Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks
Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks
复制标题
在深度神经网络硬件加速器设计中使用近似电路库
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Z. Vašíček
中科院分区：
文献类型：
--
作者：
Vojtěch Mrázek;L. Sekanina;Z. Vašíček
已经开发了近似电路以在诸如深度神经网络（DNN）的硬件加速器之类的错误恢复应用中提供功耗和服务质量之间的良好折衷。为了加速近似电路设计过程，并支持电路近似方法的公平基准测试，近似电路库已经被引入。例如，EvoApprox 8b包含数百个8位近似加法器和乘法器。通过遗传编程，我们产生了一个扩展版本的图书馆，其中包括数千个8至128位的近似运算电路。这些电路相对于若干误差度量、功耗和其他电路参数形成帕累托前沿。在我们的案例研究中，我们展示了如何使用大量近似乘法器来执行ResNet DNN硬件加速器的弹性分析，并为给定应用选择最合适的近似乘法器。报告了在CIFAR-10基准问题上训练的ResNet DNN的各种实例的结果。
Approximate circuits have been developed to provide good tradeoffs between power consumption and quality of service in error resilient applications such as hardware accelerators of deep neural networks (DNN). In order to accelerate the approximate circuit design process and to support a fair benchmarking of circuit approximation methods, libraries of approximate circuits have been introduced. For example, EvoApprox8b contains hundreds of 8-bit approximate adders and multipliers. By means of genetic programming we generated an extended version of the library in which thousands of 8- to 128-bit approximate arithmetic circuits are included. These circuits form Pareto fronts with respect to several error metrics, power consumption and other circuit parameters. In our case study we show how a large set of approximate multipliers can be used to perform a resilience analysis of a hardware accelerator of ResNet DNN and to select the most suitable approximate multiplier for a given application. Results are reported for various instances of the ResNet DNN trained on CIFAR-10 benchmark problem.