Laxity dynamics and LLF schedulability analysis on multiprocessor platforms

LLF (Least Laxity First) scheduling, which assigns a higher priority to a task with a smaller laxity, has been known as an optimal preemptive scheduling algorithm on a single processor platform. However, little work has been made to illuminate its characteristics upon multiprocessor platforms. In this paper, we identify the dynamics of laxity from the system’s viewpoint and translate the dynamics into LLF multiprocessor schedulability analysis. More specifically, we first characterize laxity properties under LLF scheduling, focusing on laxity dynamics associated with a deadline miss. These laxity dynamics describe a lower bound, which leads to the deadline miss, on the number of tasks of certain laxity values at certain time instants. This lower bound is significant because it represents invariants for highly dynamic system parameters (laxity values). Since the laxity of a task is dependent of the amount of interference of higher-priority tasks, we can then derive a set of conditions to check whether a given task system can go into the laxity dynamics towards a deadline miss. This way, to the author’s best knowledge, we propose the first LLF multiprocessor schedulability test based on its own laxity properties. We also develop an improved schedulability test that exploits slack values. We mathematically prove that the proposed LLF tests dominate the state-of-the-art EDZL tests. We also present simulation results to evaluate schedulability performance of both the original and improved LLF tests in a quantitative manner.

Constraint reasoning for differential models

The basic motivation of this work was the integration of biophysical models within the interval constraints framework for decision support. Comparing the major features of biophysical models with the expressive power of the existing interval constraints framework, it was clear that the most important inadequacy was related with the representation of differential equations. System dynamics is often modelled through differential equations but there was no way of expressing a differential equation as a constraint and integrate it within the constraints framework. Consequently, the goal of this work is focussed on the integration of ordinary differential equations within the interval constraints framework, which for this purpose is extended with the new formalism of Constraint Satisfaction Differential Problems. Such framework allows the specification of ordinary differential equations, together with related information, by means of constraints, and provides efficient propagation techniques for pruning the domains of their variables. This enabled the integration of all such information in a single constraint whose variables may subsequently be used in other constraints of the model. The specific method used for pruning its variable domains can then be combined with the pruning methods associated with the other constraints in an overall propagation algorithm for reducing the bounds of all model variables. The application of the constraint propagation algorithm for pruning the variable domains, that is, the enforcement of local-consistency, turned out to be insufficient to support decision in practical problems that include differential equations. The domain pruning achieved is not, in general, sufficient to allow safe decisions and the main reason derives from the non-linearity of the differential equations. Consequently, a complementary goal of this work proposes a new strong consistency criterion, Global Hull-consistency, particularly suited to decision support with differential models, by presenting an adequate trade-of between domain pruning and computational effort. Several alternative algorithms are proposed for enforcing Global Hull-consistency and, due to their complexity, an effort was made to provide implementations able to supply any-time pruning results. Since the consistency criterion is dependent on the existence of canonical solutions, it is proposed a local search approach that can be integrated with constraint propagation in continuous domains and, in particular, with the enforcing algorithms for anticipating the finding of canonical solutions. The last goal of this work is the validation of the approach as an important contribution for the integration of biophysical models within decision support. Consequently, a prototype application that integrated all the proposed extensions to the interval constraints framework is developed and used for solving problems in different biophysical domains.

Tomographic imaging with a scanning laser ophtalmoscop

Retinal imaging with a confocal scaning laser Ophthalmoscope (cSLO) involves scanning a small laser beam over the retina and constructing an image from the reflected light. By applying the confocal principle, tomographic images can be produced by measuring a sequence of slices at different depths. However, the thickness of such slices, when compared with the retinal thickness, is too large to give useful 3D retinal images, if no processing is done. In this work, a prototype cSLO was modified in terms hardware and software to give the ability of doing the tomographic measurements with the maximum theoretical axial resolution possible. A model eye was built to test the performance of the system. A novel algorithm has been developed which fits a double Gaussian curve to the axial intensity profiles generated from a stack of images slices. The underlying assumption is that the laser light has mainly been reflected by two structures in the retina, the internal limiting membrane and the retinal pigment epithelium. From the fitted curve topographic images and novel thickness images of the retina can be generated. Deconvolution algorithms have also been developed to improve the axial resolution of the system, using a theoretically predicted cSLO point spread function. The technique was evaluated using measurements made on a model eye, four normal eyes and seven eyes containing retinal pathology. The reproducibility, accuracy and physiological measurements obtained, were compared with available published data, and showed good agreement. The difference in the measurements when using a double rather than a single Gaussian model was also analysed.

Supporting real-time parallel task models with work-stealing

Dynamic parallel scheduling using work-stealing has gained popularity in academia and industry for its good performance, ease of implementation and theoretical bounds on space and time. Cores treat their own double-ended queues (deques) as a stack, pushing and popping threads from the bottom, but treat the deque of another randomly selected busy core as a queue, stealing threads only from the top, whenever they are idle. However, this standard approach cannot be directly applied to real-time systems, where the importance of parallelising tasks is increasing due to the limitations of multiprocessor scheduling theory regarding parallelism. Using one deque per core is obviously a source of priority inversion since high priority tasks may eventually be enqueued after lower priority tasks, possibly leading to deadline misses as in this case the lower priority tasks are the candidates when a stealing operation occurs. Our proposal is to replace the single non-priority deque of work-stealing with ordered per-processor priority deques of ready threads. The scheduling algorithm starts with a single deque per-core, but unlike traditional work-stealing, the total number of deques in the system may now exceed the number of processors. Instead of stealing randomly, cores steal from the highest priority deque.

Makespan computation for GPU threads running on a single streaming multiprocessor

Graphics processors were originally developed for rendering graphics but have recently evolved towards being an architecture for general-purpose computations. They are also expected to become important parts of embedded systems hardware -- not just for graphics. However, this necessitates the development of appropriate timing analysis techniques which would be required because techniques developed for CPU scheduling are not applicable. The reason is that we are not interested in how long it takes for any given GPU thread to complete, but rather how long it takes for all of them to complete. We therefore develop a simple method for finding an upper bound on the makespan of a group of GPU threads executing the same program and competing for the resources of a single streaming multiprocessor (whose architecture is based on NVIDIA Fermi, with some simplifying assunptions). We then build upon this method to formulate the derivation of the exact worst-case makespan (and corresponding schedule) as an optimization problem. Addressing the issue of tractability, we also present a technique for efficiently computing a safe estimate of the worstcase makespan with minimal pessimism, which may be used when finding an exact value would take too long.

Scalable data acquisition for densely instrumented cyber-physical systems

Consider the problem of designing an algorithm for acquiring sensor readings. Consider specifically the problem of obtaining an approximate representation of sensor readings where (i) sensor readings originate from different sensor nodes, (ii) the number of sensor nodes is very large, (iii) all sensor nodes are deployed in a small area (dense network) and (iv) all sensor nodes communicate over a communication medium where at most one node can transmit at a time (a single broadcast domain). We present an efficient algorithm for this problem, and our novel algorithm has two desired properties: (i) it obtains an interpolation based on all sensor readings and (ii) it is scalable, that is, its time-complexity is independent of the number of sensor nodes. Achieving these two properties is possible thanks to the close interlinking of the information processing algorithm, the communication system and a model of the physical world.

Quantifying the channel quality for interference-aware wireless sensor networks

Reliability of communications is key to expand application domains for sensor networks. SinceWireless Sensor Networks (WSN) operate in the license-free Industrial Scientific and Medical (ISM) bands and hence share the spectrum with other wireless technologies, addressing interference is an important challenge. In order to minimize its effect, nodes can dynamically adapt radio resources provided information about current spectrum usage is available. We present a new channel quality metric, based on availability of the channel over time, which meaningfully quantifies spectrum usage. We discuss the optimum scanning time for capturing the channel condition while maintaining energy-efficiency. Using data collected from a number of Wi-Fi networks operating in a library building, we show that our metric has strong correlation with the Packet Reception Rate (PRR). This suggests that quantifying interference in the channel can help in adapting resources for better reliability. We present a discussion of the usage of our metric for various resource allocation and adaptation strategies.

Estudo Estratigráfico e Paleontológico do Jurássico do Algarve Ocidental

Algarve Province, Southern Portugal, corresponds in part to a meso-cenozoic basin running along the coast from Cabo S. Vicente to beyond Spanish border. Structurally it is a big monocline plunging southwards much deformed mainly by two East-West longitudinal flexures. Lithostratigraphical and chronostratigraphical studies dealt specially with Jurassic formations. This and the geological mapping of the post-Hercynian sedimentary formations allow us to define the following units: Triassic-Lower Liassic Arenitos de Silves (Silves sandstones sensu P. Choffat, pro parte) - At their base the Silves sandstones (0-150m) are represented mainly by cross-bedded red sandstones. This unit is Upper Triassic (Keuper) in age, on the evidence of some Brachiopoda. Complexo margo-carbonatado de Silves (Silves marl-limestone complex=Silves sandstones sensu P. Choffat, pro parte) (80-200m) overlies the preceding, it may be reported to the Upper Triassic-Hettangian. It consists of a thick pelite-marl-dolomite-limestone series with many intercalations of greenstones. Since no fossils were found it is not possible to conclude whether it is still Hettangian or if it does correspond, in the whole or in part, already to the Sinemurian. Liassic Dolomitos e calcários dolomíticos de Espiche (Espiche dolomite-rocks and dolomitic-limestones) - The usually massive and finely crystalline or saccharoidal dolomites and dolomitic-limestones are the toughest strata of the Algarve margin giving rise to several hills. Its thickness attains in certain points 60 metres at least. Based on geometry and on lithological similarities with the carbonated complex of the northern basin of Tagus river (Peniche, São Pedro de Muel, Quiaios), this formation can be accepted as Sinemurian in age. As it happens with the carbonated complex, here also the first dolomite beds are non-isochronal throughout the region; upper time-limit of the dolomitic facies is either Lower Carixian, Lower Toarcian or even Lower Dogger. The dolomitization is secondary but not much later than sedimentation. However, between Cabo S. Vicente-Vila do Bispo there is evidence of an even later secondary dolomitization related to the regional fault complex. Calcário dolomítico com nódulos de silex da praia de Belixe (Belixe beach dolomitic-limestone with silex nodules) (50-55m) - Ascribed to Lower or Middle Carixian on the basis of Platypleuroceras sp., Metaderoceras sp. nov. and M. gr. Venarense. Calcário cristalino compacto com Protogrammoceras, Fuciniceras e ? Argutarpites de Belixe (Belixe compact crystalline limestone with Protogrammoceras, Fuciniceras and ? Argutarpites) (30m) - Ascribed to Lower Domerian. Middle and Upper Domerian are indicated but by a single specimen of ? Argutarpites. Calcários margosos e margas com Dactylioceras semicelatum e Harpoceratídeos de Armação Nova (Armação Nova marly limestones and marls with D. semicelatum and Harpoceratidae) (25m) -Ascribed to Lower Toarcian. Middle and Upper Toarcian formations are not known in the Algarve. Dogger Calcários oolíticos, c. corálicos, c. pisolíticos, c. calciclásticos, c. dolomíticos e dolomitos de Almadena (Almadena oolitic-limestones, coral-reef-limestones, pisolite-limestones, limeclastic-limestones, dolomitic-limestones and dolomite-rocks) (more than 50 metres), with lagoonal facies. Ascribed to Aalenian-Bathonian-? Callovian. Margas acinzentadas e calcários detríticos com Zoophycos da praia de Mareta (Mareta beach greyish marls and detritical limestones with Zoophycos) (40m) - Pelagic transreef facies with Upper Bajocian and Bathonian ammonites. Calcários margosos e margas da praia de Mareta (Mareta beach pelagic marly-limestones and marls) (110m) - Ascribed to the Callovian on its ammonites. Malm Near Cabo S. Vicente and Sagres the first Upper Jurassic level consists of a yellowish-brown nodular, compact, locally phosphated and ferruginous, sometimes conglomeratic, marly limestone (0,35-1,50m) containing a rich macrofauna, which includes: 1) Callovian forms unknown at Lower Oxfordian; 2) Upper Callovian forms that still survived in Lower and Middle Oxfordian; 3) Lower Oxfordian forms (Mariae and Cordatum Zones); 4) Lower and Middle Oxfordian forms (Mariae to Plicatilis Zone); 5) Middle Oxfordian forms (plicatilis Zone), and some ones appearing in Middle Oxfordian. This condensed deposit is therefore dated from Middle Oxfordian (Plicatilis Zone). The other Upper Jurassic lithostratigraphical units were also mapped but their detailed study is not presented in this work. Correlations between lithostratigraphical and chronostratigraphical scales from P. Choffat, J. Pratsch, C. Palain and from the author are stated. Further correlations are attempted between zonc scales of Carixian-Lower Toarcian and Upper Bajocian-Middle Oxfordian of France, Spain (Asturias, Iberian and Betic Chains), Argel (Orania) and Portugal (northern Tagus basin and Algarve). The study of pyritous fossil assemblages common in Upper Bathonian-Lower Callovian marly levels of the praia da Mareta seems to suggest that these sediments were deposited in a bay or in an almost closed coastal re-entrance virtually without deep water circulation. Although such conditions may occur at any depth one may suppose that these ones actually correspond to an infralittoral neritic environment. The thaphocoenosis collected there are almost entirely composed of nektonic (ammonites, Belemnites) and planktonic (Bositra) faunas. The sedentary (crinoids, brachiopods) or free (sea-urchins, gastropods) epibenthonic forms are very scarce; endobenthonic forms are not known. The palaeontological study of all Nautiloids and Ammonoids of the Liassic and Dogger is presented (except Kosmoceratidae and Perisphinctaceae). Among the thirty one taxa dealt with, one is new (Metaderoceras sp. nov.) and the great majority of the others has been identified for the first time in Algarve. Some others have never been reported before in Portuguese formations. The evolution, during Jurassic times, of the sedimentary basins of the Portuguese plate margin is described. The absence of Cephalopods in the very extensive marly and dolomitic limestones, partly marine, suggests that, during Lower Liassic, palaeogeography underwent no great changes. Dolomitic-limestone with silex nodules from Cabo S. Vicente contain the first ammonites recorded at the base of the Middle Liassic. This facies, although very common in Tethys, is unknown north of the Tagus. The faunal assemblage has a mediterranean to submediterranean character. Comparisons between faunal assemblage" from Algarve with the ones known north of the Tagus show that communications between Boreal Europe and Tethys, virtually non-existent during Lower and Middle Carixian, became very easy during Lower Domerian. In earlier Pliensbachian times two distinct seas were adjacent to the Iberian plate. One, an epicontinental sea with a tethyan fauna, extended southwards from the Meseta margin. Another, was a boreal sea; during its transgressive episodes boreal faunas attained into the basin north of the Tagus. During Middle Carixian and Lower Domerian, owing to simultaneous transgressions, these two seas joined together allowing faunal exchanges along the epicontinental areas which limited the emerging hercynian chains belts. During Liassic, the Algarve belonged undoubtedly to the tethyan submediterranean province. The area north of the Tagus, on the contrary, was a complex realm where subboreal and tethyan affinities alternatively prevailed. In the Algarve the first Middle Jurassic deposits do frequently show lateral thickness reductions as well as unconformities contemporaneous with other generalized disturbances on the sedimentation processes in other parts of Europe. By this time, near Sagres, a barrier reef developed separating lagoonal or ante-reef facies from the transreef pelagic zone. The presence of tethyan fauna, the abundance of Phylloceratidae and the absence of boreal forms allow us to consider the Algarve basin as a submediterranean province. The presence of Callovian pelagic fossiliferous formations in the Loulé area shows that during Middle Jurassic the marl-limestone transreef sedimentation was not confined to the western Algarve. They would extend eastwards where they only can be seen in the core of some anticlines. This is due to the progressive sinking of the meso-cenozoic formations as we proceed towards the South of the Sagres-Algoz-Querença flexure. In the whole of the Peninsule, and as for the Middle Callovian, an important regression can be clearly recognized on the evidence of an erosion surface which strikes obliquely the Middle and Upper Callovian strata. The geographic boundaries of the different faunal provinces are not changed by the presence of many Kosmoceratidae in the phosphate nodules since they are but a minority in comparison with the tethyan forms. An abstract model can be constructed showing that in Western Europe the Kosmoceratidae may have migrated South and westwards through a channel of the sea that linked Paris basin to Poitou and Aquitaine. By migrating between the Iberian meseta and the Armorican massif this fauna reached northern Tagus basin at the beginning of Upper Callovian (Athleta Zone); this south and southwest bound migration would have proceeded, allowing such forms to reach Algarve basin only in latest Callovian times (Lamberti Zone). This migration means that during Middle Jurassic a widely spread North Atlantic sea would exist, flooding the western part of Portugal up to the Poitou.

Notas sobre depósitos de Taveiro estratigrafia, paleontologia, idade, paleoecologia

This paper reports some research work that has been done to support Geological Survey's field work for the 1:50.000 Carta Geológica de Portugal, (sheets 19-C Figueira da Foz and 19-D Coimbra-Lousã). Its main purpose was to establish the age of some continental formations. At Cerâmica do Mondego, Ld.ª near Taveiro, two series were observed. The lower one is mainly pelitic, montmorillonite being predominant. It also includes some sandy beds and channel deposits with high energy sediments (conglomerate with limestone pebbles). The upper series lies unconformably upon the former, and there is a neat discontinuity surface between the two. It mainly consists of sands, kaolinite being the most abundant of the clay minerals. This seems to indicate an intensive weathering, an acid, well drained environment and transportation by quite high energy running waters. No fossils were recorded. Preliminary paleontological results are presented, along with some data concerning other localities (Aveiro, etc.). Fossils found in the lower series are: gastropoda (Bulimus gaudryi, TV. 15 bed), several vertebrates (TV. 18), fishes (TV. 19?) and plants (TV. 19-TV. 24). Vertebrata belong to the same fauna as that from Vizo, Aveiro, etc. The presence of mammals is most important as only a single tooth was previously Know in Europe (Southern France) in Late Cretaceous formations. Elsewhere there are some mammalian remains in Peru besides the rich assemblages found in the USA and Mongolia. Plants are representative of the «Debeya flora» well known at several localities in Beira Litoral province, in «Buçaco sandstones», and in Lisbon's «Basaltic Complex». The most important stratigraphical conclusion is that the lower series is Upper Campanian and/or Maastrichtian in age, and not Tertiary as sometimes it has been considered. As at Aveiro, «Bebeya flora» occurs in-beds somewhat higher than those with the Aveiro-Vizo-Taveiro vertebrate fauna. Correlation with other «Debeya flora» localities are now more clear. Data concerning Taveiro lower series, in the whole, point out to a rather warm (and moist?) environment in an occasionally (seasonally?) flooded region.

Notas sobre depósitos de Taveiro estratigrafia, paleontologia, idade, paleoecologia

This paper reports some research work that has been done to support Geological Survey's field work for the 1:50.000 Carta Geológica de Portugal, (sheets 19-C Figueira da Foz and 19-D Coimbra-Lousã). Its main purpose was to establish the age of some continental formations. At Cerâmica do Mondego, Lda. near Taveiro, two series were observed. The lower one is mainly pelitic, montmorillonite being predominant. It also includes some sandy beds and channel deposits with high energy sediments (conglomerate with limestone pebbles). The upper series lies unconformably upon the former, and there is a neat discontinuity surface between the two. It mainly consists of sands, kaolinite being the most abundant of the clay minerals. This seems to indicate an intensive weathering, an acid, well drained environment and transportation by quite high energy running waters. No fossils were recorded. Preliminary paleontological results are presented, along with some data concerning other localities (Aveiro, etc). Fossils found in the lower series are: gastropoda (Bulimus gaudryi, TV. 15 bed), several vertebrates (TV. 18), fishes (TV. 19?) and plants (TV. 19-TV. 24). Vertebrata belong to the same fauna as that from Vizo, Aveiro, etc. The presence of mammals is most important as only a single tooth was previously know in Europe (Southern France) in Late Cretaceous formations. Elsewhere there are some mammalian remains in Peru besides the rich assemblages found in the USA and Mongolia. Plants are representative of the «Debeya flora» well known at several localities in Beira Litoral province, in «Buçaco sandstones», and in Lisbon's «Basaltic Complex». The most important stratigraphical conclusion is that the lower series is Upper Campanian and/or Maastrichtian in age, and not Tertiary as sometimes it has been considered. As at Aveiro, «Bebeya flora» occurs in-beds somewhat higher than those with the Aveiro-Vizo-Taveiro vertebrate fauna. Correlation with other «Debeya flora» localities are now more clear. Data concerning Taveiro lower series, in the whole, point out to a rather warm (and moist?) environment in an occasionally (seasonally?) flooded region.

An Explicit GTS allocation algorithm for IEEE 802.15.4

The IEEE 802.15.4 standard provides appealing features to simultaneously support real-time and non realtime traffic, but it is only capable of supporting real-time communications from at most seven devices. Additionally, it cannot guarantee delay bounds lower than the superframe duration. Motivated by this problem, in this paper we propose an Explicit Guaranteed time slot Sharing and Allocation scheme (EGSA) for beacon-enabled IEEE 802.15.4 networks. This scheme is capable of providing tighter delay bounds for real-time communications by splitting the Contention Free access Period (CFP) into smaller mini time slots and by means of a new guaranteed bandwidth allocation scheme for a set of devices with periodic messages. At the same the novel bandwidth allocation scheme can maximize the duration of the CFP for non real-time communications. Performance analysis results show that the EGSA scheme works efficiently and outperforms competitor schemes both in terms of guaranteed delay and bandwidth utilization.

A multi-objective approach for the motion planning of redundant manipulators

Kinematic redundancy occurs when a manipulator possesses more degrees of freedom than those required to execute a given task. Several kinematic techniques for redundant manipulators control the gripper through the pseudo-inverse of the Jacobian, but lead to a kind of chaotic inner motion with unpredictable arm configurations. Such algorithms are not easy to adapt to optimization schemes and, moreover, often there are multiple optimization objectives that can conflict between them. Unlike single optimization, where one attempts to find the best solution, in multi-objective optimization there is no single solution that is optimum with respect to all indices. Therefore, trajectory planning of redundant robots remains an important area of research and more efficient optimization algorithms are needed. This paper presents a new technique to solve the inverse kinematics of redundant manipulators, using a multi-objective genetic algorithm. This scheme combines the closed-loop pseudo-inverse method with a multi-objective genetic algorithm to control the joint positions. Simulations for manipulators with three or four rotational joints, considering the optimization of two objectives in a workspace without and with obstacles are developed. The results reveal that it is possible to choose several solutions from the Pareto optimal front according to the importance of each individual objective.

A 12*(1+|R|/(4m))-speed algorithm for scheduling constrained-deadline sporadic real-time tasks on a multiprocessor comprising m processors where a task may request one of |R| sequentially-reusable shared resources

We present a 12*(1+|R|/(4m))-speed algorithm for scheduling constrained-deadline sporadic real-time tasks on a multiprocessor comprising m processors where a task may request one of |R| sequentially-reusable shared resources.

Improving the reliability of WiDom in a single broadcast domain

WiDom is a previously proposed prioritized medium access control protocol for wireless channels. We present a modification to this protocol in order to improve its reliability. This modification has similarities with cooperative relaying schemes, but, in our protocol, all nodes can relay a carrier wave. The preliminary evaluation shows that, under transmission errors, a significant reduction on the number of failed tournaments can be achieved.

A distributed algorithm for hexagonal topology formation in wireless sensor networks

Hexagonal wireless sensor network refers to a network topology where a subset of nodes have six peer neighbors. These nodes form a backbone for multi-hop communications. In a previous work, we proposed the use of hexagonal topology in wireless sensor networks and discussed its properties in relation to real-time (bounded latency) multi-hop communications in large-scale deployments. In that work, we did not consider the problem of hexagonal topology formation in practice - which is the subject of this research. In this paper, we present a decentralized algorithm that forms the hexagonal topology backbone in an arbitrary but sufficiently dense network deployment. We implemented a prototype of our algorithm in NesC for TinyOS based platforms. We present data from field tests of our implementation, collected using a deployment of fifty wireless sensor nodes.