no code implementations • 12 Nov 2021 • Yuhong Song, Edwin Hsing-Mean Sha, Qingfeng Zhuge, Rui Xu, Yongzhuo Zhang, Bingzhe Li, Lei Yang
Unlike ML on the edge, TinyML with a limited energy supply has higher demands on low-power execution.
no code implementations • 19 Oct 2021 • Panjie Qi, Edwin Hsing-Mean Sha, Qingfeng Zhuge, Hongwu Peng, Shaoyi Huang, Zhenglun Kong, Yuhong Song, Bingbing Li
Our HP can achieve higher sparsity ratio and is more flexible than other sparsity pattern.
no code implementations • 12 Feb 2021 • Yuhong Song, Weiwen Jiang, Bingbing Li, Panjie Qi, Qingfeng Zhuge, Edwin Hsing-Mean Sha, Sakyasingha Dasgupta, Yiyu Shi, Caiwen Ding
Specifically, RT3 integrates two-level optimizations: First, it utilizes an efficient BP as the first-step compression for resource-constrained mobile devices; then, RT3 heuristically generates a shrunken search space based on the first level optimization and searches multiple pattern sets with diverse sparsity for PP via reinforcement learning to support lightweight software reconfiguration, which corresponds to available frequency levels of DVFS (i. e., hardware reconfiguration).
1 code implementation • 6 Jul 2019 • Weiwen Jiang, Lei Yang, Edwin Sha, Qingfeng Zhuge, Shouzhen Gu, Sakyasingha Dasgupta, Yiyu Shi, Jingtong Hu
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
no code implementations • 31 Jan 2019 • Weiwen Jiang, Xinyi Zhang, Edwin H. -M. Sha, Lei Yang, Qingfeng Zhuge, Yiyu Shi, Jingtong Hu
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.