An argument for a runtime layer SPARTA design

Researchers have used advances in hardware technology to design larger and more complex real-time applications. Larger applications require new integration techniques while more complex applications require a restructuring of the underlying system support. We examine the system design issues of supporting SPARTAs (Soft Parallel Real-Time Applications). There exists a gap between hard real-time kernel mechanisms and the functionality desired by a SPARTA programmer. Thus, an integral part of supporting SPARTA design will be providing an intermediate runtime layer. We describe our experiences building Ephor, including what motivated its conception and development, and the resulting separation of responsibilities both easing SPARTA design and improving their performance.<>