Accelerating Generative Neural Networks on Unmodified Deep Learning Processors -- A Software Approach
This work addresses a bottleneck for users of generative neural networks by enabling efficient deconvolution on unmodified hardware, though it is incremental as it builds on prior acceleration schemes.
The paper tackles the problem of accelerating deconvolution operations in generative neural networks on existing deep learning processors without hardware modifications, achieving a 2.41x to 4.34x performance speedup and reducing energy consumption by 27.7% to 54.5% on benchmarks.
Generative neural network is a new category of neural networks and it has been widely utilized in applications such as content generation, unsupervised learning, segmentation and pose estimation. It typically involves massive computing-intensive deconvolution operations that cannot be fitted to conventional neural network processors directly. However, prior works mainly investigated specialized hardware architectures through intensive hardware modifications to the existing deep learning processors to accelerate deconvolution together with the convolution. In contrast, this work proposes a novel deconvolution implementation with a software approach and enables fast and efficient deconvolution execution on the legacy deep learning processors. Our proposed method reorganizes the computation of deconvolution and allows the deep learning processors to treat it as the standard convolution by splitting the original deconvolution filters into multiple small filters. Compared to prior acceleration schemes, the implemented acceleration scheme achieves 2.41x - 4.34x performance speedup and reduces the energy consumption by 27.7% - 54.5% on a set of realistic benchmarks. In addition, we also applied the deconvolution computing approach to the off-the-shelf commodity deep learning processors. The performance of deconvolution also exhibits significant performance speedup over prior deconvolution implementations.