Ryan Gary Kim

TL;DR: In this paper, a hybrid Network-on-Chip (NoC) architecture was proposed for energy-efficient training of CNNs on heterogeneous manycore platforms. But, the NoC architecture is not suitable for large-scale CNN architectures.

TL;DR: This work proposes the first architecture-independent IL-based methodology for dynamic VFI (DVFI) control in manycore systems and demonstrates that IL is able to obtain higher quality policies than RL with significantly less computation time and hardware area overheads.

TL;DR: This paper designs a hybrid Network-on-Chip (NoC) architecture, which consists of both wireline and wireless links, to improve the performance of CPU-GPU based heterogeneous manycore platforms running the above-mentioned CNN training workloads and demonstrates that the proposed hybrid NoC for heterogeneity manycore architectures is capable of significantly accelerating training of CNNs while remaining energy-efficient.

TL;DR: This paper explores the emerging paradigm of wireless NoC (WiNoC) and demonstrates that by incorporating WiNoC, VFI, and dynamic V/F tuning in a synergistic manner, it can design energy-efficient multicore platforms without introducing noticeable performance penalty.

TL;DR: The proposed hybrid NoC achieves 1.9× reduction in network latency and improves the network throughput by a factor of 2 with respect to a highly optimized mesh NoC, demonstrating the capability of the proposed hybrid and heterogeneous manycore architecture in accelerating deep learning kernels in an energy-efficient manner.