gustiks / gnnwlrnns Goto Github PK

Dear authors,

Recently I went through your paper Lossless Compression of Structured Convolutional Models via Lifting and found it very interesting.

However, I noticed that you did not correctly measure the DGL running time on GPU, and most of the DGL time you measured comes from the graph conversion overhead (the DGLGraph is converted from pyg format).

The following code section

will not correctly record the real GPU execution time because in PyTorch the GPU operators are asynchronous. To get the accuracy GPU time, you can either put torch.cuda.synchronize() after and before your time.time() statement or use torch.cuda.Event for more accurate profiling. (See https://pytorch.org/docs/stable/notes/cuda.html).

The graph conversion overhead could be hidden by enabling multi-processing data loader, I could help implement this if needed.

I know the DGL implementation only acts as a baseline in your paper but I think a fair comparison looks better :)
btw, in the DGL 0.5 release (coming soon) we greatly improved the speed performance, please stay tuned if you're interested.

Best,
Zihao