Re:Anatomy of a High-Performance Convolution
by bwasti on Monday September 02, 2019 @12:04AM
(#20856699)
Note that this a layout trick and not an algorithmic one. An algorithmic speed up that is good for dense convolutions with small kernels is to use Winograd: https://arxiv.org/abs/1509.09308
For large kernels, implementing an FFT tends to help.
Also worth keeping in mind that many modern networks use depthwise separable convolutions, which are channel wise convolutions (skipping a reduction over the channels, which is a memory bound operation) followed by 1x1 convolutions (which are exactly matrix multiplications with no im2col step).
Also worth keeping in mind that many modern networks use depthwise separable convolutions, which are channel wise convolutions (skipping a reduction over the channels, which is a memory bound operation) followed by 1x1 convolutions (which are exactly matrix multiplications with no im2col step).