Advanced multi-functional computing systems realized in forthcoming manufacturing technologies hold the promise of a significant increase in device integration density complemented by an increase in system performance and functionality. However, a dramatic reduction in single device quality and reliability is also expected.CLERECO research project recognizes early accurate reliability evaluation as one of the most important and challenging tasks throughout the design cycle of computing systems across all domains. In order to continue harvesting the performance and functionality offerings of technology scaling, we need to dramatically improve current methodologies to evaluate the reliability of the system.On one hand, we need accurate methodologies that reduce the performance and energy tax paid to guarantee correct operation of systems. The rising energy costs needed to compensate for increasing unpredictability are rapidly becoming unacceptable in today's environment where energy consumption is often the limiting factor on integrated circuit performance. On the other hand, early "budgeting" for reliability has the potential to save significant design effort and resources and has a profound impact on the TTM of a product. CLERECO addresses early reliability evaluation with a cross-layer approach across different computing disciplines, across computing system layers and across computing market segments to address reliability for the emerging computing continuum. CLERECO methodology will consider low-level information such as raw failure rates as well as the entire set of hardware and software components of the system that eventually determine the reliability delivered to the end users.The CLERECO project methodology for early reliability evaluation will be comprehensively assessed and validated in advanced designs from different applications provided by the industrial partners for the full stack of hardware and software layers.
|Titolo:||CLERECO, Cross-Layer Early Reliability Evaluation for the Computing cOntinuum, FP7|
|Data di pubblicazione:||2017|
|Digital Object Identifier (DOI):||10.21820/23987073.2017.3.71|
|Appare nelle tipologie:||1.1 Articolo in rivista|