Pervasive DataRush Parallel Dataflow Engine  

At the heart of every Pervasive DataRush-enabled application is the Pervasive DataRush Parallel Dataflow Engine. This embedded engine transforms the way your application handles large volumes of data. Developers can now build data-intensive parallel applications without specialized knowledge in parallel programming.  Deliver an order of magnitude improvement in performance by leveraging the Pervasive DataRush Parallel Dataflow Engine.  

 

Capabilities

  • Parallel Processing on Multicore and SMP Systems

    The Pervasive DataRush engine is designed to take full advantage of the disruptive shift to multicore processors enabling performance on a single server that you thought was only possible on a large cluster. Developers no longer need specialized knowledge in threading, concurrent memory access, deadlock detection or any other complex aspect of parallel programming.

  • Scalable to Big Data

    Designed to handle gigabytes to petabytes of data, the Pervasive DataRush engine scales with both the size and the dimensionality of the data. The intelligence of the engine relieves developers from worrying about the complexities of data workload partitioning/buffering.

  • Extensible

    All software projects are unique. The developer is under complete control over how their data will be processed by the Pervasive DataRush engine. Pervasive provides a Pervasive DataRush Java SDK as well as Pervasive DataRush Core Libraries to give the developer the tools they need to fully leverage the Pervasive DataRush engine.

  • Embeddable

    Pervasive Software has literally thousands of customers that have embedded our software to efficiently solve complex problems. Embedded in your application, the Pervasive DataRush engine leverages the Java JVM to provide compatibility with most operating systems and processors.

The Multicore Software Crisis

Chip vendors such as AMD, IBM, Intel and Sun Microsystems have transformed the server landscape with their introductions of 2, 4, and 8-core processors. This means that commodity SMP servers with 32 and 48 cores are now available and core counts will continue to rise.  The hardware is now delivering unprecedented performance, but that hasn’t always translated into faster software. When previous generations of processors simply increased the clock speed to deliver greater performance, software just went faster without changing the application. Unfortunately software is typically not designed to take advantage of these multicore processors and is therefore under-delivering on performance.

Software organizations are now faced with the daunting task of “parallelizing” their applications. These projects are large, complex, error-prone, and require a set of unique and highly valued skills.

Fortunately, leveraging Pervasive DataRush allows an organization’s current development team to quickly make their data-intensive applications multicore-aware and leverage the elusive performance of multicore processors. 

Next Steps