DCO: Dynamic Cache Orchestration for LLM Accelerators Through Predictive Management
- 1 December 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (12) , 4460-4474
Abstract
No abstract availableAll Related Versions
Funding Information
- ZTE Industry-University-Institute Cooperation Funds (IA20250923007)
- Hong Kong Research Grants Council (GRF16219825)
This publication has 27 references indexed in Scilit:
- Stream: A Modeling Framework for Fine-grained Layer Fusion on Multi-core DNN Accelerators2023
- Atomic Dataflow based Graph-Level Workload Orchestration for Scalable DNN Accelerators2022
- Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration2021
- Designing a Cost-Effective Cache Replacement Policy using Machine Learning2021
- Accel-Sim: An Extensible Simulation Framework for Validated GPU Modeling2020
- DaVinci: A Scalable Architecture for Neural Network Computing2019
- Timeloop: A Systematic Approach to DNN Accelerator Evaluation2019
- Coordinated static and dynamic cache bypassing for GPUs2015
- Exploring Heterogeneous NoC Design Space in Heterogeneous GPU-CPU ArchitecturesJournal of Computer Science and Technology, 2015
- Timekeeping in the memory system: predicting and optimizing memory behavior2003