NeuroSpector: Systematic Optimization of Dataflow Scheduling in DNN Accelerators.
IEEE Trans. Parallel Distributed Syst., August, 2023
The Nebula Benchmark Suite: Implications of Lightweight Neural Networks.
IEEE Trans. Computers, 2021
Energy-Efficient Acceleration of Deep Neural Networks on Realtime-Constrained Embedded Edge Devices.
IEEE Access, 2020
Duplo: Lifting Redundant Memory Accesses of Deep Neural Networks for GPU Tensor Cores.
Proceedings of the 53rd Annual IEEE/ACM International Symposium on Microarchitecture, 2020