XMA2: A crossbar-aware multi-task adaption framework via 2-tier masks
XMA2: A crossbar-aware multi-task adaption framework via 2-tier masks
复制标题
DOI：
10.3389/felec.2022.1032485
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Fan Zhang;Li Yang;Jian Meng;J.-s. Seo;Yu Cao;Deliang Fan
中科院分区：
文献类型：
--
作者：
Fan Zhang;Li Yang;Jian Meng;J.-s. Seo;Yu Cao;Deliang Fan
最近，基于ReRAM crossbar的深度神经网络（DNN）加速器得到了广泛的研究。然而，由于权重重编程的高能耗和ReRAM单元的低耐久性问题，大多数先前的工作集中于单任务推理。尚未充分探索如何将基于ReRAM纵横制的DNN加速器适应多个任务。在这项研究中，我们提出了XMA 2，这是一种新型的交叉杆感知学习方法，采用双层掩蔽技术，有效地适应部署在ReRAM交叉杆中的DNN骨干模型，以进行新任务学习。在基于XMA 2的多任务适配（MTA）期间，首先学习基于层1 ReRAM纵横制的处理元件（PE）方式掩码，以识别要针对新任务的基本新特征重新编程的最关键PE。随后，在其余的权重冻结PE内应用层2交叉杆逐列掩码，以在不修改权重值的情况下学习用于新任务学习的硬件友好和逐列缩放因子。有了这样的交叉条感知设计创新，我们可以在现有的基于交叉条的卷积引擎中实现所需的掩码操作，并以最小的硬件/内存开销来适应新的任务。大量的实验结果表明，与其他最先进的多任务自适应方法相比，XMA 2在所有流行的多任务学习数据集上都达到了最高的准确率。
Recently, ReRAM crossbar-based deep neural network (DNN) accelerator has been widely investigated. However, most prior works focus on single-task inference due to the high energy consumption of weight reprogramming and ReRAM cells’ low endurance issue. Adapting the ReRAM crossbar-based DNN accelerator for multiple tasks has not been fully explored. In this study, we propose XMA 2, a novel crossbar-aware learning method with a 2-tier masking technique to efficiently adapt a DNN backbone model deployed in the ReRAM crossbar for new task learning. During the XMA2-based multi-task adaption (MTA), the tier-1 ReRAM crossbar-based processing-element- (PE-) wise mask is first learned to identify the most critical PEs to be reprogrammed for essential new features of the new task. Subsequently, the tier-2 crossbar column-wise mask is applied within the rest of the weight-frozen PEs to learn a hardware-friendly and column-wise scaling factor for new task learning without modifying the weight values. With such crossbar-aware design innovations, we could implement the required masking operation in an existing crossbar-based convolution engine with minimal hardware/memory overhead to adapt to a new task. The extensive experimental results show that compared with other state-of-the-art multiple-task adaption methods, XMA2 achieves the highest accuracy on all popular multi-task learning datasets.