A Real Time 1280x720 Object Detection Chip With 585MB/s Memory Traffic

Memory bandwidth has become the real-time bottleneck of current deep learning accelerators (DLA), particularly for high definition (HD) object detection. Under resource constraints, this paper proposes a low memory traffic DLA chip with joint hardware and software optimization. To maximize hardware utilization under memory bandwidth, we morph and fuse the object detection model into a group fusion-ready model to reduce intermediate data access. This reduces the YOLOv2's feature memory traffic from 2.9 GB/s to 0.15 GB/s. To support group fusion, our previous DLA based hardware employes a unified buffer with write-masking for simple layer-by-layer processing in a fusion group. When compared to our previous DLA with the same PE numbers, the chip implemented in a TSMC 40nm process supports 1280x720@30FPS object detection and consumes 7.9X less external DRAM access energy, from 2607 mJ to 327.6 mJ.

Learning the Representations of Moist Convection with Convolutional Neural Networks

The representations of atmospheric moist convection in general circulation models have been one of the most challenging tasks due to its complexity in physical processes, and the interaction between processes under different time/spatial scales. This study proposes a new method to predict the effects of moist convection on the environment using convolutional neural networks. With the help of considering the gradient of physical fields between adjacent grids in the grey zone resolution, the effects of moist convection predicted by the convolutional neural networks are more realistic compared to the effects predicted by other machine learning models. The result also suggests that the method proposed in this study has the potential to replace the conventional cumulus parameterization in the general circulation models.