Israeli startup Speedata employs CGRA to accelerate data analytics
Speedata C200 is the industry's first analytics accelerator card (according to the company), housing the Callisto analytics processing unit. The card is optimized for high-bandwidth data processing and delivers dramatic acceleration for Apache Spark workloads. With its PCIe connectivity, it is engineered for seamless integration into standard server configurations.
The Callisto chip and associated software automatically delegates to the CPU the handling of SQL elements such as user-defined functions that cannot be accelerated, while still handling the rest of the query, for better performance.
In contrast to AI workloads that GPUs excel at, data analytics frequently involves complex queries that include conditional statements, joins, aggregations, and other operations that depend on the data values being processed. These tasks require frequent branching and complex control flows, making them less straightforward to parallelize.
To optimize performance for data analytic workloads, a new system architecture, Coarse-Grained Reconfigurable Architecture (CGRA), is emerging as a promising solution. A CGRA can be reconfigured for specific computational tasks, optimizing data flow through a configurable pipeline of compute elements. This architecture addresses the shortcomings of GPUs, particularly when it comes to dealing with branch divergence.
Speedata has harnessed the power of CGRA to develop Callisto, a new processor specifically designed to achieve maximum efficiency for data analytics. It leverages the advanced features of CGRA to handle complex queries with minimal idle time, offering performance advantage over GPUs in industry benchmarks like TPC-DS.
