Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Spatially Parallel Convolutions
Peter Jin, Boris Ginsburg, Kurt Keutzer
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:The training of convolutional neural networks with large inputs on GPUs is limited by the available GPU memory capacity. In this work, we describe spatially parallel convolutions, which sidestep the memory capacity limit of a single GPU by partitioning tensors along their spatial axes across multiple GPUs. On modern multi-GPU systems, we demonstrate that spatially parallel convolutions attain excellent scaling when applied to input tensors with large spatial dimensions.
TL;DR:Spatially parallel convolutions reduce per-GPU memory usage and scale excellently to multiple GPUs.
Keywords:deep learning, convolution, parallelism
Enter your feedback below and we'll get back to you as soon as possible.