Towards Enabling Dynamic Convolution Neural Network Inference for Edge Intelligence
원문 초록
Deep learning applications have achieved great success in numerous real-world applications. Deep learning models, especially Convolution Neural Networks (CNN) are often prototyped using FPGA because it offers high power efficiency and reconfigurability. The deployment of CNNs on FPGAs follows a design cycle that requires saving of model parameters in the on-chip memory during High-level synthesis (HLS). Recent advances in edge intelligence require CNN inference on edge network to increase throughput and reduce latency. To provide flexibility, dynamic parameter allocation to different mobile devices is required to implement either a predefined or defined on-the-fly CNN architecture. In this study, we present novel methodologies for dynamically streaming the model parameters at run-time to implement a traditional CNN architecture. We further propose a library-based approach to design scalable and dynamic distributed CNN inference on the fly leveraging partial-reconfiguration techniques, which is particularly suitable for resource-constrained edge devices. The proposed techniques are implemented on the Xilinx PYNQ-Z2 board to prove the concept by utilizing the LeNet-5 CNN model. The results show that the proposed methodologies are effective, with classification accuracy rates of 92%, 86%, and 94% respectively
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LLM-DSE: Searching Accelerator Parameters with LLM Agents
HLS-Eval: A Benchmark and Framework for Evaluating LLMs on High-Level Synthesis Design Tasks
Design and Implementation of an FPGA-Based Hardware Accelerator for Transformer
Neural Architecture Codesign for Fast Physics Applications
Agentic-HLS: An agentic reasoning based high-level synthesis system using large language models (AI for EDA workshop 2024)
Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.