Please note: This schedule is automatically displayed in China Standard Time (UTC +8). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change.
Many advanced data processing paradigms fit incredibly well to the parallel-architecture that GPU computing offers, and exciting advancements in the open source projects such as Vulkan and Kompute are enabling developers to take advantage of general purpose GPU computing capabilities in cross-vendor mobile and desktop GPUs including AMD, Qualcomm, NVIDIA & friends. In this talk we will provide a conceptual and practical insight into the cross-vendor GPU compute ecosystem as well as how to adopt these tools to accelerate your existing applications. In this talk we will learn to write a simple GPU accelerated machine learning algorithm from scratch which will be able to run on virtually any GPU. We will give an overview on the projects that are making it possible to accelerate applications across cross-vendor GPUs. We'll show how you can get started with the full power of your GPU using the Kompute framework with only a handful of lines of Python code, as well as providing an intuition around how optimizations can be introduced through the lower level C++ interface.
Alejandro Saucedo is the Director of Machine Learning Engineering at Seldon Technologies, where he leads teams of machine learning engineers focused on the scalability and extensibility of machine learning deployment and monitoring products with over 5 million installations. Alejandro... Read More →
Vector data, i.e., embedding data, is a common and critical data type in various AI applications. Vector databases were emerging due to the ever-growing demand for unstructured data analytics in AI-powered applications. Milvus, an open-source vector database and an LF AI & DATA graduation project, has gained huge momentum ever since its open-source. It has gained more than 1000 enterprise users worldwide in less than two years. After developing Milvus 1.0, we summarized the experiences and lessons learned from serving various AI applications. Accordingly, we designed a new architecture and applied it to Milvus 2.0. The new architecture achieves read-write and compute-storage decoupling with a flexible, easy-to-scale, and cloud-native design. In this talk, we will show the principal design considerations that guide the development of Milvus 2.0. Then we will introduce its system architecture and major components. Lastly, we will discuss the challenges we encountered.
Xiaomeng Yi, senior researcher and research team leader of Zilliz. He received his Ph.D. degree in computer architecture from Huazhong University of Science and Technology. His research interests include management of high-dimension data, large-scale information retrieval, and resource... Read More →
