In the last few years, probabilistic timing analysis (PTA) in general, and its
measurement-based variant (MBPTA) in particular, have emerged as a breakthrough timing
analysis technique approach. Owing to its observation-based nature, MBPTA requires less
information on the detailed internal behaviour of the hardware and the software of the target
system, which is the crux of classic worst-case execution time (WCET) analysis methods. PTA has
become an acknowledged area of scientific interest, with an increasing number of active researchers
and a rising score of significant publications.
This tutorial introduces attendees to Measurement-Based Probabilistic Timing Analysis (MBPTA)
with emphasis on what it takes from the end user and what it requires from the underlying hardware
and software platform. Through didactic material and several running examples, participants will be
exposed to the whole range of MBPTA concepts and procedures. The tutorial also presents the
current advances of MBPTA and the main challenges it has to address to be fully ready for
industrial use.
