CQNN: a CGRA-based QNN Framework

Conference · Tue Dec 22 04:00:00 EST 2020

OSTI ID:1763313

Geng, Tong ^[1]; Wu, Chunshu ^[1]; Tan, Cheng ^[2]; Fang, Bo ^[2]; Li, Ang ^[2]; Herbordt, Martin ^[1]

---

1. Boston University
2. BATTELLE (PACIFIC NW LAB)

We propose a novel Coarse-Grained Reconfigurable Architecture-based (CGRA) QNN acceleration framework, CQNN. CQNN has a large number of basic components for binary functions. By programming CQNN at runtime according to the target QNN models, these basic components are integrated efficiently to support QNN functions with any data-width and hyper-parameter requirements and CQNN is reconfigured to have the optimal architecture for the target models. The framework includes compiler, architecture design, simulator and RTL generator. Experimental results show CQNNs can complete the inference of AlexNet and VGG-16 within 0.13ms and 2.63ms.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1763313
• Report Number(s): PNNL-SA-153940
• Country of Publication: United States
• Language: English