Back To Schedule
Thursday, September 3 • 3:55am - 4:10am
Support TVM QNN Flow on RISC-V with SIMD Computation - Yi-Ru Chen & Jenq Kuen Lee, National Tsing Hua University, Taiwan

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
The inference phase with low power and memory limited environments is critical for deploying neural network models on edge devices. One possible approach is adopting the quantization technique to represent activations and weights in lower bits. In this work, we present the efficiently inference quantized models by supporting TVM QNN flow with RISC-V SIMD computations. As RISC-V supports both Superword SIMD and Subword SIMD, we compile models by TVM and replace the computation kernel with designated LLVM intrinsic functions for mapping with RISC-V favorable SIMD instructions. Experiments shows 1.79-7.58x reduction of instruction count compared quantized model with FP32 implementation. The accuracy loss is acceptable by evaluating on 1k images. The benchmark including MobileNet and Inception series. All experiments are executed on Spike with RISC-V SIMD supports.

avatar for Yi-Ru, Chen

Yi-Ru, Chen

Graduate student, National Tsing Hua University, Taiwan

Jenq-Kuen Lee

Professor, National Tsing Hua University, Taiwan
Jenq-Kuen Lee received the B.S. degree in computer science from National Taiwan University in 1984. He received the M.S. and Ph.D. degrees in 1991 and 1992, respectively, in computer science from Indiana University. He is now a professor in the Department of Computer Science at National... Read More →

Thursday September 3, 2020 3:55am - 4:10am PDT