2 citations · 4 across the 4 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.DC2022
Optimizing Irregular-Shaped Matrix-Matrix Multiplication on Multi-Core DSPs
Shangfei Yin, Qinglin Wang, Ruochen Hao +3
General Matrix Multiplication (GEMM) has a wide range of applications in scientific simulation and artificial intelligence. Although traditional libraries can achieve high performa…
cs.DC2022★ 1 cited
Towards Effective Depthwise Convolutions on ARMv8 Architecture
Ruochen Hao, Qinglin Wang, Shangfei Yin +4
Depthwise convolutions are widely used in lightweight convolutional neural networks (CNNs). The performance of depthwise convolutions is mainly bounded by the memory access rather…