Takeo Ueki, Keisuke Iwai, T. Matsubara, T. Kurokawa
{"title":"基于随机方法的量化神经网络加速器","authors":"Takeo Ueki, Keisuke Iwai, T. Matsubara, T. Kurokawa","doi":"10.1109/CANDARW.2018.00033","DOIUrl":null,"url":null,"abstract":"In recent years, Deep Neural Network (DNN)s have become widely spread. Several high-throughput hardware implementations for DNNs have been proposed. One of the key points for hardware implementations of DNNs is to reduce their power consumption because DNNs require a lot of product-sum operations. Previous papers presented some accelerators using logarithmic quantization to reduce the power consumption by replacing multipliers with shifters. However, most of them are implemented only for inference. In this paper, an Accelerator of Quantization neural networkS with Stochastic approach (AQSS) is proposed. It uses a stochastic approach for logarithmic quantization, and enables DNNs to infer or to learn using logarithmic quantization. A prototype of AQSS is implemented on a field-programmable gate array (FPGA) (Intel Arria 10 GX 1150) and synthesized with Intel Quartus Prime 17.1 Standard Edition. As a result, it is confirmed to have 1.8 times the power efficiency of GPU.","PeriodicalId":329439,"journal":{"name":"2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"AQSS: Accelerator of Quantization Neural Networks with Stochastic Approach\",\"authors\":\"Takeo Ueki, Keisuke Iwai, T. Matsubara, T. Kurokawa\",\"doi\":\"10.1109/CANDARW.2018.00033\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, Deep Neural Network (DNN)s have become widely spread. Several high-throughput hardware implementations for DNNs have been proposed. One of the key points for hardware implementations of DNNs is to reduce their power consumption because DNNs require a lot of product-sum operations. Previous papers presented some accelerators using logarithmic quantization to reduce the power consumption by replacing multipliers with shifters. However, most of them are implemented only for inference. In this paper, an Accelerator of Quantization neural networkS with Stochastic approach (AQSS) is proposed. It uses a stochastic approach for logarithmic quantization, and enables DNNs to infer or to learn using logarithmic quantization. A prototype of AQSS is implemented on a field-programmable gate array (FPGA) (Intel Arria 10 GX 1150) and synthesized with Intel Quartus Prime 17.1 Standard Edition. As a result, it is confirmed to have 1.8 times the power efficiency of GPU.\",\"PeriodicalId\":329439,\"journal\":{\"name\":\"2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW)\",\"volume\":\"64 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CANDARW.2018.00033\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CANDARW.2018.00033","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
近年来,深度神经网络(DNN)得到了广泛的应用。已经提出了几种dnn的高吞吐量硬件实现。由于深度神经网络需要大量的乘积和运算,因此降低其功耗是实现深度神经网络硬件的关键之一。以前的论文介绍了一些使用对数量化的加速器,通过用移位器代替乘法器来降低功耗。然而,它们中的大多数仅用于推理。本文提出了一种基于随机方法的量化神经网络加速器。它使用随机方法进行对数量化,并使dnn能够使用对数量化进行推断或学习。在现场可编程门阵列(FPGA) (Intel Arria 10 GX 1150)上实现了AQSS的原型,并使用Intel Quartus Prime 17.1标准版进行了合成。因此,它的功耗效率是GPU的1.8倍。
AQSS: Accelerator of Quantization Neural Networks with Stochastic Approach
In recent years, Deep Neural Network (DNN)s have become widely spread. Several high-throughput hardware implementations for DNNs have been proposed. One of the key points for hardware implementations of DNNs is to reduce their power consumption because DNNs require a lot of product-sum operations. Previous papers presented some accelerators using logarithmic quantization to reduce the power consumption by replacing multipliers with shifters. However, most of them are implemented only for inference. In this paper, an Accelerator of Quantization neural networkS with Stochastic approach (AQSS) is proposed. It uses a stochastic approach for logarithmic quantization, and enables DNNs to infer or to learn using logarithmic quantization. A prototype of AQSS is implemented on a field-programmable gate array (FPGA) (Intel Arria 10 GX 1150) and synthesized with Intel Quartus Prime 17.1 Standard Edition. As a result, it is confirmed to have 1.8 times the power efficiency of GPU.