MetaML-Pro: 跨阶段设计流程自动化以实现高效深度学习加速
MetaML-Pro: Cross-Stage Design Flow Automation for Efficient Deep Learning Acceleration
AI总结:
MetaML-Pro通过自动化设计流程实现高效DNN加速器的资源优化,减少手动干预并提升性能与效率。
摘要:
本文提出了一种统一的框架,用于编码和自动化优化策略,以高效地在资源受限的硬件上部署深度神经网络(DNNs),如FPGA,同时保持高性能、准确性和资源效率。在这样的平台上部署DNN涉及解决显著的挑战,即平衡性能、资源使用(例如DSPs和LUTs)和推理准确性,这通常需要大量的手动努力和领域专业知识。我们的新方法解决了两个核心问题:(i)编码自定义优化策略和(ii)启用跨阶段优化搜索。特别是,我们提出的框架无缝地将程序化DNN优化技术与基于高层次综合(HLS)的元编程相结合,利用先进的设计空间探索(DSE)策略,如贝叶斯优化,以自动化自上而下和自下而上的设计流程。因此,我们减少了对手动干预和领域专业知识的需求。此外,该框架引入了可定制的优化、转换和控制块,以提高DNN加速器的性能和资源效率。实验结果表明,对于选定的网络,DSP和LUT的使用分别减少了92%和89%,同时保持了准确性,并且与网格搜索相比,优化时间减少了15.6倍。这些结果突显了自动化生成资源高效的DNN加速器设计的潜力,只需最小的努力。
英文摘要:
This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy, and resource efficiency. Deploying DNNs on such platforms involves addressing the significant challenge of balancing performance, resource usage (e.g., DSPs and LUTs), and inference accuracy, which often requires extensive manual effort and domain expertise. Our novel approach addresses two core key issues: (i)~encoding custom optimization strategies and (ii)~enabling cross-stage optimization search. In particular, our proposed framework seamlessly integrates programmatic DNN optimization techniques with high-level synthesis (HLS)-based metaprogramming, leveraging advanced design space exploration (DSE) strategies like Bayesian optimization to automate both top-down and bottom-up design flows. Hence, we reduce the need for manual intervention and domain expertise. In addition, the framework introduces customizable optimization, transformation, and control blocks to enhance DNN accelerator performance and resource efficiency. Experimental results demonstrate up to a 92\% DSP and 89\% LUT usage reduction for select networks, while preserving accuracy, along with a 15.6-fold reduction in optimization time compared to grid search. These results highlight the potential for automating the generation of resource-efficient DNN accelerator designs with minimum effort.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。