Optimizing Grouped Convolutions on Edge Devices
This work addresses performance bottlenecks for deploying deep neural networks on constrained hardware, offering incremental improvements to existing methods.
The paper tackled the problem of inefficient grouped convolution implementations on edge devices by proposing Grouped Spatial Pack Convolutions (GSPC), which improved inference times by 3.4x, 8x, and 4x on average over existing solutions in TVM, PyTorch, and TensorFlow Lite.
When deploying a deep neural network on constrained hardware, it is possible to replace the network's standard convolutions with grouped convolutions. This allows for substantial memory savings with minimal loss of accuracy. However, current implementations of grouped convolutions in modern deep learning frameworks are far from performing optimally in terms of speed. In this paper we propose Grouped Spatial Pack Convolutions (GSPC), a new implementation of grouped convolutions that outperforms existing solutions. We implement GSPC in TVM, which provides state-of-the-art performance on edge devices. We analyze a set of networks utilizing different types of grouped convolutions and evaluate their performance in terms of inference time on several edge devices. We observe that our new implementation scales well with the number of groups and provides the best inference times in all settings, improving the existing implementations of grouped convolutions in TVM, PyTorch and TensorFlow Lite by 3.4x, 8x and 4x on average respectively. Code is available at https://github.com/gecLAB/tvm-GSPC/