Memory-Centric Hardware Synthesis from Dataflow Models

Generation of hardware architectures directly from dataflow representations is increasingly being considered as research moves toward system level design methodologies. Creation of networks of IP cores to implement actor functionality is a common approach to the problem, but often the memory sub-systems produced using these techniques are inefficiently utilised. This paper explores some of the issues in terms of memory organisation and accesses when developing systems from these high level representations. Using a template matching design study, challenges such as modelling memory reuse and minimising buffer requirements are examined, yielding results with significantly less memory requirements and costly off-chip memory accesses.

SoC memory hierarchy derivation from dataflow graphs

Hardware synthesis from dataflow graphs of signal processing systems is a growing research area as focus shifts to high level design methodologies. For data intensive systems, dataflow based synthesis can lead to an inefficient usage of memory due to the restrictive nature of synchronous dataflow and its inability to easily model data reuse. This paper explores how dataflow graph changes can be used to drive both the on-chip and off-chip memory organisation and how these memory architectures can be mapped to a hardware implementation. By exploiting the data reuse inherent to many image processing algorithms and by creating memory hierarchies, off-chip memory bandwidth can be reduced by a factor of a thousand from the original dataflow graph level specification of a motion estimation algorithm, with a minimal increase in memory size. This analysis is verified using results gathered from implementation of the motion estimation algorithm on a Xilinx Virtex-4 FPGA, where the delay between the memories and processing elements drops from 14.2 ns down to 1.878 ns through the refinement of the memory architecture. Care must be taken when modeling these algorithms however, as inefficiencies in these models can be easily translated into overuse of hardware resources.

Architecture, memory and historical continuity in Old Cairo

The hawari (local communities) of Old Cairo resemble a unique societal context whose history is actively involved in the contemporary everyday production of local habits, traditions and social practice. By the virtue of its durability and ability to survive, Architecture brings events and traditions of the past alive into the present through the spatial transformation, social practice and the value of the historical-fabric. The presence of buildings and houses from different historical periods has helped the local community’s memory to carry social practices over from one generation to another. This article explores the relationship between architecture, memory and everyday social practices through determining the way architecture moderates community experiences and communicates narratives among generations in haret al-Darb al-Asfar in old Cairo. Architecture emerges as a moderator of cross-time communication and as physical elements that help visualize history, situate values and materialize local traditions in old Cairo. Architecture, as process and product this article reports, works as agent of continuity, which in conjunction with the narrators, brings the full experience of the past alive in the present and helps guide future generations.

Baudelaire, Daumier and the Art of Memory

This article reassesses the importance of the Baudelaire's criticism of the art of Daumier in relation to his theorization of memory. It argues that more than Guys, Daumier may represent for the poet the quintessential 'peintre de la vie moderne'.

An efficient feature selection method for mobile devices with application to activity recognition

This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modelled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited. An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.

Memory-keeping effects and forgetfulness in the dynamics of a qubit coupled to a spin chain

Using recently proposed measures for non-Markovianity [H.-P. Breuer, E. M. Laine, and J. Piilo, Phys. Rev. Lett. 103, 210401 (2009)], we study the dynamics of a qubit coupled to a spin environment via an energy-exchange mechanism. We show the existence of a point, in the parameter space of the system, where the qubit dynamics is effectively Markovian and that such a point separates two regions with completely different dynamical behaviors. Indeed, our study demonstrates that the qubit evolution can in principle be tuned from a perfectly forgetful one to a deep non-Markovian regime where the qubit is strongly affected by the dynamical backaction of the environmental spins. By means of a theoretical quantum process tomography analysis, we provide a complete and intuitive characterization of the qubit channel.

The Battle of the Somme in Ulster memory and identity

One of the enduring illusions about Northern Ireland is that its society can be conceptualized through a binary distinction between protestant and catholic. unionist and nationalist. It is increasingly apparent that these broad domains are themselves fractured and diverse and that otherness is often conceived from within rather than without. Northern Ireland can also be viewed as a laboratory for identity formation as unionists and loyalists strive to reconcile themselves with the fundamental political changes that have followed in the wake of the Peace Process. This paper considers one aspect of the contestation of belonging that increasingly characterizes unionism. It examines the competition for the ownership of the mythology of the Battle of the Somme ( 1916), long a key event in the unionist narrative. In particular, the paper addresses the ways in which paramilitary organizations are using the Somme to legitimate their own activities but also to distance the loyalist working classes from the former hegemonic Britishness of official unionism and the sectarianism of the Orange Order. The analysis concludes that loyalist identity is being conceptualized thorough a narrative of betrayal from within and at an intensely localized scale.

The contours of memory in post-conflict societies: enacting public remembrance of the bomb in Omagh, Northern Ireland

Drawing on the theoretical insights of Paul Ricoeur this paper investigates the geographies of public remembrance in a post-conflict society. In Northern Ireland, where political divisions have found expression through acts of extreme violence over the past 30 years, questions of memory and an amnesty for forgetting have particular resonance both at the individual and societal level, and render Ricoeur’s framework particularly prescient. Since the signing of the Belfast Agreement in 1998, initiating the Peace Process through consociational structures, discovering a nomenclature and set of practices which would aid in the rapprochement of a deeply divided society has presented a complex array of issues. In this paper I examine the various practices of public remembrance of the 1998 bombing of Omagh as a means of understanding how memory-spaces evolve in a post-conflict context. In Omagh there were a variety of commemorative practices instituted and each, in turn, adopted a different contour towards achieving reconciliation with the violence and grief of the bombing. In particular the Garden of Light project is analysed as a collective monument which, with light as its metaphysical centre, invited the populace to reflect backward on the pain of the bombing while at the same time enabling the society to look forward toward a peaceful future where a politics of hope might eclipse a politics of despair.

Sensory systems and spatial memory in the fruit bat Rousettus aegyptiacus

The megachiropteran fruit bat Rousettus aegyptiacus is able to orient and navigate using both vision and echolocation. These two sensory systems have different environmental constraints however, echolocation being relatively short range when compared with vision. Despite this difference, an experiment testing their memory of a perch location demonstrates that once the location of a perch is learned R. aegyptiacus is not influenced by the movement of local landmark cues in the vicinity of the perch under either light or dark conditions. Thus despite the differing constraints of vision and echolocation, this suggests a place is remembered as a location in space and not by associations with landmarks in the vicinity. A decrease in initial performance when the task was repeated in the dark suggested the possibility that a memory of a location learned using vision does not generalize to echolocation.