DP-MAP: Towards Resistive Dot-Product Engines with Improved Precision
DP-MAP: Towards Resistive Dot-Product Engines with Improved Precision
复制标题
DOI：
10.1145/3400302.3415683
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Necati Uysal;Baogang Zhang;Sumit Kumar Jha;Rickard Ewetz
中科院分区：
文献类型：
--
作者：
Necati Uysal;Baogang Zhang;Sumit Kumar Jha;Rickard Ewetz
Memristor横杆阵列的自然乘积和积累特征有望为电阻点产品发动机（DPE）提供前所未有的加工功能，该功能可以加速近似矩阵 - 矢量乘法。为了克服非零阵列寄生虫上低精度设备和电压下降的挑战，可以使用两个磁带来表示每个矩阵元素。在本文中，我们提出了微分对图（DP -MAP） - Memristor电导映射算法的第一个矩阵，专门为具有差分对配置的横梁设计。相比之下，以前的作品将差分配置视为事后的想法，这限制了可实现的精度。接下来，使用准确的闭环调整将指定的电导值编程到Memristor硬件。通过明智地选择电导范围并避免将每个矩阵分解为正分量和负分量，可以实现高精度的模拟计算。使用分层优化算法和两种加速技术可以实现短运行时间。与较早的研究相比，使用3.36倍提高了计算精度。这分别为质量高61％和94％的信号和图像压缩。使用部分微分方程（PDE）建模的复杂物理系统的仿真时间减少了5.87倍。
The natural multiply and accumulate feature of memristor crossbar arrays promises unprecedented processing capabilities to resistive dot-product engines (DPEs), which can accelerate approximate matrix-vector multiplication. To overcome the challenges of low-precision devices and voltage drop over non-zero array parasitics, each matrix element can be represented using two memristors. In this paper, we propose differential pair map (DP-MAP) - the first matrix to memristor conductance mapping algorithm specifically designed for crossbars with a differential pair configuration. In contrast, previous works consider the differential pair configuration as an afterthought, which limits the achievable precision. The specified conductance values are next programmed to the memristor hardware using accurate closed-loop tuning. Analog computation with high precision is attained by judiciously selecting the conductance range and avoiding to explicitly decompose each matrix into a positive and negative component. Short run-time is achieved using a hierarchical optimization algorithm and two speed-up techniques. Compared with earlier studies, the computational accuracy is improved with 3.36X. This translates into signal and image compression with 61 % and 94% higher quality, respectively. The simulation time of complex physical systems modeled using partial differential equations (PDEs) is reduced with 5.87X.