简短声明：关于在GPU上并行化卷积神经网络的限制
Brief Announcement: On the Limits of Parallelizing Convolutional Neural Networks on GPUs
摘要：
GPU目前是训练神经网络的首选平台。然而，即使在GPU上训练深度神经网络（DNN）也是一个耗时的过程，因为必须学习大量的参数。因此，加速DNN训练在过去几年中一直是一个重要的研究领域。虽然早期的网络（如AlexNet）在层和操作之间具有线性依赖性，但最先进的网络（如ResNet，PathNet和GoogleNet）具有非线性结构，表现出更高水平的操作间并行性。然而，流行的深度学习（DL）框架（如TensorFlow和PyTorch）在GPU上串行启动大多数神经网络操作，特别是卷积，并且不利用这种操作间并行性。在这个简短的声明中，我们提出了在最先进的非线性网络中利用这种丰富的并行性来减少训练时间的需求和潜在好处。我们确定了在DL框架的GPU后端（如cuDNN）上启用并发层执行的挑战和限制，并提出了潜在的解决方案。
英文摘要：
GPUs are currently the platform of choice for training neural networks. However, training a deep neural network (DNN) is a time-consuming process even on GPUs because of the massive number of parameters that have to be learned. As a result, accelerating DNN training has been an area of significant research in the last couple of years. While earlier networks such as AlexNet had a linear dependency between layers and operations, state-of-the-art networks such as ResNet, PathNet, and GoogleNet have a non-linear structure that exhibits a higher level of inter-operation parallelism. However, popular deep learning (DL) frameworks such as TensorFlow and PyTorch launch the majority of neural network operations, especially convolutions, serially on GPUs and do not exploit this inter-op parallelism. In this brief announcement, we make a case for the need and potential benefit of exploiting this rich parallelism in state-of-the-art non-linear networks for reducing the training time. We identify the challenges and limitations in enabling concurrent layer execution on GPU backends (such as cuDNN) of DL frameworks and propose potential solutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
