In May 2012 CSCS organized a course about "Using the next-generation Cray XMT (uRiKA) for Large Scale Data Analytics".

The next-generation Cray XMT (uRiKA) is a massively multithreaded, high performance computer system built for data analytics. The system supports a semantic database capable of processing SPARQL queries against a RDF triple store. The system can also be programmed in C and C++. During the course experts from Cray Inc and Pacific Northwest National Laboratory presented talks on the system architecture, programming model, semantic database, and programming best practices. Attendees learned both how to use the resident database and write highly-scalable parallel programs to solve complex data analysis problems.

Mario Valle, CSCS - Introduction to the workshop

Many critical Big Data problems are based on graphs. Unfortunately current Big Data approaches result in low performance on graphs since graphs are hard to partition across cluster nodes, are non-deterministic, and are highly dynamic.

The Cray uRiKA graph appliance 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.

First goal of the workshop is to familiarize potential users to the functionalities offered by this machine, that is part of the CSCS portfolio.

James Maltby, Cray - Cray XMT/uRIKA overview

An overview of the XMT machine, now rechristened uRIKA, and the strategies it implements to effectively solve problems with irregular structure like graph algorithms.

uRiKa Appliance System overview »

Using and Administering the uRiKa Appliance »

The uRIKA machine comes with a software stack specialised for graph queries. Through SPARQL statements the user could submit complex queries to obtain insightful analytics on graphs

John Feo, Pacific National Northwest Laboratory (PNNL)

Programming the Cray XMT at PNNL (part 1) »

Programming the Cray XMT at PNNL (part 2) »

In depth view of the XMT programming from people that use it for their research.

How a classical problem can be redefined to exploit the XMT peculiar parallel architecture and memory structure