Optimizing batched winograd convolution on GPUs

In this paper, we present an optimized implementation for single-precision Winograd convolution on NVIDIA Volta and Turing GPUs. Compared with the state-of-the-art Winograd convolution in cuDNN 7.6.1, our implementation achieves up to 2.13X speedup on Volta V100 and up to 2.65X speedup on Turing RTX2070. On both Volta and Turing GPUs, our implementation achieves up to 93% of device peak.