Cryogenic Performance for Compute-in-Memory Based Deep Neural Network Accelerator
Cryogenic Performance for Compute-in-Memory Based Deep Neural Network Accelerator
复制标题
基于内存计算的深度神经网络加速器的低温性能
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Shimeng Yu
中科院分区：
文献类型：
--
作者：
Panni Wang;Xiaochen Peng;W. Chakraborty;A. Khan;S. Datta;Shimeng Yu
内存计算是近年来在深度神经网络中实现数据密集型计算的一个研究热点。通过在存储位置执行计算，CIM避免了过多的数据传输，从而提高了能源效率。基于SRAM的CIM是先进技术节点上技术成熟的候选者之一。为了进一步加快CMOS电路的速度，在低温下运行的低温计算已经成为数据中心高性能计算的一个有吸引力的解决方案。在这项工作中，我们修改了NeuroSim，这是一个设备到系统的建模框架，具有实验校准的28 nm晶体管参数，从室温到4K。然后，我们在ImagNet数据集上对基于SRAM的CIM进行了ResNet-18性能基准测试。在整个温度范围内比较能量延迟积，揭示了低温计算的性能和能效提升。当考虑到冷却基础设施成本时，整体能源效益被掩盖了。
Compute-in-memory has received a lot of research interests recently to implement the data-intensive computation in deep neural networks. By performing the computing at the storage location, CIM avoids the excessive data transfer thus improving the energy efficiency. SRAM based CIM is one of the promising candidates for its mature technology availability at advanced technology node. To further speed up for CMOS circuits, cryogenic computing which operates at low temperatures has emerged as an attractive solution for highperformance computing at the data center. In this work, we modified NeuroSim, a device-to-system modelling framework with experimentally calibrated 28nm transistor parameters from room temperature to 4K Then we benchmark the performance of SRAM based CIM for ResNet-18 on ImagNet dataset. The energy-delay-product is compared across the temperature, revealing the performance and energy efficiency boost by cryogenic computing. When the cooling infrastructure cost is considered, the overall energy benefits are overshadowed though.