Search papers, labs, and topics across Lattice.
The research was partially supported by the National Key R&D Program of China (Grant No. 2022YFB3608300). This research was partially conducted by ACCESS – AI Chip Center for Emerging Smart Systems, supported by the InnoHK initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government. It was also supported in part by Shenzhen Science and Technology Innovation Commission (Grant No. SGDX20220530111405040), Beijing Natural Science Foundation (Grant No. Z210006), Hong Kong Research Grant Council (Grant Nos. 27209621, 17205922, 17212923), the National Natural Science Foundation of China under Grant 62204111. (Wei Xuan and Zihao Xuan contributed equally to this work.)
1
0
3
0
Securing DNN accelerators doesn't have to break the bank: this co-design framework slashes memory overhead by 87% while boosting performance by 12%.
