Using the observations from the Atmospheric Imaging Assembly (AIA) and Helioseismic and Magnetic Imager (HMI) aboard the Solar Dynamics Observatory (SDO), we investigate six X-class and twentynine M-class flares occurring in solar active region (AR) 12192 from October 18 to 29. Among them, thirty (including six X-and twenty-four M-class) flares originated from the AR core and the other five M-flares appeared at the AR periphery. Four of the X-flares exhibited similar flaring structures, indicating they were homologous flares with analogous triggering mechanism. The possible scenario is: photospheric motions of emerged magnetic fluxes lead to shearing of the associated coronal magnetic field, which then yields a tether-cutting favorable configuration. Among the five periphery M-flares, four were associated with jet activities. The HMI vertical magnetic field data show that the photospheric fluxes of opposite magnetic polarities emerged, converged and canceled with each other at the footpoints of the jets before the flares. Only one M-flare from the AR periphery was followed by a coronal mass ejection (CME). From October 20 to 26, the mean decay index of the horizontal background field within the height range of 40-105 Mm is below the typical threshold for torus instability onset. This suggests that a strong confinement from the overlying magnetic field might be responsible for the poor CME production of AR 12192.

No abstract

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement (i.e., memory access). This work provides comprehensive analysis and methodologies to minimize the communication for the convolution in CNNs. With an in-depth analysis of the recent I/O complexity theory under the red-blue game model, we develop a general I/O lower bound theory for a composite algorithm which consists of several different sub-computations. Based on the proposed theory, we establish the data movement lower bound results for two main convolution algorithms in CNNs, namely the direct convolution and Winograd algorithm, which represents the direct and indirect implementations of a convolution respectively. Next, derived from I/O lower bound results, we design the near I/O-optimal dataflow strategies for the two main convolution algorithms by fully exploiting the data reuse. Furthermore, in order to push the envelope of performance of the near I/O-optimal dataflow strategies further, an aggressive design of auto-tuning based on I/O lower bounds, is proposed to search an optimal parameter configuration for the direct convolution and Winograd algorithm on GPU, such as the number of threads and the size of shared memory used in each thread block. Finally, experiment evaluation results on the direct convolution and Winograd algorithm show that our dataflow strategies with the auto-tuning approach can achieve about 3.32× performance speedup on average over cuDNN. In addition, compared with TVM, which represents the state-of-the-art technique for auto-tuning, not only our auto-tuning method based on I/O lower bounds can find the optimal parameter configuration faster, but also our solution has higher performance than the optimal solution provided by TVM.

No abstract