GOAI: Accelerating the Scalable Data Science Environment with GPU-enabled Python
Brad Rees, Keith Kraus, Bartley Richardson (NVIDIA)
Data Science/Data Mining is the exploration of data to extract novel knowledge and insight. That discovery process often involves a considerable amount of trial and error, after all, if you know what you are looking for you are not doing discovery. The Python programming language has grown in popularity amount data scientists for its flexibility, ease of programming, and readability. However, Python is not known for performance, which has not been an issue in the past. Unfortunately, today, a large amount of science is driven through the exploration of large volumes of data. Combined with the ever-increasing need for more complex algorithms and analytics, data scientists have had to turn more and more of their attention away from the problems they’re trying to solve and instead towards implementing their hypotheses in less friendly, “more performant” systems. Luckily, work being done in the GPU Open Analytics Initiative (GOAI) is pushing to make GPU-accelerated Data Science in Python a first-class citizen and driving performance to be on par with the other languages, including GPU-accelerated C/C++. Join NVIDIA’s engineers as they walk through a collection of data science problems and introduce the various components and features within the GOAI ecosystem that accelerate common Machine Learning / Feature Engineering / Data Manipulation / Statistical tasks as well as custom, user-defined, functions. The tutorial will focus on accelerating a data science workflow in Python on a single GPU, but will go into on how the same workflow can be applied to high-performance workstations with multiple GPUs, and large scale clusters.
Time and location will be posted when available.
Return to: Hands-on Tutorials