- The new Cray Accel AI Lab to advance the development of deep learning technologies and workflows;
- New Cray Accel AI offerings, featuring NVIDIA® Tesla® V100 GPU accelerators, which provide a range of fast-start configurations leveraging the Cray® CS-Storm™ accelerated cluster supercomputer along with a robust deep learning environment;
- A new Cray Urika®-XC analytics software suite, including the addition of the TensorFlow™ open-source machine intelligence software library and support for Jupyter Notebooks;
An AI collaboration agreement with Intel, leveraging Intel’s AI technologies to advance the state-of-the-art in distributed deep learning and machine learning.
Cray is committed to working closely with our customers, partners, and innovators in AI to drive the adoption of deep learning in science and enterprise,” said Fred Kohout, Cray’s senior vice president of products and chief marketing officer. “At Cray, we are bringing together a powerful set of innovative systems, software, deep learning architectures, and a hands-on lab environment to give organizations a trusted partner to advance AI workloads from pilot to production.”
Cray Accel AI Lab
Cray is launching a deep learning innovation center – the Cray Accel AI Lab – to serve as the focal point for the application, incubation, and advancement of supercomputing technologies in AI. The new lab will provide access to Cray systems powered by Intel® Xeon® Scalable Processors and NVIDIA Tesla GPU accelerators, and will bring together AI experts from Cray’s engineering teams, its customers, and partners to provide educational content and classes in topics ranging from developer training to advanced optimization techniques of deep learning frameworks. The Cray Accel AI Lab will accessible from Cray offices worldwide, with classroom settings available in Cray’s major office locations.
Cray Accel AI Offerings
Cray is introducing new Cray Accel AI offerings designed to make it easier for customers to get started with AI. The new, fast-start configurations range from a starter system ideal for AI exploration to a complete, production-level Cray cluster supercomputer for training and inference. Components include the Cray CS-Storm accelerated GPU system featuring NVIDIA Tesla V100 GPU accelerators powered by the NVIDIA Volta™ GPU architecture, and a comprehensive deep learning and analytics software environment from Bright Computing.
New Cray Urika-XC Analytics and AI Software Suite
The Cray Urika-XC software suite, which brings graph analytics, deep learning, and robust big data analytics tools the Company’s flagship line of Cray XC™ supercomputers, will now include the TensorFlow computational framework and enhancements to the Cray software environment that are specifically designed to accelerate machine learning frameworks. The new Cray Programming Environment (CPE) Machine Learning Library will deliver unprecedented scaling by leveraging the Aries interconnect, and will eliminate many of the mundane administrative tasks required for distributed deep learning. With the enhanced performance, data scientists will be able to train neural networks at scale on a Cray XC supercomputer – leveraging either CPUs or GPUs – to more than 500 nodes.
Additionally, Cray is adding functionality for truly interactive supercomputing for analytics and AI workloads with the addition of Jupyter Notebook support, giving users the ability to create and share executable code, graphical visualizations, monitoring widgets, and narrative text.
At the heart of artificial intelligence, machine learning, deep learning, and supercomputing are some key commonalities,” said Clint Wheelock, founder and managing director of Tractica. “At this stage in the development of the market, the timing is optimal to bring together the two areas of HPC and AI.”
AI Collaboration Agreement with Intel
Intel and Cray have signed an agreement to collaborate on the development of a scalable software environment to enable science and enterprise to take advantage of the tremendous promise of AI. The collaboration will deliver a productized software stack for deep learning at scale on Cray systems, along with targeted optimizations for popular deep learning and machine learning tools, such as TensorFlow and Intel’s BigDL distributed deep learning library for Apache Spark.
The convergence of Artificial Intelligence with traditional HPC applications holds the promise of unlocking new scientific approaches and new breakthrough discoveries,” said Trish Damkroger, Vice President of Technical Computing at Intel. “This latest collaboration with Cray, a global leader in supercomputing, will further accelerate this convergence and help extend the reach of AI tools.”