Efficiently exploring architectural design spaces via predictive modeling

Architects use cycle-by-cycle simulation to evaluate design choices and understand tradeoffs and interactions among design parameters. Efficiently exploring exponential-size design spaces with many interacting parameters remains an open problem: the sheer number of experiments renders detailed simulation intractable. We attack this problem via an automated approach that builds accurate, confident predictive design-space models. We simulate sampled points, using the results to teach our models the function describing relationships among design parameters. The models produce highly accurate performance estimates for other points in the space, can be queried to predict performance impacts of architectural changes, and are very fast compared to simulation, enabling efficient discovery of tradeoffs among parameters in different regions. We validate our approach via sensitivity studies on memory hierarchy and CPU design spaces: our models generally predict IPC with only 1-2% error and reduce required simulation by two orders of magnitude. We also show the efficacy of our technique for exploring chip multiprocessor (CMP) design spaces: when trained on a 1% sample drawn from a CMP design space with 250K points and up to 55x performance swings among different system configurations, our models predict performance with only 4-5% error on average. Our approach combines with techniques to reduce time per simulation, achieving net time savings of three-four orders of magnitude. Copyright © 2006 ACM.

Betwixt spaces: Students’ accounts of turning point experiences in first-year transitions

'Not belonging' is becoming a prevalent theme within accounts of the first-year student experience at university. In this study the notion of not belonging is extended by assuming a more active role for the idea of liminality in a student's transition into the university environments of academic and student life. In doing so, the article suggests that the transition between one place (home) and another (university) can result in an 'in-between-ness' - a betwixt space. Through an interpretative methodology, the study explores how students begin to move from this betwixt space into feeling like fully-fledged members of university life. It is concluded that there is a wide range of turning points associated with the students' betwixt transition, which shapes, alters or indeed accentuates the ways in which they make meaningful connections with university life. Moreover, transitional turning point experiences reveal a cast of characters and symbolic objects; capture contrasting motivations and evolving relationships; display multiple trajectories of interpersonal tensions and conflicts; highlight discontinuities as well as continuities; and together, simultaneously liberate and constrain the students' transition into university life.

Gendered Spaces and Wounded Bodies: Yamina Benguigui's 'Inch'Allah Dimanche'

Yamina Benguigui is a pioneer in the representation of Maghrebi immigration to France, and has produced a number of works of documentary and fictional film on the subject. This article discusses her fictional film Inch'Allah dimanche (2001). The film portrays the trajectory of a young woman, Zouina, who takes her children and mother-in-law to join her husband in France. The film is unique for its close focus on the space of the home, and the negotiation of gendered spaces within the strict confines set by Zouina's husband. In this article, I consider Zouina's tentative steps towards emancipation from these confines, focusing on preconceived notions of gendered spaces across different cultures. I consider possible interpretations of the final moment of wounding in the film, in which Zouina breaks through a window with her bare hands, destroying the barrier between the interior, private space of the home and the exterior, public space of the street.

Queer Spaces, Sexual Violence and the Desire for Safety

Queer politics and spaces have historically been associated with ideals of sexual liberation. They are conceptualised as spaces where sex, and its intersections with intimacy, friendship and love can be explored outside of normative frameworks which value monogamous reproductive heterosexuality at the expense of other non-normative sexual expressions. In recent years, however, autonomous queer spaces such as the global Queeruption gatherings and other queer community spaces in Australia have become increasingly concerned with the presence and danger of sexual violence in queer communities. Almost without exception, this danger has been responded to through the creation of ‘safe(r) spaces’ policies, generally consisting of a set of guidelines and proscribed behaviours which individuals must agree to in order to participate in or attend the event or space. The guidelines themselves tend to privilege of sexual politics of affirmative verbal consent, insisting that such consent should be sought prior to any physical or sexual contact, inferring that a failure to do so is ethically unacceptable within. This chapter reflects on the attempts to construct queer communities as ‘safer spaces,’ arguing that the concepts of consent and safety are inadequate to develop a queer response to sexual violence. Such a response, it argues, must be based on the openness to possibilities and refusal of sexual restrictions and regulations that have always been central elements of queer theory and politics.

Hybrid address spaces: A methodology for implementing scalable high-level programming models on non-coherent many-core architectures

This paper introduces hybrid address spaces as a fundamental design methodology for implementing scalable runtime systems on many-core architectures without hardware support for cache coherence. We use hybrid address spaces for an implementation of MapReduce, a programming model for large-scale data processing, and the implementation of a remote memory access (RMA) model. Both implementations are available on the Intel SCC and are portable to similar architectures. We present the design and implementation of HyMR, a MapReduce runtime system whereby different stages and the synchronization operations between them alternate between a distributed memory address space and a shared memory address space, to improve performance and scalability. We compare HyMR to a reference implementation and we find that HyMR improves performance by a factor of 1.71× over a set of representative MapReduce benchmarks. We also compare HyMR with Phoenix++, a state-of-art implementation for systems with hardware-managed cache coherence in terms of scalability and sustained to peak data processing bandwidth, where HyMR demon- strates improvements of a factor of 3.1× and 3.2× respectively. We further evaluate our hybrid remote memory access (HyRMA) programming model and assess its performance to be superior of that of message passing.

MSC-clustering and forward stepwise regression for virtual metrology in highly correlated input spaces

Increasingly semiconductor manufacturers are exploring opportunities for virtual metrology (VM) enabled process monitoring and control as a means of reducing non-value added metrology and achieving ever more demanding wafer fabrication tolerances. However, developing robust, reliable and interpretable VM models can be very challenging due to the highly correlated input space often associated with the underpinning data sets. A particularly pertinent example is etch rate prediction of plasma etch processes from multichannel optical emission spectroscopy data. This paper proposes a novel input-clustering based forward stepwise regression methodology for VM model building in such highly correlated input spaces. Max Separation Clustering (MSC) is employed as a pre-processing step to identify a reduced srt of well-conditioned, representative variables that can then be used as inputs to state-of-the-art model building techniques such as Forward Selection Regression (FSR), Ridge regression, LASSO and Forward Selection Ridge Regression (FCRR). The methodology is validated on a benchmark semiconductor plasma etch dataset and the results obtained are compared with those achieved when the state-of-art approaches are applied directly to the data without the MSC pre-processing step. Significant performance improvements are observed when MSC is combined with FSR (13%) and FSRR (8.5%), but not with Ridge Regression (-1%) or LASSO (-32%). The optimal VM results are obtained using the MSC-FSR and MSC-FSRR generated models. © 2012 IEEE.