Scaled Population Arithmetic for Efficient Stochastic Computing
Scaled Population Arithmetic for Efficient Stochastic Computing
复制标题
DOI：
10.1109/asp-dac47756.2020.9045292
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
He Zhou;S. Khatri;Jiang Hu;Frank Liu
中科院分区：
文献类型：
--
作者：
He Zhou;S. Khatri;Jiang Hu;Frank Liu
我们提出了一个新的规模人口（SP）的算术计算方法，实现了相当大的改进，现有的随机计算（SC）技术。首先，SP算法引入缩放操作，显着减少数值误差相比，SC。实验表明，一个单一的乘法和加法运算的精度提高了6美元。3 \乘以$和$4。0 \times $。其次，SP算法消除了随机计算固有的串行化，从而显著改善了计算延迟。我们将SP算法的每个操作设计为需要$\mathcal{O}$（1）个门延迟，并且消除了对种群向量的位进行串行迭代的需要。我们的SP方法相比，传统的随机计算基于FPGA的实现，提高了面积，延迟和功率。我们还将我们的SP计划的手写数字识别应用程序（MNIST），提高了32.79%的识别精度相比，SC。
We propose a new Scaled Population (SP) based arithmetic computation approach that achieves considerable improvements over existing stochastic computing (SC) techniques. First, SP arithmetic introduces scaling operations that significantly reduce the numerical errors as compared to SC. Experiments show accuracy improvements of a single multiplication and addition operation by $6. 3 \times $ and $4. 0 \times $, respectively. Secondly, SP arithmetic erases the inherent serialization associated with stochastic computing, thereby significantly improves the computational delays. We design each of the operations of SP arithmetic to take $\mathcal{O}$(1) gate delays, and eliminate the need of serially iterating over the bits of the population vector. Our SP approach improves the area, delay and power compared with conventional stochastic computing on an FPGA-based implementation. We also apply our SP scheme on a handwritten digit recognition application (MNIST), improving the recognition accuracy by 32.79% compared to SC.