Data Parallel Computations

The Star-P data-parallel libraries are high-performance optimized libraries that can be called by the client application to perform compute-intensive operations on large distributed data sets.

Star-P's parallel data I/O capabilities take advantage of native I/O hardware yielding dramatic savings when moving datasets from disk to memory.

Some libraries are proprietary to Interactive Supercomputing; others are built on top of publicly available libraries, with key enhancements in terms of correctness, accuracy, and speed. Together, the libraries represent hundreds of individual computing functions in key computational domains including linear algebra, signal processing, and others.