In this paper, we introduce a new model for the representation of distributed asynchronous implementations of synchronous specifications. The model covers classical implementations, where a notion of global synchronization is preserved by means of signaling, and globally asynchronous, locally synchronous (GALS) implementations where the global clock is removed. The new model offers a unified framework for reasoning about two essential correctness properties of an implementation: the preservation of semantics and the absence of deadlocks. We use it to derive criteria ensuring the correct deployment of synchronous specifications over GALS architectures. As the model captures the internal concurrency of the synchronous specification, our criteria support implementations that are less constrained and more efficient than existing ones. Our work also reveals strong ties between abstract semantics-preservation properties and more operational ones like the absence of deadlocks.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
W artykule przedstawiono projekt układu trygera mionowego RPC dla eksperymentu CMS na akceleratorze LHC w Genewie. W artykule opisano całość systemu a także jego elementy: elektronikę detektora, system transmisji danych z detektora do pomieszczeń sterowania (z systemem kompresji danych, pozwalającym na znaczną redukcję ilości łączy optycznych), algorytm trygera i jego implementacje z użyciem procesora PAC (ASIC). Przedstawiono sposoby synchronizowania danych oraz związanej z tym diagnostyki.
EN
In this article RPC muon trigger for CMS experiment on LHC collider is presented. The overall structure of the RPC muon trigger system is presented. More details are given for trigger algorithm built with usage of Patten Comparator (PAC) ASIC. Front End electronics is shortly discussed. Optical data link system using compression/decompression scheme allowing large number of links reduction is demonstrated. Synchronization and diagnostics tasks are discussed.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In this paper we study the problem of scheduling hard real-time periodic task sets with a dynamic and preemptive scheduler. We will focus on the response time notion, its interest and its effective computation for the deadline driven scheduler. We present a general calculation procedure for determining the response time of the kth request of a task in asynchronous systems with general as well as arbitrary deadlines. Finally, we analyze the performance of the computation so defined, both in terms of time and memory requirements.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.