Hardware-Based Event Stream Ordering for System-Level Observation Framework
Jong Chul Lee, Jovan Vance, Roman Lysecky · IEEE Embedded Systems Letters · 2014
The complexity of embedded systems presents key challenges in observing and analyzing complex hardware and software behavior. System-level observation methods provide in-situ monitoring and analysis of complex system behavior across hardware and software boundaries. Previous system-level observation methods utilized efficient pipelined hardware architectures that provide high throughput for reporting observed events but require significant area resources. Alternatively, an area-efficient round-robin priority-based event stream ordering technique significantly reduces area resources but requires tradeoffs in event stream throughput. We present a hardware-based event stream ordering technique capable of providing high throughput and flexibility in area requirements. This hardware-based event stream ordering technique reduces area requirements by 73.6% with a maximum reduction in event stream throughput of 4.6%.