GTC this year was overwhelming in size and dazzled with innovations. If you haven’t experienced the conference yet, we highly recommend you to check it out - the amount of information pouring through talks, tutorials, demos, panels, posters, startup showcases is just hard to imagine. You’ll find all you need for starting or optimizing your Deep Learning or HPC project on GPUs.
Everyone is in a hurry today. And why not? We have CPU’s with more cores than ever and we have GPU’s with over 5,000 cores. The way to use these cores is to expose parallelism in our code. By doing that we can run faster (I don’t believe anyone has ever asked for less performance). One of the best ways to do this is to use OpenACC. OpenACC is great because it is simple to use (just “comments” in your code), allows the user to have control over the parallelization, and is portable.