ye, Hanchen, et autres
Publié: (2025)

Fast Graph Vector Search via Hardware Acceleration and Delayed-Synchronization Traversal
par: Jiang, Wenqi, et autres
Publié: (2024)

SwiftKV: An Edge-Oriented Attention Algorithm and Multi-Head Accelerator for Fast, Efficient LLM Decoding
par: Zhang, Junming, et autres
Publié: (2026)

Dataflow Optimized Reconfigurable Acceleration for FEM-based CFD Simulations
par: Kapetanakis, Anastassis, et autres
Publié: (2024)

LoopTree: Exploring the Fused-layer Dataflow Accelerator Design Space
par: Gilbert, Michael, et autres
Publié: (2024)

A High-Throughput FPGA Accelerator for Lightweight CNNs With Balanced Dataflow
par: Zhao, Zhiyuan, et autres
Publié: (2024)

LoopLynx: A Scalable Dataflow Architecture for Efficient LLM Inference
par: Zheng, Jianing, et autres
Publié: (2025)

SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cross-Stage Coordinated Tiling
par: Wang, Huizheng, et autres
Publié: (2024)

LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism
par: Wang, Yimin, et autres
Publié: (2025)

Evaluation of Posits for Spectral Analysis Using a Software-Defined Dataflow Architecture
par: Deshmukh, Sameer, et autres
Publié: (2024)

Stream: Design Space Exploration of Layer-Fused DNNs on Heterogeneous Dataflow Accelerators
par: Symons, Arne, et autres
Publié: (2022)

PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs
par: Yin, Ruokai, et autres
Publié: (2025)

Learning Library Cell Representations in Vector Space
par: Liang, Rongjian, et autres
Publié: (2025)