ITC/USA 2015 Conference Proceedings / The Fifty-First Annual International Telemetering Conference and Technical Exhibition / October 26-29, 2015 / Bally's Hotel & Convention Center, Las Vegas, NV / The aeronautical industries have been suffering financial cutbacks and the market has to face new challenges associated with new companies. Telemetry community has been facing the increase of the electromagnetic spectrum usage for a variety of applications (e.g. 4G), after all telemetry is everywhere. In view of these issues and focused on the inherent requirements of the Flight Test application, the IPEV R&D group proposes the iPCM Telemetry architecture as solution for the existing reliability and bandwidth issues associated with the telemetry link. In this article, as a proof-of-concept of the iPCM architecture, it has been performed an experimental assembly. The results demonstrate the iPCM's ability to regenerate corrupted data providing the required data integrity and reliability, besides the capability to dynamically select the FTI transmitted parameter list to optimize the bandwidth link.

Afin de faire face à la demande croissante de mémoires de plus en plus performantes dans les systèmes informatiques, de nouvelles technologies se sont développées. Parmi elles, les mémoires résistives à changement de phase (ou PCM pour Phase-Change Memory) ont des propriétés et une maturité suffisante pour développer les nouvelles mémoires SCM (pour Storage Class Memory) comme en témoigne la récente commercialisation des produits Optane par la firme INTEL®. Néanmoins, la consommation énergétique des PCM lors de leur programmation reste élevée, ce qui limite leurs performances. L’intégration de super-réseaux (GeTe)2/(Sb2Te3)m dans des mémoires dites iPCM (pour interfacial Phase-Change Memory) est une des voies les plus prometteuse pour permettre une diminution significative des courants de programmation. Cependant, le mécanisme de transition des iPCM et la structure du matériau dans ses deux états de résistances sont encore méconnus. Dans ce contexte, l’objectif de cette thèse est d’élaborer des super-réseaux (GeTe)2/(Sb2Te3)m (m=1,2,4 et 8) cristallins, de déterminer leur structure puis de les intégrer dans des dispositifs mémoires. La pulvérisation cathodique alternée des matériaux GeTe et Sb2Te3 dans un équipement industriel de dépôt est utilisée pour effectuer l’épitaxie van der Waals de ces super-réseaux. Une optimisation du procédé par l’ajout d’une cible de Te en co-pulvérisation avec la cible de Sb2Te3 montre l’obtention de super-réseaux stœchiométriques présentant la périodicité souhaitée, ainsi qu’une orientation des plans cristallins (0 0 l) parallèle à la surface du substrat. Une description de l’ordre atomique local des super-réseaux ainsi optimisés est ensuite menée par l’étude d’images HAADF-STEM couplée à des simulations. Celle-ci révèle un phénomène d’inter-diffusion entre les couches de GeTe et de Sb2Te3 déposées aboutissant à la formation locale de GexSbyTez rhomboédriques, des mesures quantitatives de l’occupation des plans atomiques en Ge/Sb confirment aussi le phénomène. De plus, un modèle de structure à longue distance de ces super-réseaux considérant un empilement aléatoire de blocs cristallins permet la simulation des courbes de diffraction obtenues expérimentalement. Enfin, les premières intégrations des super-réseaux (GeTe)2/(Sb2Te3)m dans des dispositifs mémoires mettent en évidence une réduction importante des courants de programmation jusqu’à 4 fois inférieurs à une PCM et avec une endurance dépassant les 10 millions cycles. / In order to satisfy the demand for more and more efficient memory in computer systems, new technologies have been developed. Among the latter resistive phase-change memories (PCM) exhibit capacities and sufficient maturity to achieve the so-called new SCM (for Storage Class Memory) devices as evidenced by the recent commercialization of Optane products by INTEL®. Nevertheless, PCM still require strong electrical consumption limiting their performance. Integration of (GeTe)2/(Sb2Te3)m superlattices in so-called iPCM (for interfacial Phase Change Memory) was shown to permit a significant decrease in programming currents. However, the switching mechanism of this memory and the structure of the material in its two resistance states are still under debate. The aim of this thesis is therefore to deposit crystalline (GeTe)2/(Sb2Te3)m (m=1,2,4 et 8) superlattices, to determine their structure and to integrate them into memory devices. GeTe and Sb2Te3 materials are alternately deposited by means of sputtering in an industrial deposition tool to perform van der Waals epitaxy of these superlattices. Stoichiometric superlattices with the desired periodicity and with an orientation of the (0 0 l) crystalline planes parallel to the surface of the substrate are obtained by innovative co-sputtering of Sb2Te3 and Te targets during Sb2Te3 deposition. A description of the local atomic order of superlattices is then carried out by studying HAADF-STEM images coupled to simulations. Intermixing between GeTe and Sb2Te3 deposited layers is thus revealed, leading to the local formation of rhombohedral GexSbyTez. Quantitative measurements of the Ge/Sb atomic plans occupation in further confirm the phenomenon. A long-range order structural model of superlattices by means of random stacking of crystalline blocks allows the simulation of experimental diffraction curves. Finally, the first integrations of (GeTe)2/(Sb2Te3)m (with m=1,2,4 et 8) superlattices in devices demonstrate a programming current up to 4 times lower than a PCM reference with an endurance exceeding 10 millions cycles.

The future of computing lies with distributed systems, i.e. a network of workstations controlled by a modern distributed operating system. By supporting load balancing and parallel execution, the overall performance of a distributed system can be improved dramatically. Process migration, the act of moving a running process from a highly loaded machine to a lightly loaded machine, could be used to support load balancing, parallel execution, reliability etc. This thesis identifies the problems past process migration facilities have had and determines the possible differing strategies that can be used to resolve these problems. The result of this analysis has led to a new design philosophy. This philosophy requires the design of a process migration facility and the design of an operating system to be conducted in parallel. Modern distributed operating systems follow the microkernel and client/server paradigms. Applying these design paradigms, in conjunction with the requirements of both process migration and a distributed operating system, results in a system where each resource is controlled by a separate server process. However, a process is a complex resource composed of simple resources such as data structures, an address space and communication state. For this reason, a process migration facility does not directly migrate the resources of a process. Instead, it requests the appropriate servers to transfer the resources. This novel solution yields a modular, high performance facility that is easy to create, debug and maintain. Furthermore, the design easily incorporates providing multiple migration strategies. In order to verify the validity of this design, a process migration facility was developed and tested within RHODOS (ResearcH Oriented Distributed Operating System). RHODOS is a modern microkernel and client/server based distributed operating system. In RHODOS, a process is composed of at least three separate resources: process state - maintained by a process manager, address space - maintained by a memory manager and communication state - maintained by an InterProcess Communication Manager (IPCM). The RHODOS multiple strategy migration manager utilises the services of the process, memory and IPC Managers to migrate the resources of a process. Performance testing of this facility indicates that this design is as fast or better than existing systems which use faster hardware. Furthermore, by studying the results of the performance test ing, the conditions under which a particular strategy should be employed have been identified. This thesis also addresses heterogeneous process migration. The current trend is to have islands of homogeneous workstations amid a sea of heterogeneity. From this situation and the current literature on the topic, heterogeneous process migration can be seen as too inefficient for general use. Instead, only homogeneous workstations should be used for process migration. This implies a need to locate homogeneous workstations. Entities called traders, which store and disseminate knowledge about the resources of several workstations, should be used to provide resource discovery. Resource discovery will enable the detection of homogeneous workstations to which processes can be migrated.