Cray launched its new YarcData division only a few weeks ago, but in a surprise move today, the company announced its first Big Data appliance and a bevy of beta customers. Available today, the YarcData uRiKA graph appliance beging called a purpose-built solution for Big Data relationship analytics.
The uRiKA graph appliance fills an unmet need in the rapidly-growing Big Data market. While many critical Big Data problems are based on graphs, most current Big Data solutions are based on partitioned data structures that scale out on clusters. Current Big Data approaches, including graph databases, result in low performance on graphs since graphs are hard to partition across cluster nodes, are non-deterministic, and are highly dynamic. The launch of the uRiKA solution addresses the challenge of delivering insightful analytics on graphs, not only in terms of its ability to handle size and complexity of relationships, but also in terms of its response time and speed of processing.
Ok, so what exactly is inside this appliance, you might ask? With “massively-multithreaded graph processors supporting 128 threads/processor, and highly scalable I/O with data ingest rates of up to 350 terabytes per hour,” it looks to be a spinoff of the Cray XMT, the third generation of the Cray MTA supercomputer architecture originally developed by Tera. The Cray XMT has vanished from the company site, so they are now down to three compute product lines: Cray XK6 (AMD/Nvidia hybrid), Cray XE6 (AMD), and now uRIKA.