movsum slower than conv2 in GPU
2 views (last 30 days)
I have this code that tests how both movsum and conv2 perform under GPU.
Turns out conv2 takes 5ms whereas movsum takes 10ms.
movsum should have a simpler algorithm than conv2, no?
Joss Knight on 15 Oct 2019
One might theorize, perhaps, that movsum literally uses the same kernels as conv2, but first has to construct the filter of ones which takes extra time. I'm not saying that's what happens, but it's a theory. By making more generic kernels, MATLAB saves space, which is important for download times and the MATLAB Compiler Runtime.