Hacker News new | past | comments | ask | show | jobs | submit login

In hlb-CIFAR10 the MaxPooling ops are the slowest kernels now and take longer than all 7 of the convolution operations combined, if I understand correctly.

Memory-bound operations seem to rather consistently be the limiting factor in my personal ML research work, at least. It can be rather annoying!




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: