边缘AI不妥协:电阻随机存取存储器中的高效,通用和准确的神经计算
Edge AI without Compromise: Efficient, Versatile and Accurate Neurocomputing in Resistive Random-Access Memory
摘要:
直接在分布在互联网边缘的设备上实现当今的云级人工智能功能,需要能够以前所未有的能效处理多种感知数据(例如视频、音频)的边缘硬件。由于基本的“内存墙”,今天的人工智能硬件架构无法满足需求:单独的计算和内存单元之间的数据移动消耗大量能量并导致长延迟。基于电阻式随机存取存储器(RRAM)的内存计算(CIM)架构通过直接在内存中执行计算,有望带来数量级的能效改进。然而,CIM硬件设计的传统方法限制了其处理不同AI工作负载所需的功能灵活性,并且必须克服降低推理准确性的硬件缺陷。效率、多功能性和准确性之间的这种折衷不能通过在设计的任何单一层面上的孤立改进来解决。通过跨从算法和架构到电路和设备的设计的所有层次进行协同优化,我们提出了NeuRRAM -第一个使用RRAM CIM的多模式边缘AI芯片,以同时为不同的模型架构提供高度的通用性,记录能量效率$5\times$ - $8\times$在各种计算位精度上优于现有技术,在所有测量的标准AI基准测试中,推理准确性与具有4位权重的软件模型相当,包括MNIST的99.0%准确性和CIFAR-10图像分类的85.7%准确性,Google语音命令识别的84.7%准确性,在贝叶斯图像恢复任务中,图像重建误差减少了70%。这项工作为构建高效和可重新配置的边缘AI硬件平台铺平了道路,以适应未来要求更高和异构的AI应用。
英文摘要:
Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e.g. video, audio) at unprecedented energy-efficiency. AI hardware architectures today cannot meet the demand due to a fundamental "memory wall": data movement between separate compute and memory units consumes large energy and incurs long latency. Resistive random-access memory (RRAM) based compute-in-memory (CIM) architectures promise to bring orders of magnitude energy-efficiency improvement by performing computation directly within memory. However, conventional approaches to CIM hardware design limit its functional flexibility necessary for processing diverse AI workloads, and must overcome hardware imperfections that degrade inference accuracy. Such trade-offs between efficiency, versatility and accuracy cannot be addressed by isolated improvements on any single level of the design. By co-optimizing across all hierarchies of the design from algorithms and architecture to circuits and devices, we present NeuRRAM - the first multimodal edge AI chip using RRAM CIM to simultaneously deliver a high degree of versatility for diverse model architectures, record energy-efficiency $5\times$ - $8\times$ better than prior art across various computational bit-precisions, and inference accuracy comparable to software models with 4-bit weights on all measured standard AI benchmarks including accuracy of 99.0% on MNIST and 85.7% on CIFAR-10 image classification, 84.7% accuracy on Google speech command recognition, and a 70% reduction in image reconstruction error on a Bayesian image recovery task. This work paves a way towards building highly efficient and reconfigurable edge AI hardware platforms for the more demanding and heterogeneous AI applications of the future.
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。