How to use NVIDIA GPUs for Machine Learning with the new Data Science PC from Maingear

Deep Learning enables us to perform many human-like tasks, but if you're a data scientist and you don't work in a FAANG company (or if you're not developing the next AI startup) chances are that you still use good and old (ok, maybe not that old) Machine Learning to perform your daily tasks. One characteristic of Deep Learning is that it's very computationally intensive, so all the main DL libraries make use of GPUs to improve the processing speed. But if you ever felt left out of the party because you don't work with Deep Learning, those days are over: with the RAPIDS suite of libraries now we can run our data science and analytics pipelines entirely on GPUs. In this article we're going to talk about some of these RAPIDS libraries and get to know a little more about the new Data Science PC from Maingear. Generally speaking, GPUs are fast because they have high-bandwidth memories and hardware that performs floating-point arithmetic at significantly higher rates than conventional CPUs [1].