Penguin Computing: OriginAI Powered by WekaIO

Penguin Computing, Inc., a division of SMART Global Holdings, Inc., and in HPC, AI, and enterprise data center solutions, has partnered with WekaIO, Inc. to provide NVIDIA GPU-Powered OriginAI, an end-to-end solution for data center AI that maximizes the performance and utility of high-value AI systems.

Organizations are acknowledging the business potential that AI, ML, and deep learning represent. In order to adopt these technologies, organizations must implement complex new systems that are performance-optimized and secure.

In order to be successful, every component of an AI system must be expertly tuned to support an organization’s AI workloads. An un-tuned system results in data path bottlenecks that render expensive resources idle, leading to lost productivity and increased time-to-insight. Adding to the complexity, the speed at which AI evolves demands flexible, scalable architectures that have the ability to keep pace as technology advances.

OriginAI provides a single, secure, end-to-end solution for data center AI that includes architectural design, hardware and software services, hosting, and deployment. Featuring Penguin Computing ActiveData with the Weka file system (WekaFS), it frees organizations from having to focus valuable time and human resources on creating an architecture from scratch. It meets the demanding requirements of AI and analytics models, and delivers cost savings, decreases risk, offers flexibility and scalability, increases performance, and reduces time-to-insight.

“The faster organizations reach time-to-insight in their AI initiatives, the faster they bring new products and ideas to market,” said Kevin Tubbs, Ph.D., and SVP, strategic solutions group. “The OriginAI comprehensive solution for AI empowers organizations to speed time-to-insight and translate those insights to competitive marketplace advantage.“

“Weka and Penguin Computing’s capabilities deliver massive bandwidth for ingest and training, ultra-low latency for improved inference, and enterprise features to manage data workflows,” said Ken Grohe, president and CRO, WekaIO. “As the only shared storage solution that provides high bandwidth I/O to the GPUs and end-to-end data management for data-intensive AI workloads, WekaFS enables companies to quickly scale performance across the platform.“

With the launch of Penguin Computing’s 4 dedicated technology practices, OriginAI is a part of the AI and analytics practice. The AI and analytics practice removes the guesswork in deploying effective AI training and inference platforms from the core to the edge. The practice focuses on reducing time-to-insight and discovery by removing complexities involved in designing, deploying, operating and supporting AI and analytics infrastructure.

OriginAI will be available in mid-fiscal 1Q21.