Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I wonder what the application was. There is not that much deep learning in genomics.


The tensor cores are simply matrix multiplication + accumulation. They don't need to be used purely for deep learning.


The code is Comet https://www.sanger.ac.uk/science/tools/comet and based on the PR I think they ran it in embarassingly (or lightly) parallel mode (IE, very little if any communication between nodes except for periodic reduces.




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

Search: