NAAS: Neural Accelerator Architecture Search

被引：36

作者：

Lin, Yujun ^{[1
]}

Yang, Mengtian ^{[2
]}

Han, Song ^{[1
]}

机构：

[1] MIT, Cambridge, MA 02139 USA

[2] SJTU, Shanghai, Peoples R China

来源：

2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC) | 2021年

关键词：

D O I：

10.1109/DAC18074.2021.9586250

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Data-driven, automatic design space exploration of neural accelerator architecture is desirable for specialization and productivity. Previous frameworks focus on sizing the numerical architectural hyper-parameters while neglect searching the PE connectivities and compiler mappings. To tackle this challenge, we propose Neural Accelerator Architecture Search (NAAS) that holistically searches the neural network architecture, accelerator architecture and compiler mapping in one optimization loop. NAAS composes highly matched architectures together with efficient mapping. As a data-driven approach, NAAS rivals the human design Eyeriss by 4.4 x EDP reduction with 2.7% accuracy improvement on ImageNet under the same computation resource, and offers 1.4x to 3.5x EDP reduction than only sizing the architectural hyper-parameters.

引用

页码：1051 / 1056

页数：6

共 31 条

[1] Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing [J].

Albericio, Jorge ;

Judd, Patrick ;

Hetherington, Tayler ;

Aamodt, Tor ;

Jerger, Natalie Enright ;

Moshovos, Andreas .

2016 ACM/IEEE 43RD ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2016, :1-13

[2]

Cai H., 2020, P INT C LEARN REPR

[3]

Cai Han, 2019, INT C LEARN REPR ICL

[4]

Chen TQ, 2018, PROCEEDINGS OF THE 13TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P579

[5]

Chen TQ, 2018, ADV NEUR IN, V31

[6] Cloud-DNN: An Open Framework for Mapping DNN Models to Cloud FPGAs [J].

Chen, Yao ;

He, Jiong ;

Zhang, Xiaofan ;

Hao, Cong ;

Chen, Deming .

PROCEEDINGS OF THE 2019 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS (FPGA'19), 2019, :73-82

[7]

Chen YH, 2016, ISSCC DIG TECH PAP I, V59, P262, DOI 10.1109/ISSCC.2016.7418007

[8] ShiDianNao: Shifting Vision Processing Closer to the Sensor [J].

Du, Zidong ;

Fasthuber, Robert ;

Chen, Tianshi ;

Ienne, Paolo ;

Li, Ling ;

Luo, Tao ;

Feng, Xiaobing ;

Chen, Yunji ;

Temam, Olivier .

2015 ACM/IEEE 42ND ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2015, :92-104

[9]

Guo Z., 2019, Single path one-shot neural architecture search with uniform sampling

[10]

Hansen N, 2006, STUD FUZZ SOFT COMP, V192, P75

← 1 2 3 4 →