BitParticle: Partializing Sparse Dual-Factors to Build Quasi-Synchronizing MAC Arrays for Energy-efficient DNNs

Feilong Qiaoyuan, Jihe Wang, Zhiyu Sun +3

Bit-level sparsity in quantized deep neural networks (DNNs) offers significant potential for optimizing Multiply-Accumulate (MAC) operations. However, two key challenges still limi…