Imagen de Portada

DCI: A Coordinated Allocation and Filling Workload-Aware Dual-Cache Allocation GNN Inference Acceleration System

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Luo, Yi, Wang, Yaobin, Wang, Qi, Song, Yingchen, Wu, Huan, Wang, Qingfeng, Huang, Jun
Formato:	Preprint
Publicado:	2025
Materias:	Hardware Architecture
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Performance-Aware Allocation for Accelerated Machine Learning on GPU-SSD Systems
por: Gundawar, Ayush, et al.
Publicado: (2024)

Adaptive Cache Pollution Control for Large Language Model Inference Workloads Using Temporal CNN-Based Prediction and Priority-Aware Replacement
por: Liu, Songze, et al.
Publicado: (2025)

GreenMalloc: Allocator Optimisation for Industrial Workloads
por: Dakhama, Aidan, et al.
Publicado: (2025)

Mapping Space Exploration for Multi-Chiplet Accelerators Targeting LLM Inference Serving Workloads
por: Li, Boyu, et al.
Publicado: (2025)

Allspark: Workload Orchestration for Visual Transformers on Processing In-Memory Systems
por: Ge, Mengke, et al.
Publicado: (2024)

Accelerating GNN Training through Locality-aware Dropout and Merge
por: Sun, Gongjian, et al.
Publicado: (2025)

Understanding Inference-Time Token Allocation and Coverage Limits in Agentic Hardware Verification
por: Patel, Vihaan, et al.
Publicado: (2026)

ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators
por: Zou, Guoqiang, et al.
Publicado: (2025)

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
por: Fang, Yunhua, et al.
Publicado: (2025)

SpeedLLM: An FPGA Co-design of Large Language Model Inference Accelerator
por: Wang, Peipei, et al.
Publicado: (2025)

High Utilization Energy-Aware Real-Time Inference Deep Convolutional Neural Network Accelerator
por: Lin, Kuan-Ting, et al.
Publicado: (2025)

Instruction-Based Coordination of Heterogeneous Processing Units for Acceleration of DNN Inference
por: Petropoulos, Anastasios, et al.
Publicado: (2025)

HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference
por: Duan, Cenlin, et al.
Publicado: (2025)

NOVA: Coordinated Test Selection and Bayes-Optimized Constrained Randomization for Accelerated Coverage Closure
por: Peng, Weijie, et al.
Publicado: (2025)

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator
por: Wang, Zhican, et al.
Publicado: (2025)

ApproxPilot: A GNN-based Accelerator Approximation Framework
por: Zhang, Qing, et al.
Publicado: (2024)

Communication Characterization of AI Workloads for Large-scale Multi-chiplet Accelerators
por: Musavi, Mariam, et al.
Publicado: (2024)

Garibaldi: A Pairwise Instruction-Data Management for Enhancing Shared Last-Level Cache Performance in Server Workloads
por: Kwon, Jaewon, et al.
Publicado: (2025)

Messaging-based Adaptive Vector Computing (MAVeC) Accelerator for AI Workloads
por: Chowdhury, Md. Rownak Hossain, et al.
Publicado: (2024)

Aging Aware Adaptive Voltage Scaling for Reliable and Efficient AI Accelerators
por: Xie, Tong, et al.
Publicado: (2026)

A Dynamic Allocation Scheme for Adaptive Shared-Memory Mapping on Kilo-core RV Clusters for Attention-Based Model Deployment
por: Wang, Bowen, et al.
Publicado: (2025)

Be CIM or Be Memory: A Dual-mode-aware DNN Compiler for CIM Accelerators
por: Zhao, Shixin, et al.
Publicado: (2025)

Integrating Prefetcher Selection with Dynamic Request Allocation Improves Prefetching Efficiency
por: Li, Mengming, et al.
Publicado: (2025)

PREFENDER: A Prefetching Defender against Cache Side Channel Attacks as A Pretender
por: Li, Luyi, et al.
Publicado: (2023)

SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding
por: Zhong, Linfeng, et al.
Publicado: (2025)

SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cross-Stage Coordinated Tiling
por: Wang, Huizheng, et al.
Publicado: (2024)

Multi-Objective Hardware-Mapping Co-Optimisation for Multi-DNN Workloads on Chiplet-based Accelerators
por: Das, Abhijit, et al.
Publicado: (2022)

PRIMAL: Processing-In-Memory Based Low-Rank Adaptation for LLM Inference Accelerator
por: Chong, Yue Jiet, et al.
Publicado: (2026)

Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration
por: Chen, Peilin, et al.
Publicado: (2025)

HCiM: ADC-Less Hybrid Analog-Digital Compute in Memory Accelerator for Deep Learning Workloads
por: Negi, Shubham, et al.
Publicado: (2024)

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
por: Yao, Jiayi, et al.
Publicado: (2026)

MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
por: Wang, Huizheng, et al.
Publicado: (2025)

SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference
por: Choi, Yuseon, et al.
Publicado: (2025)

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
por: Huang, Zhirui, et al.
Publicado: (2025)

UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inference
por: Xu, Weikai, et al.
Publicado: (2025)

PICNIC: Silicon Photonic Interconnected Chiplets with Computational Network and In-memory Computing for LLM Inference Acceleration
por: Chong, Yue Jiet, et al.
Publicado: (2025)

STI-SNN: A 0.14 GOPS/W/PE Single-Timestep Inference FPGA-based SNN Accelerator with Algorithm and Hardware Co-Design
por: Wang, Kainan, et al.
Publicado: (2025)

Workload-Aware Early-Stage Power Delivery Network Optimization via Architectural Power Traces
por: Hayes, Oran, et al.
Publicado: (2026)

Spatzformer: An Efficient Reconfigurable Dual-Core RISC-V V Cluster for Mixed Scalar-Vector Workloads
por: Perotti, Matteo, et al.
Publicado: (2024)

SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV
por: Zhang, Jingyao, et al.
Publicado: (2025)