222 citations · 279 across the 5 of their papers we have counts for
Showing cs.ARShow all
2 papers · 1 filter
cs.AR2023★ 1 cited
KAPLA: Pragmatic Representation and Fast Solving of Scalable NN Accelerator Dataflow
Zhiyao Li, Mingyu Gao
Dataflow scheduling decisions are of vital importance to neural network (NN) accelerators. Recent scalable NN accelerators support a rich set of advanced dataflow techniques. The p…
cs.AR2022★ 1 cited
RePAST: A ReRAM-based PIM Accelerator for Second-order Training of DNN
Yilong Zhao, Li Jiang, Mingyu Gao +6
The second-order training methods can converge much faster than first-order optimizers in DNN training. This is because the second-order training utilizes the inversion of the seco…