Input-Aware Flow-Based Computing on Memristor Crossbars With Applications to Edge Detection
Input-Aware Flow-Based Computing on Memristor Crossbars With Applications to Edge Detection
复制标题
DOI：
10.1109/jetcas.2019.2933774
复制
发表时间：
2019-09-01
影响因子：
4.6
通讯作者：
Jha, Sumit Kumar
中科院分区：
文献类型：
--
作者：
Chakraborty, Dwaipayan;Raj, Sunny;Jha, Sumit Kumar
传统上，纳米级Memristor横杆中的偷偷摸摸的路径被视为将Memristor横杆用作传统挥发性公羊记忆的非挥发性替代品的问题。我们表明，可以使用Memristor横杆中的偷偷摸摸路径来执行利用设备级并行性的计算。我们的计算可以在内存中执行，并且不需要在处理器和内存单元之间移动数据 - 从而避免了von Neumann瓶颈。我们通过将其应用于计算机视觉中的基本问题：图像中的边缘检测来证明我们的方法的潜力。我们的结果表明，基于流的计算方法可以使用纳米级概述横栏中的基于流动的计算方法来获得边缘检测的高质量近似值。为此，我们已经合成了多个8 x 8横杆电路 - 一个单个横梁电路，用于检测所有可能的像素对之间的边缘，其精度与85％的精度相似，而另一个具有更高性能的输入感知横杆家族比现实世界图像更高。输入感知横梁的家族共同执行了近似的边缘检测，以分析BSD500数据库获得的一个像素对的子集，并且所得图像具有可与精确边缘检测相当的质量。
Sneak paths in nanoscale memristor crossbars have traditionally been viewed as a problem in the use of memristor crossbars as non-volatile replacements of traditional volatile RAM memories. We show that the sneak paths in a memristor crossbar can be employed to perform computation that exploits device-level parallelism. Our computation can be performed in the memory and does not require data to be moved between a processor and a memory unit - thereby, avoiding the von Neumann bottleneck. We demonstrate the potential of our approach by applying it to a basic problem in computer vision: edge detection in an image. Our results show that the flow-based computing approach on nanoscale memristor crossbars can be used to obtain high-quality approximations of edge detection. We have synthesized multiple 8 x 8 crossbar circuits for this purpose - a single crossbar circuit for detecting edges between all possible pixel pairs with similar to 85% accuracy, and another family of input-aware crossbars with higher performance over real-world images. The family of input-aware crossbars together performs approximate edge detection for a subset of pixel pairs obtained from analyzing the BSD500 database, and the resultant images are of a quality comparable to exact edge detection.