The Conference for Machine Learning Innovation

How to Write a Custom CUDA Operator

Session
Join the ML Revolution!
Register until the conference starts:
✓ 2-in-1 conference special
✓ 10 % Team Discount
Register Now
Join the ML Revolution!
Register until the conference starts:
✓ 2-in-1 conference special
✓ 10 % Team Discount
Register Now
Join the ML Revolution!
Register until August 12:
✓ML Intro Day for free
✓Save up to $380
Register Now
Join the ML Revolution!
Register until August 12:
✓ML Intro Day for free
✓Save up to $380
Register Now
Join the ML Revolution!
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now
Join the ML Revolution!
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now

When implementing a Deep Learning model with the framework of our choice these days we generally have an extensive, fast API to work with that covers most needs. But sometimes a situation may arise where the out-of-the-box components of TensorFlow, Torch, MXnet, and others are simply not enough. This can happen when we want to implement a model that is so new that we cannot create a fast enough implementation using a combination of built-in operators. Or we may have already implemented a working model but are looking to make it faster by replacing a combination of built-in operators with our own, fused version to speed up training and/or inference. In this session, we will have a look at the basics of CUDA and show how to implement and test a real-world custom operation with CUDA and integrate it with a Deep Learning framework.

This Session belongs to the Diese Session gehört zum Programm vom SingaporeSingapore program. Take me to the program of . Hier geht es zum Programm von Munich Munich .

Take me to the full program of Zum vollständigen Programm von Singapore Singapore .

This Session belongs to the Diese Session gehört zum Programm vom SingaporeSingapore program. Take me to the program of . Hier geht es zum Programm von Berlin Berlin .

This Session Diese Session belongs to the gehört zum Programm von SingaporeSingapore program. Take me to the current program of . Hier geht es zum aktuellen Programm von Munich Munich , Singapore Singapore or oder Berlin Berlin .

Behind the Tracks