Hybrid Binary-Unary Hardware Accelerator
Hybrid Binary-Unary Hardware Accelerator
复制标题
混合二进制-一元硬件加速器
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. Bazargan
中科院分区：
文献类型：
--
作者：
S. R. Faraji;K. Bazargan
近年来，随机计算已被用于通过利用数据的一元编码来创建具有显著更小面积的设计。然而，低面积优势的代价是延迟呈指数级增长，使得$面积\时间延迟$成本没有吸引力。在本文中，我们提出了一种使用混合二进制/一元表示来执行计算的新方法。我们首先将输入范围划分为几个子区域，对每个子区域单独执行一元计算，最后将所有子区域的输出打包回紧凑二进制。此外，我们提出了一种综合方法和回归模型来预测设计空间中的最优或次优设计。由于路由和触发器资源丰富，所提出的方法特别适合于FPGA。据我们所知，我们是第一个展示基于随机计算原理的可扩展方法的人，该方法可以在真实的成本方面击败传统的二进制，即，$area \times delay$.我们的方法优于二进制和完全一元的方法上的一些功能和一个共同的边缘检测算法。在$面积\时间延迟$成本方面，我们的成本平均仅为8位和10位分辨率的二进制的2.51%和10.2%。这些数字比传统随机方法的结果好2-3个数量级。我们的方法是没有竞争力的高分辨率振荡函数，如$\sin（15 x）$的二进制方法。
Stochastic computing has been used in recent years to create designs with significantly smaller area by harnessing unary encoding of data. However, the low area advantage comes at an exponential price in latency, making the $area \times delay$ cost unattractive. In this paper, we present a novel method which uses a hybrid binary / unary representation to perform computations. We first divide the input range into a few sub-regions, perform unary computations on each sub-region individually, and finally pack the outputs of all sub-regions back to compact binary. Moreover, we propose a synthesis methodology and a regression model to predict an optimal or sub-optimal design in the design space. The proposed method is especially well-suited to FPGAs due to the abundant availability of routing and flip-flop resources. To the best of our knowledge, we are the first to show a scalable method based on the principles of stochastic computing that can beat conventional binary in terms of a real cost, i.e., $area \times delay$. Our method outperforms the binary and fully unary methods on a number of functions and on a common edge detection algorithm. In terms of $area \times delay$ cost, our cost is on average only 2.51 % and 10.2% of the binary for 8- and 10-bit resolutions, respectively. These numbers are 2-3 orders of magnitude better than the results of traditional stochastic methods. Our method is not competitive with the binary method for high-resolution oscillating functions such as $\sin (15x)$.